Search

In the last few years, the use of convolutional neural networks (CNNs) in intrusion detection domains has attracted more and more attention. However, their results in this domain have not lived up to expectations compared to the results obtained in other domains, such as image classification and video analysis. This is mainly due to the datasets used, which contain preprocessed features that are not compatible with convolutional neural networks, as they do not allow a full exploit of all the information embedded in the original network traffic. With the aim of overcoming these issues, we propose in this paper a new efficient convolutional neural network model for network intrusion detection based on raw traffic data (pcap files) rather than preprocessed data stored in CSV files. The novelty of this paper lies in the proposal of a new method for adapting the raw network traffic data to the most suitable format for CNN models, which allows us to fully exploit the strengths of CNNs in terms of pattern recognition and spatial analysis, leading to more accurate and effective results. Additionally, to further improve its detection performance, the structure and hyperparameters of our proposed CNN-based model are automatically adjusted using the self-adaptive differential evolution (SADE) metaheuristic, in which symmetry plays an essential role in balancing the different phases of the algorithm, so that each phase can contribute in an equal and efficient way to finding optimal solutions. This helps to make the overall performance more robust and efficient when solving optimization problems. The experimental results on three datasets, KDD-99, UNSW-NB15, and CIC-IDS2017, show a strong symmetry between the frequency values implemented in the images built for each network traffic and the different attack classes. This was confirmed by a good predictive accuracy that goes well beyond similar competing models in the literature. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy (DR) poses a significant challenge in diabetes management, with its progression often asymptomatic until advanced stages. This underscores the urgent need for cost-effective and reliable screening methods. Consequently, the integration of artificial intelligence (AI) tools presents a promising avenue to address this need effectively. We provide an overview of the current state of the art results and techniques in DR screening using AI, while also identifying gaps in research for future exploration. By synthesizing existing database and pinpointing areas requiring further investigation, this paper seeks to guide the direction of future research in the field of automatic diabetic retinopathy screening. There has been a continuous rise in the number of articles detailing deep learning (DL) methods designed for the automatic screening of diabetic retinopathy especially by the year 2021. Researchers utilized various databases, with a primary focus on the IDRiD dataset. This dataset consists of color fundus images captured at an ophthalmological clinic situated in India. It comprises 516 images that depict various stages of DR and diabetic macular edema. Each of the chosen papers concentrates on various DR signs. Nevertheless, a significant portion primarily focused on detecting exudates, which remains insufficient to assess the overall presence of this disease. Various AI methods have been employed to identify DR signs. Among the chosen papers, 4.7 % utilized detection methods, 46.5 % employed classification techniques, 41.9 % relied on segmentation, and 7 % opted for a combination of classification and segmentation. Metrics calculated from 80 % of the articles employing preprocessing techniques demonstrated the significant benefits of this approach in enhancing results quality. In addition, multiple DL techniques, starting by classification, detection then segmentation. Researchers used mostly YOLO for detection, ViT for classification, and U-Net for segmentation. Another perspective on the evolving landscape of AI models for diabetic retinopathy screening lies in the increasing adoption of Convolutional Neural Networks for classification tasks and U-Net architectures for segmentation purposes; however, there is a growing realization within the research community that these techniques, while powerful individually, can be even more effective when integrated. This integration holds promise for not only diagnosing DR, but also accurately classifying its different stages, thereby enabling more tailored treatment strategies. Despite this potential, the development of AI models for DR screening is fraught with challenges. Chief among these is the difficulty in obtaining the high-quality, labeled data necessary for training models to perform effectively. This scarcity of data poses significant barriers to achieving robust performance and can hinder progress in developing accurate screening systems. Moreover, managing the complexity of these models, particularly deep neural networks, presents its own set of challenges. Additionally, interpreting the outputs of these models and ensuring their reliability in real-world clinical settings remain ongoing concerns. Furthermore, the iterative process of training and adapting these models to specific datasets can be time-consuming and resource-intensive. These challenges underscore the multifaceted nature of developing effective AI models for DR screening. Addressing these obstacles requires concerted efforts from researchers, clinicians, and technologists to develop new approaches and overcome existing limitations. By doing so, a full potential of AI may transform DR screening and improve patient outcomes. [ABSTRACT FROM AUTHOR]

Scene classification and recognition have always been one of the most challenging tasks of scene understanding due to the inherent ambiguity in visual scenes. The core of scene classification and recognition tasks is scene representation. Deep learning advances in computer vision, especially deep CNNs, have significantly improved scene representation in the last decade. Deep convolutional features extracted from deep CNNs provide discriminative representations of the images and are widely used in various computer vision tasks, such as scene classification. Deep convolutional features capture the appearance characteristics of the image and the spatial information about different image regions. Meanwhile, the semantic and context information obtained from high-level concepts about scene images, such as objects and their relationships, can significantly contribute to identifying scene images. Therefore, in this paper, we divide visual scenes into two categories, object-based and layout-based. Object-based scenes are scenes that have scene-specific objects and, based on those objects, can be described and identified. In contrast, the layout-based scenes do not have scene-specific objects and are described and identified based on the appearance and layout of the image. This paper proposes a new neural network model for representing and classifying visual scenes, which we call G-CNN (GNN-CNN). The proposed model includes two modules, feature extraction and feature fusion, and the feature extraction module composes of visual and semantic branches. The visual branch is responsible for extracting deep CNN features from the image, and the semantic branch is responsible for extracting semantic GNN features from the scene graph corresponding to the image. The feature fusion module is a novel two-stream neural network that fuses the CNN and GNN feature vectors to produce a comprehensive representation of the scene image. Finally, a fully-connected classifier classified the obtained comprehensive feature vector into one of the pre-defined categories. The proposed model has been evaluated on three benchmark scene datasets, UIUC Sports, MIT67, and SUN397, and obtained classification accuracy of 99.91%, 96.01%, and 85.32%, respectively. In addition, a new dataset named Scene40, which has been introduced in our previous paper, is also used for further evaluation of the proposed method. The comparison results based on classification accuracy criteria show that the proposed model can outperform the best previous methods on three benchmark scene datasets. [ABSTRACT FROM AUTHOR]

With the establishment of the "double carbon" goal, various industries are actively exploring ways to reduce carbon emissions. Cloud data centers, represented by cloud computing, often have the problem of mismatch between load requests and resource supply, resulting in excessive carbon emissions. Based on this, this paper proposes a complete method for cloud computing carbon emission prediction. Firstly, the convolutional neural network and bidirectional long-term and short-term memory neural network (CNN-BiLSTM) combined model are used to predict the cloud computing load. The real-time prediction power is obtained by real-time prediction load of cloud computing, and then the carbon emission prediction is obtained by power calculation. Develop a dynamic server carbon emission prediction model, so that the server carbon emission can change with the change of CPU utilization, so as to achieve the purpose of low carbon emission reduction. In this paper, Google cluster data is used to predict the load. The experimental results show that the CNN-BiLSTM combined model has good prediction effect. Compared with the multi-layer feed forward neural network model (BP), long short-term memory network model (LSTM), bidirectional long short-term memory network model (BiLSTM), modal decomposition and convolution long time series neural network model (CEEMDAN-ConvLSTM), the MSE index decreased by 52 % , 50 % , 34 % and 45 % respectively. [ABSTRACT FROM AUTHOR]

