In recent years, the field of deep learning achieved considerable success in pattern recognition, image segmentation and may other classification fields. There are a lot of studies and practical applications of deep learning on images, video or text classification. In this study, we suggest a method for changing the architecture of the most performing CNN models with the aim of designing new models to be used as stand-alone networks or as a component of an ensemble. We propose to replace each activation layer of a CNN (usually a ReLu layer) by a different activation function stochastically drawn from a set of activation functions: in this way the resulting CNN has a different set of activation function layers.

Neural networks were treated as black boxes for a long time. Previous works have unearthed what aspects of an image were important for convolutional layers at different positions in the network. This was done using deconvolutional networks. In this paper, we examine how well a convolutional neural network performs when those convolutional layers which are relatively unimportant for a particular image (i.e., the image does not produce one of the strongest activations) are skipped in the training, validating, and testing process.

Using traditional methods based on detection rules written by human security experts, there is a significant challenge in accurately detecting many network threats that are increasingly becoming sophisticated. In order to deal with the limitation of the traditional methods, network threat detection techniques utilizing artificial intelligence technologies such as machine learning are being extensively studied. Research has also been conducted on analyzing various string patterns in network packet payloads through natural language processing techniques to detect attack intent. However, due to the nature of packet payloads containing binary data as well as text data, a new approach is needed that goes beyond typical natural language processing techniques. In this paper, we study a token extraction method optimized for payloads using n-gram and byte pair encoding techniques. Furthermore, we generate embedding vectors that can understand the context of the packet payload using algorithms such as Word2Vec and FastText. We also compute the embedding of various header data associated with packets, such as IP addresses and ports. Given the combination of these features, we ensemble a text 1D-CNN and a multi-head attention network in a novel fashion. We validated the effectiveness of our classification technique with the CICIDS2017 open dataset and over half a million data collected by The Education Cyber Security Center (ECSC) currently operating in South Korea. The proposed model showed remarkable progress compared to previous studies, demonstrating a highly accurate classification performance with an F1-Score of 0.998. Our model can also preprocess and classify 150,000 network threats per minute to help security agents in the field divert their time to analyzing more complex attack patterns.

In recent times, with the increase of Artificial Neural Network (ANN), deep learning has brought a dramatic twist in the field of machine learning by making it more Artificial Intelligence (AI). Deep learning is used remarkably used in vast ranges of fields because of its diverse range of applications such as surveillance, health, medicine, sports, robotics, drones etc. In deep learning, Convolutional Neural Network (CNN) is at the center of spectacular advances that mixes Artificial Neural Network (ANN) and up to date deep learning strategies. It has been used broadly in pattern recognition, sentence classification, speech recognition, face recognition, text categorization, document analysis, scene, and handwritten digit recognition. The goal of this paper is to observe the variation of accuracies of CNN to classify handwritten digits using various numbers of hidden layer and epochs and to make the comparison between the accuracies. For this performance evaluation of CNN, we performed our experiment using Modified National Institute of Standards and Technology (MNIST) dataset. Further, the network is trained using stochastic gradient descent and the backpropagation algorithm.

Quinacridone (QA) and 2,9-dimethylquinacridone (DQA) are synthetic substances suitable as a hard, abrasion-resistant, self-organizing gliding layer on ice, snow, and water. For sustainable use, a large number of parameters must be considered to demonstrate that these non-biogenic substances and their by-products and degradation products are harmless to humans and the environment in the quantities released. For this task, available experimental data are used and supplemented for all tautomers by numerous relevant physical, chemical, toxicological and ecotoxicological estimated values based on various Quantitative Structure Activity Relationship (QSAR) methods. On the one hand, the low solubility of QA and DQA leads to stable gliding layers and thus low abrasion and uptake by plants, animals, and humans. On the other hand, the four hydrogen bond forming functional groups per molecule allow nanoparticle decomposition and enzymatic degradation in natural environments. All available data justify a sustainable use of QA and DQA as a gliding layer. The assessment of the toxicological properties is complemented with an investigation of the size and morphology of DQA particles as well as field tests indicating an excellent performance as a gliding layer on snow.

Quantum computing (QC) has opened the door to advancements in machine learning (ML) tasks that are currently implemented in the classical domain. Convolutional neural networks (CNNs) are classical ML architectures that exploit data locality and possess a simpler structure than fully-connected multi-layer perceptrons (MLPs) without compromising the accuracy of classification. However, the concept of preserving data locality is usually overlooked in the existing quantum counterparts of CNNs, particularly for extracting multi-features in multidimensional data. In this paper, we present a multidimensional quantum convolutional classifier (MQCC) that performs multidimensional and multi-feature quantum convolution with average and Euclidean pooling and thus adapting the CNN structure to a variational quantum algorithm (VQA). Average pooling is based on the quantum Haar transform (QHT) and Euclidean pooling is based on partial quantum measurement. The experimental work was conducted using multidimensional data to validate the correctness and demonstrate the scalability of the proposed method utilizing both noisy and noise-free quantum simulations. We evaluated the MQCC model with reference to reported work on state-of-the-art quantum simulators from IBM Quantum and Xanadu using a variety of standard ML datasets. The experimental results showed favorable characteristics of our proposed techniques compared to existing work with respect to a number of quantitative metrics such as the number of training parameters, cross-entropy loss, classification accuracy, circuit depth, and quantum gate count.

NongXiangXing Baijiu (NBJ) is produced using a solid-state fermentation system, but the impact of stratified fermented grains on fermentation remains unclear. Therefore, in a typical distillery plant, we evaluated the physical and chemical composition, volatile compound profile, and microbial community of fermented grains in NBJ both above (FG-A) and below (FG-B) the Huangshui line. Significant differences in fermentation parameters between FG-A and FG-B were observed after 30 days of fermentation (P < 0.05). Additionally, the partial least squares projection to latent structure discriminant analysis (PLS-DA) revealed distinct differences in volatile compounds between FG-B and FG-A, identifying 26 discriminant markers. The diversity of short-chain fatty acids (SCFAs) and their esters was higher in FG-B compared to FG-A. Furthermore, microbial diversity and abundance differed significantly between the two layers of fermented grains (P < 0.05). Correlation and pathway enrichment analyses indicated that the higher SCFA content in FG-B could be attributed to the greater abundance of acid-producing microorganisms compared to FG-A. This study highlights the differences between the two layers of fermented grains in NBJ fermentation, offering new insights into solid-state fermentation and expanding the current understanding of the traditional NBJ fermentation process.

As waterflooding multi-layer reservoirs get into the high-water-cut stage, inter-layer conflicts become increasingly serious, leading to a worsening development effect over time. Production layers regroup is an effective approach for resolving inter-layer conflicts and improving waterflooding efficiency. At the current stage, there are limitations for most of the methods of production layers regroup. This article proposes a smart method for optimizing the layer regroup plan based on genetic algorithm. Comprehensively considering various factors that affect the regroup of layers, based on the combination principle of "smaller intra-group variance and larger inter-group variance of each influencing factor are expected ", genetic algorithm is used to calculate the fitness value of the initial combination schemes, the advantageous schemes with higher fitness values are selected as the basis of the next generation. Then crossover and mutation operations are performed to those advantageous schemes to generate new schemes. Through continuous selection and evolution, until the global optimal solution with the highest fitness value is found, the optimal combination scheme is determined. Comparative analysis with numerical simulation results demonstrates the reliability of this intelligent method, with an increased oil recovery of 4.34% for the sample reservoir. Unlike selecting a preferable plan from a limited number of predefined combination schemes, this method is an automatic optimization to solve the optimal solution of the problem. It improves both efficiency and accuracy as compared to conventional reservoir engineering methods, numerical simulation methods and most of the mathematical methods, thus could provide effective guidance for EOR strategies of waterflooding reservoirs in high-water-cut stage.

Rice has become the second major food among rural people. It is one of the most nutrient and low-cost food available in Asia. Rice is composed of two major subspecies as Japonica and Indica and it belongs to the Poaceae family. The World Bank predicts that rice demand will grow 51% faster than population growth in 2025. It is high time to develop a model which predicts the type of infected paddy leaf and avoids the loss of grains. In this paper, the proposed hybrid CNN model, three CNN networks with different layer properties are trained parallel. The extracted feature from these CNN networks is combined to provide the classification of the type of infected leaf. Fieldwork was carried and about 340 samples are collected from five different types of classes. The proposed hybrid model was tested with both the fieldwork dataset and also with an available dataset on the internet. The experimental results show that the proposed model outperforms the other CNN network and yields an accuracy value of 98%, a precision value of 95%, and a misclassification rate of 4% respectively.

Biomaterials are the basis for the development of medicine because they allow safe contact with a living organism. The aim of this work was to produce innovative oxide layers with a porous microstructure on the surface of commercially pure titanium Grade 4 (CpTi G4), and to characterize their properties as drug carriers. Anodization of the CpTi G4 subjected to mechanical grinding and electrochemical polishing was carried out in a solution of 1M ethylene glycol with the addition of 40 g of ammonium fluoride at a voltage of 20 V for 2, 18, 24 and 48 hours at room temperature. It was found that the longer anodization time, the greater the number of pores formed on the CpTi G4 surface as revealed by FE-SEM method, and the greater the surface roughness determined in profilometric tests. As the anodizing time increases, the amount of the drug in the form of gentamicin sulfate incorporated into the resulting pores decreases. The most favorable drug release kinetics profile determined by UV-VIS absorption spectroscopy was found for the CpTi G4 anodized for 2 h making them the best choice when it comes to the drug carrier allowing full use of the therapeutic dose of the drug.

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.

In recent years, electroencephalogram (EEG) emotion recognition has emerged as a research hotspot in the field of artificial intelligence (AI). Despite advancements in EEG-based emotion recognition, room for enhancing performance persists due to EEG signal redundancy and limitations in feature extraction, leading to inefficient models and emotional information loss. To fully utilize EEG's emotional information and improve recognition accuracy while reducing computational costs, this paper proposes a Convolutional-Recurrent Hybrid Network with a dual-stream adaptive approach and an attention mechanism (CSA-SA-CRTNN). Firstly, the model utilizes a CSAM module to assign corresponding weights to EEG channels. Then, an adaptive dual-stream convolutional-recurrent network (SA-CRNN and MHSA-CRNN) is applied to extract local spatial-temporal features. After that, the extracted local features are concatenated and fed into a temporal convolutional network with a multi-head self-attention mechanism (MHSA-TCN) to capture global information. Finally, the extracted EEG information is used for emotion classification. We conducted binary and ternary classification experiments on the DEAP dataset, achieving 99.26% and 99.15% accuracy for arousal and valence in binary classification, and 97.69% and 98.05% in ternary classification, surpassing relevant algorithms. Additionally, the model's efficiency is significantly higher than other models, achieving better accuracy with lower resource consumption.

A single mode waveguide grating coupler based on multiple Si-SiO₂ pairs onto Si substrate has been designed. Numerical analysis has been carried out to calculate optimum thickness of the layers of Si-SiO₂ that ensures the constructive interference between reflected waves and actual guided wave for high coupling efficiency. Based on the results, an optimal design is developed and modeled by using a 2-D finite difference time domain (2-D FDTD) simulator that dictates a coupling efficiency of as much as 78% (-1.07 dB) at the wavelength of 1550 nm, and a 1-dB bandwidth of 77 nm. The numerical method will be useful to calculate the optimum thicknesses of the layers for any reflector based grating coupler of different materials.

