Search

The research groups in computer vision, graphics, and machine learning have dedicated a substantial amount of attention to the areas of 3D object reconstruction, augmentation, and registration. Deep learning is the predominant method used in artificial intelligence for addressing computer vision challenges. However, deep learning on three-dimensional data presents distinct obstacles and is now in its nascent phase. There have been significant advancements in deep learning specifically for three-dimensional data, offering a range of ways to address these issues. This study offers a comprehensive examination of the latest advancements in deep learning methodologies. We examine many benchmark models for the tasks of 3D object registration, augmentation, and reconstruction. We thoroughly analyse their architectures, advantages, and constraints. In summary, this report provides a comprehensive overview of recent advancements in three-dimensional deep learning and highlights unresolved research areas that will need to be addressed in the future. [ABSTRACT FROM AUTHOR]

Simple Summary: Through gesture recognition and detection of sika deer, farmers can observe the gestures of sika deer without physical contact, providing data and technical support for the intelligent and welfare-oriented breeding of sika deer. This study is based on the YOLOv8 network model. By optimizing the convolution module, incorporating the attention mechanism, and enhancing the detection head module, a new method for detecting sika deer poses was developed. The method was assessed using four behavioral datasets, which included standing, lying, eating, and attacking. The pose-recognition accuracy of sika deer significantly improved to an average of 91.6%, laying a foundation for the health assessment and information management of sika deer. As the sika deer breeding industry flourishes on a large scale, accurately assessing the health of these animals is of paramount importance. Implementing posture recognition through target detection serves as a vital method for monitoring the well-being of sika deer. This approach allows for a more nuanced understanding of their physical condition, ensuring the industry can maintain high standards of animal welfare and productivity. In order to achieve remote monitoring of sika deer without interfering with the natural behavior of the animals, and to enhance animal welfare, this paper proposes a sika deer individual posture recognition detection algorithm GFI-YOLOv8 based on YOLOv8. Firstly, this paper proposes to add the iAFF iterative attention feature fusion module to the C2f of the backbone network module, replace the original SPPF module with AIFI module, and use the attention mechanism to adjust the feature channel adaptively. This aims to enhance granularity, improve the model's recognition, and enhance understanding of sika deer behavior in complex scenes. Secondly, a novel convolutional neural network module is introduced to improve the efficiency and accuracy of feature extraction, while preserving the model's depth and diversity. In addition, a new attention mechanism module is proposed to expand the receptive field and simplify the model. Furthermore, a new pyramid network and an optimized detection head module are presented to improve the recognition and interpretation of sika deer postures in intricate environments. The experimental results demonstrate that the model achieves 91.6% accuracy in recognizing the posture of sika deer, with a 6% improvement in accuracy and a 4.6% increase in mAP50 compared to YOLOv8n. Compared to other models in the YOLO series, such as YOLOv5n, YOLOv7-tiny, YOLOv8n, YOLOv8s, YOLOv9, and YOLOv10, this model exhibits higher accuracy, and improved mAP50 and mAP50-95 values. The overall performance is commendable, meeting the requirements for accurate and rapid identification of the posture of sika deer. This model proves beneficial for the precise and real-time monitoring of sika deer posture in complex breeding environments and under all-weather conditions. [ABSTRACT FROM AUTHOR]

The identification of gas leakages is a significant factor to be taken into consideration in various industries such as coal mines, chemical industries, etc., as well as in residential applications. In order to reduce damage to the environment as well as human lives, early detection and gas type identification are necessary. The main focus of this paper is multimodal gas data that were obtained simultaneously by using multiple sensors for gas detection and a thermal imaging camera. As the reliability and sensitivity of low-cost sensors are less, they are not suitable for gas detection over long distances. In order to overcome the drawbacks of relying just on sensors to identify gases, a thermal camera capable of detecting temperature changes is also used in the collection of the current multimodal dataset The multimodal dataset comprises 6400 samples, including smoke, perfume, a combination of both, and neutral environments. In this paper, convolutional neural networks (CNNs) are trained on thermal image data, utilizing variants such as bidirectional long–short-term memory (Bi-LSTM), dense LSTM, and a fusion of both datasets to effectively classify comma separated value (CSV) data from gas sensors. The dataset can be used as a valuable source for research scholars and system developers to improvise their artificial intelligence (AI) models used for gas leakage detection. Furthermore, in order to ensure the privacy of the client's data, this paper explores the implementation of federated learning for privacy-protected gas leakage classification, demonstrating comparable accuracy to traditional deep learning approaches. [ABSTRACT FROM AUTHOR]

Advances in deep learning and computer vision techniques have made impacts in the field of remote sensing, enabling efficient data analysis for applications such as land cover classification and change detection. Convolutional neural networks (CNNs) and transformer architectures have been utilized in visual perception algorithms due to their effectiveness in analyzing local features and global context. In this paper, we propose a hybrid transformer architecture that consists of a CNN-based encoder and transformer-based decoder. We propose a feature adjustment module that refines the multiscale feature maps extracted from an EfficientNet backbone network. The adjusted feature maps are integrated into the transformer-based decoder to perform the semantic segmentation of the remote sensing images. This paper refers to the proposed encoder–decoder architecture as a semantic feature adjustment network (SFA-Net). To demonstrate the effectiveness of the SFA-Net, experiments were thoroughly conducted with four public benchmark datasets, including the UAVid, ISPRS Potsdam, ISPRS Vaihingen, and LoveDA datasets. The proposed model achieved state-of-the-art accuracy on the UAVid, ISPRS Vaihingen, and LoveDA datasets for the segmentation of the remote sensing images. On the ISPRS Potsdam dataset, our method achieved comparable accuracy to the latest model while reducing the number of trainable parameters from 113.8 M to 10.7 M. [ABSTRACT FROM AUTHOR]

