This paper investigates the effects of various process parameters, specifically the substrate temperature, on weld track geometry in Directed Energy Deposition (DED) processes. A specialized experimental setup integrated within a DED machine facilitates controlled thermal conditioning of sample sheets. Through Design of Experiments (DoE) methods, individual weld marks are generated and analysed to assess geometric characteristics. Regression models are constructed to predict machine parameters for desired weld geometry at different substrate temperatures. Validation experiments confirm the accuracy and reliability of the regression models. Results show a consistent trend towards target geometric features across a broad range of substrate temperatures. Despite deviations in measured values, successful fabrication is achieved, demonstrating robust bonding between weld and substrate. Contact angle predictions exhibit precision within a partial temperature range for proper deposition. The developed model offers insights for optimizing DED process parameters to achieve desired weld characteristics, advancing the capabilities and reliability of additive manufacturing technology. Future work aims to refine the regression model and explore additional mathematical relationships for enhanced accuracy. An implication of this work is the potential to vary the local mechanical properties of parts by controlling the temperature profile while maintaining consistent geometric characteristics. By manipulating the substrate temperature, it may be possible to tailor the microstructure and mechanical properties of fabricated components in the future to meet specific requirements in different regions of the part.

The airborne and satellite-based synthetic aperture radar enables the acquisition of high-resolution SAR oceanographic images in which even the outlines of ships can be identified. The detection of ship targets from SAR images has a wide range of applications, such as the military, where the dynamic grasp of enemy targets can help improve the early warning capability of naval defence, and the civilian detection of illegal fishing vessels can help improve the level of maritime management. Due to the density of ships in SAR images, the extreme imbalance between foreground and background clutter, and the diversity of target sizes, achieving lightweight and highly accurate multi-scale ship target detection remains a great challenge. To this end, this paper proposes an attention mechanism for multiscale receptive fields convolution block (AMMRF). AMMRF not only makes full use of the location information of the feature map to accurately capture the regions in the feature map that are useful for detection results, but also effectively captures the relationship between the feature map channels, so as to better learn the relationship between the ship and the background. Based on this, a new YOLOv7-based ship target detection method, You Only Look Once SAR Ship Identification (YOLO-SARSI), is proposed, which acquires the abstract semantic information extracted from the high-level convolution while retaining the detailed semantic information extracted from the low-level convolution. Compared to the deep learning detection methods proposed by previous authors, our model is more lightweight, only 18.43M. We examined the effectiveness of our method on two SAR image public datasets: the High-Resolution SAR Images Dataset (HRSID) and the Large-Scale SAR Ship Detection Dataset-v1.0 (LS-SSDD-V1.0). The results show that the average accuracy AP50 of the detection method YOLO-SARSI proposed in this paper on the HRSID and LS-SSDD-V1.0 datasets is 4.9% and 5% higher than that of YOLOv7, respectively.

Reliable and precise damage localization in mechanical structures is of high importance in the context of structural health monitoring (SHM). The acoustic emission (AE) method has already shown its excellent suitability for damage localization. However, low signal-to-noise ratios (SNRs) are often prevalent in SHM, thus an increase in localization accuracy and robustness is still in demand. The present study faces this task through the integration of various model knowledge for AE source localization. The basis of the presented algorithm is the consideration of the dispersive behavior of elastic waves in thin-walled structures. The continuous wavelet transform (CWT) is used to obtain time-frequency representations of the signals, where frequency-dependent values for time-of-arrival (TOA) are extracted. Furthermore, the algorithm incorporates the knowledge that all sensors receive signals with the same time and location of origin, as well as the slightly different sensitivity of the theoretically equal sensors. The final localization results are achieved by a two-parameter grid search optimization. The algorithm is experimentally tested on a large aluminum plate with four piezoelectric wafer active sensors (PWASs) arranged in an array of 100 mm × 100 mm. The mean localization error of pencil lead breaks at ten different positions within the sensor array is used as an accuracy measure. It is shown that as more of the described model knowledge is incorporated into the localization, the accuracy increases. With the final algorithm, the mean localization error is more than halved compared to AE localization based on classical TOA estimation. Although the experiment described is conducted under laboratory conditions, the remarkable increase in accuracy suggests that AE source localization may be successful even at low SNR as typical for operational conditions.

Aiming at the problems of inaccurate segmentation of long object and information loss of small object in real-time semantic segmentation algorithm, this paper proposes a lightweight multi-branch real-time semantic segmentation network based on BiseNetV2. The new auxiliary branch makes full use of spatial details and context information to cover the long object in the field of view. Meanwhile, in order to ensure the inference speed of the model, the asymmetric convolution is used in each stage of the auxiliary branch to design a structure with low computational complexity. In the multi-branch fusion stage, the alignment and fusion module is designed to provide guidance information for deep and shallow feature mapping, so as to make up for the problem of feature misalignment in the fusion of information at different scales, and thus reduce the loss of small target information. In order to further improve the model’s awareness of key information, a global context module is designed to capture the most important features in the input data. The proposed network uses NVIDIA GeForce RTX 3080 Laptop GPU experiment, on the road street view data set Cityscapes and CamVid average occurring simultaneously ratio reached 77.1% and 78.4% respectively, with running speed of 127 frames/s respectively and 112 frames/s. The experimental results show that the proposed algorithm can achieve real-time segmentation and improve the accuracy significantly, showing good semantic segmentation performance

Convolutional Neural Networks (CNNs) present drawbacks for modeling geometric transformations, such as scaling and rotation, caused by the convolution operation’s locality. Deformable convolution (DCON), a mechanism that substitutes standard convolution, increasing the receptive field to capture relevant features, is a promising approach to solve this drawback and improve the robustness of CNNs. However, the optimal way to replace the standard convolution with its deformable counterpart in a CNN model is unclear. In this study, we clarify this aseveration by conducting several experiments using deformable convolutions applied in the layers that conform a small four-layer CNN model. We also use deformable convolutions on the four-layers of several ResNet CNNs with depths 18, 34, 50, and 101. The models were tested in binary balanced classes with 2D data for image classification: Cats & Dogs, EyesPACS, Spyders & Chickens, and Shapes. After this testing, we evaluated DCON in 3D data for action recognition: UCF101 and Human2 (a dataset we compiled to control movement, clothing and background). The contribution of this research lies in a guideline to use DCON. It can be summarized as follows: if DCON is used on the first layers of the proposal of model (with simple features), the computational resources expressed as the quantity of Flops will tend to increase and produce bigger misclassification than the standard CNN. However, if the DCON is used at the end layers, the quantity of Flops used in the training and testing will decrease, and the classification accuracy will improve by up to 20% about the base model. Moreover, it gains robustness when using deformable convolutions because it can adapt to the region of interest. Also, the best kernel size of the DCON is three. It showed better results than size five. In the last case, the quantity of Flops increase quadratically, but their performance does not increase significantly. With these results, we propose a guideline to use the DCON and contribute to understanding the impact of DCON on the robustness of CNNs.

ABSTRACT Purpose: Tongue image analysis for disease diagnosis is an ancient traditional non-invasive diagnosis technique widely used by traditional medicine practitioners. Deep Learning based multi-label disease detection models offer tremendous potential to clinical decision support systems, by facilitating preliminary diagnosis. Methods: In this work, we propose a multi-label disease detection pipeline, where in observation and analysis of tongue images captured and received via smartphones assist in predicting the health status of an individual. All images are voluntarily given by subjects consulting collaborating physicians. Images thus acquired are first and foremost classified either into a diseased or a normal category by a 5-fold cross-validation algorithm using a convolution neural network (MobileNetV2) model for binary classification. Once the diseased label is predicted, the image is used to diagnose multiple diseases using the prediction algorithm based on DenseNet121. Results: Average accuracy of 93 % was achieved in classifying diseased from normal healthy tongue by detection model with MobileNetV2 architecture. Multilabel disease classification produced more than 90% accurate results for the seven class labels considered. Conclusion: AI based image analysis shows promising results and an extensive dataset could provide further improvements to this approach. Rather than employing high-cost sophisticated image capturing setup, experimenting with smartphone images opens opportunity to provide preliminary health status to individuals on smartphone prior to further line of treatment and diagnosis.

With prosperous development and successful application of deep learning technologies in the field of remote sensing, numerous deep-learning based methods have emerged for synthetic aperture radar (SAR) automatic target recognition (ATR) tasks over the past few years. Generally, most deep-learning based methods can achieve outstanding recognition performance in condition that an abundant of labeled samples are available to train the model. However, in real application scenarios, it is difficult and costly to acquire and to annotate abundant SAR images due to the imaging mechanism of SAR, which poses a big challenge to existing SAR ATR methods. Thereby, SAR target recognition under the situation of few-shot, where only a scarcely few of labeled samples are available, is a fundamental problem that needs to be solved. In this paper, we put forward a new method named enhanced prototypical network with customized region-aware convolution (CRCEPN) to specially tackle the few-shot SAR ATR tasks. To be specific, We first develop a feature extraction network based on a customized and region-aware convolution, which can adaptively adjust convolutional kernels and their receptive fields according to each SAR image’s own characteristics as well as the semantical similarity among spatial regions, thus augmenting its capability to extract more informative and discriminative features. To achieve accurate and robust target identity prediction under the few-shot condition, we then propose an enhanced prototypical network which can improve the representation ability of the class prototype by properly making use of training and test samples together, thus effectively raising the classification accuracy. Meanwhile, a new hybrid loss is designed to learn a feature space with both inter-class separability and intra-class tightness as much as possible, which can further upgrade the recognition performance of the proposed method. Experiments performed on the moving and stationary target acquisition and recognition (MSTAR) dataset and the OpenSARShip dataset demonstrate that the proposed method is competitive with some state-of-the-art methods for few-shot SAR ATR tasks.

With the increasing demand for security surveillance, assisted driving, and remote sensing, target detection networks with rich environmental perception capabilities and high detection accuracy have become a research hotspot. However, detection techniques based on single-modality images face limitations in environmental adaptability, as they are easily affected by lighting conditions, as well as obstacles such as smoke, rain, and vegetation, leading to information loss and failing to meet the required accuracy. To address these issues, we propose a target detection network—IV-YOLO, which integrates features from both visible and infrared images. We built a dual-branch fusion network based on YOLOv8 (You Only Look Once v8) that combines infrared and visible images for target detection. On this foundation, we designed a Bidirectional Pyramid Feature Fusion structure (Bi-Fusion) to fully integrate complementary features from different modalities, reducing detection errors caused by feature redundancy and extracting fine-grained features of small targets through dual-modal fusion. Additionally, we developed the Shuffle-SPP structure, which combines channel and spatial attention mechanisms to enhance focus on deep features and further aggregate upsampling, extracting richer features. To improve the model’s expressive power, we designed a loss function tailored for multi-scale target detection boxes, accelerating the network’s convergence during training. Experimental results show that the proposed IV-YOLO network achieves an average precision (mAP) of 74.6% on the UAV remote sensing dataset, 75.4% on the KAIST pedestrian dataset, and 84.8% on the FLIR dataset. While ensuring detection accuracy, our model significantly reduces computational load, making it well-suited to meet real-time requirements. This architecture is expected to find broad application in fields such as autonomous driving, public safety, and others.

Existing methods of hyperspectral anomaly detection still face several challenges: 1) Due to the limitations of self-supervision, avoiding the identity mapping of anomalies remains difficult; 2) The ineffective interaction between spatial and spectral features leads to the insufficient utilization of spatial information; 3) Current methods are not adaptable to the detection of multi-scale anomaly targets. To address the aforementioned challenges, we proposed a blind spot network based on multi-scale blind spot convolution for HAD. The multi-scale mask convolution module is employed to adapt to diverse scales of anomaly targets, while the dynamic fusion module is introduced to integrate the advantages of mask convolutions at different scales. The proposed approach includes a spatial-spectral joint module and a background feature attention mechanism to enhance the interaction between spatial-spectral features, with a specific emphasis on highlighting the significance of background features within the network. Furthermore, we propose a preprocessing technique that integrates pixel shuffle down-sampling (PD) operation with spatial spectral joint screening to address the issue of anomalous identity map-ping and facilitate finite-scale mask convolution to adapt to the detection of more scale targets. The proposed approach was assessed on four real hyperspectral datasets comprising anomaly targets of different scales. The experimental results demonstrate the effectiveness and superior performance of the proposed methodology compared with nine state-of-the art methods.

Research into lightweight structural concrete using volcanic tuff is of great importance to the construction industry. These materials have excellent thermal insulation properties, which helps improve the energy efficiency of buildings. A three-factor experimental design was used to build the statistical model. The test methods used were methods for determining the crushability of volcanic tuff, determining the average density, compressive strength and thermal conductivity of lightweight structural concrete. The influence of basalt fiber on the properties of lightweight structural concrete has been determined. The optimal compositions of lightweight structural concrete using tuff have been selected. The compressive strength of lightweight structural concrete reached 32.0 MPa. The average density range is 1754.6-2114.0 kg/m³. Good thermal conductivity values ​​were obtained in the range of 0.653-0.818 W/m·K. The article obtained the optimal compositions of lightweight structural concrete using volcanic tuff as a filler.