Electrochromic measurements have been performed throughout the full composition range of reactive magnetron-sputtered mixed Titanium oxide and Molybdenum oxide (TiO2-MoO3) to search for enhanced Coloration Efficiency (CE). Optical parameters and composition have been determined and mapped by using Spectroscopic Ellipsometry (SE). Scanning Electron Microscopy (SEM) with Energy-Dispersive X-ray Spectroscopy (EDS). EDS has been used to check the SE results as it was used in our earlier paper [N. T. Ismaeel et al, Materials 2023, 16(12), 4204] for (TiO2-SnO2). Ti and Mo targets were put separately from each other, and the Indium-Tin-Oxide (ITO) covered glass and Si-probes on a glass substrate (30 cm × 30 cm) were moved under the two separated targets (Ti and Mo) in a reactive Argon-Oxygen (Ar-O2) gas mixture. By using this combinatorial process, all the compositions (from 0 to 100%) were achieved in the same sputtering chamber after one sputtering process. The CE (the change of light transmission for the unit electric charge) of mixed metal oxides (TiO2-MoO3) that are deposited by reactive sputtering has been studied in an electrochemical cell. This paper aims to assess the results of investigations of such materials showing the enhanced electrochromic behavior compared to the pure materials and to enhance the Coloration Efficiency.

Bearing fault diagnosis is crucial for ensuring the stable operation of mechanical equipment. With the continuous development of deep learning technology, Convolutional Neural Networks (CNNs) have demonstrated significant advantages in the field of fault diagnosis. This paper proposes a new method that combines various CNN architectures to improve the accuracy of bearing fault diagnosis. We designed five different convolutional network structures, including SerConv, ResConv, One-Shot Aggregation Convolution (OSAConv), Cross-Stage Aggregation Convolution (CSAConv), and MD-DAConv. Experimental results on the Case Western Reserve University (CWRU) bearing dataset show that the proposed method exhibits high accuracy and robustness in fault diagnosis. The results indicate that strategies such as multi-directional, multi-scale, and residual connections play a crucial role in enhancing the depth and breadth of feature extraction, while simple and effective feature fusion and information transmission mechanisms are key to ensuring the robustness and generalization ability of the model.

Deep convolutional neural networks (CNNs) have revolutionised computer vision technology by automatically learning hierarchical representations of image data, leading to state-of-the-art performance in visual recognition tasks. This article presents a comprehensive review of deep CNNs, from their evolution and architectures to the current state-of-the-art research. The review also provides the core concepts and building blocks of CNNs and their concise mathematical representations. Furthermore, it explores applications of deep CNNs in three popular domains, including medical diagnosis, remote sensing, and facial recognition. This review will benefit researchers and practitioners in computer vision and artificial intelligence, as well as industry professionals seeking to leverage the latest advancements in deep learning technologies.

A Cu₂ZnSnS₄ (CZTS) film with a thickness of approximately 1.5 μm was fabricated on a Mo-coated glass substrate by annealing a CZTS precursor fabricated from nanoparticle ink. The chemical states of the elements in the CZTS thin film in the depth direction were studied to identify the presence of secondary phases, which are detrimental to the performance of solar cells containing CZTS. X-ray diffraction was unable to detect any secondary phases in CZTS because of their small relative amount. Instead, X-ray photoelectron spectroscopy (XPS), which is highly sensitive to chemical state, was conducted at different depths in the CZTS film to further check the presence of secondary phases. XPS analysis revealed peaks shift consistent with the presence of secondary phases. For the CZTS film annealed in a S atmosphere at 575 °C for 3 h, the film surface consisted of a secondary-phase layer composed of CuS, ZnS, and SnSx (x=1 or 2) originating from the decomposition of CZTS. At depths below 80 nm, the film was pure CZTS. Formation of MoS2 at the CZTS–Mo interface was confirmed by XPS analysis of Mo and S.

This paper proposes two max-pooling engines, named the RTB-MAXP engine and the CMB-MAXP engine, with a scalable window size parameter for FPGA-based convolutional neural network (CNN) implementation. The max-pooling operation for the CNN can be decomposed into two stages, i.e., a horizontal axis max-pooling operation and a vertical axis max-pooling operation. These two one-dimensional max-pooling operations are performed by tracking the rank of the values within the window in the RTB-MAXP engine and cascading the maximum operations of the values in CMB-MAXP engine. Both the RBM-MAXP engine and the CMB-MAXP engine were implemented using VHSIC Hardware Description Language (VHDL) and verified by simulations. They have been employed for and tested in our CNN accelerator targeting at the CNN model YOLOv4-CSP-S-Leaky for object detection.

This study explores novel techniques to improve the detection accuracy of skarn iron deposits using advanced image processing methodologies. Leveraging the capabilities of Aster image, Band Ratio (BR) images, and Principal Component Analysis (PCA), alongside the power of 3D Convolutional Neural Networks (3D-CNN), the research aims to enhance the precision and efficiency of ore detection in complex geological environments. The proposed method employs a specific 3D-CNN architecture, accepting input as a 7×7×C image patch, where C represents the combined number of selected Aster image bands, Principal Component (PC) bands, and computed BR images. To evaluate the accuracy of the proposed method, five distinct image bands combinations, including the proposed bands combination, were tested and evaluated based on the overall accuracy (OA), average accuracy (AA), and kappa coefficient. The results demonstrated that while the incorporation of BR images alongside Aster bands initially seemed promising, it introduced significant confusion in certain classifications, leading to unexpected mis-classification rates. Surprisingly, utilizing solely Aster bands as input parameters yielded higher accuracy rates (OA= 93.13%, AA = 91.96%, Kappa = 90.91%) compared to scenarios involving the integration with band ratios (OA = 87.02%, AA = 79.15, and Kappa = 82.60%) or the integration of BR images to PC bands (OA= 87.78%, AA = 82.39%, Kappa = 83.81%). However, the amalgamation of Aster bands with selected PC bands showed slight improvements in accuracy (OA= 94.65%, AA = 92.93%, Kappa = 93.45%), although challenges in accurately classifying certain features persisted. Ultimately, the proposed combination of Aster bands, PC bands, and BR images (proposed bands combination) presented the most visually appealing and statistically accurate results (OA = 96.95%, AA= 94.87%, and Kappa = 95.93%), effectively addressing misclassifications observed in the other combinations. These findings underscore the synergistic contributions of each of the Aster bands, PC bands, and BR images, with Aster bands proving pivotal for optimal skarn classification, PC bands enhancing intrusions classification accuracy, and BR images strengthening wall rock classification accuracy. In conclusion, the proposed combination of input image bands emerges as a robust and comprehensive methodology, demonstrating unparalleled accuracy in the remote sensing detection of skarn iron minerals.

Parkinson’s Disease (PD) is a neurodegenerative and progressive disease that impacts the nerve cells in the brain and varies from person to person. The exact cause of PD is still unknown, and the diagnosis of PD does not include a specific objective test with certainty. Although deep learning has made great progress in medical neuroimaging analysis, these methods are very susceptible to biases present in neuroimaging datasets. An innovative decorrelated deep learning technique is introduced to mitigate class bias and scanner bias while simultaneously focusing on finding distinguishing characteristics in resting-state functional MRI (rs-fMRI) data, which assist in recognizing the PD with good accuracy. The decorrelation function reduces the non-linear correlation between features and bias in order to learn bias-invariant features. The Parkinson’s Progression Markers Initiative (PPMI) dataset, referred to as a single scanner imbalanced dataset in this study used to validate our method. The imbalanced dataset problem affects the performance of the deep learning framework by overfitting to the majority class. To resolve this problem, we propose a new Decorrelated Convolutional Neural Networks (DcCNN) framework by applying decorrelation-based optimization to Convolutional Neural Networks(CNN). An analysis of evaluation metrics comparisons shows that integrating the decorrelation function boosts the performance of PD recognition by removing class bias. Specifically, our DcCNN model performs significantly better than existing traditional approaches to tackle the imbalance problem. Finally, the same framework can be extended to create scanner invariant features without significantly impacting the performance of a model. The obtained dataset is a multi-scanner dataset which leads to scanner bias due to the differences in acquisition protocols and scanners. The multi-scanner dataset is a combination of two datasets, namely PPMI and FTLDNI - frontotemporal lobar degeneration neuroimaging initiative (NIFD) dataset. The results of t-distributed stochastic neighbor embedding (t-SNE) and scanner classification accuracy of our proposed Feature Extraction-DcCNN (FE-DcCNN) model validated the effective removal of scanner bias. Our method achieves an average accuracy of 77.80% on a multi-scanner dataset for differentiating PD from healthy control, which is superior to the DcCNN model trained on a single scanner imbalanced dataset.

In the present paper we investigate the conservative conditions in Quadratic Gravity. It is shown explicitly that the Bianchi identities lead to the conservative condition of the left-hand-side of the (gravitational) field equation. Therefore, the total energy-momentum tensor is conservative in the bulk (like in General Relativity). However, in Quadratic Gravity it is possible to have singular hupersurfaces separating the bulk regions with different behavior of the matter energy-momentum tensor or different vacua. They require special consideration. We derived the conservative conditions on such singular hypersurfaces and demonstrated the very possibility of the matter creation. In the remaining part of the paper we considered some applications illustrating the obtained results.

The detection and recognition of tables in image-based documents is a challenging and essential task for automated data extraction and anal- ysis. This paper introduces a methodology that utilizes Convolutional Neural Networks (CNNs) to address this problem. By harnessing the ro- bust visual recognition abilities of CNNs, the proposed method effectively detects and extracts tables from image-based documents. Additionally, an Encoder-Dual Decoder (EDD) architecture is employed to extract the textual content from table cells, enabling the transformation of visual data into structured, machine-readable formats. This structured data is then further processed using a Vector Space Model (VSM)-based language modeling technique for query-based table retrieval. The methodology’s accuracy is assessed by analyzing the spatial relationships between the extracted cells and comparing them against a pre-defined table structure. The results provide an evidence to the effectiveness of the proposed ap- proach, with an impressive 85% accuracy rate and a corresponding error rate of 15%. This accurate extraction and recognition of tables from image-based documents can significantly enhance applications in data analysis, information retrieval, and knowledge extraction.

Aiming at solving difficulties related to aero-engine classification and identification, the infrared spectra of aero-engine hot jets are measured by telemetry Fourier transform infrared spectrometer, and a six types aero-engine hot jet spectrum data set is generated. The spectrum data set were randomly sampled at a ratio of 8:1:1 to generate training set, validation set and prediction set. In this paper, a Peak Finding Siamese Convolutional Neural Network (PF-SCNN) is designed to match and classify spectrum data. In the first place, the matching pairs of training set and validation set are made independently with the labels of positive and negative samples creating. The spectrum feature extraction and distance similarity calculation are carried out by the Siamese convolutional neural network (SCNN). When entering the prediction phase, the prediction set and training set are integrated to predict in the trained model. The prediction set labels are ultimately determined by matching them with the training set labels having the highest similarities to ensure accurate predictions. To improve the operation efficiency of the SCNN, a peak finding method is introduced to extract the spectrum peaks. Peak positions of high frequency are counted, while the peak data are extracted. The peak data are used to take the place of the original data for training and prediction. The performance measures are defined as Accuracy, Precision, Recall, Confusion matrix and F1-score, and the prediction accuracy was up to 99%. The experimental results indicate that the proposed PF-SCNN is suitable for our spectral dataset and can complete the task of infrared spectrum classification of aero-engine hot jets.