To overcome AMR s limited generalization and low classification accuracy in non-cooperative communication contexts with low signal-to-noise ratio, this paper proposed a model named CGDNN, which integrated CNN, GRU and deep neural networks. To mitigate noise impact on modulation detection, this paper initially denoised I/Q sampled signal using wavelet thresholding. Subsequently, this paper utilized CNN and GRU for extracting spatial and temporal features from signals before proceeding to classification through fully connected layers. Besides enhancing AMR performance, the CGDNN model significantly reduced computational complexity compared to competitors. Experiment results demonstrate an average recognition accuracy of 64.32% on the RML2016. 10b dataset, with an enhancement in signal classification accuracy from 12 dB to 0 dB. Moreover, the model substantially decreased confusion between 16QAM and 64QAM, achieving a peak recognition accuracy of 93.9% at 18 dB. CGDNN model effectively improved AMR detection accuracy under low signal-to-noise ratio conditions and enhanced model training efficiency. [ABSTRACT FROM AUTHOR]

Mental stress is a common problem that affects individuals all over the world. Stress reduces human functionality during routine work and may lead to severe health defects. Early detection of stress is important for preventing diseases and other negative health-related consequences of stress. Several neuroimaging techniques have been utilized to assess mental stress, however, due to its ease of use, robustness, and non-invasiveness, electroencephalography (EEG) is commonly used. This paper aims to fill a knowledge gap by reviewing the different EEG-related deep learning algorithms with a focus on Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTMs) for the evaluation of mental stress. The review focuses on data representation, individual deep neural network model architectures, hybrid models, and results amongst others. The contributions of the paper address important issues such as data representation and model architectures. Out of all reviewed papers, 67% used CNN, 9% LSTM, and 24% hybrid models. Based on the reviewed literature, we found that dataset size and different representations contributed to the performance of the proposed networks. Raw EEG data produced classification accuracy around 62% while using spectral and topographical representation produced up to 88%. Nevertheless, the roles of generalizability across different deep learning models and individual differences remain key areas of inquiry. The review encourages the exploration of innovative avenues, such as EEG data image representations concurrently with graph convolutional neural networks (GCN), to mitigate the impact of inter-subject variability. This novel approach not only allows us to harmonize structural nuances within the data but also facilitates the integration of temporal dynamics, thereby enabling a more comprehensive assessment of mental stress levels. [ABSTRACT FROM AUTHOR]

Understanding road conditions is essential for implementing effective road safety measures and driving solutions. Road situations encompass the day-to-day conditions of roads, including the presence of vehicles and pedestrians. Surveillance cameras strategically placed along streets have been instrumental in monitoring road situations and providing valuable information on pedestrians, moving vehicles, and objects within road environments. However, these video data and information are stored in large volumes, making analysis tedious and time-consuming. Deep learning models are increasingly utilized to monitor vehicles and identify and evaluate road and driving comfort situations. However, the current neural network model requires the recognition of situations using time-series video data. In this paper, we introduced a multi-directional detection model for road situations to uphold high accuracy. Deep learning methods often integrate long short-term memory (LSTM) into long-term recurrent network architectures. This approach effectively combines recurrent neural networks to capture temporal dependencies and convolutional neural networks (CNNs) to extract features from extensive video data. In our proposed method, we form a multi-directional long-term recurrent convolutional network approach with two groups equipped with CNN and two layers of LSTM. Additionally, we compare road situation recognition using convolutional neural networks, long short-term networks, and long-term recurrent convolutional networks. The paper presents a method for detecting and recognizing multi-directional road contexts using a modified LRCN. After balancing the dataset through data augmentation, the number of video files increased, resulting in our model achieving 91% accuracy, a significant improvement from the original dataset. [ABSTRACT FROM AUTHOR]

The paper presents the analysis of modern Artificial Intelligence algorithms for the automated system supporting human beings during their conversation in Polish language. Their task is to perform Automatic Speech Recognition (ASR) and process it further, for instance fill the computer-based form or perform the Natural Language Processing (NLP) to assign the conversation to one of predefined categories. The state-of-the-art review is required to select the optimal set of tools to process speech in the difficult conditions, which degrade accuracy of ASR. The paper presents the top-level architecture of the system applicable for the task. Characteristics of Polish language are discussed. Next, existing ASR solutions and architectures with the End-To-End (E2E) Deep Neural Network (DNN) based ASR models are presented in detail. Differences between Recurrent Neural Networks (RNN), Convolutional Neural Networks (CNN) and transformers in the context of ASR technology are also discussed. [ABSTRACT FROM AUTHOR]

This paper introduces a novel one-dimensional convolutional neural network that utilizes clinical data to accurately detect choledocholithiasis, where gallstones obstruct the common bile duct. Swift and precise detection of this condition is critical to preventing severe complications, such as biliary colic, jaundice, and pancreatitis. This cutting-edge model was rigorously compared with other machine learning methods commonly used in similar problems, such as logistic regression, linear discriminant analysis, and a state-of-the-art random forest, using a dataset derived from endoscopic retrograde cholangiopancreatography scans performed at Olive View–University of California, Los Angeles Medical Center. The one-dimensional convolutional neural network model demonstrated exceptional performance, achieving 90.77% accuracy and 92.86% specificity, with an area under the curve of 0.9270. While the paper acknowledges potential areas for improvement, it emphasizes the effectiveness of the one-dimensional convolutional neural network architecture. The results suggest that this one-dimensional convolutional neural network approach could serve as a plausible alternative to endoscopic retrograde cholangiopancreatography, considering its disadvantages, such as the need for specialized equipment and skilled personnel and the risk of postoperative complications. The potential of the one-dimensional convolutional neural network model to significantly advance the clinical diagnosis of this gallstone-related condition is notable, offering a less invasive, potentially safer, and more accessible alternative. [ABSTRACT FROM AUTHOR]

This paper addresses issues concerning biometric authentication based on handwritten signatures. Our research aimed to check whether a handwritten signature acquired with a mobile device can effectively verify a user's identity. We present a novel online signature verification method using coordinates of points and pressure values at each point collected with a mobile device. Convolutional neural networks are used for signature verification. In this paper, three neural network models are investigated, i.e., two self-made light SigNet and SigNetExt models and the VGG-16 model commonly used in image processing. The convolutional neural networks aim to determine whether the acquired signature sample matches the class declared by the signer. Thus, the scenario of closed set verification is performed. The effectiveness of our method was tested on signatures acquired with mobile phones. We used the subset of the multimodal database, MobiBits, that was captured using a custom-made application and consists of samples acquired from 53 people of diverse ages. The experimental results on accurate data demonstrate that developed architectures of deep neural networks can be successfully used for online handwritten signature verification. We achieved an equal error rate (EER) of 0.63% for random forgeries and 6.66% for skilled forgeries. [ABSTRACT FROM AUTHOR]

Radio frequency interference (RFI) significantly hampers the target detection performance of frequency-modulated continuous-wave radar. To address the problem and maintain the target echo signal, this paper proposes a priori assumption on the interference component nature in the radar received signal, as well as a method for interference estimation and mitigation via time–frequency analysis. The solution employs Fourier synchrosqueezed transform to implement the radar's beat signal transformation from time domain to time–frequency domain, thus converting the interference mitigation to the task of time–frequency distribution image restoration. The solution proposes the use of image processing based on the dual-tree complex wavelet transform and combines it with the spatial domain-based approach, thereby establishing a dual-domain fusion interference filter for time–frequency distribution images. This paper also presents a convolutional neural network model of structurally improved UNet++, which serves as the interference estimator. The proposed solution demonstrated its capability against various forms of RFI through the simulation experiment and showed a superior interference mitigation performance over other CNN model-based approaches. [ABSTRACT FROM AUTHOR]