Accurate and reliable PV power probabilistic-forecasting results can help grid operators and market participants better understand and cope with PV energy volatility and uncertainty and improve the efficiency of energy dispatch and operation, which plays an important role in application scenarios such as power market trading, risk management, and grid scheduling. In this paper, an innovative deep learning quantile regression ultra-short-term PV power-forecasting method is proposed. This method employs a two-branch deep learning architecture to forecast the conditional quantile of PV power; one branch is a QR-based stacked conventional convolutional neural network (QR_CNN), and the other is a QR-based temporal convolutional network (QR_TCN). The stacked CNN is used to focus on learning short-term local dependencies in PV power sequences, and the TCN is used to learn long-term temporal constraints between multi-feature data. These two branches extract different features from input data with different prior knowledge. By jointly training the two branches, the model is able to learn the probability distribution of PV power and obtain discrete conditional quantile forecasts of PV power in the ultra-short term. Then, based on these conditional quantile forecasts, a kernel density estimation method is used to estimate the PV power probability density function. The proposed method innovatively employs two ways of a priori knowledge injection: constructing a differential sequence of historical power as an input feature to provide more information about the ultrashort-term dynamics of the PV power and, at the same time, dividing it, together with all the other features, into two sets of inputs that contain different a priori features according to the demand of the forecasting task; and the dual-branching model architecture is designed to deeply match the data of the two sets of input features to the corresponding branching model computational mechanisms. The two a priori knowledge injection methods provide more effective features for the model and improve the forecasting performance and understandability of the model. The performance of the proposed model in point forecasting, interval forecasting, and probabilistic forecasting is comprehensively evaluated through the case of a real PV plant. The experimental results show that the proposed model performs well on the task of ultra-short-term PV power probabilistic forecasting and outperforms other state-of-the-art deep learning models in the field combined with QR. The proposed method in this paper can provide technical support for application scenarios such as energy scheduling, market trading, and risk management on the ultra-short-term time scale of the power system. [ABSTRACT FROM AUTHOR]

Tool condition monitoring technology is an indispensable part of intelligent manufacturing. Most current research focuses on complex signal processing techniques or advanced deep learning algorithms to improve prediction performance without fully leveraging the end-to-end advantages of deep learning. The challenge lies in transforming multi-sensor raw data into input data suitable for direct model feeding, all while minimizing data scale and preserving sufficient temporal interpretation of tool wear. However, there is no clear reference standard for this so far. In light of this, this paper innovatively explores the processing methods that transform raw data into input data for deep learning models, a process known as an input paradigm. This paper introduces three new input paradigms: the downsampling paradigm, the periodic paradigm, and the subsequence paradigm. Then an improved hybrid model that combines a convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) was employed to validate the model's performance. The subsequence paradigm demonstrated considerable superiority in prediction results based on the PHM2010 dataset, as the newly generated time series maintained the integrity of the raw data. Further investigation revealed that, with 120 subsequences and the temporal indicator being the maximum value, the model's mean absolute error (MAE) and root mean square error (RMSE) were the lowest after threefold cross-validation, outperforming several classical and contemporary methods. The methods explored in this paper provide references for designing input data for deep learning models, helping to enhance the end-to-end potential of deep learning models, and promoting the industrial deployment and practical application of tool condition monitoring systems. [ABSTRACT FROM AUTHOR]

This document discusses the advancements in deep learning technology and image sensing. It highlights the role of deep learning in improving image recognition data and sensor performance in various applications, such as autonomous driving and smartphone camera functionalities. The document presents eleven papers published in a special issue on deep learning technology and image sensing, covering topics like medical imaging, image enhancement, object detection, and innovation in image sensing technologies. The papers demonstrate innovative approaches and methodologies in diverse domains, including liver segmentation, brain tumor classification, optic cup and disc edge detection, image-to-image translation in astronomy, super-resolution imaging, and object detection systems. These studies contribute to the interdisciplinary field of deep learning-based imaging and sensing and offer valuable insights for various fields, including healthcare, astronomy, and robotics. [Extracted from the article]

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]

With the continuous advancement of the economy and technology, the number of cars continues to increase, and the traffic congestion problem on some key roads is becoming increasingly serious. This paper proposes a new vehicle information feature map (VIFM) method and a multi-branch convolutional neural network (MBCNN) model and applies it to the problem of traffic congestion detection based on camera image data. The aim of this study is to build a deep learning model with traffic images as input and congestion detection results as output. It aims to provide a new method for automatic detection of traffic congestion. The deep learning-based method in this article can effectively utilize the existing massive camera network in the transportation system without requiring too much investment in hardware. This study first uses an object detection model to identify vehicles in images. Then, a method for extracting a VIFM is proposed. Finally, a traffic congestion detection model based on MBCNN is constructed. This paper verifies the application effect of this method in the Chinese City Traffic Image Database (CCTRIB). Compared to other convolutional neural networks, other deep learning models, and baseline models, the method proposed in this paper yields superior results. The method in this article obtained an F1 score of 98.61% and an accuracy of 98.62%. Experimental results show that this method effectively solves the problem of traffic congestion detection and provides a powerful tool for traffic management. [ABSTRACT FROM AUTHOR]