Antimony (Sb) has gained significance as a critical raw material (CRM) within the European Union (EU) due to its strategic importance in various industrial sectors, particularly in the textile industry for flame retardants and as a component of Sb-based semiconductor materials. Moreover, Sb is emerging as a potential alternative for anodes used in lithium-ion batteries, a key element in the Energy transition. This study focused on exploring the feasibility of identifying and quantifying Sb mineralizations through the spectral signature of soils using reflectance spectroscopy, a non-invasive remote sensing technique, and by employing deep learning algorithms such as Convolutional Neural Networks (CNNs). Common signal preprocessing techniques were applied to the spectral data, and the soils were analyzed by Inductively Coupled Plasma Mass Spectrometry (ICP-MS). Despite achieving high R-squared values, the study faces a significant challenge of generalization of the model to new data. Despite the limitations, this study provides valuable insights into potential strategies for future research in this field.

Functional connectivity (FC) is a potential candidate that can increase the performance of brain-computer interfaces (BCIs) in the elderly because of its compensatory role in neural circuits. However, it is difficult to decode FC by current machine learning techniques because of a lack of its physiological understanding. To investigate the suitability of FC in BCI for the elderly, we propose the decoding of lower- and higher-order FCs using a convolutional neural network (CNN) in six cognitive-motor tasks. The layer-wise relevance propagation (LRP) method describes how age-related changes in FCs impact BCI applications for the elderly compared to younger adults. Seventeen younger (24.5±2.7 years) and twelve older (72.5±3.2 years) adults were recruited to perform tasks related to hand-force control with or without mental calculation. CNN yielded a six-class classification accuracy of 75.3% in the elderly, exceeding the 70.7% accuracy for the younger adults. In the elderly, the proposed method increases the classification accuracy by 88.3% compared to the filter-bank common spatial pattern (FBCSP). LRP results revealed that both lower- and higher-order FCs were dominantly overactivated in the prefrontal lobe depending on task type. These findings suggest a promising application of multi-order FC with deep learning on BCI systems for the elderly.

This study examines the feasibility of using event-related potentials (ERPs) obtained from electroencephalographic (EEG) recordings as biomarkers for long-term memory item classification. Previous studies have identified old/new effects in memory paradigms associated with explicit long-term memory and familiarity. Recent advancements in convolutional neural networks (CNNs) have enabled the classification of ERP trials under different conditions and identification of features related to neural processes at the single-trial level. We employed this approach to compare three CNN models with distinct architectures using experimental data. Participants (N = 25) performed an association memory task while recording ERPs that were used for training and validation of the CNN models. The EEGNET-based model achieved the most reliable performance in terms of precision, recall, and specificity compared with the shallow and deep convolutional approaches. The classification accuracy of this model reached 70% for known items and 62% for unknown items. Good overall accuracy requires a trade-off between recall and specificity and depends on the architecture of the model and the dataset size. These results suggest the possibility of integrating ERP and CNN into online learning tools and identifying the underlying processes related to long-term memorization.

In this study, the Bohler K 190 steel was used. The steel was manufactured by the powder metallurgy (PM) process. The boronizing process was carried out in the range of 1173 to 1323 K, for 1-10 h. The samples were boronized in solid medium, called the Durborid powder mixture. For the microstructural observations, the scanning electron microscopy was utilized for determining the morphology of interfaces and measuring the layers’ thicknesses. The phase composition of boride layers was also determined with X-ray diffraction analysis. To investigate the redistribution of chemical elements redistribution during the boronizing process, the EDS mapping and EDS point analysis were used. The boride layers were constituted by FeB and Fe2B phases except for 1173 K for 1 h. The values of Vickers microhardness of Fe2B, FeB and transition zone were estimated. Finally, to assess the boron activation energies in FeB and Fe2B, the so-called integral method was applied and the results in terms of activation energies were confronted with the literature data.

The involvement of macular function in its preganglionic elements, during the neurodegenerative process of multiple sclerosis (MS), is controversial. In this case-control observational and retrospective study, we assessed multifocal electroretinogram (mfERG) responses from 41 healthy Controls, 41 relapsing-remitting MS patients without optic neuritis (ON) (MS-noON Group), 47 MS patients with ON: 27 with full recovery of high-contrast best corrected visual acuity (BCVA) (MS-ON-G Group) and 20 with poor recovery of BCVA (MS-ON-P Group). MfERG N1 and P1 implicit times (ITs), and N1-P1 response amplitude densities (RADs) were measured from concentric rings (R) with increasing foveal eccentricity: 0-5° (R1), 5-10° (R2), 10-15° (R3), 15-20° (R4), 20- 25° (R5), and from retinal sectors [superior, nasal, inferior and temporal] between 0-15° and 0- 25°. In MS-ON-P Group, mean mfERG RADs detected from R1 (0-5°) and from the central nasal quadrant (0-15°) were significantly reduced (p<0.01) with respect to those of Control, MS-noON and MS-ON-G Groups. No other significant differences between Groups for any mfERG parameters were found. Our results suggest that in MS, exclusively after ON with poor recovery of BCVA, the neurodegenerative process can induce dysfunctional mechanisms involving photoreceptors and bipolar cells of the fovea and of the more central nasal macular area.

The identification of solitonlike coherent structure (SCS) in boundary layer flows is crucial for understanding turbulence origins and in particular for laminar-turbulence transition. However, the task of finding solutions for solitonlike coherent structure from the Navier-Stokes equations poses a significant challenge. In this paper, based on the author's previous work [Sun (2023) in Ref.31], we are able to study convergent flow boundary layers, whose solution encompasses both shock wave and solitary wave solutions, and their superposition gives rise to solitary-like waves, namely solitonlike coherent structure. It is found that the solitonlike coherent structure can only be obtained by combining the Navier-Stokes equations and mass conservation, since the combined equations will have the third order derivatives respect to coordinate $x$, in other words, without the mass conservation condition, the Navier-Stokes equations does not contain solitonlike coherent structure by itself. Finally proved solitonlike coherent structure do exit in all kind of flows.

The exact similarity solutions (also called as special exact solutions) of two dimensional laminar boundary layer were obtained by Blasius in 1908, however, no similarity solutions for two dimensional turbulent boundary layers have been reported in the literature. With the help of dimensional analysis and invariance principle, Prandtl mixing length $\ell=\kappa y$ for one dimensional turbulent boundary layer is extended to $\ell(x,y)=\kappa y (1-\frac{y}{\delta})\sqrt{\frac{\nu}{U\delta}} $ for the two dimensional turbulent boundary layers, furthermore, with a similarity transformation, we successfully transform the two dimensional turbulent boundary layers partial differential equations into a single ordinary differential equation $f'''+ ff''+\beta(1-f'^2)+\kappa^2[\eta^2(1-\eta)^2f''|f''|]'=0$. As an application, similarity solutions of the two dimensional turbulent boundary layer on a flat plate at zero incidence have been studied in detail. To solve the ordinary differential equation numerically, a complete Maple code is provided.

Early diagnosis of paroxysmal atrial fibrillation (PAF) could suggest patients to receive timely interventions in clinical practice. Various PAF onset prediction algorithms might benefit from accurate heart rate variability (HRV) analysis and machine learning classification but to be challenged in real-time monitoring scenarios. The aim of this study is to present an end-to-end deep learning based PAFNet model that integrates a sliding window technique on raw R-R interval of electrocardiogram (ECG) segments to achieve a real-time prediction of PAF onsets. This integration enable the deep convolutional neural network (CNN) to be customized as a light-weight architecture that accommodates the size of sliding windows simply by altering the input layer, specifically its effectiveness in making a new prediction with each new heartbeat. Catering to potential influence of input sizes, three CNN models were trained using 50, 100, and 200 R-R intervals, respectively. For each model, the performance of automated algorithms was evaluated for PAF prediction using a ten-fold cross-validation. As a results, a total of 56,381 PAFN-type and 56,900 N-type R-R interval segments was collected from publicly accessible ECG databases, and a promising prediction performance of the automated algorithm with a 100 R-R intervals was achieved in terms of the sensitivity of 97.12%, the specificity of 97.77%, and the accuracy of 97.45%, respectively. Importantly, the automated algorithm with a sliding windows step of 1 could process one sample in only 23.1 milliseconds and identify the onset of PAF at least 45 minutes in advance. The present results suggest that the sliding window technique on raw R-R interval sequences along by deep learning based algorithms may offers the possibility of providing an accurate, real-time, and end-to-end clinical tool for mass monitoring of PAF.

Public transportation scheduling aims to optimize the allocation of transportation resources, enhance transportation efficiency, and increase passenger satisfaction, which is crucial for building a sustainable urban transportation system. As a complement to public transportation, shared bikes provide users with a solution for the last mile of travel, compensating for the lack of flexibility in public transportation and helping to improve its utilization rate. Due to the characteristics of shared bikes, such as peak usage periods in the morning and evening and significant fluctuations in demand across different areas, the optimization of shared bike dispatch can better meet user needs, thereby reducing vehicle vacancy rates and increasing operating revenue. Addressing this issue, this paper designs a comprehensive decision-making approach for spatio-temporal demand prediction and bike dispatch optimization. For demand prediction, we designed a T-GCN based bike demand prediction model. In terms of dispatch optimization, we considered factors such as dispatch capacity, distance restrictions, and dispatch costs, and designed an optimization solution based on genetic algorithms. Finally, this paper validates the approach using shared bike operating data, shows that T-GCN can effectively predict short-term demand for shared bikes. Meanwhile, the optimization model based on genetic algorithms provides a complete dispatch solution verifying the model’s effectiveness. The shared bike dispatch approach proposed in this paper, which combines demand prediction with resource scheduling. This scheme can also be extended to other transportation scheduling problems with uncertain demand, such as store replenishment delivery and intercity inventory dispatch.

This article is the fourth part of a scientific project under the general title “Geometrized vacuum physics based on the Algebra of Signatures". In the first three articles [1,2,3], the foundations of the Algebra of Stignatures were laid and the main aspects of the kinematics of vacuum layers were considered. This article continues the development of the mathematical apparatus of the proposed project, in particular, the dynamics of vacuum layers is developed based on the Algebra of Signatures. The development of this direction of research (with simplifications related to Riemann's differential geometry) led to the possibility of a geometrized representation of the electric field strength and magnetic field induction. This geometrized mathematical apparatus allows one to interpret the electromagnetic field as an interweaving of accelerated and rotational flows of the adjacent layers of vacuum. The proposed dynamic models of accelerated movements and rotations of vacuum layers can provide a theoretical basis for the development of “zero” (i.e. vacuum) technologies.

We fabricate large-area atomically thin MoS₂ layers through the direct transformation of crystalline molybdenum trioxide (MoO₃) by sulfurization at relatively low temperatures. The obtained MoS₂ sheets are polycrystalline (~10-20 nm single-crystal domain size) with areas of up to 300×300 µm² with 2-4 layers in thickness and show a marked p-type behaviour. The synthesized films are characterized by a combination of complementary techniques: Raman spectroscopy, X-ray diffraction, transmission electron microscopy and electronic transport measurements.

