Search Results (14,126)

In the task of human behavior detection, video classification based on deep learning has become a prevalent technique. The existing models are limited due to an inadequate understanding of behavior characteristics, which restricts their ability to achieve more accurate recognition results. To address this issue, this paper proposes a new model, which is an improvement upon the existing PPTSM model. Specifically, our model employs a multi-scale dilated attention mechanism, which enables the model to integrate multi-scale semantic information and capture characteristic information of abnormal human behavior more effectively. Additionally, to enhance the characteristic information of human behavior, we propose a gradient flow feature information fusion module that integrates high-level semantic features with low-level detail features, enabling the network to extract more comprehensive features. Experiments conducted on an elevator passenger dataset containing four abnormal behaviors (door picking, jumping, kicking, and door blocking) show that the top-1 Acc of our model is improved by 10% compared to the PPTSM model, reaching 95%. Moreover, experiments with four publicly available datasets(UCF24, UCF101, HMDB51, and the Something-Something-v1 dataset) demonstrate that our method achieves results superior to PPTSM by 6.8%, 6.1%, 21.2%, and 3.96%, respectively. Full article

In this study, we propose a dual-stream UNet neural network architecture design named CPF-UNet, specifically designed for efficient semantic pixel-level segmentation tasks. This architecture cleverly extends the basic structure of the original UNet, mainly through the addition of a unique attention-guided branch in the encoder part, aiming to enhance the model’s ability to comprehensively capture and deeply fuse contextual information. The uniqueness of CPF-UNet lies in its dual-path mechanism, which differs from the dense connectivity strategy adopted in networks such as UNet++. The dual-path structure in this study can effectively integrate deep and shallow features without relying excessively on dense connections, achieving a balanced processing of image details and overall semantic information. Experiments have shown that CPF-UNet not only slightly surpasses the segmentation accuracy of UNet++, but also significantly reduces the number of model parameters, thereby improving inference efficiency. We conducted a detailed comparative analysis, evaluating the performance of CPF-UNet against existing UNet++ and other corresponding methods on the same benchmark. The results indicate that CPF-UNet achieves a more ideal balance between accuracy and parameter quantity, two key performance indicators. Full article

This study proposes a method based on image segmentation for accurately identifying liquid aluminum leakage during deep well casting, which is crucial for providing early warnings and preventing potential explosions in aluminum processing. Traditional DeepLabV3+ models in this domain encounter challenges such as prolonged training duration, the requirement for abundant data, and insufficient understanding of the liquid surface characteristics of casting molds. This work presents an enhanced DeepLabV3+ method to address the restrictions and increase the accuracy of calculating liquid surface areas for casting molds. This algorithm substitutes the initial feature extraction network with ResNet-50 and integrates the CBAM attention mechanism and transfer learning techniques. The results of ablation experiments and comparative trials demonstrate that the proposed algorithm can achieve favorable segmentation performance, delivering an MIoU of 91.88%, an MPA of 96.53%, and an inference speed of 55.05 FPS. Furthermore, this study presents a technique utilizing OpenCV to accurately measure variations in the surface areas of casting molds when there are leakages of liquid aluminum. In addition, this work introduces a measurement to quantify these alterations and establish an abnormal threshold by utilizing the Interquartile Range (IQR) method. Empirical tests confirm that the threshold established in this study can accurately detect instances of liquid aluminum leakage. Full article

Forest resources are one of the indispensable resources of the earth, which are the basis for the survival and development of human society. With the swift advancements in computer vision and artificial intelligence technology, the utilization of deep learning for smoke detection has achieved remarkable results. However, the existing deep learning models have poor performance in forest scenes and are difficult to deploy because of numerous parameters. Hence, we introduce an optimized forest fire smoke monitoring system for embedded edge devices based on a lightweight deep learning model. The model makes full use of the multi-scale variable attention mechanism of Transformer architecture to strengthen the ability of image feature extraction. Considering the needs of application scenarios, we propose an improved lightweight network model LCNet for feature extraction, which can reduce the parameters and enhance detecting ability. In order to improve running speed, a simple semi-supervised label knowledge distillation scheme is used to enhance the overall detection capability. Finally, we design and implement a forest fire smoke detection system on an embedded device, including the Jetson NX hardware platform, high-definition camera, and detection software system. The lightweight model is transplanted to the embedded edge device to achieve rapid forest fire smoke detection. Also, an asynchronous processing framework is designed to make the system highly available and robust. The improved model reduces three-fourths of the parameters and increases speed by 3.4 times with similar accuracy to the original model. This demonstrates that our system meets the precision demand and detects smoke in time. Full article