Strip steel surface defect recognition research has important research significance in industrial production. Aiming at the problems of defect feature extraction difficulty, slow detection speed and insufficient dataset, YOLOv5 is improved on the basis of YOLOv5, and YOLO-LFPD (Lightweight fine particle detection) model is proposed. By introducing the RepVGG (Re-param VGG) module, the robustness of the model to the surface defect features of strip steel is enhanced, and the expressive ability of the model is improved. FasterNet is used to replace the backbone network, which ensures the accuracy and accelerates the inference speed, making the model more suitable for real-time monitoring. The use of pruning, GA genetic algorithm with OTA loss function method further reduces the model size while better learning the strip steel defect feature information, thus improving the generalisation ability and accuracy of the model. The experimental results show that the introduction of the RepVGG module and the use of FasterNet can well improve the model performance, with a reduction of 48% in the number of parameters, a reduction of 13% in the number of GFLOPs, an inference time of 77% of the original, and an optimal accuracy compared with the network models in recent years. The experimental results on the NEU-DET dataset show that the accuracy of YOLO-LFPD is improved by 3% to 81.2%, which is better than other models, and provides new ideas and references for the lightweight strip steel surface defect detection scenarios and application deployment.

Traffic sign detection plays a pivotal role in autonomous driving systems. The intricacy of the detection model necessitates high-performance hardware. Real-world traffic environments exhibit considerable variability and diversity, posing challenges for effective feature extraction by the model. Therefore, it is imperative to develop a detection model that is not only highly accurate but also lightweight. In this paper, we proposed YOLO-ADual, a novel lightweight model. Our method leverages the C3Dual and Adown lightweight modules as replacements for CPS and CBL modules in YOLOv5. The Adown module effectively mitigates feature loss during downsampling while reducing computational costs. Meanwhile, C3Dual optimizes the processing power for kernel feature extraction, enhancing computation efficiency while preserving network depth and feature extraction capability. Furthermore, the inclusion of the CBAM module enables the network to focus on salient information within the image, thus augmenting its feature representation capability. Our proposed algorithm achieves a [email protected] of 70.1% while significantly reducing the number of parameters and computational requirements to 51.83% and 64.73% of the original model, respectively. Compared to various lightweight models, our approach demonstrates competitive performance in terms of both computational efficiency and accuracy.

The dynamic behaviour of a machine tool (MT) directly influences the machining performances. The adoption of lightweight structures may reduce the effects of undesired vibrations and increasing the workpiece quality. This paper aims to present and compare a set of hybrid materials that may be excellent candidate to fabricate the MT moving parts. The selected materials have high dynamic characteristics and capacity to damp mechanical vibrations. In this way, starting by the kinematic model of a milling machine that highlights the main critical factors, this study paper evaluates a number of prototypes made of Al Foam sandwiches (AFS), Al Corrugated sandwiches (ACS) and materials reinforced by carbon fibres (CFRP). A set of prototypes has been fabricated, represented the Z-axis ram of a commercial milling machine. The static and dynamical properties have been evaluated by using both FE simulations and experimental tests. The obtained results show that the proposed structures may be a valid alternative to the conventional materials of MT moving parts, increasing machining performances. In particular, the AFS prototype highlighted a damping coefficient that is 20 times greater than a conventional ram (e.g. steel). The CFRP structure is able to satisfy the machining requirements with a reduced weight of 48.5%, while the ACS prototype showed a good trade-off between stiffness and damping.

In order to shorten the detection time and improve the average precision on embedded devices, A lightweight and high accuracy model is proposed for passion fruit in complex environments (backlight, occlusion, overlap, sunny, cloudy, rainy). Firstly, replacing the backbone network of YOLOv5 with a lightweight GhostNet model reduces the number of parameters and computation while improving detection speed. Secondly, a new feature branch is added to the GhostNet network, and the feature fusion layer in the neck network is reconstructed to effectively combine the lower-level and higher-level features, which not only improves the accuracy of the model but also maintains its lightweight. Finally, the knowledge distillation methods are used to transfer the knowledge from the more capable teacher model to the less capable student model, which significantly improving the detection accuracy. The improved model is denoted as G-YOLO-NK. The average accuracy of the G-YOLO-NK network is 96.00%, which is 1.00% higher than the original YOLOv5s model. Furthermore, the improved model size is 7.14MB, reduced to half of the original model, and the real-time detection frame rate is 11.25 FPS on the Jetson Nano. Compared to the state-of-the-art model, the proposed model outperforms them in terms of average precision and detection performance. The present work provides an effective model for real-time detection of passion fruits in complex orchard scenes, which can provide valuable technical support for the development of orchard picking robots and greatly improve the intelligence level of orchards.

Currently there are fewer depth models applied to pepper picking detection, while the existing generalized neural networks have problems such as large model parameters, long training time, and low model accuracy.In order to solve the above problems, this paper proposes a Yolo-chili target detection algorithm for chili pepper detection. First, the classical target detection algorithm yolov5 is used as a benchmark model, and an adaptive spatial feature pyramid structure combining the attention mechanism and the idea of multi-scale prediction is introduced to improve the model's detection effect on occluded peppers and small target peppers. Secondly, a three-channel attention mechanism module is introduced to improve the algorithm's long-distance recognition ability and reduce the interference of redundant testers. Finally, the quantized pruning method is used to reduce the model parameters and realize the lightweight processing of the model. Applying the method to the homemade chili pepper dataset, the AP value of chili pepper reaches 93.11%; the accuracy rate is 93.51% and the recall rate is 92.55%.The experimental results show that yolo-chili is able to achieve accurate and real-time pepper detection under complex orchards.

Chip pad alignment inspection is of great importance in the industrial field. However, due to the fact that chip pads are usually small, problems such as misdetection and missed detection often occur. When applying deep learning methods for chip pad detection, it is necessary to ensure accurate detection of small target chips while meeting the requirements of lightweight detection models for industrial needs. To solve the above problems, this paper proposes a lightweight model based on improved YOLOv5s. Firstly, the feature extraction part is improved to increase the network's focus on the target. Secondly, the feature fusion layer is improved to double the resolution of the prediction head, and the context-aware network is designed to enhance the context-capture ability of key features of small targets. Finally, SIoU is adopted as the loss function to improve the speed and accuracy of the regression frame. The experimental results show that the improved YOLOv5s algorithm improves the detection accuracy by 2.3% and reduces the network parameters by 81.8% compared to the original algorithm. The improved algorithm is combined with image processing techniques to design correction methods for alignment anomalies and realize real-time alignment anomaly correction in industry.

Laser-targeted weeding methods further enhance the sustainable development of green agriculture, with one key technology being the improvement of weed localization accuracy. Here, we propose an improved YOLOv8 instance segmentation based on bidirectional feature fusion and deformable convolution (BFFDC-YOLOv8-seg) to address the challenges of insufficient weed localization accuracy in complex environments with resource-limited laser weeding devices. Initially, by training on extensive datasets of plant images, the most appropriate model scale and training weights are determined, facilitating the development of a lightweight network. Subsequently, the introduction of the Bidirectional Feature Pyramid Network (BiFPN) during feature fusion effectively prevents the omission of weeds. Lastly, the use of Dynamic Snake Convolution (DSConv) to replace some convolutional kernels enhances flexibility, benefiting the segmentation of weeds with elongated stems and irregular edges. Experimental results indicate that the BFFDC-YOLOv8-seg model achieves a 4.9% increase in precision, an 8.1% increase in recall rate, and a 2.8% increase in mAP50 value to 98.8% on a vegetable weed dataset compared to the original model. It also shows improved mAP50 over other typical segmentation models such as Mask R-CNN, YOLOv5-seg, and YOLOv7-seg by 10.8%, 13.4%, and 1.8%, respectively. Furthermore, the model achieves a detection speed of 24.8 FPS on the Jetson Orin nano standalone device, with a model size of 6.8MB that balances between size and accuracy. The model meets the requirements for real-time precise weed segmentation, suitable for complex vegetable field environments and resource-limited laser weeding devices.

Glaucoma, a global leading cause of blindness, necessitates accurate segmentation of the optic disc (OD) and optic cup (OC) for effective screening. However, existing segmentation methods based on convolutional neural networks (CNNs) suffer from high computational complexity and long inference times. In this paper, we propose an end-to-end segmentation method for the OD and OC using a lightweight MobileNetv3 as the feature extraction network. Our approach incorporates boundary branches and an adversarial learning network to achieve multi-label segmentation of the OD and OC. We evaluate the proposed method on three publicly available datasets: Drishti-GS, RIM-ONE-r3, and REFUGE. The experimental results demonstrate segmentation accuracies of 0.974/0.900, 0.966/0.875, and 0.962/0.880 for the OD and OC on the respective datasets, while significantly reducing inference time.

This paper introduces an innovative approach to lipreading, leveraging a web application designed to generate subtitles for videos where the speaker's mouth is visible and a comprehensive literature review that precedes the discussion, encompassing a thorough examination of various lipreading methods employed over the past decade. Our method employs a powerful deep learning model, featuring a 3D-convolution network and bidirectional LSTM, enabling accurate sentence-level predictions based solely on visual lip movements. With an impressive accuracy of 97%, our model is trained using pre-segmented lips regions, transformed into animated GIFs for effective pre-training. This work stands as a significant contribution to the evolving landscape of lipreading research, offering a practical and accurate solution for real-world applications.

K-band radar waves have high penetration and low attenuation coefficients. However, the wavelength of this radar wave is relatively short; thus, designing and preparing both broadband and wide-angle radar wave absorbers in this band presents considerable challenges. In this study, a resin-based K-band radar wave absorber with a biomimetic lotus leaf structure was designed and formed by UV curing. Here, microscale lotus leaf papillae and antireflection structures were prepared using a DLP 3D printer, and the contact angle between the material and water droplets was increased from 56° to 130°. In addition, the influence of the geometric parameters of the lotus leaf antireflection structure on the electromagnetic absorption performance and mechanical strength was investigated. After simulation optimization, the maximum electromagnetic loss of the lotus leaf structure 3D printed sample was −32.3 dB, and the electromagnetic loss was below −10 dB in the 20.8–26.5 GHz frequency range. When the radar incidence angle was 60°, the maximum electromagnetic loss was still less than −10 dB. The designed lotus leaf structure has a higher mechanical energy absorption per unit volume (337.22 KJ/m3) and per unit mass (0.55 KJ/Kg) than commonly used honeycomb lightweight structures during the elastic deformation stage, and we expect that the designed structure can be used as an effective lightweight material for K-band radar stealth.

Cyberattacks are rapidly evolving both in terms of techniques and frequency, from low-level attacks through to sophisticated Advanced Persistent Threat (APT). There is a need to consider how testbed environments such as cyber ranges can be readily deployed to improve examination of attack characteristics and the assessment of defences. Whilst cyber ranges are not new, they can often be computational expensive, require significant setup and configuration, or may not provide full support for areas such as logging or ongoing learning. In this paper, we propose GoibhniUWE, a container-based cyber range that provides a flexible platform for investigating the full lifecycle of a cyber attack. Adopting a modular approach, users can seamlessly switch out existing, containerised vulnerable services, deploying multiple different services at once allowing for the creation of complex and realistic deployments. The range is fully instrumented with logging capabilities from a variety of sources including Intrusion Detection Systems (IDS), service logging, and network traffic captures. To demonstrate the effectiveness of our approach, we deploy the GoibhniUWE range under multiple conditions to simulate various vulnerable environments, reporting on and comparing key metrics such as CPU and memory usage. We simulate complex attacks which span multiple services and networks, with logging at multiple levels, modelling an Advance Persistent Threat (APT) and their associated Tactics, Techniques, and Procedures (TTPs). We find that even under continuous, active and targeted deployment GoibhniUWE averaged a CPU usage of less than 2 processors and memory usage of less than 4.5 GB.

Detecting cracks in structural health monitoring is crucial for ensuring infrastructure safety and longevity. Using drones to obtain crack images and automate processing can improve the efficiency of crack detection. To address the challenges posed by the limited computing resources of edge devices in practical applications, we propose CrackScopeNet, a lightweight segmentation network model that simultaneously considers local and global crack features, suitable for deployment on drone platforms with limited computational power and memory. CrackScopeNet features a multi-scale branch to improve sensitivity to cracks of varying sizes without substantial computational overhead and a stripe-wise context attention mechanism to enhance the capture of long-range contextual information, mitigating the interference from complex backgrounds. Experimental results on CrackSeg9k dataset demonstrate that CrackScopeNet leads to a significant improvement in prediction performance, with the highest mean intersection over union (mIoU) scores reaching 82.12%, while maintaining a lightweight architecture with only 1.05M parameters and 1.58G floating point operations (FLOPs). Besides, CrackScopeNet excels in inference speed on edge devices without GPU because of its low FLOPs. CrackScopeNet contributes to the development of efficient and effective crack segmentation networks, suitable for practical structural health monitoring applications using drone platforms.

This paper proposes a novel facial expression recognition network called the Lightweight Facial Network with Spatial Bias (LFNSB). The LFNSB model balances model complexity and recognition accuracy. It has two key components: a lightweight feature extraction network (LFN) and a Spatial Bias (SB) module for aggregating global information. The LFN introduces combined channel operations and depthwise convolution techniques, effectively reducing the number of parameters while enhancing feature representation capability. The Spatial Bias module enables the model to focus on local facial features while also capturing the dependencies between different facial regions. Additionally, a novel loss function called Cosine-Harmony Loss is designed. This function optimizes the relative positions of feature vectors in high-dimensional space, resulting in better feature separation and clustering. Experimental results on the AffectNet and RAF-DB datasets show that the proposed LFNSB model performs excellently in facial expression recognition tasks. It achieves high recognition accuracy while significantly reducing the number of parameters, thus substantially lowering model complexity.

In this paper we use the Mellin convolution theorem, which is related to Perron's formula. Also we introduce new explicit formulae for arithmetic function which generalize the explicit formulae of Weil for other arithmetic functions different from the Von-Mangoldt function.