The traditional method for retrieving cloud optical thickness (COT) is carried out through a Look-Up Table (LUT). Researchers must make a series of idealized assumptions and conduct extensive observations and record features in this scenario, consuming considerable resources. The emergence of deep learning effectively addresses the shortcomings of the traditional approach. In this paper, we first propose a daytime (SOZA < 70°) COT retrieval algorithm based on FY-4A AGRI. We establish and train a Convolutional Neural Network (CNN) model for COT retrieval, CM4CR, with the CALIPSO's COT product spatially and temporally synchronized as the ground truth. Then, a deep learning method extended from video prediction models is adopted to predict COT values based on the retrieval results obtained from CM4CR. The COT prediction model (CPM) consists of an encoder, a predictor, and a decoder. On this basis, we further incorporated a time embedding module to enhance the model's ability to learn from irregular time intervals in the input COT sequence. During the training phase, we employed Charbonnier Loss and Edge Loss to enhance the model's capability to represent COT details. Experiments indicate that our CM4CR outperforms existing COT retrieval methods, with predictions showing better performance across several metrics than other benchmark prediction models. Additionally, this paper also investigates the impact of different lengths of COT input sequences and the time intervals between adjacent frames of COT on prediction performance. [ABSTRACT FROM AUTHOR]

Sign language is an essential means of communication for individuals with hearing disabilities. However, there is a significant shortage of sign language interpreters in some languages, especially in Saudi Arabia. This shortage results in a large proportion of the hearing-impaired population being deprived of services, especially in public places. This paper aims to address this gap in accessibility by leveraging technology to develop systems capable of recognizing Arabic Sign Language (ArSL) using deep learning techniques. In this paper, we propose a hybrid model to capture the spatio-temporal aspects of sign language (i.e., letters and words). The hybrid model consists of a Convolutional Neural Network (CNN) classifier to extract spatial features from sign language data and a Long Short-Term Memory (LSTM) classifier to extract spatial and temporal characteristics to handle sequential data (i.e., hand movements). To demonstrate the feasibility of our proposed hybrid model, we created a dataset of 20 different words, resulting in 4000 images for ArSL: 10 static gesture words and 500 videos for 10 dynamic gesture words. Our proposed hybrid model demonstrates promising performance, with the CNN and LSTM classifiers achieving accuracy rates of 94.40% and 82.70%, respectively. These results indicate that our approach can significantly enhance communication accessibility for the hearing-impaired community in Saudi Arabia. Thus, this paper represents a major step toward promoting inclusivity and improving the quality of life for the hearing impaired. [ABSTRACT FROM AUTHOR]

Emotion recognition has become increasingly important in the field of Deep Learning (DL) and computer vision due to its broad applicability by using human–computer interaction (HCI) in areas such as psychology, healthcare, and entertainment. In this paper, we conduct a systematic review of facial and pose emotion recognition using DL and computer vision, analyzing and evaluating 77 papers from different sources under Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Our review covers several topics, including the scope and purpose of the studies, the methods employed, and the used datasets. The scope of this work is to conduct a systematic review of facial and pose emotion recognition using DL methods and computer vision. The studies were categorized based on a proposed taxonomy that describes the type of expressions used for emotion detection, the testing environment, the currently relevant DL methods, and the datasets used. The taxonomy of methods in our review includes Convolutional Neural Network (CNN), Faster Region-based Convolutional Neural Network (R-CNN), Vision Transformer (ViT), and "Other NNs", which are the most commonly used models in the analyzed studies, indicating their trendiness in the field. Hybrid and augmented models are not explicitly categorized within this taxonomy, but they are still important to the field. This review offers an understanding of state-of-the-art computer vision algorithms and datasets for emotion recognition through facial expressions and body poses, allowing researchers to understand its fundamental components and trends. [ABSTRACT FROM AUTHOR]

With the continuous development of automotive intelligence, vehicle occupant detection technology has received increasing attention. Despite various types of research in this field, a simple, reliable, and highly private detection method is lacking. This paper proposes a method for vehicle occupant detection using millimeter-wave radar. Specifically, the paper outlines the system design for vehicle occupant detection using millimeter-wave radar. By collecting the raw signals of FMCW radar and applying Range-FFT and DoA estimation algorithms, a range–azimuth heatmap was generated, visually depicting the current status of people inside the vehicle. Furthermore, utilizing the collected range–azimuth heatmap of passengers, this paper integrates the Faster R-CNN deep learning networks with radar signal processing to identify passenger information. Finally, to test the performance of the detection method proposed in this article, an experimental verification was conducted in a car and the results were compared with those of traditional machine learning algorithms. The findings indicated that the method employed in this experiment achieves higher accuracy, reaching approximately 99%. [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]