In complex environments a single visible image is not good enough to perceive the environment, this paper proposes a novel dual-stream real-time detector designed for target detection in extreme environments such as nighttime and fog, which is able to efficiently utilise both visible and infrared images to achieve Fast All-Weatherenvironment sensing (FAWDet). Firstly, in order to allow the network to process information from different modalities simultaneously, this paper expands the state-of-the-art end-to-end detector YOLOv8, the backbone is expanded in parallel as a dual stream. Then, for purpose of avoid information loss in the process of network deepening, a cross-modal feature enhancement module is designed in this study, which enhances each modal feature by cross-modal attention mechanisms, thus effectively avoiding information loss and improving the detection capability of small targets. In addition, for the significant differences between modal features, this paper proposes a three-stage fusion strategy to optimise the feature integration through the fusion of spatial, channel and overall dimensions. It is worth mentioning that the cross-modal feature fusion module adopts an end-to-end training approach. Extensive experiments on two datasets validate that the proposed method achieves state-of-the-art performance in detecting small targets. The cross-modal real-time detector in this study not only demonstrates excellent stability and robust detection performance, but also provides a new solution for target detection techniques in extreme environments. Full article

In recent years, advancements in the Internet of Things (IoT), manufacturing processes, and material synthesis technologies have positioned flexible sensors as critical components in wearable devices. These developments are propelling wearable technologies based on flexible sensors towards higher intelligence, convenience, superior performance, and biocompatibility. Recently, two-dimensional nanomaterials known as MXenes have garnered extensive attention due to their excellent mechanical properties, outstanding electrical conductivity, large specific surface area, and abundant surface functional groups. These notable attributes confer significant potential on MXenes for applications in strain sensing, pressure measurement, gas detection, etc. Furthermore, polymer substrates such as polydimethylsiloxane (PDMS), polyurethane (PU), and thermoplastic polyurethane (TPU) are extensively utilized as support materials for MXene and its composites due to their light weight, flexibility, and ease of processing, thereby enhancing the overall performance and wearability of the sensors. This paper reviews the latest advancements in MXene and its composites within the domains of strain sensors, pressure sensors, and gas sensors. We present numerous recent case studies of MXene composite material-based wearable sensors and discuss the optimization of materials and structures for MXene composite material-based wearable sensors, offering strategies and methods to enhance the development of MXene composite material-based wearable sensors. Finally, we summarize the current progress of MXene wearable sensors and project future trends and analyses. Full article

Castings’ surface-defect detection is a crucial machine vision-based automation technology. This paper proposes a fusion-enhanced attention mechanism and efficient self-architecture lightweight YOLO (SLGA-YOLO) to overcome the existing target detection algorithms’ poor computational efficiency and low defect-detection accuracy. We used the SlimNeck module to improve the neck module and reduce redundant information interference. The integration of simplified attention module (SimAM) and Large Separable Kernel Attention (LSKA) fusion strengthens the attention mechanism, improving the detection performance, while significantly reducing computational complexity and memory usage. To enhance the generalization ability of the model’s feature extraction, we replaced part of the basic convolutional blocks with the self-designed GhostConvML (GCML) module, based on the addition of p2 detection. We also constructed the Alpha-EIoU loss function to accelerate model convergence. The experimental results demonstrate that the enhanced algorithm increases the average detection accuracy ([email protected]) by 3% and the average detection accuracy ([email protected]:0.95) by 1.6% in the castings’ surface defects dataset. Full article

In the realm of special equipment, significant advancements have been achieved in fault detection. Nonetheless, faults originating in the equipment manifest with diverse morphological characteristics and varying scales. Certain faults necessitate the extrapolation from global information owing to their occurrence in localized areas. Simultaneously, the intricacies of the inspection area’s background easily interfere with the intelligent detection processes. Hence, a refined YOLOv8 algorithm leveraging the Swin Transformer is proposed, tailored for detecting faults in special equipment. The Swin Transformer serves as the foundational network of the YOLOv8 framework, amplifying its capability to concentrate on comprehensive features during the feature extraction, crucial for fault analysis. A multi-head self-attention mechanism regulated by a sliding window is utilized to expand the observation window’s scope. Moreover, an asymptotic feature pyramid network is introduced to augment spatial feature extraction for smaller targets. Within this network architecture, adjacent low-level features are merged, while high-level features are gradually integrated into the fusion process. This prevents loss or degradation of feature information during transmission and interaction, enabling accurate localization of smaller targets. Drawing from wheel–rail faults of lifting equipment as an illustration, the proposed method is employed to diagnose an expanded fault dataset generated through transfer learning. Experimental findings substantiate that the proposed method in adeptly addressing numerous challenges encountered in the intelligent fault detection of special equipment. Moreover, it outperforms mainstream target detection models, achieving real-time detection capabilities. Full article