In order to accurately estimate the period of X-ray pulsars to improve navigation performance, this paper proposes a pulsar period estimation method based on photon energy using reverse Hilbert coding and double Convolutional Neural Networks (CNNs) discrimination. This method uses photon energy information to perform epoch folding. It converts one-dimensional contour information into two-dimensional image signals through reverse Hilbert curve and recognizes contour image features through CNN models to determine the optimal period. According to the simulation results, the period estimation accuracy of this method is 0.5350 ns, which is 65.71% higher than the χ 2 epoch folding method. The contour phase accuracy is 0.0004767, which is 41.93% higher than the χ 2 epoch folding method. At the same time, the observation time and noise interference that may affect the accuracy of period estimation are also quantitatively analyzed. In addition, in order to simulate real navigation scenarios, this paper also conducts dynamic period estimation experiments on PSR B0531+21 pulsar in a specific period of time. The method proposed in this paper has the advantages of high precision, fast calculation speed, strong anti-interference ability and accurate dynamic period estimation, which can significantly improve the navigation performance of X-ray pulsars. • The proposed period estimation method uses photon energy information for contour weighted folding. • The proposed method uses reverse Hilbert curve to convert one-dimensional contour information into two-dimensional image information. • Convolutional Neural Network models are used to optimize pulsar period estimation. [Display omitted] [ABSTRACT FROM AUTHOR]

Visual information is important in final approach and landing phases for an approaching aircraft, it presents supplementary source for navigation system, and provides backup guidance when radio navigation fails, or even supports a complete vision‐based landing. Relative position and attitude can be solved from the runway features in the image. Traditional runway detection methods have high latency and low accuracy, which is unable to satisfy the requirements for a safe landing. This paper proposes a real‐time runway detection model, efficient runway feature extractor (ERFE), based on deep convolutional neural network, generating semantic segmentation and feature lines output. In order to evaluate the model's effectiveness, a benchmark is proposed to calculate the actual error between predicted feature line and ground truth one. A novel runway dataset which is based on pictures from Microsoft Flight Simulator 2020 (FS2020), is also proposed in this paper to train and test the model. The dataset will be released at https://www.kaggle.com/datasets/relufrank/fs2020‐runway‐dataset. ERFE shows excellent performance in FS2020 dataset, it gives satisfactory results even for real runway images excluded from our dataset. [ABSTRACT FROM AUTHOR]

Convolutional Neural Networks (CNNs) are a kind of artificial neural network designed to extract features and find out patterns for tasks such as segmentation, recognizing objects, and drawing up classification. Within a CNNs architecture, pooling operations are used until the number of parameters and the computational complexity are reduced. Numerous papers have focused on investigating the impact of pooling on the performance of Convolutional Neural Networks (CNNs), leading to the development of various pooling models. Recently, a fuzzy pooling operation based on type-1 fuzzy sets was introduced to cope with the local imprecision of the feature maps. However, in fuzzy set theory, it is not always accurate to assume that the degree of non-membership of an element in a fuzzy set is simply the complement of the degree of membership. This is due to the potential existence of a hesitation degree, which implies a certain level of uncertainty. To overcome this limitation, intuitionistic fuzzy sets (IFS) were introduced to incorporate the concept of a degree of hesitation. In this paper, we introduce a novel pooling operation based on intuitionistic fuzzy sets to incorporate the degree of hesitation heretofore neglected by a fuzzy pooling operation based on classical fuzzy sets, and we investigate its performance in the context of image classification. Intuitionistic pooling is performed in four steps: bifuzzification (by the transformation of data through the use of membership and non-membership maps), first aggregation (through the transformation of the IFS into a standard fuzzy set, second aggregation (through the transformation and use of a sum operator), and the defuzzification of feature map neighborhoods by using a max operator. IFS pooling is used for the construction of an intuitionistic pooling layer that can be applied as a drop-in replacement for the current, fuzzy (type-1) and crisp, pooling layers of CNN architectures. Various experiments involving multiple datasets demonstrate that an IFS-based pooling can enhance the classification performance of a CNN. A benchmarking study reveals that this significantly outperforms even the most recent pooling models, especially in stochastic environments. [ABSTRACT FROM AUTHOR]

The paper focuses on two kinds of rotating machinery, miniature table drilling machine and automobile engine, as the research object. Traditional machine learning has the need for manual feature extraction, and is very dependent on expert diagnostic experience and expertise, but also has the disadvantages of low accuracy, low timeliness, low efficiency, etc. For the traditional rotating machinery fault diagnosis method is more based on the traditional machine learning model, this paper puts forward a one-dimensional convolutional neural network-based fault identification method. According to the characteristics of the miniature table drilling machine and the automobile engine which are not detachable, the corresponding faults are set up respectively, Vibration signals of the attitude sensor are obtained by using the signal collector, and the collected data are preprocessed, then the CNN model is built for fault identification, and the network structure is constantly optimized to obtain the optimal network model with high accuracy (up to 100 %) and robustness. The results show that the one-dimensional convolutional neural network model improves the fault recognition accuracy and reduces the cost compared with the traditional machine learning SVM model when the original signal is used as the input signal. [ABSTRACT FROM AUTHOR]

Training in Feed Forward Deep Neural Networks is a memory-intensive operation which is usually performed on GPUs with limited memory capacities. This may force data scientists to limit the depth of the models or the resolution of the input data if data does not fit in the GPU memory. The re-materialization technique, whose idea comes from the checkpointing strategies developed in the Automatic Differentiation literature, allows data scientists to limit the memory requirements related to the storage of intermediate data (activations), at the cost of an increase in the computational cost. This paper introduces a new strategy of re-materialization of activations that significantly reduces memory usage. It consists in selecting which activations are saved and which activations are deleted during the forward phase and then recomputing the deleted activations when they are needed during the backward phase. We propose an original computation model that combines two types of activation savings: either only storing the layer inputs or recording the complete history of operations that produced the outputs. This paper focuses on the fully heterogeneous case, where the computation time and the memory requirement of each layer is different. We prove that finding the optimal solution is NP-hard and that classical techniques from Automatic Differentiation literature do not apply. Moreover, the classical assumption of memory persistence of materialized activations, used to simplify the search of optimal solutions, does not hold anymore. Thus, we propose a weak memory persistence property and provide a dynamic program to compute the optimal sequence of computations. This algorithm is made available through the Rotor software, a PyTorch plug-in dealing with any network consisting of a sequence of layers, each of them having an arbitrarily complex structure. Through extensive experiments, we show that our implementation consistently outperforms existing re-materialization approaches for a large class of networks, image sizes, and batch sizes. [ABSTRACT FROM AUTHOR]

Deep learning, a crucial technique for achieving artificial intelligence (AI), has been successfully applied in many fields. The gradual application of the latest architectures of deep learning in the field of time series forecasting (TSF), such as Transformers, has shown excellent performance and results compared to traditional statistical methods. These applications are widely present in academia and in our daily lives, covering many areas including forecasting electricity consumption in power systems, meteorological rainfall, traffic flow, quantitative trading, risk control in finance, sales operations and price predictions for commercial companies, and pandemic prediction in the medical field. Deep learning-based TSF tasks stand out as one of the most valuable AI scenarios for research, playing an important role in explaining complex real-world phenomena. However, deep learning models still face challenges: they need to deal with the challenge of large-scale data in the information age, achieve longer forecasting ranges, reduce excessively high computational complexity, etc. Therefore, novel methods and more effective solutions are essential. In this paper, we review the latest developments in deep learning for TSF. We begin by introducing the recent development trends in the field of TSF and then propose a new taxonomy from the perspective of deep neural network models, comprehensively covering articles published over the past five years. We also organize commonly used experimental evaluation metrics and datasets. Finally, we point out current issues with the existing solutions and suggest promising future directions in the field of deep learning combined with TSF. This paper is the most comprehensive review related to TSF in recent years and will provide a detailed index for researchers in this field and those who are just starting out. [ABSTRACT FROM AUTHOR]