The fetal electrocardiogram (FECG) records changes in the graph of fetal cardiac action potential during conduction, reflecting the developmental status of the fetus in utero and its physiological cardiac activity. Morphological alterations in the FECG can indicate intrauterine hypoxia, fetal distress, and neonatal asphyxia early on, enhancing maternal and fetal safety through prompt clinical intervention, thereby reducing neonatal morbidity and mortality. To reconstruct FECG signals with clear morphological information, this paper proposes a novel deep learning model, CBLS-CycleGAN. The model's generator combines spatial features extracted by the CNN with temporal features extracted by the BiLSTM network, thus ensuring that the reconstructed signals possess combined features with spatial and temporal dependencies. The model's discriminator utilizes PatchGAN, employing small segments of the signal as discriminative inputs to concentrate the training process on capturing signal details. Evaluating the model using two real FECG signal databases, namely "Abdominal and Direct Fetal ECG Database" and "Fetal Electrocardiograms, Direct and Abdominal with Reference Heartbeat Annotations", resulted in a mean MSE and MAE of 0.019 and 0.006, respectively. It detects the FQRS compound wave with a sensitivity, positive predictive value, and F1 of 99.51%, 99.57%, and 99.54%, respectively. This paper's model effectively preserves the morphological information of FECG signals, capturing not only the FQRS compound wave but also the fetal P-wave, T-wave, P-R interval, and ST segment information, providing clinicians with crucial diagnostic insights and a scientific foundation for developing rational treatment protocols. [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]

With the rapid development of the modern world, it is imperative to achieve effective and efficient monitoring for territories of interest, especially for the broad ocean area. For surveillance of ship targets at sea, a common and powerful approach is to take advantage of satellite synthetic aperture radar (SAR) systems. Currently, using satellite SAR images for ship classification is a challenging issue due to complex sea situations and the imaging variances of ships. Fortunately, the emergence of advanced satellite SAR sensors has shed much light on the SAR ship automatic target recognition (ATR) task, e.g., utilizing dual-polarization (dual-pol) information to boost the performance of SAR ship classification. Therefore, in this paper we have developed a novel cross-polarimetric interaction network (CPINet) to explore the abundant polarization information of dual-pol SAR images with the help of deep learning strategies, leading to an effective solution for high-performance ship classification. First, we establish a novel multiscale deep feature extraction framework to fully mine the characteristics of dual-pol SAR images in a coarse-to-fine manner. Second, to further leverage the complementary information of dual-pol SAR images, we propose a mixed-order squeeze–excitation (MO-SE) attention mechanism, in which the first- and second-order statistics of the deep features from one single-polarized SAR image are extracted to guide the learning of another polarized one. Then, the intermediate multiscale fused and MO-SE augmented dual-polarized deep feature maps are respectively aggregated by the factorized bilinear coding (FBC) pooling method. Meanwhile, the last multiscale fused deep feature maps for each single-polarized SAR image are also individually aggregated by the FBC. Finally, four kinds of highly discriminative deep representations are obtained for loss computation and category prediction. For better network training, the gradient normalization (GradNorm) method for multitask networks is extended to adaptively balance the contribution of each loss component. Extensive experiments on the three- and five-category dual-pol SAR ship classification dataset collected from the open and free OpenSARShip database demonstrate the superiority and robustness of CPINet compared with state-of-the-art methods for the dual-polarized SAR ship classification task. [ABSTRACT FROM AUTHOR]

Digitals twins, used to represent dynamic environments, require accurate tracking of human movement to enhance their real-world application. This paper contributes to the field by systematically evaluating and comparing pre-existing tracking methods to identify strengths, weaknesses and practical applications within digital twin frameworks. The purpose of this study is to assess the efficacy of existing human movement tracking techniques for digital twins in real world environments, with the goal of improving spatial analysis and interaction within these virtual modes. We compare three approaches using indoor-mounted lidar sensors: (1) a frame-by-frame method deep learning model with convolutional neural networks (CNNs), (2) custom algorithms developed using OpenCV, and (3) the off-the-shelf lidar perception software package Percept version 1.6.3. Of these, the deep learning method performed best (F1 = 0.88), followed by Percept (F1 = 0.61), and finally the custom algorithms using OpenCV (F1 = 0.58). Each method had particular strengths and weaknesses, with OpenCV-based approaches that use frame comparison vulnerable to signal instability that is manifested as "flickering" in the dataset. Subsequent analysis of the spatial distribution of error revealed that both the custom algorithms and Percept took longer to acquire an identification, resulting in increased error near doorways. Percept software excelled in scenarios involving stationary individuals. These findings highlight the importance of selecting appropriate tracking methods for specific use. Future work will focus on model optimization, alternative data logging techniques, and innovative approaches to mitigate computational challenges, paving the way for more sophisticated and accessible spatial analysis tools. Integrating complementary sensor types and strategies, such as radar, audio levels, indoor positioning systems (IPSs), and wi-fi data, could further improve detection accuracy and validation while maintaining privacy. [ABSTRACT FROM AUTHOR]

Deep learning methods like convolution neural networks (CNNs) and transformers are successfully applied in hyperspectral image (HSI) classification due to their ability to extract local contextual features and explore global dependencies, respectively. However, CNNs struggle in modeling long-term dependencies, and transformers may miss subtle spatial-spectral features. To address these challenges, this paper proposes an innovative hybrid HSI classification method aggregating hierarchical spatial-spectral features from a CNN and long pixel dependencies from a transformer. The proposed aggregation multi-hierarchical feature network (AMHFN) is designed to capture various hierarchical features and long dependencies from HSI, improving classification accuracy and efficiency. The proposed AMHFN consists of three key modules: (a) a Local-Pixel Embedding module (LPEM) for capturing prominent spatial-spectral features; (b) a Multi-Scale Convolutional Extraction (MSCE) module to capture multi-scale local spatial-spectral features and aggregate hierarchical local features; (c) a Multi-Scale Global Extraction (MSGE) module to explore multi-scale global dependencies and integrate multi-scale hierarchical global dependencies. Rigorous experiments on three public hyperspectral image (HSI) datasets demonstrated the superior performance of the proposed AMHFN method. [ABSTRACT FROM AUTHOR]