The article addresses manufacturing structures made of biodegradable materials that can be successfully used as energy-absorbing liner of sports helmets of all kinds, replacing the previously used expanded polystyrene. The paper is focused on injection technological tests and tensile tests (in quasi-static and dynamic conditions) of several composites based on a PLA matrix with the addition of other biodegradable softening agents, such as PBAT and TPS. Next, the thin-walled elements (dimensions of 55 x 55 x 20 mm) were manufactured and evaluated using a spring-loaded drop hammer. The 60J impact energy was tested according to EN 1078 standard. The dynamic crushing testing included checking the influence of the materials temperature (-20, 0, 20, and 40 °C) and the impact velocity. The PLA15PBAT85 blend was selected as the most effective material in terms of its use as energy-absorbing liner for sport helmets.

The application of artificial intelligence to point-of-care testing (POCT) disease detection has become a hot research field, in which breath detection which detects the patient's exhaled VOCs combined with sensor arrays of Convolutional Neural Network (CNN) algorithms as a new lung cancer detection is attracting more researchers' attention. However, due to low accuracy, high complexity computation and large number of parameters make the CNN algorithms difficult transplant to the embedded system of POCT devices. A lightweight neural network (LTNet) in this work is proposed to deal with this problem, and meanwhile, achieve high-precision classification of acetone and ethanol gases, which are respiratory markers for lung cancer patients. Compared to currently popular lightweight CNN models such as EfficientNet, LTNet has fewer parameters (32K) and its training weight size is only 0.155 MB. LTNet achieved an overall classification accuracy of 99.06% and 99.14% in the own mixed gas dataset and the University of California (UCI) dataset, which are both higher than that of the five existing models’, and it also offers the shortest training (844.38s and 584.67s) and inference time (23s and 14s) in the same validation set. Compared to the existing CNN models, LTNet is more suitable for resource-limited POCT devices.

Let be a power function $f_{r,M}(s)$ defined for every $s$ within the finite set $M$ as follows $$f_{r,M}(s)= \begin{cases} s^r, \ &s\in M,\\ 0, \ &\mathrm{otherwise}. \end{cases} $$ Let a discrete convolution of $f_{r,M}(s)$ be denoted as follows $\mathrm{Conv}_{r,M}[n]=(f_{r,M}*f_{r,M})[n]$. Let a real coefficients $A_{m,j}$ be given by the following recurrence $$ A_{m,j} = \begin{cases} 0, & \mathrm{if } \ j<0 \ \mathrm{or } \ j>m, \\ (2j+1)\binom{2j}{j} \sum_{d=2j+1}^{m} A_{m,d} \binom{d}{2j+1} \frac{(-1)^{d-1}}{d-j} B_{2d-2j}, & \mathrm{if } \ 0 \leq j < m, \\ (2j+1)\binom{2j}{j}, & \mathrm{if } \ j=m. \end{cases} $$ In this paper we show that for every $n>0$ the following odd-power identities involving coefficients $A_{m,j}$ and convolution transform $\mathrm{Conv}_{r,M}[n]$ hold $$ \begin{split} n^{2m+1}+1&=\sum_{r=0}^{m}A_{m,r}\mathrm{Conv}_{r,\mathbb{N}}[n],\\ n^{2m+1}-1&=\sum_{r=0}^{m}A_{m,r}\mathrm{Conv}_{r,\mathbb{Z}_{>0}}[n],\\ n^{2m+1}&=\sum_{r=0}^{m}A_{m,r}\sum_{k=1}^{n} k^r(n-k)^r\\ &=\sum_{r=0}^{m}A_{m,r}\sum_{k=0}^{n-1} k^r(n-k)^r. \end{split} $$

Amid the swift progression of the global automobile industry, the aspiration for lightweight vehicle design has surfaced as a crucial approach to boost fuel efficiency and curtail environmental impact. The objective of this study revolves around achieving holistic optimization of vehicle structure via detailed scrutiny of vehicle process characteristics, amalgamated with a Back Propagation neural network (BPNN) optimized by a genetic algorithm (GA) and a topology optimization (TO) method.The process initiates with an examination of the vehicle's technical characteristics, succeeded by an optimization protocol that couples GA with BPNN. This exhaustive optimization procedure derives the best-fit values of design parameters and identifies the globally optimal lightweight design approach. Subsequently, a comprehensive structural optimization is actualized by modifying the topological distribution of the structure.A simulation experiment of the conceptual car body beam skeleton is conducted as a conclusive step, and the anti-collision capacity of the car body beam skeleton is assessed by measuring deformation intrusion. The findings reveal that in the vehicle topology optimization, a comparative analysis of pre and post-optimization results indicates an improved topological density across diverse sections. The topological density of the vehicle's frontal structure escalates from 0.75 to 0.8. Following optimization, the stiffness assessment records a marginal increase (within the range of 0.02–0.05), implying that the lightweight design does not compromise the general rigidity of the structure.The optimized body structure manifests superior crashworthiness in the crash test: the deformation intrusion diminishes by 27% in front-end collisions. In side impacts, the deformation and intrusion at critical points are reduced by 13.15% to 10% respectively. The comprehensive method proposed herein proves to be an efficient strategy to actualize the lightweight design of vehicles.

With the progression of AI, embedding advanced AI technologies into small robotics and mobile devices has become essential, driving research towards lightweighting AI models. Our study enhances the EPINET depth estimation model for light field images, aiming for compactness and faster inference while preserving accuracy. We conducted two-step experiments aimed at enhancing inference efficiency: Initially, by adjusting input streams and convolution layers, we simplified the CNN model, achieving faster inference times at the cost of reduced accuracy. To address this reduction in accuracy, we then applied knowledge distillation, allowing the simplified model to learn from the original model’s more complex patterns. In our quantitative experiments using two error metrics, MSE (Mean Squared Error) and BadPix, we identified optimal knowledge positions and evaluated the required complexity for the student model. As a result, our method improved MSE by 21% and BadPix by 14% compared to training without it. Furthermore, the student model achieved an inference speed 13% faster than the teacher model and surpassed its accuracy by 10% in MSE. Additionally, we demonstrated that repeatedly applying our approach could further enhance both model compactness and accuracy.

Object detection algorithms for open water aerial images present challenges such as small object size, unsatisfactory detection accuracy, numerous network parameters, and enormous computational demands. Current detection algorithms struggle to meet the accuracy and speed requirements while being deployable on small mobile devices. This paper proposes DFLM-YOLO, a lightweight small-object detection network based on the YOLOv8 algorithm with multiscale feature fusion. Firstly, to solve the class imbalance problem of the SeaDroneSee dataset, we propose a data augmentation algorithm called Small Object Multiplication (SOM). SOM enhance dataset balance by increasing the number of objects in specific categories, thereby improving model accuracy and generalization capabilities. Secondly, we optimize the backbone network structure by implementing Depthwise Separable Convolution (DSConv) and the newly designed FC-C2f, which reduces the model's parameters and inference time. Finally, we design the Lightweight Multiscale Feature Fusion Network (LMFN) to address the challenges of multiscale variations by gradually fusing the four feature layers extracted from the backbone network in three stages. In addition, LMFN incorporates the Dilated Re-param Block structure to increase the effective receptive field and improve the model's classification ability and detection accuracy. Experimental results on the SeaDroneSea dataset indicate that DFLM-YOLO improves mAP by 12.4% compared to the original YOLOv8s, while reducing parameters by 67.2%. This achievement provides a new solution for UAVs to conduct object detection missions in open water efficiently.

Convolution forms one of the most essential operations for the FPGA-based hardware accelerator. However, the existing designs often neglect the inherent architecture of FPGA, which puts forward an austere challenge on hardware resource requirements. Even though some previous works have proposed approximate multipliers or convolution acceleration algorithms to deal with this issue, the inevitable accuracy loss and resource occupation easily lead to performance degradation. Toward this, we first propose two kinds of resource-efficient optimized accurate multipliers based on LUTs or carry chains. Then targeting FPGA-based platforms, a generic multiply-accumulate structure is constructed by directly accumulating the partial products produced by our proposed optimized radix-4 Booth multipliers without intermediate multiplication and addition results. Experimental results demonstrate that our proposed multiplier achieves a maximum 51% look-up-table (LUT) reduction compared to the Vivado area optimized multiplier IP. Furthermore, the convolutional process unit using the proposed structure achieves a 36% LUT reduction compared to existing methods. As case studies, the proposed method is applied to DCT transformer and LeNet to achieves hardware resource saving without loss of accuracy.

FV (finger vein) identification is a biometric identification technology that extracts the features of FV images for identity authentication. To address the limitations of CNN-based FV identification, particularly the challenge of small receptive fields and difficulty in capturing long-range dependencies, an FV identification method Let-Net(Large kernel and attention mechanism Network) was introduced, which combines local and global information. Firstly, Let-Net employs large kernels to broaden the receptive field and incorporates depthwise convolution with residual connections to reduce parameter count. Secondly, Let-Net integrates an attention mechanism to enhance the information flows in channels and spaces for more comprehensive and distinctive FV feature extraction. The experimental results on nine public datasets show that Let-Net has excellent identification performance, and the EER and accuracy rate on the FV_USM dataset can reach 0.04% and 99.77%. The parameter number and FLOPs of Let-Net are only 0.89M and 0.25G, which means that the time cost of training and reasoning of the model is low, and it is easier to deploy and integrate into various applications.

This paper presents the Advanced Syntactic-Graph Convolutional Model (ASGCM), a pioneering approach in Aspect-Based Sentiment Analysis (ABSA) that integrates syntactic dependency features within a graph convolution framework. ASGCM stands out for its novel use of dependency edge encoding and tag-based graph convolutions, providing a fine-grained analysis of sentiments associated with specific aspects in text. This model meticulously captures the intricacies of syntactic structures, thereby offering enhanced precision in sentiment analysis. Notably, ASGCM incorporates a dual-layer graph convolution system: one layer processes syntactic dependencies (edges), while the other interprets semantic roles (tags), ensuring a comprehensive understanding of both structural and contextual elements in text. We rigorously tested ASGCM on multiple datasets, including both English and Chinese languages, and our findings reveal a significant improvement in sentiment classification accuracy compared to existing models. The versatility of ASGCM makes it a robust tool for diverse linguistic environments, setting a new standard for ABSA methodologies.

Research on image-inpainting tasks has mainly focused on enhancing performance by augmenting various stages and modules. However, this trend does not consider the increase in the number of model parameters and operational memory, which increases the burden on computational resources. To solve this problem, we propose a Parametric Efficient Image InPainting Network (PEIPNet) for efficient and effective image-inpainting. Unlike other state-of-the-art methods, the proposed model has a one-stage inpainting framework in which depthwise and pointwise convolutions are adopted to reduce the number of parameters and computational costs. To generate semantically appealing results, we selected three unique components: spatially-adaptive denormalization (SPADE), dense dilated convolution module (DDCM), and efficient self-attention (ESA). The SPADE was adopted to conditionally normalize activations according to the mask to distinguish between damaged and undamaged regions. The DDCM was employed at every scale to overcome the gradient-vanishing obstacle and gradually fill-in pixels by capturing global information along the feature maps. The ESA was utilized to obtain clues from unmasked areas by extracting long-range information. In terms of efficiency, our model has the lowest operational memory compared with other state-of-the-art methods. Both qualitative and quantitative experiments demonstrate the generalized inpainting of our method on three public datasets: Paris StreetView, CelebA, and Places2.

Identification of plants is a challenging task which aims to identify the family, genus, and species level according to morphological features. Automated deep learning-based computer vision algorithms are widely used for identifying plants and can help users to narrow down the possibilities. However, numerous morphological similarities between and within species make the classification difficult. In this paper, we tested a custom convolution neural network (CNN) and vision transformer (ViT) based models using the PyTorch framework to classify plants. We used a large dataset of 88K and 16K images for classifying plants at genus and species levels respectively. Our results show that for classifying plants at the genus level, ViT models perform better compared to CNN-based models ResNet50 and ResNet-RS-420, and other state-of-the-art CNN-based models suggested in previous studies on a similar dataset. The ViT model achieved top accuracy of 83.3% for classifying plants at the genus level. ViT models also perform better for classifying plants at the species level compared to CNN-based models ResNet50 and ResNet-RS-420, with a top accuracy of 92.5%. We show that the correct set of augmentation techniques plays an important role in classification success.

This study introduces SkinLiTE, a lightweight supervised contrastive learning model, tailored to enhance the detection and typification of skin lesions in dermoscopic images. The core of SkinLiTE lies in its unique integration of supervised and contrastive learning approaches, which leverages labeled data to learn generalizable representations. This approach is particularly adept at handling the complexities and imbalances inherent in skin lesions datasets. The methodology encompasses a two-phase learning process. In the first phase, SkinLiTE utilizes an encoder network and a projection head to transform and project dermoscopic images into a feature space where contrastive loss is applied, focusing on minimizing intra-class variations while maximizing inter-class differences. The second phase freezes the encoder's weights, leveraging the learned representations for classification through a series of dense and dropout layers. The model was evaluated using three datasets from Skin Cancer ISIC 2019-2020, covering a wide range of skin conditions. SkinLiTE demonstrated superior performance across various metrics—accuracy, AUC , and F1 score—particularly when compared with traditional supervised learning models. Notably, SkinLiTE achieved an accuracy of 0.9087 using AugMix augmentation for binary classification of skin lesions. It also showed comparable results with the state-of-the-art approaches of ISIC challenge without relying on external data, underscoring its efficacy and efficiency. The results highlight the potential of SkinLiTE as a significant step forward in the field of dermatological AI, offering a robust, efficient, and accurate tool for skin lesion detection and classification. Its lightweight architecture and ability to handle imbalanced datasets make it particularly suited for integration into Internet of Medical Things environments, paving the way for enhanced remote patient monitoring and diagnostic capabilities. This research contributes to the evolving landscape of AI in healthcare, demonstrating the impact of innovative learning methodologies in medical image analysis.