This document is an editorial for a special issue titled "Machine Learning in Computer Vision and Image Sensing: Theory and Applications." The editorial highlights the diverse applications of machine learning (ML) models in various domains such as medical imaging, signal processing, remote sensing, and human activity detection. The special issue includes 11 papers that cover topics such as image segmentation, fluvial navigation, Alzheimer's disease classification, pneumothorax detection, lung cancer malignancy prediction, amniotic fluid volume detection, COVID-19 detection, and Parkinson's disease detection. The papers showcase the progress and potential of ML models in computer vision applications and provide valuable insights for future research. [Extracted from the article]

This paper investigates a method for precise mapping of human arm movements using sEMG signals. A multi-channel approach captures the sEMG signals, which, combined with the accurately calculated joint angles from an Inertial Measurement Unit, allows for action recognition and mapping through deep learning algorithms. Firstly, signal acquisition and processing were carried out, which involved acquiring data from various movements (hand gestures, single-degree-of-freedom joint movements, and continuous joint actions) and sensor placement. Then, interference signals were filtered out through filters, and the signals were preprocessed using normalization and moving averages to obtain sEMG signals with obvious features. Additionally, this paper constructs a hybrid network model, combining Convolutional Neural Networks and Artificial Neural Networks, and employs a multi-feature fusion algorithm to enhance the accuracy of gesture recognition. Furthermore, a nonlinear fitting between sEMG signals and joint angles was established based on a backpropagation neural network, incorporating momentum term and adaptive learning rate adjustments. Finally, based on the gesture recognition and joint angle prediction model, prosthetic arm control experiments were conducted, achieving highly accurate arm movement prediction and execution. This paper not only validates the potential application of sEMG signals in the precise control of robotic arms but also lays a solid foundation for the development of more intuitive and responsive prostheses and assistive devices. [ABSTRACT FROM AUTHOR]

Due to the complex structure of most frame structure, a large amount of sensor data needs to be processed for damage diagnosis, which increases the computational cost of diagnosis models and poses a serious challenge to their fast, accurate, and efficient damage diagnosis. In order to address this issue, this paper proposes a novel lightweight damage diagnosis method of frame structure for mobile devices based on convolutional neural networks. This method first uses mean filtering to process the vibration data collected by sensors, and then innovatively combines two convolutional neural network models, ShuffleNet and GhostNet, to form a new lightweight convolutional neural network model called SGNet, thereby reducing the computational cost of the model while ensuring diagnosis accuracy. In order to test the performance of the method proposed in this article, experimental research on damage degree diagnosis and damage type diagnosis is conducted by taking the frame structure provided by Columbia University as the research object, and comparative experiments of performance are conducted with MobileNet, GhostNet, and ShuffleNet. The experimental results show that the lightweight damage diagnosis method for frame structure proposed in this article not only has high damage diagnosis accuracy, but also has fewer computational parameters, when the highest accuracy is 99.8%, the computational parameters are only 1 million. At the same time, it is superior to MobileNet, GhostNet, ShuffleNet in terms of diagnosis accuracy and computational cost, so it is an effective high-precision lightweight damage diagnosis method for frame structure. [ABSTRACT FROM AUTHOR]

The accuracy and reliability of soil moisture retrieval based on Global Positioning System (GPS) single-star Signal-to-Noise Ratio (SNR) data is low due to the influence of spatial and temporal differences of different satellites. Therefore, this paper proposes a Random Forest (RF)-based multi-satellite data fusion Global Navigation Satellite System Interferometric Reflectometry (GNSS-IR) soil moisture retrieval method, which utilizes the RF Model's Mean Decrease Impurity (MDI) algorithm to adaptively assign arc weights to fuse all available satellite data to obtain accurate retrieval results. Subsequently, the effectiveness of the proposed method was validated using GPS data from the Plate Boundary Observatory (PBO) network sites P041 and P037, as well as data collected in Lamasquere, France. A Support Vector Machine model (SVM), Radial Basis Function (RBF) neural network model, and Convolutional Neural Network model (CNN) are introduced for the comparison of accuracy. The results indicated that the proposed method had the best retrieval performance, with Root Mean Square Error (RMSE) values of 0.032, 0.028, and 0.003 cm3/cm3, Mean Absolute Error (MAE) values of 0.025, 0.022, and 0.002 cm3/cm3, and correlation coefficients (R) of 0.94, 0.95, and 0.98, respectively, at the three sites. Therefore, the proposed soil moisture retrieval model demonstrates strong robustness and generalization capabilities, providing a reference for achieving high-precision, real-time monitoring of soil moisture. [ABSTRACT FROM AUTHOR]

In this article, a deep neural network (DNN)-based underwater acoustic (UA) communication receiver is proposed. Conventional orthogonal frequency-division multiplexing (OFDM) receivers perform channel estimation using linear interpolation. However, due to the significant delay spread in multipath UA channels, the frequency response often exhibits strong non-linearity between pilot subcarriers. Since the channel delay profile is generally unknown, this non-linearity cannot be modeled precisely. A neural network (NN)-based receiver effectively tackles this challenge by learning and compensating for the non-linearity through NN training. The performance of the DNN-based UA communication receiver was tested recently in river trials in Western Australia. The results obtained from the trials prove that the DNN-based receiver performs better than the conventional least-squares (LS) estimator-based receiver. This paper suggests that UA communication using DNN receivers holds great potential for revolutionizing underwater communication systems, enabling higher data rates, improved reliability, and enhanced adaptability to changing underwater conditions. [ABSTRACT FROM AUTHOR]

Information hiding in images has gained popularity. As image steganography gains relevance, techniques for detecting hidden messages have emerged. Statistical steganalysis mechanisms detect the presence of hidden secret messages in images, rendering images a prime target for cyber-attacks. Also, studies examining image steganography techniques are limited. This paper aims to fill the existing gap in extant literature on image steganography schemes capable of resisting statistical steganalysis attacks, by providing a comprehensive systematic literature review. This will ensure image steganography researchers and data protection practitioners are updated on current trends in information security assurance mechanisms. The study sampled 125 articles from ACM Digital Library, IEEE Explore, Science Direct, and Wiley. Using PRISMA, articles were synthesized and analyzed using quantitative and qualitative methods. A comprehensive discussion on image steganography techniques in terms of their robustness against well-known universal statistical steganalysis attacks including Regular-Singular (RS) and Chi-Square (X2) are provided. Trends in publication, techniques and methods, performance evaluation metrics, and security impacts were discussed. Extensive comparisons were drawn among existing techniques to evaluate their merits and limitations. It was observed that Generative Adversarial Networks dominate image steganography techniques and have become the preferred method by scholars within the domain. Artificial intelligence-powered algorithms including Machine Learning, Deep Learning, Convolutional Neural Networks, and Genetic Algorithms are recently dominating image steganography research as they enhance security. The implication is that previously preferred traditional techniques such as LSB algorithms are receiving less attention. Future Research may consider emerging technologies like blockchain technology, artificial neural networks, and biometric and facial recognition technologies to improve the robustness and security capabilities of image steganography applications. [ABSTRACT FROM AUTHOR]