With the rapid growth of the economy, people are increasingly reliant on energy sources. However, in recent years, the energy crisis has gradually intensified. As a clean energy source, methane has garnered widespread attention for its development and utilization. This study employed both large-scale computational screening and machine learning to investigate the adsorption and diffusion properties of thousands of metal–organic frameworks (MOFs) in six gas binary mixtures of CH₄ (H₂/CH₄, N₂/CH₄, O₂/CH₄, CO₂/CH₄, H₂S/CH₄, He/CH₄) for methane purification. Firstly, a univariate analysis was conducted to discuss the relationships between the performance indicators of adsorbents and their characteristic descriptors. Subsequently, four machine learning methods were utilized to predict the diffusivity/selectivity of gas, with the light gradient boosting machine (LGBM) algorithm emerging as the optimal one, yielding R² values of 0.954 for the diffusivity and 0.931 for the selectivity. Furthermore, the LGBM algorithm was combined with the SHapley Additive exPlanation (SHAP) technique to quantitatively analyze the relative importance of each MOF descriptor, revealing that the pore limiting diameter (PLD) was the most critical structural descriptor affecting molecular diffusivity. Finally, for each system of CH₄ mixture, three high-performance MOFs were identified, and the commonalities among high-performance MOFs were analyzed, leading to the proposals of three design principles involving changes only to the metal centers, organic linkers, or topological structures. Thus, this work reveals microscopic insights into the separation mechanisms of CH₄ from different binary mixtures in MOFs. Full article

Hepatocellular carcinoma (HCC) has become the fourth leading cause of cancer-related deaths worldwide; annually, approximately 830,000 deaths related to liver cancer are diagnosed globally. Since early-stage HCC is clinically asymptomatic, traditional treatment modalities, including surgical ablation, are usually not applicable or result in recurrence. Immunotherapy, particularly immune checkpoint blockade (ICB), provides new hope for cancer therapy; however, immune evasion mechanisms counteract its efficiency. In addition to viral exposure and alcohol addiction, nonalcoholic steatohepatitis (NASH) has become a major cause of HCC. Owing to NASH-related aberrant T cell activation causing tissue damage that leads to impaired immune surveillance, NASH-associated HCC patients respond much less efficiently to ICB treatment than do patients with other etiologies. In addition, abnormal inflammation contributes to NASH progression and NASH–HCC transition, as well as to HCC immune evasion. Therefore, uncovering the detailed mechanism governing how NASH-associated immune cells contribute to NASH progression would benefit HCC prevention and improve HCC immunotherapy efficiency. In the following review, we focused our attention on summarizing the current knowledge of the role of CD4⁺T cells in NASH and HCC progression, and discuss potential therapeutic strategies involving the targeting of CD4⁺T cells for the treatment of NASH and HCC. Full article

Objectives: This study aimed to use deep learning to identify glaucoma and normal eyes in groups with high myopia using fundus photographs. Methods: Patients who visited Tri-Services General Hospital from 1 November 2018 to 31 October 2022 were retrospectively reviewed. Patients with high myopia (spherical equivalent refraction of ≤−6.0 D) were included in the current analysis. Meanwhile, patients with pathological myopia were excluded. The participants were then divided into the high myopia group and high myopia glaucoma group. We used two classification models with the convolutional block attention module (CBAM), an attention mechanism module that enhances the performance of convolutional neural networks (CNNs), to investigate glaucoma cases. The learning data of this experiment were evaluated through fivefold cross-validation. The images were categorized into training, validation, and test sets in a ratio of 6:2:2. Grad-CAM visual visualization improved the interpretability of the CNN results. The performance indicators for evaluating the model include the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. Results: A total of 3088 fundus photographs were used for the deep-learning model, including 1540 and 1548 fundus photographs for the high myopia glaucoma and high myopia groups, respectively. The average refractive power of the high myopia glaucoma group and the high myopia group were −8.83 ± 2.9 D and −8.73 ± 2.6 D, respectively (p = 0.30). Based on a fivefold cross-validation assessment, the ConvNeXt_Base+CBAM architecture had the best performance, with an AUC of 0.894, accuracy of 82.16%, sensitivity of 81.04%, specificity of 83.27%, and F1 score of 81.92%. Conclusions: Glaucoma in individuals with high myopia was identified from their fundus photographs. Full article