Bundle recommendation is provided to users by combining related items into a bundle, enhancing the user's shopping experience and increase the merchant's sales revenue. Despite the success of existing solutions based on Graph Neural Networks(GNN), there are still some significant challenges: (1)It is demanding to explicitly model multiple complex associations using standard graph neural networks. (2)Numerous additional nodes and edges are introduced to approximate higher-order associations. (3)The user-bundle historical interaction data is highly sparse. In this work, we propose a Global Structural Hypergraph Convolution model for Bundle Recommendation (SHCBR) to address the above problems. Specifically, we jointly incorporate multiple complex interactions between users, items, and bundles(three entities) into a relational hypergraph without introducing additional nodes and edges. Higher-order associations are already involved in the hypergraph structure which alleviate the training burden of neural networks and the dilemma of scarce data. In addition, we design a special matrix propagation rule that captures non-pairwise complex relationships between entities. Using item nodes as links, hypergraph convolution propagation between user and bundle nodes generates the learned representations. Experimental results on two real-world datasets demonstrate that SHCBR outperforms the state-of-the-art baselines by 11.07%-25.66\% on Recall and 16.81%-33.53% on NDCG. We publicly release the codes and datasets at https://github.com/Lxtdzh/SHCBR-master/.

Multi-task Gaussian processes (MTGPs) are a powerful approach for modeling structured dependencies among multiple tasks. Researchers on MTGPs have contributed to enhance this approach in various ways. Current MTGP methods, however, cannot model nonlinear task correlations in a general way. In this paper we address this problem. We focus on spectral mixture (SM) based kernels and propose an enhancement of this type of kernels, called multi-task generalized convolution spectral mixture (MT-GCSM) kernel. The MT-GCSM kernel can model nonlinear task correlations and mixtures dependency, including time and phase delay, not only between different tasks but also within a task at the spectral mixture level. Each task in MT-GCSM has its own generalized convolution spectral mixture kernel (GCSM) with a different number of convolution structures and all spectral mixtures from different tasks are dependent. Furthermore, the proposed kernel uses inner and outer full cross convolution between base spectral mixtures, so that the base spectral mixtures in the tasks are not necessarily aligned. Extensive experiments on synthetic and real-life datasets illustrate the difference between MT-GCSM and other kernels as well as the practical effectiveness of MT-GCSM.

This paper deals with the merger of the two lightweight stream ciphers—A5/1 and Trivium. The idea is to make the key stream generation more secure and to remove the attacks of the individual algorithms. The bits generated by the Trivium cipher (output) will act as the input of the A5/1 cipher. The registers used in the A5/1 cipher will be filled by the output bits of the Trivium cipher. The three registers will then be connected to generate an output which will be our required key stream.

In this paper, a relatively new hyper convolution spectra for characterization liquid, viscoelastic and solid samples is presented. Special attention is paid to the biophysical characterization of epithelial tissues and early detection of cancer of the skin, cervix, colon, and oral cavity. The method is based on the use of two types of white light, diffuse and polarized, from the same LED light sources. Based on the subtraction of the intensity values of these two lights and using the hyper convolution algorithm, the ratio of paired and unpaired electrons of tissue is obtained. This ratio correlates well with the state of the tissue: normal, irritating, precancerous, and cancerous. First, a proof-of-concept studies were performed, and later clinical studies on samples from one thousand two hundred fifteen people were performed. It showed that hyper Opto-Magnetic Imaging Spectroscopy (OMIS) can detect epithelial tissue cancers with an accuracy of 85-96%. Bearing in mind that the OMIS method also acquires the biophysical characteristics of the deeper skin layers (epidermis, basement membrane, dermis) by analysing convolution spectra of RGB channels of both diffuse and polarized white light, it is possible to apply this method in cosmetics (skin hydration, collagen, and elastin states, etc.). During OMIS applications, we noticed places where improvements could be made to increase method’s accuracy using advanced machine learning methodologies.

Addressing real-time aircraft target detection in microsatellite-based visible light remote sensing video imaging requires considering the limitations of imaging payload resolution, complex ground backgrounds, and the relative positional changes between the platform and aircraft. These factors lead to multi-scale variations in aircraft targets, making high-precision real-time detection of small targets in complex backgrounds a significant challenge for the detection algorithms. Hence, this paper introduces a real-time aircraft target detection algorithm for remote sensing imaging using an improved lightweight attention mechanism that relies on the YOLOv7 framework (SE-CBAM-YOLOv7). The proposed algorithm replaces the standard convolution (Conv) with a lightweight convolutional SEConv to reduce the computational parameters and accelerate the detection process of small aircraft targets, thus enhancing real-time onboard processing capabilities. Besides, the SEConv-based SPPCSPC (Spatial Pyramid Pooling and Connected Spatial Pyramid Convolution) module extracts image features. It improves detection accuracy while the feature fusion section integrates the CBAM hybrid attention network, forming the CBAMCAT module. Furthermore, it optimizes small aircraft target features in channel and spatial dimensions, improving the model's feature fusion capabilities. Experiments on public remote sensing datasets reveal the proposed SE-CBAM-YOLOv7 improves detection accuracy by 3% and mAP value by 4.2% compared to YOLOv7, significantly enhancing the detection capability for small-sized aircraft targets in satellite remote sensing imaging.

In this study, a novel porous geopolymer mortar (GP) was produced and tested experimentally. Industrial waste materials/by-products were used as constituents of the GP, along with dune sand. One sample was produced as a control sample for benchmarking. For the rest of the samples, 15%, 30%, and 45% by volume, the solid constituents were replaced with expanded polystyrene foam (EPS) beads. These mortar samples were heat cured to depolymerize the EPS to cause porosity inside the samples. Indoor experiments were conducted to evaluate the response of produced porous GP to high heat flux. The porous samples were able to reduce heat transmission across the opposite surfaces. Induced porosity resulted in a decrement in compressive strength from 77.2 MPa for the control sample to 15.8 MPa for 45% porous sample. However, the limit lies within the standards for partitioning walls in buildings and pavements in urban areas to absorb rainwater.

Ming-style round-backed armchairs as a classic Chinese chair design are renowned for the blend of ergonomics, practicality, and elegance. Although the Chinese armchair furniture industry has made strides in sustainability, there is still a need for further improvements in material selection, manufacturing processes, and supply chain management to fully support the development of sustainable furniture. Laminated bamboo lumber as new sustainable materials are becoming a popular option for furniture designers in the era of "sustainable design". This research aims to investigate the feasibility and application of laminated bamboo lumber in the design of Chinese armchair furniture and proposes innovative ideas for optimizing the armchair's design. First, an empirical study was conducted to comprehensively understand the classification of Ming-style round-backed armchairs’ structure to develop a 3D model. Secondly, an experimental research method was then employed to explore the parameters of laminated bamboo lumber for future studies. Additionally, a validation experiment was conducted to compare real-world scenarios with simulations using finite element analysis in Ansys. Finally, finite element analysis was used to test the feasibility and application of laminated bamboo lumber in furniture design, focusing on the material’s mechanical properties. Results indicated that laminated bamboo lumber has excellent mechanical properties as furniture design materials, subsequently, using the optimized results, the use of 0.6319 kg of steel was successfully reduced by 23.68% to ensure the armchair’s stability. This provides a reference for the future compter-assist and standardized innovative design of Chinese armchair. By incorporating compter-assist design and lightweight optimization, it is possible to save materials and make more efficient use of resources, thereby contributing to sustainable development goals in the field of furniture design.

Accurate and robust deep learning models for facial expression recognition are challenging to achieve, given the diversity of human faces and variations in images, including different facial poses and lighting conditions. In this work, we proposed a clock-driven convolutional Spiking Neural Network (SNN) and STDP fine-tune architecture, meticulously calibrated its hyperparameters, and experimented with various optimization methods. The best model resulted was trained and evaluated on the Fer2013 and FER+ database, obtaining an accuracy of 61.87% and 79.97% without requiring auxiliary training data or face registration. To our best knowledge, the proposed SNN achieved comparable accuracy to CNNs of similar depth and possessed the advantages of low energy consumption and high computational efficiency. The computational efficiency of the proposed SNN is approximately three times that of CNNs. Along with this, we introduced the very recent cumulative spike guided encoder visualization technique and revealed the strong encoding capability of the proposed SNN.

In recent years, there has been significant growth in the ubiquity and popularity of three dimensional(3D) point clouds, with an increasing focus on the classification of 3D point clouds. To extract richer features from point clouds, many researchers have turned their attention to various point set regions and channels within irregular point clouds. However, this approach has limited capability in attending to crucial regions of interest in 3D point clouds and may overlook valuable information from neighboring features during feature aggregation. Therefore, this paper proposes a novel 3D point cloud classification method based on global attention and adaptive graph convolution. The method consists of two main branches: the first branch com-putes attention masks for each point, while the second branch employs adaptive graph convolu-tion to extract global features from the point set. It dynamically learns features based on point interactions, generating adaptive kernels to effectively and precisely capture diverse relationships among points from different semantic parts. Experimental results demonstrate that the proposed model achieves 93.8% in overall accuracy and 90.8% in average accuracy on the ModeNet40 dataset.

Multi-floor environments are usually ignored while designing an autonomous robot for indoor cleaning applications. However, for efficient operation in such environments, the ability of a robotic platform to traverse staircases is crucial. Staircase detection and localization is highly important for planning the traversal on staircases. This paper describes a deep learning approach using Convolutional Neural Networks (CNNs) based Robot Operation System (ROS) to staircase detection and localization. We use an object detection network to detect staircases in images. We also localize these staircases using a contour detection algorithm to detect the target point, a point close to the center of the first step, and the angle of approach to the target point. Experiments are performed with data obtained from images captured on different types of staircases at different view points/angles. Results show that the approach is very accurate in identifying the presence of the staircase in the working environment and is also able to locate the target point with good accuracy.

Cerebrovascular and airway structures are tubular structures used for transporting blood and gases, respectively, providing essential support for the normal activities of the human body. Accurately segmenting these tubular structures is the basis of morphology research and patho-logical detection. Nevertheless, accurately segmenting these structures from images presents great challenges due to their complex morphological and topological characteristics. To address this challenge, this paper proposes a framework UARAI based on the U-Net multi-scale reverse at-tention network and sparse convolution network. The framework utilizes a multi-scale structure to effectively extract the global and deep detail features of vessels and airways. Further, it enhances the extraction ability of fine-edge features by a joint reverse attention module. In addition, the sparse convolution structure is introduced to improve the features' expression ability without increasing the model's complexity. Finally, the proposed training sample cropping strategy re-duces the influence of block boundaries on the accuracy of tubular structure segmentation. The experimental findings demonstrate that the UARAI-based metrics, namely Dice and IoU, achieve impressive scores of 90.31% and 82.33% for cerebrovascular segmentation and 93.34% and 87.51% for airway segmentation, respectively. Compared to commonly employed segmentation tech-niques, the proposed method exhibits remarkable accuracy and robustness in delineating tubular structures such as cerebrovascular and airway. These results hold significant promise in facilitating medical image analysis and clinical diagnosis, offering invaluable support to healthcare profes-sionals.

Many studies in the current literature annotate patterns in stock prices and use computer vision models to learn and recognize these patterns from stock price-action chart images. Additionally, current literature also use Long Short-Term Memory Networks to predict prices from continuous dollar amount data. In this study, we combine the two techniques. We annotate the consolidation breakouts for a given stock price data, and we use continuous stock price data to predict consolidation breakouts. Unlike computer vision models that look at the image of a stock price action, we explore using the convolution operation on raw dollar values to predict consolidation breakouts under a supervised learning problem setting. Unlike LSTMs that predict stock prices given continuous stock data, we use the continuous stock data to classify a given price window as breakout or not. Finally, we do a regularization study to see the effect of L₁, L₂, and Elastic Net regularization. We hope that combining regression and classification shed more light on stock market prediction studies.

As the embedded device and internet of things (IoTs) concept prevalent in today's world, there is an increasing demand for the security and performance requirements on deploying these devices to private and public sectors. The crucial part of it is to protect privacy, confidentiality and integrity, meanwhile, maintain an adequate level of performance during transmission, storage and access of critical information. While the conventional cryptography methods, such as the Advanced Encryption Standard (AES), SHA$-$2 hashing method and RSA and Diffie Hellman for message authentication and identification, work well on systems which have reasonable processing power and memory capabilities. These do not scale well into a world with embedded systems and sensor networks, in conjunction with their nature of smaller size and lower cost. Thus, in the context of resource constrained device, lightweight cryptography methods are proposed to overcome many of the problems of conventional cryptography possessed. This includes constraints related to physical size, processing requirement, memory limitation, energy drain and production cost. This paper provides a survey of the architectures that are defined as replacements for conventional ciphers within an IoTs space and discuss some trends in the design of future lightweight algorithms. The performance metrics are carefully chosen to reflect and assess the suitability for embedded devices. The aim of this research is to identify the various performance metrics applied on different types of symmetric block ciphers especially lightweight ciphers and compare the results on versatile platforms with stream ciphers and public key methods. The comparative analysis on efficient LW cipher will be tested against other similar block ciphers on both MacBook Pro with Intel core and resource constrained device Raspberry Pi with ARM processor.