Coconut is an important multipurpose crop wherein different stages of its maturity are used for different products. Traditional approach of its classification use sound formed by tapping the fruit, and the tapper will base its judgment through the sound he heard. The procedure was highly subjective and attempts had been made by other researchers to automate and classify the adulthood of the coconut objectively. Nowadays, deep learning techniques are being utilized to solve classification problems. One such method is Convolutional Neural Network (CNN) that takes raw pixel data, learns to extract features, and ultimately classifies the input. In this study, a portable device was developed that takes audio signals generated from tapping the fruit mechanically. This audio clip was converted to spectrogram and was used as input to a LeNet CNN architecture. We argue that CNN classifier has improved accuracy compared to the non-deep learning system. Our evaluation confirmed that the use of CNN had improved the accuracy of classifying coconut by about 15%.

A convolutional neural network (CNN) is sometimes understood as a black box in the sense that while it can approximate any function, studying its structure will not give us any insights into the nature of the function being approximated. In other terms, the discriminative ability does not reveal much about the latent representation of a network. This research aims to establish a framework for interpreting the CNNs by profiling them in terms of interpretable visual concepts and verifying them by means of Integrated Gradient. We also ask the question, "Do different input classes have a relationship or are they unrelated?" For instance, could there be an overlapping set of highly active neurons to identify different classes? Could there be a set of neurons that are useful for one input class whereas misleading for a different one? Intuition answers these questions positively, implying the existence of a structured set of neurons inclined to a particular class. Knowing this structure has significant values; it provides a principled way for identifying redundancies across the classes. Here the interpretability profiling has been done by evaluating the correspondence between individual hidden neurons and a set of human-understandable visual semantic concepts. We also propose an integrated gradient-based class-specific relevance mapping approach that takes the spatial position of the region of interest in the input image. Our relevance score verifies the interpretability scores in terms of neurons tuned to a particular concept/class. Further, we perform network ablation and measure the performance of the network based on our approach.

MPC (Magneto-Photonic Crystal) Optimisation is a feature-rich Windows software application designed to enable researchers to analyze the optical and magneto-optical spectral properties of multilayers containing gyrotropic constituents. A set of computational algorithms aimed at enabling the design optimization and optical or magneto-optical (MO) spectral analysis of 1D magnetic photonic crystals (MPC) is reported, together with its Windows software implementation. Relevant material property datasets (e.g., the optical spectra of refractive index, absorption, and gyration) of several important optical and MO materials are included, enabling easy reproduction of the previously published results from the field of MPC-based Faraday rotator development, and an effective demonstration-quality introduction of future users to the multiple features of this package. We also report on the methods and algorithms used to obtain the absorption coefficient spectral dispersion datasets for new materials, for which the film thickness, transmission spectrum, and refractive index dispersion function are known.

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.

Alzheimer's disease (AD) is a progressive and evolving neurodegenerative disease with an insidious onset that can lead to memory loss and cognitive impairment. There is no effective treatment for this disease. However, early diagnosis plays an important role in treatment planning to slow down its progression, as treatment has the greatest impact in the early stages of the disease. Neurological images obtained through different imaging techniques provide powerful information and help diagnose the disease. With the wide application of deep learning techniques in disease diagnosis, especially the prominence of Convolutional Neural Networks (CNNs) in computer vision and image processing, more and more studies are proposing the use of this algorithm for the diagnosis of AD. In this paper, we first systematically introduce the impact of AD on people, detailing the biomarkers, early clinical symptoms, and risk factors of this disease. Secondly, it goes on to detail the development of CNNs, their form, and methods to help diagnose AD. It is proposed that CNNs can help diagnose AD by analyzing medical imaging data, particularly structural brain scans such as magnetic resonance imaging (MRI) and functional scans such as positron emission tomography (PET). Finally, it is concluded that CNNs are of great importance for the diagnosis of AD and that they are likely to play an increasingly important role in the early detection of the disease, the understanding of disease mechanisms, and ultimately, in the development of effective AD therapies and interventions. CNNs are playing an increasingly important role in the Their potential impact on healthcare emphasizes the importance of continued research and innovation in neural networks and medical imaging.

The efficiency of organic solar cells (OSCs) is influenced by various factors, among which environmental temperature plays a significant role. Previous studies have shown that the thermal stability of these cells can be enhanced by incorporating a third component into their structure. Ternary organic solar cells, in particular, have shown promising results in improving thermal stability. A well-designed electron transport layer (ETL) can significantly bolster thermal stability by facilitating efficient charge transport and reducing charge recombination. In this study, we investigated the effect of temperature on the efficiency of inverted ternary structures, ranging from 300 K to 400 K. The structures examined include FTO/SnO2/PM6:D18:L8-BO/PEDOT: PSS/Ag, FTO/Spiro-OMeTAD/PM6:D18:L8-BO/PEDOT: PSS/Ag, and FTO/PC60BM/PM6:D18:L8-BO/PEDOT: PSS/Ag. Through simulations employing three different electron transport layers—SnO2, Spiro-OMeTAD, and PC60BM—we observed that at 340 K (65°C) these structures maintained 92% of their original high efficiency of ~20% at 300 K, which represents a high level of thermal stability under the high PCE condition.

Research subjects of this study are four representative locations in the industrial complex, in the city of Banja Luka, Republic of Srpska, Bosnia and Herzegovina. 16 polycyclic aromatic hydrocarbons (PAHs) (∑16PAHs), humus and pH were determined. The main objective of the paper is to determine the concentration levels, to assess the probable sources of PAHs contamination in soil and groundwater and to determine the ecological risk. The ∑16PAHs in soil (at depths of 30 cm, 100 cm, 200 cm, 300 cm and 400 cm) ranged from 0.99 to 2.24 mg/kg, from 0.34 to 0.46, from 0.24 to 0.32, from 0.13 to 0.27 and from 0.13 to 0.47, with mean values of 1.70 mg/kg, 0.40 mg/kg, 0.28 mg/kg, 0.20 mg/kg and 0.26 mg/kg, respectively. The ∑16PAHs in groundwater ranged from 0.23 to 4.50 mg/m³, with a mean value of 1.42 mg/m³. Surface soil and groundwater are heavily contaminated. All values of ∑PAHs in soil layers were lower in the depths of the soil. Factor analysis indicates three sources of contamination, i.e. principal component (PC) PC1 (pyrogenic), PC2 (petrogenic) and PC3 (biomass), with 52.39%, 26.14% and 8.46% of the total variance, respectively. ∑PAH and PAHs indicate high ecological risk for most PAHs, which decreases with soil depth.

In the realm of computer vision, semantic segmentation is the task of recognizing objects in images at the pixel level. This is done by performing a classification of each pixel. The task is complex and requires sophisticated skills and knowledge about the context to identify objects’ boundaries. The importance of semantic segmentation in many domains is undisputed. In medical diagnostics, it simplifies the early detection of pathologies, thus mitigating the possible consequences. In this work, we provide a review of the literature on deep ensemble learning models for polyp segmentation and we develop new ensembles based on convolutional neural networks and transformers. The development of an effective ensemble entails ensuring diversity between its components. To this end, we combine different models (HarDNet-MSEG, Polyp-PVT, and HSNet) trained with different data augmentation techniques, optimization methods, and learning rates, which we experimentally demonstrate to be useful to form a better ensemble. Most importantly, we introduce a new method to obtain the segmentation mask which is more suitable for combining transformers in an ensemble. In our extensive experimental evaluation, the proposed ensembles exhibit state-of-the-art performance.

An application of deep convolutional neural network and recurrence plot for financial market movement prediction is presented. Though it is challenging and subjective to interpret its information, the pattern formed by a recurrence plot provide a useful insight into the dy- namical system. We used a recurrence plot of seven financial time series to train a deep neural network for financial market movement predic- tion. Our approach is tested on our dataset and achieved an average of 53.25% classification accuracy. The result suggests that a well trained deep convolutional neural network can learn a recurrence plot and pre- dict a financial market direction.

With the increase of the Artificial Neural Network (ANN), machine learning has taken a forceful twist in recent times. One of the most spectacular kinds of ANN design is the Convolutional Neural Network (CNN). The Convolutional Neural Network (CNN) is a technology that mixes artificial neural networks and up to date deep learning strategies. In deep learning, Convolutional Neural Network is at the center of spectacular advances. This artificial neural network has been applied to several image recognition tasks for decades and attracted the eye of the researchers of the many countries in recent years as the CNN has shown promising performances in several computer vision and machine learning tasks. This paper describes the underlying architecture and various applications of Convolutional Neural Network.

Carbon fibers (CFs) cannot be directly used for the preparation of CF paper because of their chemically inert nature. Herein, the surface of CF was modified via the spontaneous oxidative self-polymerization of dopamine. By taking full advantage of the spontaneous oxidation and self-polymerization properties of PD to maintain the maximum strength of CFs, a polydopamine-modified CF paper (PDA-CFP) with excellent performance was prepared using PD-modified CFs (PDA-CFs), which increased the proportion of hydrophilic functional groups on the surface of carbon fibers, increased the O/C ratio on the CF surface by 6 times, and improved the bond strength between the modified CF and the adhesive by making full use of the interaction force between polydopamine and PVA fibers. In this way, the primary properties of the CF paper was improved. Overall, the results showed that the dispersion of CF was considerably improved by the dopamine modification. In addition, the primary physical properties of PDA-CFP were better than those of virgin CF paper (CFP-0). PDA-CFP exhibited a maximum tensile strength of 2.04 kN/m2, a minimum resistivity of 0.06055 Ω·cm and a minimum porosity of 72.4%. The tightness could be increased by up to 12.1%.

The Sun is a huge gaseous body. However, we cannot observe events in the inner Sun due to the convection zone opacity according to previous models. Therefore, the flares originate from the front surface of the Sun. But the current study relied on the distance distribution of X-Ray solar flares, which concluded that the inner layers have much lower opacity than expected. It is even less than what was expected by the latest models based on helioseismology. This means that the flares may originate from the solar interior or solar core, and perhaps from the backside surface, and even appear to us from the frontside surface. Which the re-estimate and correct the currently listed solar flare’s location is needed. Additionally, the flare’s distance illustrations the solar interior layers and appears their boundaries from the core to the photosphere. This method allows us to monitor the variation of the core’s radius with time. The model of the flare’s distance has been developed in current study. But this needs to redevelopment after re-estimating the solar flares locations.

Mixed cadmium tellurides – cadmium sulfides thin layers were formed on the polyamide PA 6. Monotelluropentathionic acid (H2TeS4O6) was used as precursor of tellurium and sulfur. We applied a low-temperature, nontoxic and cost-effective SILAR method. Cadmium telluride (CdTe) and sulfide (CdS) layers were formed through consecutive reactions of sorbed/diffused chalcogens species from telluropentathionate anion (TeS4O62–) with functional groups of polyamide and alkaline cadmium sulfate. The pseudo-second-order rate and Elovich kinetic models best fitted to quantify an uptake of chalcogens and cadmium on PA6. The effects of chalcogens and Cd on the structure and optical properties of PA6 were characterized using UV/Vis and IR spectra. The clear changes of these properties found in dependence on the concentration and exposure time in precursor's solutions. Fourier transform infrared spectroscopy and an ultraviolet-visible spectroscopy were applied in order to evaluate the effect of the chalcogens having particles on the changes in structure of polyamide 6 films depending on the exposure time in the solution of the chalcogens precursor and its concentration. The optical band gap energy of formed layers was found to be in the order of 1.52–2.36 eV. Studies of scanning electron microscopy and atomic force microscopy reveal that the diameter of the average grain is about 30 nm. The grains are conical in shape and unevenly distributed all over the surface of the substrate.