Objectives: Vegetation widely spread in the southwestern mountainous regions of China. In the remote sensing images of this area, the landslides are usually shaded by vegetation. The error rate of forested landslide detection in remote sensing images is high, which is hard to meet practical needs. Methods: To address this issue, this paper uses light detection and ranging (LiDAR)-derived digital elevation mode (DEM) and hillshade to remove the forest on the landslides. In addition, a new dataset for forested landslide detection is also constructed. On this basis, an intelligent landslide detection model base on multi-modal deep learning is proposed. The proposed model uses DEM and hillshade to identify forested landslides, which consists of three neural network models: A transformer network for automatically extracting DEM features, a transformer network for automatically extracting hillshade features, and a convolution neural network with attention mechanism for merging multi-modal remote sensing data. Results: The proposed model is compared with ResU-Net, LandsNet, HRNet and SeaFormer. Experimental results show that the proposed model achieves the highest prediction accuracy. Intersection over union and F1 are improved by 9.3% and 6.8%, respectively. Conclusions: LiDAR is able to remove the impact of forest cover, which is suitable for identifying the forested landslides in the southwest mountain areas of China. The proposed LiDAR-based landslide detection model is able to predict the position of landslides, which is useful for deciding the position of landslide monitoring devices. [ABSTRACT FROM AUTHOR]

The skin, a crucial organ, plays a protective role in the human body, emphasizing the significance of early detection of skin diseases to prevent potential progression to skin cancer. The challenge lies in diagnosing these diseases at their early stages, where visual resemblance complicates differentiation, highlighting the need for an innovative automated method for precisely identifying skin lesions in biomedical images. This paper introduces a holistic methodology that combines DenseNet, multi‐scale feature boundary module (MFBM), and feature fusion and decoding engine (FFDE) to tackle challenges in existing deep‐learning image segmentation methods. Furthermore, a convolutional neural network model is designed for the classification of segmented images. The DenseNet encoder efficiently extracts features at four resolution levels, leveraging dense connectivity to capture intricate hierarchical features. The proposed MFBM plays a crucial role in extracting boundary information, employing parallel dilated convolutions with various dilation rates for effective multi‐scale information capture. To overcome potential disadvantages related to the conversion of features during segmentation, our approach ensures the preservation of context features. The proposed FFDE method adaptively fuses features from different levels, restoring skin lesion location information while preserving local details. The evaluation of the model is conducted on the HAM10000 dataset, which consists of 10 015 dermoscopy images, yielding promising results. [ABSTRACT FROM AUTHOR]

Short-term load forecasting is a challenging research problem and has a tremendous impact on electricity generation, transmission, and distribution. A robust forecasting algorithm can help power system operators to better tackle the ever-changing electric power demand. This paper presents a novel deep neural network for short-term electric load forecasting for the St. John's campus of Memorial University of Newfoundland (MUN). The electric load data are obtained from the Memorial University of Newfoundland and combined with metrological data from St. John's. This dataset is used to formulate a multivariate time-series forecasting problem. A novel deep learning algorithm is presented, consisting of a 1D Convolutional Neural Network, which is followed by an encoder–decoder-based network with attention. The input used for this model is the electric load consumption and metrological data, while the output is the hourly prediction of the next day. The model is compared with Gated Recurrent Unit (GRU) and Long Short Term Memory (LSTM)-based Recurrent Neural Network. A CNN-based encoder–decoder model without attention is also tested. The proposed model shows a lower mean absolute error (MAE), mean squared error (MSE), mean absolute percentage error (MAPE), and higher R2 score. These evaluation metrics show an improved performance compared to GRU and LSTM-based RNNs as well as the CNN encoder–decoder model without attention. [ABSTRACT FROM AUTHOR]

In many modern machine learning (ML) models, attention mechanisms (AMs) play a crucial role in processing data and identifying significant parts of the inputs, whether these are text or images. This selective focus enables subsequent stages of the model to achieve improved classification performance. Traditionally, AMs are applied as a preprocessing substructure before a neural network, such as in encoder/decoder architectures. In this paper, we extend the application of AMs to intermediate stages of data propagation within ML models. Specifically, we propose a generalized attention mechanism (GAM), which can be integrated before each layer of a neural network for classification tasks. The proposed GAM allows for at each layer/step of the ML architecture identification of the most relevant sections of the intermediate results. Our experimental results demonstrate that incorporating the proposed GAM into various ML models consistently enhances the accuracy of these models. This improvement is achieved with only a marginal increase in the number of parameters, which does not significantly affect the training time. [ABSTRACT FROM AUTHOR]

The epidemic diseases such as COVID-19 are rapidly spreading all around the world. The diagnosis of epidemic at initial stage is of high importance to provide medical care to and recovery of infected people as well as protecting the uninfected population. In this paper, an automatic COVID-19 detection model using respiratory sound and medical image based on internet of health things (IoHT) is proposed. In this model, primarily to screen those people having suspected Coronavirus disease, the sound of coughing used to detect healthy people and those suffering from COVID-19, which finally obtained an accuracy of 94.999%. This approach not only expedites diagnosis and enhances accuracy but also facilitates swift screening in public places using simple equipment. Then, in the second step, in order to help radiologists to interpret medical images as best as possible, we use three pre-trained convolutional neural network models InceptionResNetV2, InceptionV3 and EfficientNetB4 and two data sets of chest radiology medical images, and CT Scan in a three-class classification. Utilizing transfer learning and pre-existing knowledge in these models leads to notable improvements in disease diagnosis and identification compared to traditional techniques. Finally, the best result obtained for CT-Scan images belonging to InceptionResNetV2 architecture with 99.414% accuracy and for radiology images related to InceptionV3 and EfficientNetB4 architectures with the accuracy is 96.943%. Therefore, the proposed model can help radiology specialists to confirm the initial assessments of the COVID-19 disease. [ABSTRACT FROM AUTHOR]

Protein structure prediction is one of the main research areas in the field of Bio-informatics. The importance of proteins in drug design attracts researchers for finding the accurate tertiary structure of the protein which is dependent on its secondary structure. In this paper, we focus on improving the accuracy of protein secondary structure prediction. To do so, a Multi-scale convolutional neural network with a Gated recurrent neural network (MCNN-GRNN) is proposed. The novel amino acid encoding method along with layered convolutional neural network and Gated recurrent neural network blocks helps to retrieve local and global relationships between features, which in turn effectively classify the input protein sequence into 3 and 8 states. We have evaluated our algorithm on CullPDB, CB513, PDB25, CASP10, CASP11, CASP12, CASP13, and CASP14 datasets. We have compared our algorithm with different state-of-the-art algorithms like DCNN-SS, DCRNN, MUFOLD-SS, DLBLS_SS, and CGAN-PSSP. The Q3 accuracy of the proposed algorithm is 82–87% and Q8 accuracy is 69–77% on different datasets. [ABSTRACT FROM AUTHOR]