Aiming at the problem of accurate AC series arc fault detection, this paper proposes a low voltage AC series arc fault intelligent detection model based on deep learning. According to the GB/T 31143—2014 standard, an experimental platform was established. This system comprises a lower computer (slave computer) and an upper computer (master computer). It facilitates the acquisition of experimental data and the detection of arc faults during the data acquisition process. Based on a one-dimensional Convolutional Neural Network (CNN), Residual model (Res) and RIME optimization algorithm (RIME) are introduced to optimize the CNN. The current signals collected using high-frequency current, low-frequency coupled current, and high-frequency coupled current are used to construct an arc fault feature set for training of the necessary detection model. The experimental results indicate that the RIME optimization algorithm delivers the best performance when optimizing a one-dimensional CNN detection model with an introduced Res. This model achieves a detection accuracy of 99.42% ± 0.13% and a kappa coefficient of 95.69% ± 0.96%. For collection methods, high-frequency coupled current signals are identified as the optimal choice for detecting low-voltage AC series arc faults. Regarding feature selection, random forest-based feature importance ranking proves to be the most effective method. [ABSTRACT FROM AUTHOR]

Vision-based laser penetration control has become an important research area in the field of welding quality control. Due to the complexity and large number of parameters in the monitoring model, control of the welding process based on deep learning and the reliance on long-term information for penetration identification are challenges. In this study, a penetration recognition method based on a two-stage temporal convolutional network is proposed to realize the online process control of laser welding. In this paper, a coaxial vision welding monitoring system is built. A lightweight segmentation model, based on channel pruning, is proposed to extract the key features of the molten pool and the keyhole from the clear molten pool keyhole image. Using these molten pool and keyhole features, a temporal convolutional network based on attention mechanism is established. The recognition method can effectively predict the laser welding penetration state, which depends on long-term information. In addition, the penetration identification experiment and closed-loop control experiment of unequal thickness plates are designed. The proposed method in this study has an accuracy of 98.96% and an average inference speed of 20.4 ms. The experimental results demonstrate that the proposed method exhibits significant performance in recognizing the penetration state from long sequences of welding image signals, adjusting welding power, and stabilizing welding quality. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) is the second most common movement disorder in the world. It is characterized by motor and non-motor symptoms that have a profound impact on the independence and quality of life of people affected by the disease, which increases caregivers' burdens. The use of the quantitative gait data of people with PD and deep learning (DL) approaches based on gait are emerging as increasingly promising methods to support and aid clinical decision making, with the aim of providing a quantitative and objective diagnosis, as well as an additional tool for disease monitoring. This will allow for the early detection of the disease, assessment of progression, and implementation of therapeutic interventions. In this paper, the authors provide a systematic review of emerging DL techniques recently proposed for the analysis of PD by using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The Scopus, PubMed, and Web of Science databases were searched across an interval of six years (between 2018, when the first article was published, and 2023). A total of 25 articles were included in this review, which reports studies on the movement analysis of PD patients using both wearable and non-wearable sensors. Additionally, these studies employed DL networks for classification, diagnosis, and monitoring purposes. The authors demonstrate that there is a wide employment in the field of PD of convolutional neural networks for analyzing signals from wearable sensors and pose estimation networks for motion analysis from videos. In addition, the authors discuss current difficulties and highlight future solutions for PD monitoring and disease progression. [ABSTRACT FROM AUTHOR]

In contemporary society, rich in mineral resources, efficiently and accurately identifying and classifying minerals has become a prominent issue. Recent advancements in artificial intelligence, particularly breakthroughs in deep learning, have offered new solutions for intelligent mineral recognition. This paper introduces a deep-learning-based object detection model for intelligent mineral identification, specifically employing the YOLOv8 algorithm. The model was developed with a focus on seven common minerals: biotite, quartz, chalcocite, silicon malachite, malachite, white mica, and pyrite. During the training phase, the model learned to accurately recognize and classify these minerals by analyzing and annotating a large dataset of mineral images. After 258 rounds of training, a stable model was obtained with high performance on key indicators such as Precision, Recall, mAP50, and mAP50–95, with values stable at 0.91766, 0.89827, 0.94300, and 0.91696, respectively. In the testing phase, using samples provided by the Geological and Mineral Museum at the School of Earth Sciences and Engineering, Sun Yat-sen University, the model successfully identified all test samples, with 83% of them having a confidence level exceeding 87%. Despite some potential misclassifications, the results of this study contribute valuable insights and practical experience to the development of intelligent mineral recognition technologies. [ABSTRACT FROM AUTHOR]