This article focuses on generating an alternative in order to identify traffic officers during driving. This research employed the latest You Only Look Once (YOLO) model, using a six-phase methodology: data collection, data preparation involving resizing and labeling, implementation of various filters to avoid overfitting, model training, prediction evaluation, and result interpretation. The YOLO model was applied across three iterations using a dataset of 1862 images. To enhance training efficiency and detection speed, the graphics processing unit (GPU) acceleration was utilized, further enhancing the experimental process. The results of this study revealed that the YOLOv8x variant produced the most promising results. This proposed model attained a remarkable F1 score of 0.95, bolstered by a confidence score of 0.631, with the potential for an increase to 0.80 in confidence without significantly compromising the F1-score. These findings are poised to make a substantial contribution to the broader research landscape, particularly in advancing the effectiveness of detection models for traffic officers.

Convolutional neural network (CNN), a class of artificial neural network (ANN) is attracting interests of researchers in all research domain. CNN was invented for computer vision. They have also shown to be useful for semantic parsing, sentence modeling and other natural language processing related tasks. Here in this paper we discuss the basics of CNN models and their scope to provide a reference/baseline to the researchers interested in using CNN models in their research.

Many works have recently identified the need to combine deep learning with extreme learning to strike a performance balance with accuracy especially in the domain of multimedia applications. Considering this new paradigm, namely convolutional extreme learning machine (CELM), we present a systematic review that investigates alternative deep learning architectures that use extreme learning machine (ELM) for a faster training to solve problems based on image analysis. We detail each of the architectures found in the literature, application scenarios, benchmark datasets, main results, advantages, and present the open challenges for CELM. We follow a well structured methodology and establish relevant research questions that guide our findings. We hope that the observation and classification of such works can leverage the CELM research area providing a good starting point to cope with some of the current problems in the image-based computer vision analysis.

Laser heat treatment is applied after coating. Evaluation of the results was performed by studying the microstructures by metallographic, SEM/EDX microscopy and the mechanical properties were obtained by microscopic hardness and abrasion resistance. The objective of this study was to investigate the effect of laser heat treatment on the wear resistance of metal coatings. The results show the influence of the microstructure and chemical composition of the electrodes used on the micro-hardness and wear resistance of the metal coatings.

The color of a thin copper oxide layer formed on a copper plate was transformed from reddish-brown into blue-purple by irradiation with 5 keV Ar+ ions to a fluence as low as 1 1015 Ar+ cm–2. In the unirradiated copper oxide layer, the copper valence state of Cu2+ as well as Cu+ and/or Cu0 was included as indicated by the presence of a shake-up satellite line in a photoemission spectrum. While for the irradiated one, the satellite line decreased in intensity, indicating that irradiation resulted in the reduction from Cu2+ to Cu+ and/or Cu0. Furthermore, nuclear reaction analysis using a 16O(d, p)17O reaction with 0.85 MeV deuterons revealed a significant loss of oxygen (51015 O atoms cm–2) in the irradiated layer. Thus, the chromatic change observed in the present work originated in the irradiation-induced reduction of a copper oxide.

This paper presents the results of the investigation of composite sinters W-TiB2 which were used as an electrode in the process of electro-spark deposition (ESD) and the examination of the deposited layers. The scope of the study includes detailed characteristics of powder mixtures, composite sinters made using the spark plasma sintering method (SPS) and layers deposited in the electro-spark process. The ESD process, using the W+30 vol.% TiB2 electrode, was carried out using an automated device. The substrates were made of copper and aluminium. The topography analysis of the surfaces of the composite layer and the evaluation of their wear resistance properties are also presented. The analysis of the results of research showed the possibility to obtain, using the SPS method, composite materials of good quality, which can be used as electrodes in the ESD process. The obtained layers had increased wear resistance in relation to the substrate material.

The effect of growth temperature and precursor flows on the doping level and surface morphology of Ge-doped GaN layers was researched. The results show that germanium is more readily incorporated at low temperature, high growth rate and high V/III ratio, thus revealing a similar behavior to what was previously observed for indium. V-pit formation can be blocked at high temperature but also at low V/III ratio, the latter of which however causing step bunching.

This paper proposes an interpretable geometry solution based on the formal language set of text and diagram. Geometry problems are solved by machines, which still poses challenges in natural language processing and computer vision. Significant progress promotes existing methods in the extraction of geometric formal languages. However, the neglect of the graph structure information in the formal language and the lack of further refinement of the extracted language set can lead to the poor effect of the theorem prediction and affect the accuracy in problem solving. In this paper, the formal language graph is constructed by the extracted formal language set and used to theorem prediction by graph convolutional network. So as to better extract the relationship set of diagram elements, an improved diagram parser was proposed. The test results indicate that the improved method has good results in solving the problem with interpretability geometry.

Autonomous image recognition has numerous potential applications in the field of planetary science and geology. For instance, having the ability to classify images of rocks would allow geologists to have immediate feedback without having to bring back samples to the laboratory. Also, planetary rovers could classify rocks in remote places and even in other planets without needing human intervention. Shu et al. classified 9 different types of rock images using a Support Vector Machine (SVM) with the image features extracted autonomously. Through this method, the authors achieved a test accuracy of 96.71%. In this research, Convolutional Neural Networks(CNN) have been used to classify the same set of rock images. Results show that a 3-layer network obtains an average accuracy of 99.60% across 10 trials on the test set. A version of Self-taught Learning was also implemented to prove the generalizability of the features extracted by the CNN. Finally, one model has been chosen to be deployed on a mobile device to demonstrate practicality and portability. The deployed model achieves a perfect classification accuracy on the test set, while taking only 0.068 seconds to make a prediction, equivalent to about 14 frames per second.

Objectives: In order to solve the problem that most of the existing research focuses on the binary tactile attributes of objects,which ignores the tactile attribute strength and category recognition,an attribute strength and category recognition method based on convolutional neural network matrix-label is proposed. Methods:Firstly,in the data preparation stage,we preprocess the raw data and determine the matrix labels to build the haptic dataset.Secondly,in the feature extraction stage,we fuse the haptic data of two fingers and use the convolutional neural network to extract the attribute strength features.Finally,in the attribute strength and category recognition stage,all channel haptic data is fused to predict the attribute strength and category.Results:We compared with the multi-label convolutional neural network method in terms of elastic strength,hardness strength and category,and compared the attribute strength recognition capabilities of the two methods using novel objects outside the haptic dataset.The results show that the accuracy of the last 20 iterations of the matrix-label method has an average elastic strength of 96.73%,hardness strength of 97.34%,and category of 96.67%.The performance is better.When the Euclidean distance between the prediction of the novel object and the real label is less than 1,the accuracy of the elastic strength is best to reach 100%,and the hardness strength is best to reach 100%.The performance is better. Conclusions:The effectiveness of the method has been verified.Comparing with the convolutional neural network method,our method can effectively recognize the attribute strength and category of objects.

The detection of seismic events at regional and teleseismic distances is critical to Nuclear Treaty Monitoring. Traditionally, detecting regional and teleseismic events has required the use of an expensive multi-instrument seismic array; however in this work, we present DeepPick, a novel seismic detection algorithm capable of array-like performance from a single trace. We achieve this directly, by training our single-trace detector against labeled events from an array catalog, and by utilizing a deep temporal convolutional neural network. The training data consists of all arrivals in the International Seismological Centre Catalog for seven seismic arrays over a five year window from 1 Jan 2010 to 1 Jan 2015, yielding a total training set of 608,362 detections. The test set consists of the same seven arrays over a one year window from 1 Jan 2015 to 1 Jan 2016. We report our results by training the algorithm on six of the arrays and testing it on the seventh, so as to demonstrate the transportability and generalization of the technique to new stations. Detection performance against this test set is outstanding. Fixing a type-I error rate of 1%, the algorithm achieves an overall recall rate of 73% on the 141,095 array beam picks in the test set, yielding 102,394 correct detections. This is more than 4 times the 23,259 detections found in the analyst-reviewed single-trace catalogs over the same period, and represents an 8dB improvement in detector sensitivity over current methods. These results demonstrate the potential of our algorithm to significantly enhance the effectiveness of the global treaty monitoring network.

Amorphous ferrite-type rare-earth (RE) substituted garnets and garnet-oxide nanocomposite layers are prepared on clear glass substrates by using RF magnetron sputter-deposition process. By using a combination approach employing custom-built spectrum-fitting software in conjunction with Swanepoel’s envelope method, the spectral dispersion function of optical constants and the layer thicknesses are derived accurately from the transmission spectra of the as-deposited samples. The effects of excess metal-oxides added to the base material systems during the co-deposition process are found to affect the refractive index and the optical absorption coefficients of garnet-oxide composites. A number of optical constant datasets are presented, enabling the experimentalists to design nanophotonic or integrated-optics devices employing these functional materials.

In this paper, we present a study of various ZnO/SiO2-stacked thin film structures for flexible micro-energy harvesting devices. Two groups of micro-energy harvesting devices, SiO2/ZnO/SiO2 micro-energy generators (SZS-MGs) and ZnO/SiO2/ZnO micro-energy generators (ZSZ-MGs), were fabricated by stacking both SiO2 and ZnO thin films, and the resulting devices were characterized. With a particular interest in the fabrication of flexible devices, all the ZnO and SiO2 thin films were deposited on ITO-coated PEN substrates using an RF magnetron sputtering technique. The effects of the thickness and/or position of the SiO2 films on the device performance were investigated by observing the variations of output voltage in comparison with that of a control sample. As a result, compared to the ZnO single-layer device, all the ZSZ-MGs showed much better output voltages, while all the SZS-MG showed only slightly better output voltages. Among the ZSZ-MGs, the highest output voltages were obtained from the ZSZ-MGs where the SiO2 thin films were deposited using a deposition power of 150 W. Overall, the device performance seems to depend significantly on the position as well as the thickness of the SiO2 thin films in the ZnO/ SiO2-stacked multilayer structures, in addition to the processing conditions.

Celiac disease is a gluten-sensitive immune-mediated enteropathy of the small intestine that occurs in genetically predisposed individuals. Abnormal immune response results in mucosal inflammation, villous atrophy, and crypt hyperplasia. This study was a proof-of-concept exercise that used a convolutional neural network to classify hematoxylin and eosin (H&E) histological images of celiac disease, normal small intestine control, and non-specified duodenal inflammation; 7294, 11,642, and 5966 images, respectively. The trained network classified celiac disease images with high performance (accuracy 99.7%, precision 99.6%, recall 99.3%, F1-score 99.5%, and specificity 99.8%). Interestingly, when the same network (already trained for the 3 class images), analyzed duodenal adenocarcinoma (3723 images), the new images were classified as duodenal inflammation in 63.65%, small intestine control in 34.73%, and celiac disease in 1.61% of the cases. Finally, when the network was retrained using the 4 histological subtypes of images, all performance parameters were above 99% for celiac disease. In conclusion, the convolutional neural network (CNN)-based deep neural system was able to classify medical histological images with high performance. Narrow artificial intelligence (AI) is designed to perform tasks that typically require human intelligence, but it operates within limited constraints and is task specific.

Creating intelligent systems capable of recognizing emotions is a difficult task, especially when looking at emotions in animals. This paper describes the process of designing a “proof of concept” system to recognize emotions in horses. This system is formed by two elements, a detector and a model. The detector is a fast region-based convolutional neural network that detects horses in an image. The model is a convolutional neural network that predicts the emotions of those horses. These two elements were trained with multiple images of horses until they achieved high accuracy in their tasks. 400 images of horses were collected and labeled to train both the detector and the model while 80 were used to validate the system. Once the two components were validated, they were combined into a testable system that would detect equine emotions based on established behavioral ethograms indicating emotional affect through head, neck, ear, muzzle and eye position. The system showed an accuracy of between 69% and 74% on the validation set, demonstrating that it is possible to predict emotions in animals using autonomous intelligent systems. Such a system has multiple applications including further studies in the growing field of animal emotions as well as in the veterinary field to determine the physical welfare of horses or other livestock.