The three Ground Reaction Force (GRF) components can be estimated using pressure insole sensors. In this paper, we compare the accuracy of estimating GRF components for both feet using six methods: three Deep Learning (DL) methods (Artificial Neural Network, Long Short-Term Memory, and Convolutional Neural Network) and three Supervised Machine Learning (SML) methods (Least Squares, Support Vector Regression, and Random Forest (RF)). Data were collected from nine subjects across six activities: normal and slow walking, static with and without carrying a load, and two Manual Material Handling activities. This study has two main contributions: first, the estimation of GRF components (Fx, Fy, and Fz) during the six activities, two of which have never been studied; second, the comparison of the accuracy of GRF component estimation between the six methods for each activity. RF provided the most accurate estimation for static situations, with mean RMSE values of RMSE_Fx = 1.65 N, RMSE_Fy = 1.35 N, and RMSE_Fz = 7.97 N for the mean absolute values measured by the force plate (reference) RMSE_Fx = 14.10 N, RMSE_Fy = 3.83 N, and RMSE_Fz = 397.45 N. In our study, we found that RF, an SML method, surpassed the experimented DL methods. [ABSTRACT FROM AUTHOR]

Deep learning has brought great development to radar emitter identification technology. In addition, specific emitter identification (SEI), as a branch of radar emitter identification, has also benefited from it. However, the complexity of most deep learning algorithms makes it difficult to adapt to the requirements of the low power consumption and high-performance processing of SEI on embedded devices, so this article proposes solutions from the aspects of software and hardware. From the software side, we design a Transformer variant network, lightweight convolutional Transformer (LW-CT) that supports parameter sharing. Then, we cascade convolutional neural networks (CNNs) and the LW-CT to construct a one-dimensional-CNN-Transformer(1D-CNN-Transformer) lightweight neural network model that can capture the long-range dependencies of radar emitter signals and extract signal spatial domain features meanwhile. In terms of hardware, we design a low-power neural network accelerator based on an FPGA to complete the real-time recognition of radar emitter signals. The accelerator not only designs high-efficiency computing engines for the network, but also devises a reconfigurable buffer called "Ping-pong CBUF" and two-level pipeline architecture for the convolution layer for alleviating the bottleneck caused by the off-chip storage access bandwidth. Experimental results show that the algorithm can achieve a high recognition performance of SEI with a low calculation overhead. In addition, the hardware acceleration platform not only perfectly meets the requirements of the radar emitter recognition system for low power consumption and high-performance processing, but also outperforms the accelerators in other papers in terms of the energy efficiency ratio of Transformer layer processing. [ABSTRACT FROM AUTHOR]

Simple Summary: Accurate identification of individual Amur tigers is vital for their conservation, as it helps us understand their population and distribution. Existing identification methods often fall short in accuracy, and our study focuses on creating a more accurate method for identifying individual Amur tigers using advanced deep learning techniques. We improved an existing neural network model called InceptionResNetV2 by adding features like dropout layers and dual-attention mechanisms to better capture the unique stripe patterns of each tiger and reduce errors during training. We tested our model on a large dataset of tiger images and found it to be highly effective, achieving an average recognition accuracy of over 95% for different body parts, with left stripes reaching the highest 99.37%. This method significantly outperforms previous models and provides a reliable tool for wildlife researchers and conservationists to monitor and protect Amur tigers. By improving the ability to track individual tigers, our research offers practical benefits for preserving this endangered species and enhancing wildlife management practices globally. Accurate and intelligent identification of rare and endangered individuals of flagship wildlife species, such as Amur tiger (Panthera tigris altaica), is crucial for understanding population structure and distribution, thereby facilitating targeted conservation measures. However, many mathematical modeling methods, including deep learning models, often yield unsatisfactory results. This paper proposes an individual recognition method for Amur tigers based on an improved InceptionResNetV2 model. Initially, the YOLOv5 model is employed to automatically detect and segment facial, left stripe, and right stripe areas from images of 107 individual Amur tigers, achieving a high average classification accuracy of 97.3%. By introducing a dropout layer and a dual-attention mechanism, we enhance the InceptionResNetV2 model to better capture the stripe features of individual tigers at various granularities and reduce overfitting during training. Experimental results demonstrate that our model outperforms other classic models, offering optimal recognition accuracy and ideal loss changes. The average recognition accuracy for different body part features is 95.36%, with left stripes achieving a peak accuracy of 99.37%. These results highlight the model's excellent recognition capabilities. Our research provides a valuable and practical approach to the individual identification of rare and endangered animals, offering significant potential for improving conservation efforts. [ABSTRACT FROM AUTHOR]

Due to the insufficient feature learning ability and the bloated network structure, the gear fault diagnosis methods based on traditional deep neural networks always suffer from poor diagnosis accuracy and low diagnosis efficiency. Therefore, a small channel convolutional neural network under the multiscale fusion attention mechanism (MSFAM‐SCCNN) is proposed in this paper. First, a small channel convolutional neural network (SCCNN) model is constructed based on the framework of the traditional AlexNet model in order to lightweight the network structure and improve the learning efficiency. Then, a novel multiscale fusion attention mechanism (MSFAM) is embedded into the SCCNN model, which utilizes multiscale striped convolutional windows to extract key features from three dimensions, including temporal, spatial, and channel‐wise, resulting in more precise feature mining. Finally, the performance of the MSFAM‐ SCCNN model is verified using the vibration data of tooth‐broken gears obtained by a self‐designed experimental bench of an ammunition supply and delivery system. [ABSTRACT FROM AUTHOR]

Speech Emotion Recognition (SER) is a challenging task, and the typical convolutional neural network (CNN) cannot well handle the speech data directly. Because CNN tends to understand local information and ignores the overall characteristics. This paper proposes a Capsule Network with Two-Way Attention MechanismTWACapsNet for short) for the SER problem. TWACapsNet accepts the spatial and spectral features as inputs, and the convolutional layer and the capsule layer are deployed to process these two types of features in two ways separately. After that, two attention mechanisms are designed to enhance the information obtained from the spatial and spectral features. Finally, the results of these two ways are combined to form the final decision. The advantage of TWACapsNet is verified by experiments on multiple SER data sets, and experimental results show that the proposed method outperforms the widely-deployed neural network models on three typical SER data sets. Furthermore, the combination of the two ways contributes to the higher and more stable performance of TWACapsNet. [ABSTRACT FROM AUTHOR]

In Computer-Controlled Optical Surfacing technology, the precision of the removal function directly affects the accuracy of computer-aided processing software predictions, which in turn influences subsequent polishing machine processing. A key parameter for constructing the removal function is the material removal rate, which is often challenging to obtain accurately. Currently, the Preston equation is widely used to describe the principles of material removal. However, as a linear equation that omits many factors, it struggles to accurately model the removal function in complex machining scenarios. Therefore, this paper proposes a hybrid neural network model combining Convolutional Neural Networks and Bidirectional Long Short-Term Memory to predict the material removal rate. The model's parameters are optimized using an improved Grey Wolf Optimization algorithm, ultimately establishing a removal function closely consistent with an actual removal function. We first tested our method on the PHM2016 Data Challenge dataset, achieving a mean squared error of 6.19 and an R2 of 0.9949, outperforming other mainstream neural network prediction models developed in recent years. Additionally, we further validated the performance of the neural network using a small grinding head polishing dataset, achieving MSE and R2 values of 1.9035 and 0.99902, respectively. Finally, we applied this method to construct the removal function on an actual small grinding head production line. Compared to the traditional Preston equation-based removal function, the predicted residual surface's PV and RMS errors were reduced from 28.24 % to 35.58 %–4.563 % and 4.86 %, respectively. These validation results demonstrate that the proposed method not only facilitates easier acquisition of the removal function model but also significantly enhances the accuracy of computer-aided processing software predictions, thereby better guiding ultra-precision machining processes. • Proposed a CNN-BiLSTM hybrid neural network to predict material removal rates. • First to construct a small grinding head removal function using a BiLSTM Predictor. • Optimized the neural network parameter sets using an improved Grey Wolf algorithm. • Achieved MSE of 6.19 and R2 of 0.9949 on the PHM2016 Data Challenge dataset. • Reduced polishing residual surface PV and RMS prediction errors to 4.563 % and 4.86 %. [ABSTRACT FROM AUTHOR]