The detection accuracy of bridge superficial defect using the deep neural network approach decreases significantly under light variation and weak texture condition. To address these issues, an enhanced intelligent detection method based on the YOLOv8 deep neural network is proposed in this study. Firstly, multi-branch coordinate attention (MBCA) is proposed to improve the accuracy of coordinate positioning by introducing a global perception module in coordinate attention mechanism. Furthermore, a deformable convolution based on MBCA is developed to improve the adaptability for complex feature shapes. Lastly, the deformable convolutional network-attention-YOLO (DAC-YOLO) detection algorithm is formed by replacing the deep C2F structure in the YOLOv8 architecture with deformable convolution. A supervised dataset consisting of 4794 bridge surface damage images is employed to verify the proposed method, and results show that it achieves improvements of 2.0% and 3.4% in mAP and R. Meanwhile, the model complexity decreases by 1.2G, increasing the detection speed by 3.5/f·s-1.

The primary goal of picture compression is to reduce the amount of unused image data while still storing or transmitting it in a format that is appropriate. The compression of raw binary data is quite different from the compression of a picture, and these differences may be rather substantial. In light of this, compression is often regarded as an essential technique for the purposes of both data storage an d transmission in order to mitigate the excessive amounts of data that are generated by these images. In order to transmit enormous datasets, particularly for the purposes of telemedicine and teleradiology, one needs a significant amount of storage capacity as well as an expansive network. As a result, compression is an important aspect of medical imaging. In addition to the importance of compression, the quality of the photos themselves is also an essential factor in the success of analysis. In addition to this, the amount of time necessary to compress the photographs before sending them should be reduced.

Speech emotion recognition remains a heavy lifting in natural language processing. It has strict requirements to the effectiveness of feature extraction and that of acoustic model. With that in mind, a Heterogeneous Parallel Convolution Bi-LSTM model is proposed to address these challenges. It consists of two heterogeneous branches: the left one contains two dense layers and a Bi-LSTM layer, while the right one contains a dense layer, a convolution layer, and a Bi-LSTM layer. It can exploit the spatiotemporal information more effectively, and achieves 84.65%, 79.67%, and 56.50% unweighted average recall on the benchmark databases EMODB, CASIA, and SAVEE, respectively. Compared with the previous research results, the proposed model achieves better performance stably.

Currently, most deep learning methods cannot solve the problem of scarcity of industrial product defect samples and significant differences in characteristics. This paper proposes an unsupervised defect detection algorithm based on a reconstruction network, which is realized using only a large number of easily obtained defect-free sample data. The network includes two parts: image reconstruction and surface defect area detection. The reconstruction network is designed through a fully convolutional autoencoder with a lightweight structure. Only a small number of normal samples are used for training so that the reconstruction network can be A defect-free reconstructed image is generated. A function combining structural loss and L1 loss is proposed as the loss function of the reconstruction network to solve the problem of poor detection of irregular texture surface defects. Further, the residual of the reconstructed image and the image to be tested is used as the possible region of the defect, and conventional image operations can realize the location of the fault. The unsupervised defect detection algorithm of the proposed reconstruction network is used on multiple defect image sample sets. Compared with other similar algorithms, the results show that the unsupervised defect detection algorithm of the reconstructed network has strong robustness and accuracy.

Focusing on the problem of identifying and classifying aero-engine models, this paper measures the infrared spectrum data of aero-engine hot jets using a telemetry Fourier transform infrared spectrometer. Simultaneously, infrared spectral data sets with the six different types of aero-engines are created. For the purpose of classifying and identifying infrared spectral data, a CNN architecture based on the continuous wavelet transform peak seeking attention mechanism (CWT-AM-CNN) is suggested. This method calculates the peak value of middle wave band by continuous wavelet transform, and the peak data is extracted by the statistics of the wave number locations with high frequency. Attention mechanism is used for the peak data, and the attention mechanism is weighted to the feature map of the feature extraction block. The training set, vali-dation set and prediction set are divided in the ratio of 8:1:1 for the infrared spectral data sets. For three different data sets, CWT-AM-CNN proposed in this paper is compared with the classical classifier algorithm based on CO2 feature vector and the popular AE, RNN and LSTM spectral processing networks. The prediction accuracy of the proposed algorithm in the three data sets is as high as 97%, and the lightweight network structure design not only guarantees high precision, but also has a fast running speed, which can realize the rapid and high-precision classification of the infrared spectral data of the aero-engine hot jets.

Amyotrophic Lateral Sclerosis (ALS) is a prototypical neurodegenerative disease characterized by progressive degeneration of motor neurons to severely effect the functionality to control voluntary muscle movement. Most of the non additive genetic aberrations responsible for ALS make its molecular classification very challenging along with limited sample size, curse of dimensionality, class imbalance and noise in the data. Deep learning methods have been successful in many other related areas but have low minority class accuracy and suffer from the lack of explainailbilty when used directly with RNA expression features for ALS molecular classification. In this paper we propose a deep learning based molecular ALS classification and interpretation framework. Our framework is based on training a convolution neural network (CNN) on images obtained from converting RNA expression values into pixels based on DeepInsight similarity technique. Then we employed Shapley Additive Explanations (SHAP) to extract pixels with higher relevance to ALS classifications. These pixels were mapped back to the genes which made them up. This enabled us to classify ALS samples with high accuracy for a minority class along with identifying genes that might be playing an important role in ALS molecular classifications. Taken together with RNA expression images classified with CNN, our preliminary analysis of the genes identified by SHAP interpretation demonstrate the value of utilising Machine Learning to perform molecular classification of ALS and uncover disease-associated genes.

Agriculture is one of the indispensable fields for the survival of mankind. Potatoes also have a significant role in the field of agriculture. The quality and quantity of potatoes are significantly impacted by several diseases, such as early blight and late blight, and manual interpretation of these leaf diseases is time-consuming and inconvenient. Fortunately, leaf appearance is used to detect diseases in potato plants. Productivity will considerably rise if the infections are detected early. Different types of image processing methods and machine learning methods are used for early recognition of those diseases from leaf images so that the product losses are decreased significantly. For the incredible and marvelous performance of CNN, it is the most popular deep learning method that is used immensely for the recognition of leaf diseases from images. Several pretrained deep learning models, such as VGG16, ResNet50, InceptionV3, MobileNetV2, Xception, and a deep learning model developed using CNN, are employed for potato leaf disease classification and recognition on the same dataset. The transfer learning technique is applied to the pretrained model and the data augmentation technique is applied to the Proposed CNN model for potato disease classification from leaf samples. Compared to pretrained models, the proposed CNN model offers the lowest loss and highest accuracy for potato leaf disease detection while using fewer parameters and layers. It achieves the best performance with a test accuracy of 99.33% compared to other Pretrained models used in the diagnosis of potato leaf disease.

In this study, we investigate the performance of the saddlepoint approximation of the probability mass function and the cumulative distribution function for the weighted sum of independent Poisson random variables. The goal is to approximate the hazard rate function for this complicated model. The better performance of this method is shown by numerical simulations and comparison with a performance of other approximation methods.

Cyber security plays an important role to protect our computer, network, program and data from unauthorized access. Intrusion detection system (IDS) and intrusion prevention system (IPS) are two main categories of cyber security, designed to identify any suspicious activities present in inbound and outbound network packets and restrict the suspicious incident. Deep neural network plays a significant role in the construction of IDS and IPS. This paper highlights a novel IDS using optimized convolution neural network (CNN-IDS). An optimized CNNIDS model is an improvement over CNN which selects the best weighted model by considering the loss in every epoch. All the experiments have been conducted on the well known NSL-KDD dataset. Information gain has been used for dimensionality reduction. The accuracy of the proposed model is evaluated through optimized CNN for both binary and multiclass categories. Finally, a critical comparison has been performed with other general classifiers like J48, Naive Bayes, NB tree, Random forest, Multilayer Perceptron (MLP), Support Vector Machine (SVM), Recurrent Neural Network (RNN) and Convolution Neural Network(CNN). All the experimental results demonstrate that the optimized CNN-IDS model records the best recognition rate with minimum model construction time.

Using machine learning or deep learning to solve the problem of garbage recognition and classification is an important application in computer vision, but due to the incomplete establishment of garbage datasets and the poor performance of complex network models on smart terminal devices, the existing garbage classification models The effect is not good.This paper presents a waste classification and identification method base on transfer learning and lightweight neural network. By migrating the lightweight neural network MobileNetV2 and rebuild it, The reconstructed network is used for feature extraction, and the extracted features are introduced into the SVM to realize the identification of 6 types of garbage. The model was trained and verified by using 2527 pieces of garbage labeled data in the TrashNet dataset, which ultimately resulted in a classification accuracy of 98.4% of the method, which proves that the method can effectively improve the classification accuracy and time and overcome the problem of weak data and less labeling. The over-fitting phenomenon encountered by small data sets in deep learning makes the model robust.

Aiming at the problem of small size of some spots on apple leaves and the difficulty of accurate detection of spot targets brought by the complex background of the orchard, this paper takes the alternaria leaf spot, rust, brown spot, grey spot and frog eye leaf spot on apple leaves as the research object, and proposes a high-accuracy detection model YOLOv5-Res and lightweight detection model YOLOv5-Res4 are proposed. Firstly, a multiscale feature extraction module ResBlock is designed by combining the Inception multi-branch structure and ResNet residual idea. Secondly, a lightweight feature fusion module C4 is designed to reduce the number of model parameters while improving the detection ability of small targets. Finally, a parameter streamlining strategy based on optimized model architecture is proposed. The experimental results show that the performance of YOLOv5-Res model and YOLOv5-Res4 model is significantly improved, the [email protected] value is improved by 2.8% and 2.2% compared with YOLOv5s model and YOLOv5n model, respectively, and the size of YOLOv5-Res model and YOLOv5-Res4 model is only 10.8MB and 2.4MB, and the number of model parameters is reduced compared with YOLOv5s model and YOLOv5n model. counts are reduced by 22% and 38.3% compared to the YOLOv5s model and YOLOv5n model.

According to the risk investigations of being involved in an accident, alcohol-impaired driving is one of the major causes of motor-vehicles accidents. Preventing highly intoxicated persons from driving would potentially save many lives. This paper proposes a lightweight in-vehicle alcohol detection that processes the data generated from 6-alcohol sensors (MQ-3 Alcohol Sensors) using an optimizable shallow neural network (O-SNN). The experimental evaluation results exhibit a high-performance detection system scoring a 99.8% of detection accuracy with a very short inferencing delay of 2.22 µ seconds. Hence, the proposed model can be efficiently deployed and used to discover in-vehicle alcohol with high accuracy and low inference overhead as a part of the driver alcohol detection system for safety (DADSS) system aiming at massive deployment of alcohol sensing systems that could potentially save thousands of lives annually.

In recent years, many algorithms based on end-to-end deep networks have been proposed to deal with the target detection problem of videos. However, the deep network models usually consume a lot of computing resources during the procedure of analysis of videos with complex dynamic backgrounds. In this paper, a new method of object detection based on information theory is presented. Firstly, each frame in a video is converted into an effective information map by using the Harris corner detection method. Secondly, the sensitive areas in the frame are extracted by using the context information and the effective information maps of the consecutive video frames. The sensitive areas in the video frame are the candidate areas where the target objects would be appeared at high probabilities. Thirdly, the information entropy features of each sensitive area are extracted to form the feature matrix, based on which, an SVM model is trained for selecting the target areas from the sensitive areas. Finally, the locations of the objects are detected based on the target areas in the video with a complex dynamic background. As a lightweight video detection framework, the method presented in this paper can save a lot of computing resources. Experimental results show that this method can achieve good results in the benchmark of CDnet 2014.

In this study, seven mortar mixes were prepared by replacing natural sand by crumb rubber ,CR, (10%, 25%, 50%, 60%, 75% and 100%). The properties of mortars, both in their fresh and hardened states, were studied. Key characterisitcs, including density, water absorption coefficient, porosity, thermal conductivity, heat capacity, shrinkage/swelling, elastic modulus, compressive strength, flexure strength, fracture energy and performance after exposure to heat, were evaluated. The results obtained showed that as the CR fraction increased, density, initial setting time, and workability decreased but mortars with CR fractions ranged between 25% and 50% are lightweight and can be used for repairing as they fulfill satndards. It was observed that strengths and stiffness decreased with higher CR content while shrinkage increased for CR percentage higher than 60%. However, up to 50% of CR content the mortars obey to the standards for repair. Interestingly, incorporating up to 50% waste tires proved to improve comfort and thermal resistance without affecting thermal inertia. A slight increase in the mass loss is observed when mortars are exposed to high temperatures. Mortars containing CR between 25% and 50% can be classified as lightweight and thermally insulating mortars, suitable for repairing concrete structures in accordance with industry standards.