Banks are normally offered two kinds of deposit accounts. It consists of deposits like current/saving account and term deposits like fixed or recurring deposits. For enhancing the maximized profit from bank as well as customer perspective, term deposit can accelerate uplifting of finance fields. This paper focuses on likelihood of term deposit subscription taken by the customers. Bank campaign efforts and customer detail analysis can influence term deposit subscription chances. An automated system is approached in this paper that works towards prediction of term deposit investment possibilities in advance. This paper proposes deep learning based hybrid model that stacks Convolutional layers and Recurrent Neural Network (RNN) layers as predictive model. For RNN, Gated Recurrent Unit (GRU) is employed. The proposed predictive model is later compared with other benchmark classifiers such as k-Nearest Neighbor (k-NN), Decision tree classifier (DT), and Multi-layer perceptron classifier (MLP). Experimental study concludes that proposed model attains an accuracy of 89.59% and MSE of 0.1041 which outperform well other baseline models.

Nowadays smartphone utilization for disease diagnosis and remote health care applications has become promising due to their ubiquity. Here, a novel convolutional neural network method for detecting keratoconus that is wholly implemented on a smartphone is proposed. The proposed method provides accurate detection of over 72.9% for all stages of keratoconus. Preliminary results indicate 90%, 83%, 64% and 52% detection rate for severe, advanced, moderate and mild stages of disease, respectively.

The Station logo is a way for a TV station to claim copyright, which can realize the analysis and understanding of the video by the identification of the station logo, so as to ensure that the broadcasted TV signal will not be illegally interfered. In this paper, we design a station logo detection method based on Convolutional Neural Network by the characteristics of the station, such as small scale-to-height ratio change and relatively fixed position. Firstly, in order to realize the preprocessing and feature extraction of the station data, the video samples are collected, filtered, framed, labeled and processed. Then, the training sample data and the test sample data are divided proportionally to train the station detection model. Finally, the sample is tested to evaluate the effect of the training model in practice. The simulation experiments prove its validity.

The effects of the solvent used for the active layer materials of an OLED based on TADF emitters plays a fundamental role in solution-deposited devices. This work focuses the effects on the performance of different solvents employed to fabricate a very simple two organic layer OLED based on a green TADF emitter, under the concept of host:guest matrix. From the different results of the main figures of merit, it was possible to conclude that the OLED that used toluene as solvent for the active layer reached a maximum EQE of 14%, almost the maximum already obtained for this emitter in more complex device structures. With the analysis of the charge transport processes, it was possible to establish an explanatory model for the obtained results. Through impedance spectroscopy, additional characterization about the nature of charge transport processes was carried out. With these results, it was possible to corelate the relaxation times, with the electrical properties of the active layer, and infer about the interaction between the electrical charges and the defect levels opening new possibilities to further development in the printed OLEDs.

Quasistatic nanoindentation is a proven tool that provides information on the micromechanical behavior of wood cell walls. However, quasistatic tests cannot probe the time-dependent mechanical behavior shown by wood. Nanoindentation dynamic mechanical analysis (nanoDMA) can mesaure the viscoelastic properties of wood cell walls. This research aimed to study the quasistatic and viscoelastic properties of individual radiata pine wood (Pinus radiata D. Don) cell wall layers. To minimize variability and retrieve both properties at the same locations, a load function composed of a multiload-quasistatic function followed by dynamic reference frequency segments was developed. Nanoindentations were then performed on the S2 layer and compound corner middle lamella (CCML) of unembedded latewood cells. Because the S2 layer is anisotropic, both transverse and longitudinal-tangential wood planes were studied. In the transverse plane, the average results of the quasistatic elastic moduli (Es) for the S2 layer and CCML were 15.7 GPa and 4.6 GPa, respectively. In the longitudinal-tangential plane, the E_s was 3.9 GPa. In the transverse section, the hardness (H) of the S2 layer and CCML were 331 MPa and 277 MPa, respectively, and in the longitudinal-tangential section H was 244 MPa. To acquire the viscoelastic properties, measurements were made over more than three decades of frequency. An increase of the storage modulus (E'), and a reduction of the loss modulus (E'') and loss factor (tan⁡ δ ) as frequency increased were found in both wood orientations. The quasi-static and dynamic indentations equivalent at 0.1 Hz showed similar values for Es and E’. This study contributes to our knowledge of wood cell wall micromechanical properties.

A case study is presented which demonstrates the value and validity of a novel approach to the use of consolidated amateur (‘ham’) radio reception reports as indicators of the presence of intense ionospheric sporadic E (Es). It is shown that the use of amateur data can provide an important supplement to other techniques, allowing the detection and tracking of Es where no suitable ionosonde or other measurements are available. The effectiveness of the approach is demonstrated by reference to ionosonde data, and the advantages and limitations of the technique are discussed.

Archie model is the basis of calculating oil saturation, but there are some limitations when using this model to calculate oil saturation in water-flooded layer. The main reason is that the main parameters, such as rock resistivity and formation water resistivity, are constantly changing dynamic parameters in the underground with the influence of injected water. Considering that water-flooded layers changes with injection waters, influence factors of rock resistivity and formation water resistivity of primary parameters are analyzed. Considering the dynamic data of water cut is the most reactive underground fluid characteristics of real information, combined with dynamic and static, and the “double ratio” model of later development by the same sedimentary layer is established, which realizes the inversion of rock resistivity and formation water resistivity, then modified Archie model relating to water-flooded layers of the same sedimentary explaining formation. The explanation of actual data indicates that the “double ratio” model well considers the dynamic variation of production data, which makes the inversion of the flooded rock resistivity relatively accurate, besides, the modified Archie model can accurately calculate the oil saturation of water-flooded layers with a reasonable result, which offers scientific basis for the predicting of remaining oil distribution rules.

In this work, we study the dynamical behaviors of the electromagnetic fields and material responses in the hyperbolic metamaterial consisting of periodically arranged metallic and dielectric layers. The thickness of each unit cell is assumed to be much smaller than the wavelength of the electromagnetic waves, so the effective medium concept can be applied. When electromagnetic (EM) fields are present, the responses of the medium in the directions parallel to and perpendicular to the layers are like that of Drude and Lorentz media, respectively. We derive the energy density of the EM fields and the power loss in the effective medium based on Poynting theorem and the dynamical equations of the polarization field. We also show that the Lagrangian density of the system can be constructed. The Euler-Lagrangian equations yield the correct dynamical equations of the electromagnetic fields and the polarization field in the medium. The canonical momentum conjugates to every dynamical field can be derived from the Lagrangian density via differentiation or variation with respect to that field. We apply Legendre transformation to this system, and find that the resultant Hamitonian density is identical to the energy density, up to an irrelevant divergence term.

The nitrogen-doped amorphous oxide semiconductor (AOS) thin film transistors (TFTs) with double-stacked channel layers (DSCL) were prepared and characterized. The DSCL structure composed of nitrogen-doped amorphous InGaZnO and InZnO films (a-IGZO:N/a-IZO:N or a-IZO:N/a-IGZO:N) made the corresponding TFT devices exhibit quite large field-effect mobility due to the existence of double conduction channels. Especially, the a-IZO:N/a-IGZO:N TFTs showed even better electrical performance (μ_FE = 15.0 cm²·V^-1·s^-1, SS = 0.5 V/dec, V_TH = 1.5 V, I_ON/I_OFF = 1.1×10⁸) and stability (V_TH shift of 1.5, -0.5, and -2.5 V for positive bias-stress, negative bias-stress and thermal stress tests, respectively) than the a-IGZO:N/a-IZO:N TFTs. Based on the X-ray photoemission spectroscopy measurements and energy band analysis, it was assumed that the optimized interface trap states, the less ambient gas adsorption, and the better suppression of oxygen vacancies in the a-IZO:N/a-IGZO:N hetero-structures might be responsible for the better behaviors of the corresponding TFTs.

This study develops a 7-layer Long Short-Term Memory (LSTM) model to enhance early diabetes detection in Oman, aligning with the theme of 'Artificial Intelligence in Healthcare'. The model focuses on addressing the increasing prevalence of Type 2 diabetes, projected to impact 23.8% of Oman's population by 2050. It employs LSTM neural networks to manage factors contributing to this rise, including obesity and genetic predispositions, and aims to bridge the gap in public health awareness and prevention. The model's performance is evaluated through various metrics. It achieves an accuracy of 99.40%, specificity and sensitivity of 100% for positive cases, a recall of 99.34% for negative cases, an F1 score of 96.24%, and an AUC score of 94.51%. These metrics indicate the model's capability in diabetes detection. The implementation of this LSTM model in Oman's healthcare system is proposed to enhance early detection and prevention of diabetes. This approach reflects an application of AI in addressing a significant health concern, with potential implications for similar healthcare challenges globally.st diagnostic capabilities, representing a significant leap forward in healthcare technology in Oman.

Epilepsy is a neurological disorder that affects approximately 1% of the world's population. To diagnose and estimate the occurrence of epilepsy, the analysis of recorded brain activity is performed by a neurologist, which is not only time-consuming and tedious but also occasionally accompanied by human error. Therefore, in recent decades, researchers have aimed to unravel an approach for designing and building an automated method for diagnosing and estimating the occurrence of epilepsy. Accordingly, the present study proposed two new-fangled ways based on brain signals and a convolutional neural network (CNN). Moreover, this research implements a CNN with a sequential three-layer structure. Numerous experiments were performed, and the accuracy of estimating epilepsy using the developed methods was achieved at 95% without feedback and 97% with feedback. The proposed methods were proven to be more accurate than the previous techniques and can be employed as a physician's assistant once entering the field of operation.

Zeta potential refers to the electrokinetic potential present in colloidal systems, exerting significant influence on the diverse properties of nano-drug delivery systems. The impact of dielectric constant on the zeta potential and charge inversion of highly charged colloidal particles, immersed in a variety of solvents spanning from polar, such as water, to nonpolar solvents, and in the presence of multivalent salts, was investigated through primitive model Monte Carlo (MC) simulations. Zeta potential ξ is decreased as decreasing the dielectric constant of the solvent, and upon further increase in the salinity and the valency of the salt. At elevated levels of salt, the colloidal particles become overcharged, in all solvents. As a result, their apparent charge becomes opposite in sign to the stoichiometric charge. This reversal of charge intensifies until reaching a saturation point with further increase in salinity, as a result, their apparent charge becomes opposite in sign to the stoichiometric charge. This reversal of charge intensifies until reaching a saturation point with further increase in salinity.

The establishment of an isolation layer in submarine mining has long presented an enduring challenge. In the context of this research, we conducted a similarity simulation test to preliminarily ascertain the interplay between the thickness and extent of the isolation layer. Subsequently, we introduce an innovative approach that integrates fractal theory and the bonded block model (BBM) to simulate undersea isolation layer mining. The validation of this method hinges on on-site borehole scanning and displacement monitoring, which serve to depict the intricate fractal evolution of fractures and predict the optimal thickness of the isolation layer. Our findings affirm the robustness and validity of this method. Evaluation of the fractal dimensions of fractures reveals that a critical threshold of 1.7 exists to prevent structural failure of the isolation layer, while a limit of 1.5 is necessary to avert significant water ingress. Remarkably, the correlation dimension of the settlement time series closely aligns with the fractal dimension of the fractures, underscoring the feasibility of ensuring the safety of isolation layer mining through real-time settlement monitoring.