Summary: Non‐orthogonal multiple access (NOMA) is an efficient technology for future wireless communication systems. The resource management on NOMA networks is flattering for improving energy efficiency (EE) of systems. Therefore, self‐attention convolutional neural network (SACNN) optimized with Remora Optimization Algorithm (ROA) for energy aware resource management in NOMA network (SACNN‐ROA‐EE) is proposed in this paper for solving user allocation, channel allocation, and power allocation problems. The Matching‐Coalition approach is considered to face the user allocation issue, and the SACNN is considered to face the channel allocation and power allocation problems. SACNN does not adopt any optimization methods to determine the optimal parameters in channel allocation and power allocation. Therefore, the ROA is applied to optimize the SACNN weight parameters. The proposed technique is activated in MATLAB, and its efficacy is analyzed with under performances metrics, such as minimum user rate, sum rate, energy, and spectral performance. The proposed SACNN‐ROA‐EE attains 24.35%, 27.84%, and 38.58% better sum rate and 27.45%, 43.28%, 30.56% better EE compared with existing methods, such as EE utilizing communication deep neural network optimized with power allocation optimization (PAO‐CDNN‐EE), EE under deep transfer deterministic policy gradient along deep deterministic policy gradient approach (DPPGA‐DTDPPG‐EE), and EE utilizing deep reinforcement learning with baseline algorithms (BA‐DRL‐EE), respectively. [ABSTRACT FROM AUTHOR]

Visible and near-infrared (VIS-NIR) spectral technology is fast, accurate, and non-destructive, which meets the requirements of the separation of coal and gangue. However, the performance of the classification models established by the spectra collected according to the usual single-location collection methods was unsatisfactory. Simulating the production conditions of coal gangue sorting, this paper proposed a multilocation spectral feature fusion identification method for coal and gangue to improve the identification accuracy and developed an identification system. In the multilocation spectral collection method, the spectra of the sample were collected at three locations under the probe, which obtained richer information. In the classification models built based on different feature fusion methods, the one-dimensional convolutional neural network model with feature layer fusion had the strongest classification ability, with an accuracy of 97.61%, an improvement of 8.84% over the best single-location model. The regions of interest for model decision-making were visualized using the Gradient-weighted Class Activation Mapping (Grad-CAM) method to explore the reasons why the multilocation feature fusion method was more advanced. Furthermore, a coal gangue identification system was developed using LabVIEW, which can achieve fast and accurate recognition with an accuracy of 93.15% and an expenditure time of 1.241 s. [ABSTRACT FROM AUTHOR]

Breast cancer is one of the most common causes of death in women. Early signs of breast cancer can be an abnormality depicted on breast images like breast ultrasonography. Unfortunately, ultrasound images contain a lot of noise, which greatly increases the difficulty for doctors to interpret them. In recent years, computer-aided diagnosis (CAD) has been widely used in medical images, reducing the workload of doctors and the probability of misdiagnosis. However, it still faces the following challenges in clinical practice: one is the lack of interpretability, and another is that the accuracy is not high enough. In this paper, we propose a classification model of breast ultrasound images that leverages tumor boundaries as prior knowledge and strengthens the model to guide classification. Furthermore, we employ the advantages of convolutional neural network (CNN) to extract local features and Transformer to extract global features to achieve information balance and complementarity between the two neural network models which increase the recognition performance of the model. Additionally, an explanation method is used to generate visual results, thereby improving the poor interpretability of deep learning models. Finally, we evaluate the model on the BUSI dataset and compare it with other CNN and Transformer models. Experimental results show that the proposed model obtains an accuracy of 0.9870 and an F1 score of 0.9872, achieving state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Extracting the desired information from sensor data with various internal and external effects is a significant challenge in sensor applications. Difficult‐to‐control factors such as temperature, humidity, and sample position can significantly affect the stability and reliability of sensor data. In this paper, a deep learning‐based glucose sensing method that is robust to variations in sample position is proposed. It is shown that the variations in sample position affect the sensor data measured by the designed split ring resonator‐based microwave sensor. Then, artificial neural network and 1D convolutional neural network (CNN) models are evaluated for extracting glucose concentration information from the sensor data measured at random sample positions. The concentration of the glucose solution ranged from 1% to 23% (2% increments). The 1D CNN with all frequencies (0.5–18 GHz) of the and datasets outperformed the other model, with a mean absolute error (MAE) of 0.695% and a mean squared error (MSE) of 0.876 evaluated via cross‐validation. The study demonstrated that the sensor system can be applied in real life by performing fruit Brix estimation based on transfer learning of the previous 1D CNN network, and the MAE and MSE are 0.450% and 0.305, respectively. [ABSTRACT FROM AUTHOR]

This document is an editorial that summarizes several research papers on the topic of human recognition and the interactions between different channels of recognition, such as voice and face processing. The papers explore various aspects of this topic, including voice processing in challenging listening conditions, the role of familiarity in voice and face recognition, and the functional reorganization of neural systems in blind individuals. The papers highlight the importance of familiarity factors in recognition, the role of brain asymmetries, and the early integration of voice and face processing. The findings suggest that voice and face recognition are closely linked and influenced by familiarity, and that the right temporal lobe may play a significant role in vocal processing abilities in blind individuals. [Extracted from the article]

Recent research has revealed that subtle imperceptible perturbations can deceive well-trained neural network models, leading to inaccurate outcomes. These instances, known as adversarial examples, pose significant threats to the secure application of machine learning techniques in safety-critical systems. In this paper, we delve into the study of one-pixel attacks in deep neural networks, recently reported as a kind of adversarial examples. To identify such one-pixel attacks, most existing methodologies rely on the differential evolution method, which utilizes random selection from the current population to escape local optima. However, the differential evolution technique might waste search time and overlook good solutions if the number of iterations is insufficient. Hence, in this paper, we propose a gradient ascent with momentum approach to efficiently discover good solutions for the one-pixel attack problem. As our method takes a more direct route to the goal compared to existing methods relying on blind random walks, it can effectively identify one-pixel attacks. Our experiments conducted on popular CNNs demonstrate that, in comparison with existing methodologies, our technique can detect one-pixel attacks significantly faster. [ABSTRACT FROM AUTHOR]

This paper presents a novel sound event detection (SED) system for rare events occurring in an open environment. Wavelet multiresolution analysis (MRA) is used to decompose the input audio clip of 30 seconds into five levels. Wavelet denoising is then applied on the third and fifth levels of MRA to filter out the background. Significant transitions, which may represent the onset of a rare event, are then estimated in these two levels by combining the peak-finding algorithm with the K-medoids clustering algorithm. The small portions of one-second duration, called 'chunks' are cropped from the input audio signal corresponding to the estimated locations of the significant transitions. Features from these chunks are extracted by the wavelet scattering network (WSN) and are given as input to a support vector machine (SVM) classifier, which classifies them. The proposed SED framework produces an error rate comparable to the SED systems based on convolutional neural network (CNN) architecture. Also, the proposed algorithm is computationally efficient and lightweight as compared to deep learning models, as it has no learnable parameter. It requires only a single epoch of training, which is 5, 10, 200, and 600 times lesser than the models based on CNNs and deep neural networks (DNNs), CNN with long short-term memory (LSTM) network, convolutional recurrent neural network (CRNN), and CNN respectively. The proposed model neither requires concatenation with previous frames for anomaly detection nor any additional training data creation needed for other comparative deep learning models. It needs to check almost 360 times fewer chunks for the presence of rare events than the other baseline systems used for comparison in this paper. All these characteristics make the proposed system suitable for real-time applications on resource-limited devices. [ABSTRACT FROM AUTHOR]