To address the problems of poor recognition, low detection accuracy, a large number of model parameters and computation, complex network structure, and unfavorable portability to embedded devices in traditional tennis ball detection algorithms, this study proposes a lightweight tennis ball detection algorithm YOLOv5s-Z based on Robomater EP. The main work is as follows: Firstly, constructing lightweight G-Backbone and G-Neck network layers to reduce the number of parameters and computation of the network structure. Secondly, the convolutional coordinate attention is incorporated in G-Backbnone to embed the location information into the channel attention, which makes the network obtain the location information in a larger area through multiple convolutions and enhances the expression ability of the mobile network learning features. In addition, the Concat module in the original feature fusion is modified into a weighted bi-directional feature pyramid W-BiFPN with settable learning weights to improve the feature fusion capability and achieve efficient weighted feature fusion and bi-directional cross-scale connectivity. The EIOU loss is introduced to split the influence factor of aspect ratio and calculate the length and width of the target frame and anchor frame respectively, combined with Focal-EIOU Loss to solve the problem of imbalance between difficult and easy samples. The activation function Meta-ACON is introduced to achieve an adaptive selection of whether to activate the neurons and improve the detection accuracy. Finally, the experimental results show that compared with the original algorithm, the YOLOv5s-Z algorithm reduces the number of parameters and computation by 42$\%$ and 44$\%$, the model size by 39$\%$, and 2$\%$ improvement in average accuracy mean value, which verifies the effectiveness of the improved algorithm and the light weight of the model to meet the deployment requirements of embedded devices, and adapts Robomaster EP for accurate detection and real-time recognition of tennis balls.

The coexistence of ferroelectric and magnetic order parameters in multiferroic materials opens up a host of new collective properties. In particular, the magnetoelectric (ME) effect namely the induction of electric polarization by a magnetic field or magnetization by an electric field has been widely studied in multiferroics. PVDF is a ferroelectric polymer that has attracted considerable research interest for sensing applications. Compared to traditional ceramic composites, the polymer-ceramic nanocomposites offer inherent advantages, including easy processing, mechanical flexibility and the ability to be moulded into complicated configurations for advanced devices with reduced volume and weight. Additionally, polymer composites generally exhibit superior ME coefficients, attributable to the improved displacement transfer capability of the flexible polymer matrix. In this report, free-standing, flexible and lightweight polymer–ceramic nanocomposite thin films with a fixed weight percentage of ferromagnetic CoFe2O4 nanoparticles have been fabricated using a solution casting technique. The structural, microstructural, and electrical properties of the composite have been characterized by standard experimental techniques. The structural and chemical analyses prove a homogeneous dispersion of the fillers in the microstructure of the composite. The electrical response investigated by impedance spectroscopy reveals the contributions of grains and grain boundaries to the whole impedance of the composites. The ac conductivity as a function of frequency obeys Jonscher’s power law. The improved magnetoelectric properties suggest promising applications in multifunctional devices, including field sensor applications.

Deep learning methods have been widely used in PolSAR image classification. To learn the polarimetric information, many deep learning methods expect to learn high-level semantic features from original PolSAR data. However, only original data cannot learn multiple scattering features and complex structures for extremely heterogeneous terrain objects. In addition, deep learning methods always cause edge confusion due to the high-level features. To overcome these shortages, we propose a double-channel CNN network combined with an edge-preserving MRF model(DCCNN-MRF) for PolSAR image classification. Firstly, to combine complex matrix data and multiple scattering features together, a double-channel convolution network(DCCNN) is developed, which consists of a Wishart-based complex matrix and multi-feature subnetworks. The Wishart-based complex matrix network can learn the statistical characteristics and channel correlation well, and the multi-feature network can learn high-level semantic features well. Then, a unified network framework is designed to fuse two kinds of features to enhance advantageous features and reduce redundant ones. Finally, an edge preserving MRF model is designed to combine with the DCCNN network. In the MRF model, a sketch map-based edge energy function is designed by defining adaptive weighted neighborhood for edge pixels. Experiments are conducted on four real PolSAR data sets with different sensors and bands. Experimental results demonstrate the effectiveness of the proposed DCCNN-MRF method.

Background: Strength assessment is one of the main fields in sports performance, physical rehabilitation, physical activity and health. Purpose: To compare maximal voluntary isometric contractions (MVIC) and paired voluntary isometric contractions (VIC) of knee extensors between an isokinetic dynamometer (BIODEX) and a portable and lightweight device (DINABANG). Methods: From 19 volunteers (age: 28.7±7 y; body mass: 72±10 kg and height: 173±7 cm) we obtained 114 paired MVIC measures and, from the force-time curves of these repetitions, 22507 paired VIC measures of knee extensors. Results: We observed “excellent” repeatability for MVIC (ICC:1.00; p&lt;0.001) between BIODEX (247±79.5 Nm) and DINABANG (247±74.8 Nm), with “trivial” effect (mean difference: 0.12 Nm (0.02%); 95%CI: -0.13 to 0.23 Nm; p=0.606; d=0.048). Bland-Altman plots revealed high accuracy for MVIC (bias: 0.12 Nm) and consistent distribution (precision) inside the limits of agreement (-4.81 to 5.06 Nm) and respective 95%CI. “Excellent” repeatability was also observed for VIC (ICC:1.00; p&lt;0.001) between BIODEX (219±84.1 Nm) and DINABANG (218±84.0 Nm), with “trivial” effect (0.24 Nm (0.11%); 0.08 to 0.11 Nm; p&lt;0.001; d=0.100). Bland-Altman plots revealed high accuracy for VIC (bias: 0.24 Nm) and consistent distribution (precision) inside the limits of agreement (-4.5 to 4.9 Nm) and respective 95%CI. Conclusion: DINABANG is accurate, precise and reliable for torque measurement.

In recent years, neural networks based on attention mechanisms have been increasingly widely used in speech recognition, separation, enhancement, and other fields. In particular, the convolution-augmented transformer has achieved good performance as it can combine the advantages of convolution and self-attention. Recently, the gated attention unit (GAU) has been proposed. Compared with the traditional multi-head self-attention, approaches with GAU are effective and computationally efficient. In this article, we propose a network for speech enhancement called CGA-MGAN, a kind of Metric GAN based on convolution-augmented gated attention. CGA-MGAN captures local and global correlations in speech signals at the same time through the fusion of convolution and gated attention units. Experiments on Voice Bank + DEMAND show that the CGA-MGAN we propose achieves an excellent performance (3.47 PESQ, 0.96 STOI, and 11.09dB SSNR) at a relatively small model size (1.14M).

The widespread adoption of IoT networks has revolutionized modern life thanks to their diverse range of applications. With their increased usage, the need to transfer data securely has never been more vital. Often IoT devices are battery-driven and possess limited processing and storage capabilities. In response to those limitations, there has been a shift towards the implementation of resource-efficient and lighter protocols. This research aims to evaluate how lightweight key establishment through Object Security for Constrained RESTful Environments (OSCORE) and Ephemeral Diffie-Hellman Over COSE (EDHOC) can enhance cybersecurity in IoT networks where resources are limited. The study aims to explore different key management approaches and the effects of certificates on security, efficiency, and power consumption. The research methodology consists of the practical implementation of the protocols in a physical system where factors such as the impact of hardware acceleration on computational overhead and overall power consumption will be assessed. Furthermore, the study will verify the cost of resources and overall efficiency, evaluating them against real-world scenarios. The expected contributions of this study are insights into the tradeoffs between security, power consumption, and efficiency in resource-limited IoT environments.

This study aimed to compare the differences in durability and prestress loss between normal-weight concrete (NC) and lightweight aggregate concrete (LWC) prestressed box girders, which were constructed at the same time in the same area, so as to verify the superiority of using synthetic lightweight aggregate (LWA) made from reservoir sediments in prestressed bridges. For the NCs and LWCs used in prestressed box girders, the basic mechanical properties were tested on the one hand, and the durability properties were tested on the other hand. Then, through the prestress monitoring system, the prestress loss of the two groups of the prestressed box girders was tracked. The results of the durability test confirmed that LWC can inhibit the penetration of air, water, and chloride ions by strengthening the interfacial transition zone between the aggregate and the cement paste, thereby improving its durability. Moreover, the magnetic flux prestress loss of the NC prestressed box girder reached 8.1%. In contrast, the magnetic flux prestress losses on both sides of the LWC prestressed box girder were 4.6% and 4.9%, respectively. This verified that, under the same environmental conditions, the use of LWC produced less of a prestress loss than the use of NC.

After the great success of Mobile wallet, the Internet of Things (IoT) leaves the door wide open for consumers to use their connected devices to access their bank accounts and perform routine banking activities from anywhere, anytime and with any device. However, consumers need to feel safe when interacting with IoT-based payment systems, and their personal information should be protected as much as possible. Unlike as usually done in the literature, in this paper, we introduce two lightweight and secure IoT-based payment protocols based on an identity-based signature scheme. We adopt a server-aided verification technique to construct the first scheme. This technique allows to outsource the heavy computation overhead on the sensor node to a cloud server while maintaining the user's privacy. The second scheme is built upon a pairing-free ECC-based security protocol to avoid the heavy computational complexity of bilinear pairing operations. The security reduction results of both schemes are held in the Random Oracle Model (ROM) under the discrete logarithm and computational Diffie-Hellman assumptions. Finally, we experimentally compare the proposed schemes against each other and against the original scheme on the most commonly used IoT devices: a smartphone, a smartwatch and the embedded device Raspberry Pi. Compared with existing schemes, our proposed schemes achieve significant efficiency in the term of communication and computational overheads

With the ever-growing emphasis on global decarbonization and rapid increases in the power density of electronics equipment in recent years, new methods and lightweight materials have been developed to manage heat load as well as interfacial stresses associated with Coefficient of Thermal Expansion (CTE) mismatch between components. The Al-Si system provides an attractive combination of CTE performance and high thermal conductivity whilst being a very lightweight option. Such materials are of interest to industries where thermal management is a key design criterion, such as aerospace, automotive, consumer electronics, defense, EV and space. This paper will describe the development and manufacture of a family of high-performance hypereutectic Al-Si alloys (AyontEX™) by a powder metallurgy method. These alloys are of particular interest for structural heat sink applications that require high reliability under thermal cycling (CTE of 17μm/(m·°C)) as well as reflective optics and instrument assemblies that require good thermal and mechanical stability (CTE of 13μm/(m·°C)). Critical performance relationships are presented, coupled with the microstructure, physical and mechanical properties of these Al-Si alloys.

As the world increasingly becomes more interconnected, the demand for safety and security is ever-increasing, particularly for industrial networks. This has prompted numerous researchers to investigate different methodologies and techniques suitable for intrusion detection systems (IDS) requirements. Over the years, many studies have proposed various solutions in this regard including signature-based and machine-learning (ML) based systems. More recently, researchers are considering deep learning (DL) based anomaly detection approaches. Most proposed works in this research field aimed to achieve either one or a combination of high accuracy, considerably low false alarm rates (FARs), high classification specificity and detection sensitivity, achieving lightweight DL models, or other ML and DL-related performance measurement metrics. In this study, we propose a novel method to convert a raw dataset to an image dataset to magnify patterns. Based on this we devise an anomaly detection for IDS using a lightweight convolutional neural network (CNN) that classifies denial of service and distributed denial of service. The proposed methods were evaluated using a modern dataset, CSE-CIC-IDS2018, and a legacy dataset, NSL-KDD. We have also applied a combined dataset to assess the generalization of the proposed model across various datasets. Our experimental results have demonstrated that the proposed methods achieved high accuracy and considerably low FARs with high specificity and sensitivity. The resulting loss and accuracy curves have also demonstrated the excellent generalization of the proposed lightweight CNN model, effectively avoiding overfitting. This holds for both the modern and legacy datasets, including their mixed version.

We propose Context-aware Feature Transformer Network (CaFTNet), a novel network for human pose estimation. To address the issue of limited modeling of global dependencies in convolutional neural networks, we design Transformerneck to strengthen the expressive power of features. Transformerneck directly substitutes the 3×3 convolution in bottleneck of HRNet with Contextual Transformer (CoT) block, while reducing the complexity of the network. Specifically, CoT first produces keys with static contextual information through 3×3 convolution. Then, relying on the query and contextualization keys, the dynamic contexts are generated through two concatenated 1×1 convolutions. Static and dynamic contexts are eventually fused as an output. Additionally, for the multi-scale networks, in order to further refine the features of the fusion output, we propose an Attention Feature Aggregation Module(AFAM). Technically, given an intermediate input, AFAM successively deduces attention maps along channel and spatial dimensions. Then, Adaptive refinement module(ARM) is exploited to activate the obtained attention maps. Finally, the input undergoes adaptive feature refinement through multiplication with the activated attention maps. Through the above studies, our lightweight network provides a powerful clue for detection of keypoints. Experiments are implemented on the COCO and MPII datasets. The model achieves 76.2 AP on the COCO val2017. Compared to other methods with the CNN as the backbone, CaFTNet reduces the number of parameters by 72.9 %. On the MPII, our method uses only 60.7% of the number of parameters, acquiring semblable results to other methods with the CNN as the backbone.

Seniors safety is a compelling need, which necessitates 24/7 real-time monitoring and timely dangerous action recognition. Being able to mirror characteristics of physical objects (PO) to corresponding logical objects (LO) and seamlessly monitor their footprints thus detect anomaly parameters, Digital Twins (DT) has been considered a practical way to provide virtual health services for seniors safety. Meanwhile, widely adopted Internet of Medical Things (IoMT) consisting of wearable sensors and non-contact optical cameras for self and remote health data monitoring also raises concerns on information security and privacy violation. Therefore, security of POs, LOs and reliable data sharing among healthcare professionals are challenging as constructing trust and privacy-preserving virtual health services. Thanks to characteristics of decentralization, traceability and unalterability, Blockchain is promising to enhance security and privacy properties in many areas like data analysis, finance and healthcare. This paper envisions a lightweight authentication framework (LAF) to enable secure and privacy-preserving virtual healthcare services. Leveraging Non-Fungible Token (NFT) technology to tokenize LOs and data streams on blockchain, anyone can certify the authenticity of a digital LO along with its synchronized data between PO without relying on a third-party agency. In addition, the NFT-based tokenization not only allows owners fully control their IoMT devices and data, but it also enables verifiable ownership and traceable transferability during data sharing process. Moreover, NFT only contains references to encrypted raw data that are saved on off-chain storage like local files or distributed databases, such a hybrid storage strategy ensures privacy-preservation for sensitive information. A proof-of-concept prototype is implemented and tests are conducted on a case study of seniors safety. The experimental evaluation shows the feasibility and effectiveness of the proposed LAF solution.