In this paper, I present a comprehensive pipeline integrating a Fine-Tuned Convolutional Neural Network (FT-CNN) and a Residual-UNet (RUNet) architecture for the automated analysis of MRI brain scans. The proposed system addresses the dual challenges of brain tumor classification and segmentation, which are crucial tasks in medical image analysis for precise diagnosis and treatment planning. Initially, the pipeline preprocesses the FigShare brain MRI image dataset, comprising 3064 images, by normalizing and resizing them to achieve uniformity and compatibility with the model. The FT-CNN model then classifies the preprocessed images into distinct tumor types: glioma, meningioma, and pituitary tumor. Following classification, the RUNet model performs pixel-level segmentation to delineate tumor regions within the MRI scans. The FT-CNN leverages the VGG19 architecture, pre-trained on large datasets and fine-tuned for specific tumor classification tasks. Features extracted from MRI images are used to train the FT-CNN, demonstrating robust performance in discriminating between tumor types. Subsequently, the RUNet model, inspired by the U-Net design and enhanced with residual blocks, effectively segments tumors by combining high-resolution spatial information from the encoding path with context-rich features from the bottleneck. My experimental results indicate that the integrated pipeline achieves high accuracy in both classification (96%) and segmentation tasks (98%), showcasing its potential for clinical applications in brain tumor diagnosis. For the classification task, the metrics involved are loss, accuracy, confusion matrix, and classification report, while for the segmentation task, the metrics used are loss, accuracy, Dice coefficient, intersection over union, and Jaccard distance. To further validate the generalizability and robustness of the integrated pipeline, I evaluated the model on two additional datasets. The first dataset consists of 7023 images for classification tasks, expanding to a four-class dataset. The second dataset contains approximately 3929 images for both classification and segmentation tasks, including a binary classification scenario. The model demonstrated robust performance, achieving 95% accuracy on the four-class task and high accuracy (96%) in the binary classification and segmentation tasks, with a Dice coefficient of 95%. [ABSTRACT FROM AUTHOR]

This paper presents a comparative analysis of deep learning techniques for anomaly detection and failure prediction. We explore various deep learning architectures on an IoT dataset, including recurrent neural networks (RNNs, LSTMs and GRUs), convolutional neural networks (CNNs) and transformers, to assess their effectiveness in anomaly detection and failure prediction. It was found that the hybrid transformer-GRU configuration delivers the highest accuracy, albeit at the cost of requiring the longest computational time for training. Furthermore, we employ explainability techniques to elucidate the decision-making processes of these black box models and evaluate their behaviour. By analysing the inner workings of the models, we aim at providing insights into the factors influencing failure predictions. Through comprehensive experimentation and analysis on sensor data collected from a water pump, this study contributes to the understanding of deep learning methodologies for anomaly detection and failure prediction and underscores the importance of model interpretability in critical applications such as prognostics and health management. Additionally, we specify the architecture for deploying these models in a real environment using the RAI4.0 metamodel, meant for designing, configuring and automatically deploying distributed stream-based industrial applications. Our findings will offer valuable guidance for practitioners seeking to deploy deep learning techniques effectively in predictive maintenance systems, facilitating informed decision-making and enhancing reliability and efficiency in industrial operations. [ABSTRACT FROM AUTHOR]

Recurrent neural networks (RNNs) have significantly advanced the field of machine learning (ML) by enabling the effective processing of sequential data. This paper provides a comprehensive review of RNNs and their applications, highlighting advancements in architectures, such as long short-term memory (LSTM) networks, gated recurrent units (GRUs), bidirectional LSTM (BiLSTM), echo state networks (ESNs), peephole LSTM, and stacked LSTM. The study examines the application of RNNs to different domains, including natural language processing (NLP), speech recognition, time series forecasting, autonomous vehicles, and anomaly detection. Additionally, the study discusses recent innovations, such as the integration of attention mechanisms and the development of hybrid models that combine RNNs with convolutional neural networks (CNNs) and transformer architectures. This review aims to provide ML researchers and practitioners with a comprehensive overview of the current state and future directions of RNN research. [ABSTRACT FROM AUTHOR]

Electric motors play a crucial role in self-driving vehicles. Therefore, fault diagnosis in motors is important for ensuring the safety and reliability of vehicles. In order to improve fault detection performance, this paper proposes a motor fault diagnosis method based on vibration signals. Firstly, the vibration signals of each operating state of the motor at different frequencies are measured with vibration sensors. Secondly, the characteristic of Gram image coding is used to realize the coding of time domain information, and the one-dimensional vibration signals are transformed into grayscale diagrams to highlight their features. Finally, the lightweight neural network Xception is chosen as the main tool, and the attention mechanism Convolutional Block Attention Module (CBAM) is introduced into the model to enforce the importance of the characteristic information of the motor faults and realize their accurate identification. Xception is a type of convolutional neural network; its lightweight design maintains excellent performance while significantly reducing the model's order of magnitude. Without affecting the computational complexity and accuracy of the network, the CBAM attention mechanism is added, and Gram's corner field is combined with the improved lightweight neural network. The experimental results show that this model achieves a better recognition effect and faster iteration speed compared with the traditional Convolutional Neural Network (CNN), ResNet, and Xception networks. [ABSTRACT FROM AUTHOR]