The exact similarity solutions of two dimensional laminar boundary layer were obtained by Blasius in 1908, however, for two dimensional turbulent boundary layers, no similarity solutions (special exact solutions) have ever been found. In the light of Blasius' pioneer works, we extend Blasius similarity transformation to the two dimensional turbulent boundary layers, and successfully transform the two dimensional turbulent boundary layers partial differential equations into a single ordinary differential equation. By author's Maple code, we numerically solve the ordinary differential equation and produce some useful quantities.

Various type of soils have been identified based on their electrical and magnetic properties, especially with regards to peat soils. Peat soils are commonly considered as partly decomposed vegetation. In this study, electrical and magnetic properties have been used in K-means clustering to identify layers of peat soils. K-means clustering is a partitioning method that treats observations in the data. Data cores were obtained at every centimeter and examined for their electrical conductivity (σ) and magnetic susceptibility (χ_m) properties. A 291 cm core was obtained at Tegal Arum Village in South Kalimantan, Indonesia. The K-means clustering results indicate two different layers at 148 cm, and this is supported by loss on ignition (LOI) measurements. In the first layers, a 87.65% LOI was found associated with peat soils (above 248 cm). Whereas, in the second layers, there was a 26.11% LOI associated with mineral soils (below 248 cm). The results of this study using K-means clustering can be used to delineate soil layers.

In this paper, a framework for simultaneous tracking and recognizing drone targets using a low-cost and small-sized millimeter-wave radar is presented. The radar collects the reflected signals of multiple targets in the field of view including drone and non-drone targets. The analysis of the received signals allows multiple targets to be distinguished because of the different reflection patterns. The proposed framework consists of four processes including signal processing, cloud points clustering, target tracking, and target recognition. Signal processing translates the raw signals into spare cloud points. These points are merged into several clusters, each representing a single target. Target tracking estimates the new locations of each detected target. A novel convolutional neural network model is developed for drone and/or non-drone targets feature extraction and recognition. For performance evaluation, a dataset collected with an IWR6843ISK mmWave sensor by Texas Instruments is used for training and testing the convolutional neural network. The proposed recognition model achieves an accuracy of 98.4% for one target and 98.1% for two targets.

Seawater density is an important physical property in oceanography that affects the accuracy of calculations such as gravity fields and tidal potentials, and the calibration of acoustic and optical oceanographic sensors. In related studies, constant density values are frequently used, which can introduce significant errors. Therefore, this study employs a basic convolutional neural network model to construct a comprehensive model showing the seawater density distribution across the globe. The model takes into account depth, latitude, longitude, and month as inputs. Numerous real seawater datasets were used to train the model, and it has been shown that the model has an absolute mean error and root mean square error of less than 2 kg/m3 in 99% of the test set samples. The model effectively demonstrates the influence of input parameters on the distribution of seawater density. In this paper, we present a newly developed global model for distributing seawater density which is both comprehensive and accurate, surpassing previous models. The utilization of the model presented in this paper for estimating seawater density can minimize errors in theoretical ocean models and serve as a foundation for designing and analyzing ocean exploration systems.

Handwriting is a form of biometric behavioral characteristic with evident individual distinctiveness. With the surge of the deep learning trend and the demand for forensic identification, handwriting identification has become one of the focal points of research in the field of pattern recognition. The research on handwriting identification in major world languages has reached a mature stage. However, there is still a notable lack of relevant research in the field of Mongolian handwriting identification, despite the fact that Mongolian is used by over 4 million people in China. This paper embarks on an initial exploration of Mongolian handwriting identification by constructing a convolutional neural network named MWInet-12. In this paper, the model evaluation experiments were conducted using a dataset comprising 156,372 samples contributed by 125 authors from the MOLHW dataset. The dataset was divided into training, validation, and test sets in an 8:1:1 ratio. The final results of the experiments reveal impressive accuracy on the test set, achieving a top-1 accuracy of 89.60% and a top-5 accuracy of 97.53%. Furthermore, through comparative experiments involving Resnet, Fragnet, and GRRNN models, this paper establishes that the proposed model yields the most favorable results for Mongolian handwriting identification.

Near Earth Asteroids represent potential threats to human life because their trajectories may bring them in the proximity of the Earth. Monitoring these objects could help predict future impact events, but such efforts are hindered by the large numbers of objects that pass through the Earth’s vicinity. Additionally, there is also the problem of distinguishing asteroids from other objects in the night sky, which implies sifting through large sets of telescope image data. Within this context, we believe that employing machine learning techniques could greatly improve the detection process by sorting out the most likely asteroid candidates to be reviewed by human experts. At the moment, the use of machine learning techniques is still limited in the field of astronomy and the main goal of the present paper is to study the effectiveness of deep CNNs for the classification of astronomical objects, asteroids in this particular case, by comparing some of the well-known deep convolutional neural networks, including InceptionV3, Xception, InceptionResNetV2 and ResNet152V2. We have applied transfer learning and fine-tuning on these pre-existing deep convolutional networks and from the results that we have obtained one can see the potential of using deep convolutional neural networks in the process of asteroid classification. The InceptionV3 model has the best results in the asteroid class, meaning that by using it, we loose the least number of valid asteroids.

Personality is the most critical feature that tells us about an individual. It is the collection of the individual’s thoughts, opinions, emotions and more. Personality detection is an emerging field in research and Deep Learning models have only recently started being developed. There is a need for a larger dataset that is unbiased as the current dataset that is used is in the form of questionnaires that the individuals themselves answer, hence increasing the chance of unconscious bias. We have used the famous stream-of-consciousness essays collated by James Pennbaker and Laura King. We have used the Big Five Model often known as the five-factor model or OCEAN model. Document-level feature extraction has been performed using Google’s word2vec embeddings and Mairesse features. The processed data has been fed into a deep convolutional network and a binary classifier has been used to classify the presence or absence of the personality trait. Hold- out method has been used to evaluate the model, and the F1 score has been used as the performance metric.

Convolutional neural networks (CNNs), inspired by biological visual cortex systems, are a powerful category of artificial neural networks that can extract the hierarchical features of raw data to greatly reduce the network parametric complexity and enhance the predicting accuracy. They are of significant interest for machine learning tasks such as computer vision, speech recognition, playing board games and medical diagnosis [1-7]. Optical neural networks offer the promise of dramatically accelerating computing speed to overcome the inherent bandwidth bottleneck of electronics. Here, we demonstrate a universal optical vector convolutional accelerator operating beyond 10 Tera-OPS (TOPS - operations per second), generating convolutions of images of 250,000 pixels with 8-bit resolution for 10 kernels simultaneously — enough for facial image recognition. We then use the same hardware to sequentially form a deep optical CNN with ten output neurons, achieving successful recognition of full 10 digits with 900 pixel handwritten digit images with 88% accuracy. Our results are based on simultaneously interleaving temporal, wavelength and spatial dimensions enabled by an integrated microcomb source. This approach is scalable and trainable to much more complex networks for demanding applications such as unmanned vehicle and real-time video recognition.

This paper presents a study and implementation of a convolutional neural network to identify and recognize humpback whale specimens from the unique patterns of their tails. Starting from a dataset composed of images of whale tails, all the phases of the process of creation and training of a neural network are detailed – from the analysis and pre-processing of images to the elaboration of predictions, using TensorFlow and Keras frameworks. Other possible alternatives are also explained when it comes to tackling this problem and the complications that have arisen during the process of developing this paper.

A new three-dimensional numerical model of a polymer electrolyte fuel cell (PEFC) with a single straight channel has been developed to primarily investigate the important impact of the double-sided microporous layer (MPL) coating on the overall performance of the fuel cell and the distribution of the current and the oxygen concentration within the cathode gas diffusion layers (GDLs). Realistic experimentally estimated interfacial contact resistance values between the gas diffusion layer and each of the bipolar plates and the catalyst layer values were incorporated into the model, and parametric studies were performed. The results showed that the double-sided MPL coating could significantly improve the fuel cell performance by up to 30%. Also, it was shown that the neglect of the contact resistance between the MPL and the catalyst layer could overestimate the fuel cell performance by up to 6%. In addition, the results showed that the fuel cell performance and the distribution of the current and oxygen are more sensitive to the porosity of the MPL facing the bipolar plate than the porosity of the MPL facing the catalyst layer. All the above results are presented and critically discussed in detail.

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 hyperpa-rameters, 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 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.

Weeds are unwanted and invasive plants that proliferate and compete for resources such as space, water, nutrients, and sunlight, affecting the quality and productivity of the desired crops. Weed detection is crucial for the application of precision agriculture methods and for this purpose machine learning techniques can be used, specifically convolutional neural networks (CNN). This study focuses on the search for CNN architectures and technology used to detect and identify weeds in different crops; 61 articles applying CNN architectures and technology were analyzed in the last five years (2019-2023). The results show the used of different devices to acquire the image for training, such as digital cameras, smartphones, and drone cameras. Additionally, the YOLO family and algorithms are the most widely adopted architectures, followed by VGG, ResNet, Faster R-CNN, AlexNet, and MobileNet, respectively. This study provides an update on CNNs that will serve as a starting point for researchers wishing to implement these weed detection and identification techniques.

In recent years, Edge Intelligence (EI) has emerged, combining edge computing with AI, specifically deep learning, to run AI algorithms directly on edge devices. In practical applications, EI faces challenges related to computational power, power consumption, size, and cost, with the primary challenge being the trade-off between computational power and power consumption. This has rendered traditional computing platforms unsustainable, making heterogeneous parallel computing platforms a crucial pathway for implementing EI. In our research, we leveraged the Xilinx Zynq 7000 heterogeneous computing platform, employed High-Level Synthesis (HLS) for design, and implemented two different accelerators for LeNet-5 using loop unrolling and pipelining optimization techniques. The experimental results show that when running at a clock speed of 100 MHz, the PIPELINE accelerator, compared to the UNROLL accelerator, experiences an 8.09% increase in power consumption but speeds up by 14.972 times, making the PIPELINE accelerator superior in performance. Compared to the CPU, the PIPELINE accelerator reduces power consumption by 91.37% and speeds up by 70.387 times, while compared to the GPU, it reduces power consumption by 93.35%.This study provides two different optimization schemes for edge intelligence applications through design and experimentation, and demonstrates the impact of different quantization methods on FPGA resource consumption. These experimental results can provide a reference for practical applications, thereby providing a reference hardware acceleration scheme for edge intelligence applications.