When we talk about the Internet of Things, we are referring to the connecting of things to a1 physical network that is embedded with software, sensors, and other devices that allow information2 to be exchanged between devices. It is possible that the interconnection of devices will present3 issues in terms of security, trustworthiness, reliability, and confidentiality, among other things.4 The proposed approach is effective at detecting intrusions into the Internet of Things network.5 Initially, the privacy-preserving technology was deployed utilising a Blockchain-based methodology6 to ensure that personal information was protected. Patients’ health records (PHR) security is the7 most crucial component of encryption over the Internet because of the value and importance of these8 records, particularly in the context of the Internet of Medical Things (IoMT). The search terms access9 mechanism is one of the most common approaches used to access personal health records from a10 database, but it is vulnerable to a number of security flaws. However, while blockchain-enabled11 healthcare systems provide increased security, they may also introduce weaknesses into the current12 state of the art. Blockchain-enabled frameworks have been proposed in the literature as a means13 of resolving those challenges. These solutions, on the other hand, are primarily concerned with14 data storage, with Blockchain serving as a database. To enable secure search and keyword-based15 access to a distributed database, this study proposes the use of blockchain technology as a distributed16 database, together with a homomorphic encryption mechanism. Aside from that, the suggested17 system includes a secure key revocation mechanism that can be used to automatically update various18 policies.As a result, our proposed approach provides greater security, efficiency, and transparency19 while also being more cost-effective. We have compared the findings of our proposed models with20 those of the benchmark models, if appropriate. Our comparison research demonstrates that our21 suggested framework provides a more secure and searchable mechanism for the healthcare system22 than the current state of the art.

In the modern construction industry, lightweight aggregate concrete (LWAC) is often used in the production of load-bearing structural members. LWAC can be up to 40% lighter by volume in comparison to normal strength concrete. On the other hand, the lack of adequate numerical models often limits the practical application of innovative building materials, such as lightweight concrete, in real projects. This trend is due to the uncertainties in design standard methods and calculation errors, the level of which is generally unacceptable to civil engineers in terms of safety and reliability. In the present paper, a comparative numerical deformation analysis of a full-scale bridge deck slab and girder has been carried out. Using the physical model proposed by the authors and the finite element software ATENA, the deformations of full–scale lightweight and traditional reinforced concrete elements under short-term effects of permanent and variable loads was compared. Depending on the safety and serviceability limit requirements, it was found that the amount of longitudinal reinforcement in lightweight reinforced concrete elements can be reduced compared to normal reinforced concrete elements with the same parameters. The results of the numerical analysis show that the deformation analysis model proposed by the authors can be a reliable tool for the design of lightweight concrete flexural members by selecting the optimum geometrical and reinforcement parameters limited by the stiffness condition.

In the present trend of constructing taller and longer structures, the application of lightweight aggregate concrete is becoming an increasing important advanced solution in the modern construction industry. In engineering practice, the analysis of lightweight concrete elements is performed using the same algorithms used for normal concrete elements. As an alternative to traditional engineering methods, nonlinear numerical algorithms based on constitutive material models may be used. The paper presents a comparative analysis of curvature calculations for flexural lightweight concrete elements, incorporating analytical code methods EN 1992-1 and ACI 318-14, as well as a numerical analysis using the constitutive model of cracked tensile lightweight concrete recently proposed by the authors. To evaluate the adequacy of the theoretical predictions, experimental data of 51 lightweight concrete beams tested during five different programmes were collected. A comparison of theoretical and experimental results showed that the most accurate predictions are obtained using numerical analysis and the constitutive model proposed by the authors. In the future, the latter algorithm can be used as a reliable tool for improving the design standard methods or numerical modelling of lightweight concrete elements subjected to short-term loading.

Today, the style of light construction materials used in building is one of the most important factors in reducing building's dead load and better performance of the structures in the earthquake. One of the ways to reduce the structure weight is to use lightweight blocks instead of using traditional materials. The main purpose of this research is to compare density, compressive strength and water absorption volume of non-load-bearing lightweight blocks made of natural and artificial lightweight aggregates. Scoria lightweight aggregates of Sanandaj, Ghorveh mine, pumice in Tabriz, Bostanabad mine, and Leca in Leca enterprise have been used to make the samples. Given the importance of the materials used, grading of coarse-grained materials has been conducted based on the standard of 7657 and grading of fine materials have been conducted based on the standard of 302.The experiments' results show that Scoria blocks due to hard texture, and high mechanical resistance of their lightweight aggregates, have had higher compressive strength, and density and lower water absorption volume compared to pumice and Lika lightweight aggregate blocks. Pumice blocks despite having desirable compressive strength and lower density compared to the two other blocks have higher water absorption volume, and do not meet the standard conditions. This same factor causes it faces with less interest. Among these Lika blocks with density of 1151.94 (kg per cubic meter) below 2000 kilograms per cubic meter of Iran density standard of 7782 (28-day compressive strength of 2.57 MPa), higher than 2.5 MPa of Iran compressive strength standard of 7782 (and water absorption volume of 282.92 kg per cubic meter) below 288 kilograms per cubic meter of Iran water absorption volume standard of 7782 (as a non-load-bearing lightweight block) have been diagnosed desirable.

Table detection is a preliminary step in extracting reliable information from tables in scanned document images. We present CasTabDetectoRS, a novel end-to-end trainable table detection framework that operates on Cascade Mask R-CNN, including Recursive Feature Pyramid network and Switchable Atrous Convolution in the existing backbone architecture. By utilizing a comparatively lightweight backbone of ResNet-50, this paper demonstrates that superior results are attainable without relying on pre and post-processing methods, heavier backbone networks (ResNet-101, ResNeXt-152), and memory-intensive deformable convolutions. We evaluate the proposed approach on five different publicly available table detection datasets. Our CasTabDetectoRS outperforms the previous state-of-the-art results on four datasets (ICDAR-19, TableBank, UNLV, and Marmot) and accomplishes comparable results on ICDAR-17 POD. Upon comparing with previous state-of-the-art results, we obtain a significant relative error reduction of 56.36%, 20%, 4.5%, and 3.5% on the datasets of ICDAR-19, TableBank, UNLV, and Marmot, respectively. Furthermore, this paper sets a new benchmark by performing exhaustive cross-datasets evaluations to exhibit the generalization capabilities of the proposed method.

Rapid advancements in the fifth generation (5G) communication technology and mobile edge computing (MEC) paradigm lead to the proliferation of unmanned aerial vehicles (UAV) in urban air mobility (UAM) networks, which provide intelligent services for diversified smart city scenarios. Meanwhile, the widely deployed internet of drones (IoD) in smart cities also brings up new concerns on performance, security, and privacy. The centralized framework adopted by conventional UAM networks is not adequate to handle high mobility and dynamicity. Moreover, it is necessary to ensure device authentication, data integrity, and privacy preservation in UAM networks. Thanks to characteristics of decentralization, traceability, and unalterability, Blockchain is recognized as a promising technology to enhance security and privacy for UAM networks. In this paper, we introduce LightMAN, a lightweight microchained fabric for data assurance and resilience-oriented UAM networks. LightMAN is tailored for small-scale permissioned UAV networks, in which a microchain acts as a lightweight distributed ledger for security guarantees. Thus, participants are enabled to authenticate drones and verify the genuineness of data that is sent to/from drones without relying on a third-party agency. In addition, a hybrid on-chain and off-chain storage strategy is adopted that not only improves performance (e.g,.latency and throughput) but also ensures privacy preservation for sensitive information in UAM networks. A proof-of-concept prototype is implemented and tested on a Micro Air Vehicle Link (MAVLink) simulator. The experimental evaluation validates the feasibility and effectiveness of the proposed LightMAN solution.

Extensive growth in the volume of irregular brain cells is known as brain tumor. Human brain is surrounded by stiff skull. There are various issues that occur due to the growth of any tumor inside this restricted space. The malignant and benign are two main categories of the brain tumor. The skull is pressurized to enlarge from inside in case of growth of any benign or malignant tumor. This tumor leads to harm in brain and it may be dangerous to life also. The brain tumor is divided into two kinds - primary or secondary. The brain tumor detection techniques have various phases. In this paper, comparative study of CNN with GLCM approach and superpixel based spectral clustering is done tumor. This work takes into account metrics like accuracy, sensitivity and specificity for drawing the comparison between both the techniques.

Edge AI accelerators have been emerging as a solution for near customers’ applications in areas such as unmanned aerial vehicles (UAVs), image recognition sensors, wearable devices, robotics, and remote sensing satellites. These applications not only require meeting performance targets but also meeting strict reliability and resilience constraints due to operations in harsh and hostile environments. Numerous research articles have been proposed, but not all of these include full specifications. Most of these tend to compare their architecture with other existing CPUs, GPUs, or other reference research. This implies that the performance results of the articles are not comprehensive. Thus, this work lists the three key features in the specifications such as computation ability, power consumption, and the area size of prior art edge AI accelerators and the CGRA accelerators during the past few years to define and evaluate the low power ultra-small edge AI accelerators. We introduce the actual evaluation results showing the trend in edge AI accelerator design about key performance metrics to guide designers on the actual performance of existing edge AI accelerators’ capability and provide future design directions and trends for other applications with challenging constraints.

With the continuous development of deep learning, the application of object detection based on deep neural network in the coal mine has been expanding. Simultaneously, as the production applications demand higher recognition accuracy, most research chooses to enlarge the depth and parameters of the network to improve accuracy. However, due to the limited computing resources in the coal mining face, it is challenging to meet the computation demands of a large number of hardware resources. Therefore, this paper proposes a lightweight object detection algorithm designed specifically for coal mining face, referred to as CM-YOLOv8. The algorithm introduces adaptive predefined anchor boxes tailored to the coal mining face dataset to enhance the detection performance of various targets. Simultaneously, a pruning method based on the L1 norm is designed, significantly compressing the model's computation and parameter volume without compromising accuracy. The proposed algorithm is validated on the coal mining dataset DsLMF+, achieving a compression rate of 40% on the model volume with less than a 1% drop in accuracy. Comparative analysis with other existing algorithms demonstrates its efficiency and practicality in coal mining scenarios. The experiments confirm that CM-YOLOv8 significantly reduces the model's computational requirements and volume while maintaining high accuracy.

Defect detection plays a pivotal role in quality control for fabrics. In order to enhance the accuracy and efficiency of fabric defect detection, we have proposed the PRC-Light YOLO model for fabric defect detection and have established a detection system. Firstly, we add new convolution operators in Backbone for the YOLOv7 and integrate them with Extended-Efficient Layer Aggregation Network. This combination constructs a new feature extraction module that not only reduces the computational effort of the network model, but also extracts spatial features effectively. Secondly, we employ multi-branch dilated convolutions feature pyramid, and introduce lightweight upsampling operators to improve performance of the feature fusion network. This module achieves an expanded receptive field by generating real-time adaptive convolution kernels, allowing for the collection of crucial information from regions with a richer contextual context. To further minimize the computation during network model training, we adopt the HardSwish activation function. Finally, we apply the Wise-IOU v3 bounding box loss function as a dynamic non-monotonic focusing mechanism, which decreases adverse gradients from low-quality instances. We conduct data augmentation on real fabric dataset to raise the generalization capability of the PRC-Light YOLO model. Compared with the YOLOv7 model, numerous simulation experiments show that our proposed methods reduce the model’s parameters and computation by 18.03% and 20.53%, respectively. Simultaneously, there has been a 7.6% improvement in mAP.

The rate of accidents in Morocco is experiencing a significant increase. Automatic license plate detection and recognition (ALPR) is an essential road safety technology. It facilitates applications such as traffic control, law enforcement, and toll collection by allowing for the automated recognition of vehicles on the road. In this study, we incorporated ShuffleNet V2 into the end-to-end YOLOV5 object detection system. The objective was to develop a model capable of identifying Moroccan license plates with an accuracy of 87%. The proposed model is intended to attain a high processing performance of 60 frames per second (FPS) while maintaining a low weight of 1.3 megabytes (MB) and a parameter count of 0.44 million floating point operations (MGFLOP). Our model maintains superior performance and is highly compatible with embedded systems compared to other models utilized in the same context.

With the rapid development of electronic and communication technology in military radar, the demand for microwave absorbing materials in low-frequency with thin layer is growing increasingly. In this study, flexible Co3O4/CC (carbon cloth) composites derives from Co-MOFs (metal-organic frameworks)/CC are prepared by hydrothermal and thermal treatment processes. The flexible precursors of Co-MOFs/CC are calcined with different calcination temperatures, which the material structure, dielectric properties and microwave absorption performance are changed. With the increase of calcination temperature, the minimum reflection loss of the corresponding Co3O4/CC composites gradually moves to the lower frequency with thinner thickness. In addition, the Co3O4/CC composites with 25 wt% filler loading ratio exhibit the minimum reflection loss (RL) of -46.59 dB at 6.24 GHz with 4.2 mm thickness. When the thickness is 3.70 mm, the effective absorption bandwidth is 3.04 GHz from 5.84 to 8.88 GHz. This study not only proves that the composite Co3O4/CC is a kind of outstanding microwave absorbing material with better flexibility, but also provides a useful inspiration for the low frequency and broadband microwave absorbing material.