Deep neural networks are extensively used in text mining and Natural Language Processing is to enable computers to understand, analyze, and generate natural language data, such as text or speech, but semantic resources, such as taxonomies and ontologies, are not fully included in deep learning. In this paper, we use Deep Convolutional Neural Network (Deep CNN) to classify research papers using the Computer Science Ontology, an ontology of research areas in the field of computer science. It takes as input the abstract and keywords of a particular research paper and returns the relevant research topic. To evaluate our ontology, we used a gold standard dataset that includes research articles. To further improve text classification results, we propose to design a Deep CNN model. We then used ontology matching to reduce the classes and get better results. Experimental results show that the proposed approach outperforms the one with the highest precision, recall, and F1-score. [ABSTRACT FROM AUTHOR]

Recent technological developments have enabled computers to identify and categorize facial expressions to determine a person's emotional state in an image or a video. This process, called "Facial Expression Recognition (FER)", has become one of the most popular research areas in computer vision. In recent times, deep FER systems have primarily concentrated on addressing two significant challenges: the problem of overfitting due to limited training data availability, and the presence of expression-unrelated variations, including illumination, head pose, image resolution, and identity bias. In this paper, a comprehensive survey is provided on deep FER, encompassing algorithms and datasets that offer insights into these intrinsic problems. Initially, this paper presents a detailed timeline showcasing the evolution of methods and datasets in deep facial expression recognition (FER). This timeline illustrates the progression and development of the techniques and data resources used in FER. Then, a comprehensive review of FER methods is introduced, including the basic principles of FER (components such as preprocessing, feature extraction and classification, and methods, etc.) from the pro-deep learning era (traditional methods using handcrafted features, i.e., SVM and HOG, etc.) to the deep learning era. Moreover, a brief introduction is provided related to the benchmark datasets (there are two categories: controlled environments (lab) and uncontrolled environments (in the wild)) used to evaluate different FER methods and a comparison of different FER models. Existing deep neural networks and related training strategies designed for FER, based on static images and dynamic image sequences, are discussed. The remaining challenges and corresponding opportunities in FER and the future directions for designing robust deep FER systems are also pinpointed. [ABSTRACT FROM AUTHOR]

The March issue of the IETE Journal of Research features 80 papers covering a wide range of topics in electrical engineering and power systems. The articles provide insights into recent breakthroughs and ongoing research in areas such as communications, opto-electronics, control engineering, and power electronics. The papers discuss various innovative technologies and propose solutions to specific challenges in these fields. The research findings can be valuable for researchers and professionals conducting research in electrical engineering. [Extracted from the article]

The purpose of this paper is to investigate the utilization of artificial neural networks (ANNs) in learning models that address the nonlinear anisotropic flow and hysteresis retention behavior of deformable porous materials. Herein, the micro‐geometries of various networks of porous Bentheimer Sandstones subjected to several degrees of strain from the literature are considered. For the generation of the database required for the training, validation, and testing of the machine learning (ML) models, single‐phase and biphasic lattice Boltzmann (LB) simulations are performed. The anisotropic nature of the intrinsic permeability is investigated for the single‐phase LB simulations. Thereafter, the database contains the computed average fluid velocities versus the pressure gradients. In this database, the range of applied fluid pressure gradients includes Darcy as well as non‐Darcy flows. The generated output from the single‐phase flow simulations is implemented in a feed‐forward neural network, representing a path‐independent informed graph‐based model. Concerning the two‐phase LB simulations, the Shan‐Chen multiphase LB model is used to generate the retention curves of the cyclic drying/wetting processes in the deformed porous networks. Consequently, two different ML path‐dependent approaches, that is, 1D convolutional neural network and the recurrent neural network, are used to model the biphasic flow through the deformable porous materials. A comparison in terms of accuracy and speed of training between the two approaches is presented. Conclusively, the outcomes of the papers show the capability of the ML models in representing constitutive relations for permeability and hysteretic retention curves accurately and efficiently. [ABSTRACT FROM AUTHOR]

Accurate prediction of sea level height is critically important for the government in assessing sea level risk in coastal areas. However, due to the nonlinear, time-varying and highly uncertain characteristics of sea level change data, sea level prediction is challenging. To improve the accuracy of sea level prediction, this paper uses a new swarm intelligence algorithm named the sparrow search algorithm (SSA), which can imitate the foraging behavior and antipredation behavior of sparrows, to determine optimal solutions. To avoid the algorithm falling into a local optimal situation, this paper integrates the sine–cosine algorithm and the Cauchy variation strategy into the SSA to obtain an algorithm named the SCSSA. The SCSSA is used to optimize the parameter values of the CNN-BiLSTM (convolutional neural network combined with bidirectional long short-term memory neural network) model; finally, a combined neural network model (named SCSSA-CNN-BiLSTM) is proposed. In this paper, the time series data of seven tidal stations located in coastal China are used for experimental analysis. First, the SCSSA-CNN-BiLSTM model is compared with the CNN-BiLSTM model to predict the time series data of SHANWEI Station. With respect to the training and test sets of data, the SCSSA-CNN-BiLSTM model outperforms the other models on all the evaluation metrics. In addition, the remaining six tide station datasets and five neural network models, including the SCSSA-CNN-BiLSTM model, are used to further study the performance of the proposed prediction model. Four evaluation indices including the root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE) and coefficient of determination (R2) are adopted. For six stations, the RMSE, MAE, MAPE and R2 of SCSSA-CNN-BiLSTM model are ranged from 20.9217 ~ 27.8427 mm, 9.4770 ~ 17.8603 mm, 0.1322% ~ 0.2482% and 0.9119 ~ 0.9759, respectively. The experimental analysis results show that the SCSSA-CNN-BiLSTM model makes effective predictions at all stations, and the prediction performance is better than that of the other models. Even though the combination of SCSSA algorithm may increase the complexity of the model, indeed the proposed model is a new prediction method with good accuracy and robustness for predicting sea level change. [ABSTRACT FROM AUTHOR]

Previously, single classification models were mainly studied to classify human protein cell images, i.e., to identify a certain protein based on a set of different cells. However, a classifier can identify only one protein, in fact, a single cell usually consists of multiple proteins, and the proteins are not completely independent of each other. In this paper, we build a human protein cell classification model by multi-label learning. The logical relationship and distribution characteristics among the labels are analyzed to determine the different proteins contained in a set of different cells (i.e., containing multiple elements in the output space). In this paper, using human protein image data, we conducted comparison experiments on pre-trained Xception and InceptionResnet V2 to optimize the two models in terms of data augmentation, channel settings, and model structure. The results show that the Optimized InceptionResnet V2 model achieves high performance in the classification task. The final accuracy of the Optimized InceptionResnet V2 model we obtained reached 96.1%, which is a 2.82% improvement relative to that before the optimized model. [ABSTRACT FROM AUTHOR]