Convolutional neural networks (CNN) have attracted much attention as a commonly used method for hyperspectral image (HSI) classification in recent years, however, CNNs can only be applied to Euclidean data and have limitations in dealing with relationships due to the limitations of local feature extraction. However, each pixel of a hyperspectral image contains a set of spectral bands that are correlated and interact with each other, and the methods used to process Euclidean data cannot effectively obtain these correlations. In contrast, the graph convolutional network (GCN) can be used in non-Euclidean data, but usually leads to oversmoothing and ignoring local detail features due to the need for superpixel segmentation processing to reduce computational effort. To overcome the above problems, we constructed a network a fusion network based on GCN and CNN, which contains two branches: a graph convolutional network based on superpixel segmentation and a convolutional network with added attention mechanism. The graph convolu-tional branch can extract the structural features and capture the relationships between the nodes, and the convolutional branch can extract the detailed features in the local fine region. Owing to the fact that the features extracted from the two branches are different, the classification performance can be improved by fusing the complementary features extracted from the two branches. To vali-date the proposed algorithm, experiments were conducted on three widely used datasets, namely Indian Pines, Pavia University, and Salinas, and the overall accuracy of 98.78% was obtained in the Indian Pines dataset, and the overall accuracy of 98.99% and 98.69% was obtained in the other two datasets. The results showed that the proposed fusion network can obtain richer features and achieve high classification accuracy.

To solve two key problems in the identification of people who are infected with COVID-19: the first problem is that the identification accuracy is not high enough. The second problem is that present identification method such as nucleic acid testing is expensive in many countries. Methods: So, I decided to design a fast identification method for COVID-19 patients which is based on deep learning. After the model (CoughNet) learns more than 6,000 cough spectrograms of both COVID-19 patients and normal people, the accuracy rate of identification of COVID-19 patients and normal people is higher than 99% in the test set. Structure: This paper is mainly divided into three parts: the first part introduces the main background and research status of the research; The second part introduces the research methods; The third part introduces the specific process of the experiment.

Recently, much attention has been devoted to finding highly efficient and powerful activation functions for CNN layers. Because activation functions inject different nonlinearities between layers that affect performance, varying them is one method for building robust ensembles of CNNs. The objective of this study is to examine the performance of CNN ensembles made with different activation functions, including six new ones presented here: 2D Mexican ReLU, TanELU, MeLU+GaLU, Symmetric MeLU, Symmetric GaLU, and Flexible MeLU. The highest performing ensemble was built with CNNs having different activation layers that randomly replaced the standard ReLU. A comprehensive evaluation of the proposed approach was conducted across fifteen biomedical data sets representing various classification tasks. The proposed method was tested on two basic CNN architectures: Vgg16 and ResNet50. Results demonstrate the superiority in performance of this approach. The MATLAB source code for this study will be available at https://github.com/LorisNanni.

Topology optimization is a pioneering design method that can provide various candidates with high mechanical properties. However, the high-resolution for the optimum structures is highly desired, normally in turn leading to computationally intractable puzzle, especially for the famous Solid Isotropic Material with Penalization (SIMP) method. In this paper, an efficient and high-resolution topology optimization method is proposed based on the Super-Resolution Convolutional Neural Network (SRCNN) technique in the framework of SIMP. The SRCNN includes four processes, i.e. refining, path extraction & representation, non-linear mapping, and reconstruction. The high computational efficiency is achieved by a pooling strategy, which can balance the number of finite element analysis (FEA) and the output mesh in optimization process. To further reduce the high computational cost of 3D topology optimization problems, a combined treatment method using 2D SRCNN is built as another speeding-up strategy. A number of typical examples justify that the high-resolution topology optimization method adopting SRCNN has excellent applicability and high efficiency for 2D and 3D problems with arbitrary boundary conditions, any design domain shape, and varied load.

This work is devoted to consideration and analysis of the application of molecular dynamics simulation (MDS) methods to the study of nanosized polymer polyvinylidene fluoride (PVDF) thin ferroelectric films (two-dimensional ferroelectrics) and their composites with graphene layers: 1) to study and calculations of the polarization switching time depending on the electric field and PVDF film thickness; 2) to study and calculations of the polarization switching time depending changes of the PVDF on PVDF-TrFE film; 3) to study the polarization switching time in PVDF under influence of graphene layers. All calculations at each MDS step were carried out using quantum semi-empirical methods PM3. A comparison and analysis of the results of these calculations and the kinetics of polarization switching within the framework of the Landau-Ginzburg-Devonshire theory for homogeneous switching in ferroelectric polymer films is carried out. The study of the composite heterostructures of the “graphene-PVDF” type and calculations of their polarization switching times were presented too. It is shown that replacing PVDF with PVDF-TrFE significantly changes the polarization switching times in these thin polymer films, and that introducing various graphene layers into the PVDF layered structure leads to both an increase and a decrease in the polarization switching time. Here everything also depends on the position and displacement of the ferroelectric coercive field depending on the system damping parameters.

In this work, the possibility of fabrication magneto-optical ceramics by vacuum sintering of compacts prepared by electrophoretic deposition (EPD) from suspensions of (Ho0.95La0.05)2O3 (HoLa) nanopowders made by self-propagating high-temperature synthesis and (Y0.9La0.1)2O3 (YLa) nanopowders made by laser synthesis was systematically investigated. The processes of the formation of bulk one- and two-layer compacts by the EPD method from non-aqueous suspensions of nanopowders was studied. The use of acetylacetone and polyvinyl butyral (PVB) was shown to make it possible to obtain stable alcohol suspensions of the nanopowders characterized by high zeta potential values (+29…+80 mV) and to carry out a stable EPD process. One-layer compacts were made from the YLa and HoLa nanopowders with a density of 30–43%. It was found out that the introduction of PVB into the suspension leads to a decrease in the mass and thickness of the green bodies deposited, but does not significantly affect their density. A possibility to make two-layers (YLa/HoLa) compacts with a thickness of up to 2.6 mm and a density of up to 46% was demonstrated. Sintering such compacts in a vacuum at a temperature of 1750°C for 10 hours leads to the formation of ceramics with a homogeneous boundary between the YLa/HoLa layers and thickness of the interdiffused ions layer of about 30 μm.

Popular geo-computer vision works make use of aerial imager with sizes ranging from 64 × 64 to 1024 × 1024 pixels without any overlap, although the learning process of deep learning models can be affected by the reduced semantic context or the lack of information near image boundaries. In this work, the impact of three image sizes (256 × 256, 512 × 512, and 1024 × 1024 pixels) and two image overlap levels (no overlap and 12.5% overlap) on the performance of road classification models was statistically evaluated. For this, two convolutional neural networks used in various tasks of geospatial object extraction were trained (using the same hyperparameters) on a large dataset (containing aerial image data covering 8650 km² of the Spanish territory that was labelled with binary road information) under twelve different scenarios, each scenario featuring a different combination of tile size and overlap. To assess their generalisation capacity, the performance of all resulting models was evaluated on a data from novel areas covering approximately 825 km². The performance metrics obtained were analysed using appropriate descriptive and inferential statistical techniques to evaluate the impact of the performance at distinct levels of the fixed factors (tile size, tile overlap, neural network architecture). Statistical tests were applied to study the main and interaction effects of the fixed factors on the performance. A significance level of 0.05 was applied to all the null hypothesis tests. The results were highly significant for the main effects (p-values lower than 0.001), while the two-way and three-way interaction effects among them had different levels of significance. The results indicate that the training of road classification models on images with a higher tile size (more semantic context) and tile overlap (additional border context and continuity) significantly impacts their performance. The best model was trained on a dataset featuring tiles with a size of 1024 × 1024 pixels and a 12.5% overlap and achieved a loss value of 0.0984, an F1 score of 0.8728, and an ROC-AUC score of 0.9766, together with an error rate of 3.5% on the test set.

GaN nanowires grown on metal substrates attract an increasing interest for a wide range of applications. Herein, we report GaN nanowires grown by plasma-assisted molecular beam epitaxy on thin polycrystalline ZrN buffer layers, sputtered onto Si(111) substrates. The nanowire orientation is studied experimentally and described within a model as a function of the Ga beam angle, nanowire tilt angle and substrate rotation. We show that vertically aligned nanowires grow faster than inclined nanowires, which leads to an interesting effect of geometrical selection of the nanowire orientation in the directional molecular beam epitaxy technique. After a given growth time, this effect depends on the nanowire surface density. At low density, the nanowires continue to grow with random orientations as nucleated. At high density, the effect of preferential growth induced by unidirectional supply of material in MBE starts to dominate. Faster growing nanowires with smaller tilt angles shadow more inclined nanowires that grow slower. This helps to obtain more regular ensembles of vertically oriented GaN nanowires despite their random position induced by the metallic grains at nucleation. The obtained dense ensembles of vertically aligned GaN nanowires on ZrN/Si(111) surfaces are highly relevant for device applications. These results are not specific for GaN nanowires and should be relevant for any nanowires which are epitaxially linked to the randomly oriented surface grains in the directional molecular beam epitaxy.

Porous materials can be characterized by well-trained neural networks. In this study, fibrous paper-type gas diffusion layers were trained with artificial data created by a stochastic geometry model. The features of the data were calculated by means of transport simulations using the Lattice–Boltzmann method based on stochastic micro-structures. A convolutional neural network was developed that can predict the permeability and tortuosity of the material, through-plane and in-plane. The characteristics of real data, both uncompressed and compressed, were predicted. The data was represented by reconstructed images of different sizes and image resolutions. Image artifacts are also a source of potential errors in the prediction. The Kozeny–Carman trend was used to evaluate the prediction of permeability and tortuosity of compressed real data. Using this method, it was possible to decide if the predictions on compressed data were appropriate.

Mid-latitude sporadic-E (Es) is an intermittent phenomenon of the lower E region of the ionosphere. Es clouds are thin, transient, and patchy layers of intense ionization, with ionization densities which can be much higher than in the background ionosphere. Oblique reflection of radio signals in the very high frequency (VHF) range is regularly supported, but the mechanism for it has never been clearly established - specular reflection, scattering, and magnetoionic double refraction have all been suggested. This article proposes using the polarization behaviour of signals reflected from intense midlatitude sporadic-E clouds as an indicator of the true reflection mechanism. Results are presented from a measurement campaign in the summer of 2018, which gathered a large amount of data at a receiving station in the UK using 50 MHz amateur radio beacons as signal sources. In all cases the signals received were elliptically polarized, despite being transmitted with linear polarization; there were also indications that polarization behaviour varied systematically with the orientation of the path to the geomagnetic field. This represents, for all the examples recorded, clear evidence that signals were reflected from midlatitude Es by magnetoionic double refraction.

Structure quality of LuFeO3 epitaxial layers grown by pulsed-laser deposition on sapphire substrates with and without platinum interlayers has been investigated by in-situ high-resolution x-ray diffraction (reciprocal-space mapping). The parameters of the structure such as size and misorientation of mosaic blocks have been determined as functions of the thickness of LuFeO3 during the PLD growth and for different platinum interlayers thicknesses up to 40 nm. The x-ray diffraction results combined with ex-situ scanning electron microscopy and high-resolution transmission electron microscopy demonstrate that the Pt interlayer significantly improves the structure of LuFeO3 by reducing the misfit of the LuFeO3 lattice with respect to the material underneath.

Diabetic retinopathy, a common complication of diabetes, is further exacerbated by factors such as hypertension and obesity. This study introduces the Diabetic Retinopathy Convolutional Transformer (DRCT) model, which combines convolutional and transformer techniques to enhance the classification of retinal images. The DRCT model achieved an impressive average F1 score of 0.97, reflecting its high accuracy in detecting true positives while minimizing false positives. Throughout 100 training epochs, the model exhibited strong generalization capabilities, achieving superior validation accuracy with minimal overfitting. On a newly evaluated dataset, the model attained precision and recall scores of 96.93% and 98.89%, respectively, indicating a well-balanced handling of false positives and false negatives. The model's ability to classify retinal images into five distinct diabetic retinopathy categories demonstrates its potential to significantly improve automated diagnosis and aid in clinical decision-making.