Underwater robotics equipped with visual detection systems have the function of detecting un-derwater artifacts, which is of great significance to deep-sea archaeology. Underwater artifacts are located in complex environments with poor imaging conditions, and the targets have chal-lenging problems such as breakage, stacking, and sediment burial, which causes the marine cul-tural target detection failures. To solve these problems, this paper proposes an underwater cul-tural target detection algorithm based on the deformable deep aggregation network model for underwater robotics exploration. To fully extract the target feature information of underwater targets in complex environments, this paper designs a multi-scale deep aggregation network with deformable convolutional layers. Besides, the BAM attention module is designed for fea-ture optimization, which enhances the potential feature information of the target while weak-ening the background interference information. Finally, the target prediction is achieved through feature fusion at different scales. The proposed algorithm has been extensively validat-ed and analyzed on the collected underwater artifact datasets, and the precision, recall, and mAP of the algorithm have reached 93.1%, 91.4%, and 92.8%, respectively. In addition, the present al-gorithm has been practically deployed on the underwater robotics. In the deep-sea tests, the ar-tifact detection frame rate reaches up to 19 fps, which satisfies the real-time target detection。

Grapes are a globally popular fruit, with grape cultivation worldwide being second only to citrus. This article focuses on the low efficiency and accuracy of traditional manual grading of red grape external appearance and proposes a small-sample red grape external appearance grading model based on transfer learning with convolutional neural networks (CNNs). Initially, the CNN transfer learning method was used to transfer the pre-trained AlexNet, VGG16, GoogleNet, InceptionV3, and ResNet50 network models on the ImageNet image dataset to the red grape image grading task. By comparing the classification performance of the CNN models of these five different network depths with fine-tuning, ResNet50 with a learning rate of 0.001 and a loop number of 10 was determined to be the best feature extractor for red grape images. Moreover, given the small number of red grape image samples in this study, different convolutional layer features output by the ResNet50 feature extractor were analyzed layer by layer to determine the effect of deep features extracted by each convolutional layer on SVM classification performance. This analysis helped to obtain a ResNet50+SVM red grape external appearance grading model based on the optimal ResNet50 feature extraction strategy. Experimental data showed that the classification model constructed using the feature parameters extracted from the 10th node of the ResNet50 network achieved an accuracy rate of 95.08% for red grape grading. These research results provide a reference for the online grading of red grape clusters based on external appearance quality and have certain guiding significance for the quality and efficiency of grape industry circulation and production.

Deep neural network (DNN) watermarking is a potential approach for protecting the intellectual property rights of DNN models. Similar to classical watermarking techniques for multimedia content, the requirements for DNN watermarking include capacity, robustness, and transparency, and other factors. Studies have focused on robustness against retraining and fine-tuning. However, less important neurons in the DNN model may be pruned. Moreover, although the encoding approach in renders DNN watermarking robust against pruning attacks, the watermark is assumed to be embedded only into the fully connected layer in the fine-tuning model. In this study, we extended the method such that the model can be applied to any convolution layer of the DNN model and designed a watermark detector based on a statistical analysis of the extracted weight parameters to evaluate whether the model is watermarked. Using a nonfungible token mitigates the overwriting of the watermark and enables checking when the DNN model with the watermark was created.

The colossal depths of the deep neural network sometimes suffer from ineffective backpropagation of the gradients through all its depths. Whereas, The strong performance of shallower multilayer neural structures prove their ability to increase the gradient signals in the early stages of training which easily gets backpropagated for global loss corrections. Shallow neural structures are always a good starting point for encouraging the sturdy feature characteristics of the input. In this research, a shallow, deep neural structure called PrimeNet is proposed. PrimeNet is aimed to dynamically identify and encourage the quality visual indicators from the input to be used by the subsequent deep network layers and increase the gradient signals in the lower stages of the training pipeline. In addition to this, the layerwise training is performed with the help of locally generated errors which means the gradient is not backpropagated to previous layers, and the hidden layer weights are updated during the forward pass, making this structure a backpropagation free variant. PrimeNet has obtained state-of-the-art results on various image datasets, attaining the dual objective of (1) compact dynamic deep neural structure, which (2) eliminates the problem of backwards-locking. The PrimeNet unit is proposed as an alternative to traditional convolution and dense blocks for faster and memory-efficient training, outperforming previously reported results aimed at adaptive methods for parallel and multilayer deep neural systems.

Infrared and visible light image fusion technology integrates image feature information from two different modalities to generate an image that integrates complementary information from the source images. However, in low-light scenarios, the degradation of lighting in visible light images leads to existing fusion methods being unable to effectively extract texture detail information from the scene. At this time, the target prominence information provided by infrared images alone is far from sufficient. To address this challenge, this paper proposes a lightweight infrared and visible light image fusion method based on low-light enhancement, named LLE-Fuse. Firstly, the method improves the MobileOne Block by embedding the Sobel operator in the Edge-MobileOne Block to perform feature extraction and downsampling on the source images. Then, intermediate features of different scales are obtained and fused through a cross-modal attention fusion module, followed by image reconstruction using a decoder with upsampling. Next, the CLAHE algorithm is used for image enhancement of infrared and visible light images, and the enhanced loss guides the network model to learn the capability of low-light enhancement. Finally, upon completion of the network training, the method optimizes the Edge-MobileOne Block into the direct connection structure of MobileNetV1 through structural re-parameterization, effectively reducing the computational resource consumption of the model network. Through extensive experimental comparisons, this paper's method demonstrates excellent performance in both visual appeal and evaluation metrics, providing satisfactory fusion results even in low-light scenarios.

In recent years, the demand for coffee has increased tremendously. During the production process, green coffee beans are traditionally screened manually for defective beans before they are packed into coffee bean packages; however, this method is not only time-consuming but also increases the rate of human error due to fatigue. Therefore, this paper proposed a lightweight deep convolutional neural network (LDCNN) for the quality detection system of green coffee beans, which combined depthwise separable convolution (DSC), squeeze-and-excite block (SE block), skip block, and other frameworks. To avoid the influence of low parameters of the lightweight model caused by the model training process, rectified Adam (RA), lookahead (LA), and gradient centralization (GC) were included to improve efficiency; the model was also put into the embedded system. Finally, the local interpretable model-agnostic explanations (LIME) model was employed to explain the predictions of the model. The experimental results indicated that the accuracy rate of the model could reach up to 98.38% and the F1 score could be as high as 98.24% when detecting the quality of green coffee beans. Hence, it can obtain higher accuracy, lower computing time, and lower parameters. Moreover, the interpretable model verified that the lightweight model in this work is reliable, providing the basis for screening personnel to understand the judgment through its interpretability, thereby improving the classification and prediction of the model.

The annual construction and demolition waste (CDW) generated from EU construction sector was 850 million tons, which represented 31% of the total waste generation and about 28% of CDW was ceramics (bricks and tiles). In this study, the feasibility of using CDW brick powder as the precursor of alkali activated mortar (AAM) and extruded polystyrene (XPS) as the lightweight aggregates to form lightweight brick powder AAM (LW-BP-AAM) for non-structural applications was investigated. The thermal conductivity of LP-BPAAM was 0.112 W/m·K with density of about 1,135 kg/m³ which was lower than the counterparts with similar density in literature. The acid resistance of LW-BP-AAM is comparable to conventional fly ash based AAM and superior than ordinary Portland cement. From the scanning electron microscopy with energy dispersive X-ray spectroscopy, there was no severe damage on the surface of LW-BP-AAM but aluminate was removed from the matrix which was further verified in Fourier transform infrared spectroscopy. The mass and strength loss of LP-BP-AAM was 1.5% and 33%, respectively. Although the compressive strength of the LP-BP-AAM was low (about 1.8 MPa), it can be improved by optimising the particle size of the XPS aggregates.

This study is focused on the experimental investigation of compressive strength and durability properties of lightweight concrete mixtures with fine expanded glass and expanded clay aggregates using different microfillers. The paper proposes the relationships between the compressive strength and density of concrete mixtures with different proportions of lightweight aggregates mentioned above. The performed experimental studies have revealed the tendencies of possible usage of different amount of fine lightweight aggregates and their combinations in the production of concrete mixtures depending on the demands of practical application. Following the requirements for structural concrete subjected to environmental effects, durability properties (alkaline corrosion and freeze–thaw resistance) of the selected concrete mixtures with expanded glass aggregate were studied. The results of the experimental investigations have shown that durability of tested concrete specimens was sufficient. The study has concluded that the mixtures under consideration can be applied for the production of structural elements to which durability requirements are significant.

Abstract: For the problem of small target of printed circuit board surface defects and low detection accuracy, the printed circuit board surface defect detection network DCR-YOLO is designed to meet the premise of real-time detection speed and effectively improve the detection accuracy. Firstly, the backbone feature extraction network DCR-backbone, consisting of two CR residual blocks and one common residual block, is used for small target defect extraction on printed circuit boards. Secondly, the SDDT-FPN feature fusion module is responsible for the fusion of high level features to low level features, while enhancing feature fusion for the feature fusion layer where the small target prediction head YOLO Head-P3 is located to further enhance the low level feature representation. the PCR module enhances the feature fusion mechanism between the backbone feature extraction network and the SDDT-FPN feature fusion module at different scales of feature layers. the C5ECA module is responsible for adaptive adjustment of feature weights and adaptive attention to the requirements of small target defect information, further enhancing the adaptive feature extraction capability of the feature fusion module. Finally, three YOLO-Heads are responsible for predicting small target defects for different scales. Experiments show that the DCR-YOLO network model detection Map reaches 98.58%, the model size is 7.73MB, which meets the lightweight requirement, and the detection speed reaches 103.15fps, which meets the application requirements for real-time detection of small target defects.

To improve the interfacial compatibility between cement matrix and expanded polystyrene (EPS) in the core-shell lightweight aggregates (CSLA), the effects of sodium silicate, Polyvinyl alcohol (PVA) emulsion, Vinyl acetate-ethylene (VAE) emulsion, acrylic acid, and acetic acid on the cement-EPS interface were investigated. The denseness of the interface was studied by scanning electron microscopy (SEM), and the effect of interfacial agents on the hydration process of cement was studied by the heat of hydration and induction resistivity. The macroscopic properties of the interface of the CSLA were characterized by the "leak-white" rate, drop resistance and numerical crushing strength. The results show that the sodium silicate densifies the interface by generating hydration products on the EPS surface. At the same time, organic acid enhances the interfacial properties of EPS and cement by increasing the surface roughness and allowing hydration products to grow in the surface micropores. In terms of the cement hydration process, both two interfacial agents delay the cement hydration. Above all, with comprehensive interface properties, "leak-white" rate, and mechanical properties, VAE emulsion and sodium silicate can achieve the best performance with a final crushing resistance of 5.7 MPa.

Computers have evolved over the years and as the evolution continues, we have been ushered into an era where high-speed internet has made it possible for devices in our homes, hospital, energy and industry to communicate with each other. This era is what is known as the Internet of Things (IoT). IoT has several benefits in the health, energy, transportation and agriculture sectors of a country’s economy. These enormous benefits coupled with the computational constraint of IoT devices which makes it difficult to deploy enhanced security protocols on them make IoT devices a target of cyber-attacks. One approach that has been used in traditional computing over the years to fight cyber-attacks is Intrusion Detection System (IDS). However, it is practically impossible to deploy IDS meant for traditional computers in IoT environments because of the computational constraint of these devices. In this regard, this study proposes a lightweight IDS for IoT devices using an incremental ensemble learning technique. We used Gaussian Naive Bayes and Hoeffding tree to build our incremental ensemble model. The model was then evaluated on the TON IoT dataset. Our proposed model was compared with other state-of-the-art methods proposed and evaluated using the same dataset. The experimental results show that the proposed model achieved an average accuracy of 99.98%. We also evaluated the memory consumption of our model which showed that our model achieved a lightweight model status of 650.11KB as the highest memory consumption and 122.38KB as the lowest memory consumption.

Convolutional neural network architectures have become increasingly complex, which has improved the performance slowly on well-known benchmark datasets in the recent years. In this research, we have analyzed the true need for such complexity. We have introduced G-Net light, a lightweight modified GoogleNet with improved filter count per layer to reduce feature overlaps and complexity. Additionally, by limiting the amount of pooling layers in the proposed architecture, we have exploited the skip connections to minimize the spatial information loss. The investigations on the proposed architecture are evaluated on three retinal vessel segmentation publicly available datasets. The proposed G-Net light outperforms other vessel segmentation architectures by reducing the number of trainable parameters..

Automated Electrocardiogram (ECG) processing is an important technique which helps in identifying abnormalities in the heart before any formal diagnosis. This research presents a real-time and lightweight R-assisted feature extraction algorithm and a heartbeat classification scheme which achieves highly accurate abnormality detection. In the proposed algorithm, we extract fifteen features from each heartbeat taken from raw Lead-II ECG signals. The features carry medically valuable information such as locations, amplitude and energy of ECG waves (P, Q, R, S, T waves) which are then used for detection of any abnormality that might be present in the heartbeat using various classification algorithms. We have used four popular databases from Physionet and extracted ten thousand ECG signals from each for training the models and benchmarking results. Four classification models i.e. Naïve Bays, k-Nearest Neighbor, Neural Network, Decision Tree were used for abnormality detection validating the efficiency of the system.