The increasing complexity of deep learning models can make it difficult to interpret and fit models beyond a purely accuracy-focused evaluation. This is where interpretable and eXplainable Artificial Intelligence (XAI) come into play to facilitate an understanding of the inner workings of models. Consequently, alternatives have emerged, such as class activation mapping (CAM) techniques aimed at identifying regions of importance for an image classification model. However, the behavior of such models can be highly dependent on the type of architecture and the different variants of convolutional neural networks. Accordingly, this paper evaluates three Convolutional Neural Network (CNN) architectures (VGG16, ResNet50, ConvNext-T) against seven CAM models (GradCAM, XGradCAM, HiResCAM, LayerCAM, GradCAM++, GradCAMElementWise, and EigenCAM), indicating that the CAM maps obtained with ConvNext models show less variability among them, i.e., they are less dependent on the selected CAM approach. This study was performed on an image dataset for the classification of coffee leaf rust and evaluated using the RemOve And Debias (ROAD) metric. [ABSTRACT FROM AUTHOR]

Potholes and other road surface damages pose significant risks to vehicles and traffic safety. The current methods of in situ visual inspection for potholes or cracks are inefficient, costly, and hazardous. Therefore, there is a pressing need to develop automated systems for assessing road surface conditions, aiming to efficiently and accurately reconstruct, recognize, and locate potholes. In recent years, various methods utilizing (a) computer vision, (b) three-dimensional (3D) point clouds, or (c) smartphone data have been employed to map road surface quality conditions. Machine learning and deep learning techniques have increasingly enhanced the performance of these methods. This review aims to provide a comprehensive overview of cutting-edge computer vision and machine learning algorithms for pothole detection. It covers topics such as sensing systems for acquiring two-dimensional (2D) and 3D road data, classical algorithms based on 2D image processing, segmentation-based algorithms using 3D point cloud modeling, machine learning, deep learning algorithms, and hybrid approaches. The review highlights that hybrid methods combining traditional image processing and advanced machine learning techniques offer the highest accuracy in pothole detection. Machine learning approaches, particularly deep learning, demonstrate superior adaptability and detection rates, while traditional 2D and 3D methods provide valuable baseline techniques. By reviewing and evaluating existing vision-based methods, this paper clarifies the current landscape of pothole detection technologies and identifies opportunities for future research and development. Additionally, insights provided by this review can inform the design and implementation of more robust and effective systems for automated road surface condition assessment, thereby contributing to enhanced roadway safety and infrastructure management. [ABSTRACT FROM AUTHOR]

Accurate and timely forecasting of traffic on local road networks is crucial for deploying effective dynamic traffic control, advanced route planning, and navigation services. This task is particularly challenging due to complex spatio-temporal dependencies arising from non-Euclidean spatial relations in road networks and non-linear temporal dynamics influenced by changing road conditions. This paper introduces the spatio-temporal network embedding (STNE) model, a novel deep learning framework tailored for learning and forecasting graph-structured traffic data over extended input sequences. Unlike traditional convolutional neural networks (CNNs), the model employs graph convolutional networks (GCNs) to capture the spatial characteristics of local road network topologies. Moreover, the segmentation of very long input traffic data into multiple sub-sequences, based on significant temporal properties such as closeness, periodicity, and trend, is performed. Multi-dimensional long short-term memory neural networks (MDLSTM) are utilized to flexibly access multi-dimensional context. Experimental results demonstrate that the STNE model surpasses state-of-the-art traffic forecasting benchmarks on two large-scale real-world traffic datasets. [ABSTRACT FROM AUTHOR]

Precise measurement of fiber diameter in animal and synthetic textiles is crucial for quality assessment and pricing; however, traditional methods often struggle with accuracy, particularly when fibers are densely packed or overlapping. Current computer vision techniques, while useful, have limitations in addressing these challenges. This paper introduces a novel deep-learning-based method to automatically generate distance maps of fiber micrographs, enabling more accurate fiber segmentation and diameter calculation. Our approach utilizes a modified U-Net architecture, trained on both real and simulated micrographs, to regress distance maps. This allows for the effective separation of individual fibers, even in complex scenarios. The model achieves a mean absolute error (MAE) of 0.1094 and a mean square error (MSE) of 0.0711 , demonstrating its effectiveness in accurately measuring fiber diameters. This research highlights the potential of deep learning to revolutionize fiber analysis in the textile industry, offering a more precise and automated solution for quality control and pricing. [ABSTRACT FROM AUTHOR]

Bird strikes are a substantial aviation safety issue that can result in serious harm to aircraft components and even passenger deaths. In response to this increased tendency, the implementation of new and more efficient detection and prevention technologies becomes urgent. The paper presents a novel deep learning model which is developed to detect and alleviate bird strike issues in airport conditions boosting aircraft safety. Based on an extensive database of bird images having different species and flight patterns, the research adopts sophisticated image augmentation techniques which generate multiple scenarios of aircraft operation ensuring that the model is robust under different conditions. The methodology evolved around the building of a spatiotemporal convolutional neural network which employs spatial attention structures together with dynamic temporal processing to precisely recognize flying birds. One of the most important features of this research is the architecture of its dual-focus model which consists of two components, the attention-based temporal analysis network and the convolutional neural network with spatial awareness. The model's architecture can identify specific features nested in a crowded and shifting backdrop, thereby lowering false positives and improving detection accuracy. The mechanisms of attention of this model itself enhance the model's focus by identifying vital features of bird flight patterns that are crucial. The results are that the proposed model achieves better performance in terms of accuracy and real time responses than the existing bird detection systems. The ablation study demonstrates the indispensable roles of each component, confirming their synergistic effect on improving detection performance. The research substantiates the model's applicability as a part of airport bird strike surveillance system, providing an alternative to the prevention strategy. This work benefits from the unique deep learning feature application, which leads to a large-scale and reliable tool for dealing with the bird strike problem. [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]