Poly(L-Lactide) (PLA), a fully biobased aliphatic polyester, has attracted significant attention in the last decade due to its exceptional set of properties, such as high tensile modulus/strength, biocompatibility, (bio)degradability in various media, easy recyclability and good melt-state processability by the conventional processes of the plastic/textile industry. Blending PLA with other polymers represents one of the most cost-effective and efficient approaches to develop a next-generation of PLA-based materials with superior properties. In particular, intensive research has been carried out on PLA-based blends with engineering polymers such as polycarbonate (PC), poly(ethylene terephthalate) (PET), poly(butylene terephthalate) (PBT) and various polyamides (PA). This overview, consequently, aims to gather recent works over the last 10 years on these immiscible PLA-based blends processed by melt extrusion, such as twin screw compounding. Furthermore, for a better scientific understanding of various ultimate properties, processing by internal mixers has also been ventured. A specific emphasis on blend morphologies, compatibilization strategies and final (thermo)mechanical properties (tensile/impact strength, ductility and heat deflection temperature) for potential durable and high-performance applications, such as electronic parts (3C parts, electronic cases) to replace PC/ABS blends, has been made. Full article

Citrus fruits, renowned for their abundant of phytochemicals and bioactive compounds, hold a prominent position as commercially grown fruits with health-promoting properties. In this context, tangerine peel (Citri Reticulatae Pericarpium, CRP) is garnering attention as a byproduct of citrus fruits. Within the framework of the circular economy, CRP has emerged as a focal point due to its potential health benefits. CRP, extracted from Citrus reticulata cv. and aged for over three years, has attracted increasing attention for its diverse health-promoting effects, including its anticancer, cardiovascular-protecting, gastrointestinal-modulating, antioxidant, anti-inflammatory, and neuroprotective properties. Moreover, CRP positively impacts skeletal health and various physiological functions. This review delves into the therapeutic effects and molecular mechanisms of CRP. The substantial therapeutic potential of CRP highlights the need for further research into its applications in both food and medicine. As a value-added functional ingredient, CRP and its constituents are extensively utilized in the development of food and health supplements, such as teas, porridges, and traditional medicinal formulations. Full article

In the domain of space rendezvous and docking, visual navigation plays a crucial role. However, practical applications frequently encounter issues with poor image quality. Factors such as lighting uncertainties, spacecraft motion, uneven illumination, and excessively dark environments collectively pose significant challenges, rendering recognition and measurement tasks during visual navigation nearly infeasible. The existing image enhancement methods, while visually appealing, compromise the authenticity of the original images. In the specific context of visual navigation, space image enhancement’s primary aim is the faithful restoration of the spacecraft’s mechanical structure with high-quality outcomes. To address these issues, our study introduces, for the first time, a dedicated unsupervised framework named SpaceLight for enhancing on-orbit navigation images. The framework integrates a spacecraft semantic parsing network, utilizing it to generate attention maps that pinpoint structural elements of spacecraft in poorly illuminated regions for subsequent enhancement. To more effectively recover fine structural details within these dark areas, we propose the definition of a global structure loss and the incorporation of a pre-enhancement module. The proposed SpaceLight framework adeptly restores structural details in extremely dark areas while distinguishing spacecraft structures from the deep-space background, demonstrating practical viability when applied to visual navigation. This paper is grounded in space on-orbit servicing engineering projects, aiming to address visual navigation practical issues. It pioneers the utilization of authentic on-orbit navigation images in the research, resulting in highly promising and unprecedented outcomes. Comprehensive experiments demonstrate SpaceLight’s superiority over state-of-the-art low-light enhancement algorithms, facilitating enhanced on-orbit navigation image quality. This advancement offers robust support for subsequent visual navigation. Full article

In this study, we explore how transformer models, which are known for their attention mechanisms, can improve pathogen prediction in pastured poultry farming. By combining farm management practices with microbiome data, our model outperforms traditional prediction methods in terms of the F1 score—an evaluation metric for model performance—thus fulfilling an essential need in predictive microbiology. Additionally, the emphasis is on making our model’s predictions explainable. We introduce a novel approach for identifying feature importance using the model’s attention matrix and the PageRank algorithm, offering insights that enhance our comprehension of established techniques such as DeepLIFT. Our results showcase the efficacy of transformer models in pathogen prediction for food safety and mark a noteworthy contribution to the progress of explainable AI within the biomedical sciences. This study sheds light on the impact of effective farm management practices and highlights the importance of technological advancements in ensuring food safety. Full article