With the development of the power system, power users begin to use their own power supply in order to improve the power economy, but this also leads to the occurrence of the risk of self-provided power supply. The actual distribution network has few samples of power supply risk and it is difficult to identify the power supply risk by using conventional deep learning methods. In order to achieve high accuracy of self-provided power supply risk identification with small samples, this paper proposes a combination of transfer learning, convolutional block attention module (CBAM), and convolutional neural network (CNN) to identify the risk of self-provided power supply in an active distribution network. Firstly, in order to be able to further identify whether or not a risk will be caused based on completing the identification of the faulty line, we propose that it is necessary to identify whether or not the captive power supply on the faulty line is in operation. Second, in order to achieve high-precision identification and high-efficiency feature extraction, we propose to embed the CBAM into a CNN to form a CBAM-CNN model, so as to achieve high-efficiency feature extraction and high-precision risk identification. Finally, the use of transfer learning is proposed to solve the problem of low risk identification accuracy due to the small number of actual fault samples. Simulation experiments show that compared with other methods, the proposed method has the highest recognition accuracy and the best effect, and the risk recognition accuracy of active distribution network backup power is high in the case of fewer samples. [ABSTRACT FROM AUTHOR]

Due to the continuous degradation of onboard satellite instruments over time, satellite images undergo degradation, necessitating calibration for tasks reliant on satellite data. The previous relative radiometric calibration methods are mainly categorized into traditional methods and deep learning methods. The traditional methods involve complex computations for each calibration, while deep-learning-based approaches tend to oversimplify the calibration process, utilizing generic computer vision models without tailored structures for calibration tasks. In this paper, we address the unique challenges of calibration by introducing a novel approach: a multi-task convolutional neural network calibration model leveraging temporal information. This pioneering method is the first to integrate temporal dynamics into the architecture of neural network calibration models. Extensive experiments conducted on the FY3A/B/C VIRR datasets showcase the superior performance of our approach compared to the existing state-of-the-art traditional and deep learning methods. Furthermore, tests with various backbones confirm the broad applicability of our framework across different convolutional neural networks. [ABSTRACT FROM AUTHOR]

The transmission of high-frequency signals over long distances depends on the ionosphere's reflective properties, with the selection of operating frequencies being closely tied to variations in the ionosphere. The accurate prediction of ionospheric critical frequency foF2 and other parameters in low latitudes is of great significance for understanding ionospheric changes in high-frequency communications. Currently, deep learning algorithms demonstrate significant advantages in capturing characteristics of the ionosphere. In this paper, a state-of-the-art hybrid neural network is utilized in conjunction with a temporal pattern attention mechanism for predicting variations in the foF2 parameter during high- and low-solar activity years. Convolutional neural networks (CNNs) and bidirectional long short-term memory (BiLSTM), which is capable of extracting spatiotemporal features of ionospheric variations, are incorporated into a hybrid neural network. The foF2 data used for training and testing come from three observatories in Brisbane (27°53′S, 152°92′E), Darwin (12°45′S, 130°95′E) and Townsville (19°63′S, 146°85′E) in 2000, 2008, 2009 and 2014 (the peak or trough years of solar activity in solar cycles 23 and 24), using the advanced Australian Digital Ionospheric Sounder. The results show that the proposed model accurately captures the changes in ionospheric foF2 characteristics and outperforms International Reference Ionosphere 2020 (IRI-2020) and BiLSTM ionospheric prediction models. [ABSTRACT FROM AUTHOR]

Applying deep learning to high-precision ionospheric parameter prediction is a significant and growing field within the realm of space weather research. This paper proposes an improved model, Mixed Convolutional Neural Network (CNN)—Bidirectional Long Short-Term Memory (BiLSTM), for predicting the Total Electron Content (TEC) in China. This model was trained using the longest available Global Ionospheric Maps (GIM)-TEC from 1998 to 2023 in China, and underwent an interpretability analysis and accuracy evaluation. The results indicate that historical TEC maps play the most critical role, followed by Kp, ap, AE, F10.7, and time factor. The contributions of Dst and Disturbance Index (DI) to improving accuracy are relatively small but still essential. In long-term predictions, the contributions of the geomagnetic index, solar activity index, and time factor are higher. In addition, the model performs well in short-term predictions, accurately capturing the occurrence, evolution, and classification of ionospheric storms. However, as the predicted length increases, the accuracy gradually decreases, and some erroneous predictions may occur. The northeast region exhibits lower accuracy but a higher F1 score, which may be attributed to the frequency of ionospheric storm occurrences in different locations. Overall, the model effectively predicts the trends and evolution processes of ionospheric storms. [ABSTRACT FROM AUTHOR]

Hyperspectral unmixing (HU) aims to decompose mixed pixels into a set of endmembers and corresponding abundances. Deep learning-based HU methods are currently a hot research topic, but most existing unmixing methods still rely on per-pixel training or employ convolutional neural networks (CNNs), which overlook the non-local correlations of materials and spectral characteristics. Furthermore, current research mainly focuses on linear mixing models, which limits the feature extraction capability of deep encoders and further improvement in unmixing accuracy. In this paper, we propose a nonlinear unmixing network capable of extracting global spatial-spectral features. The network is designed based on an autoencoder architecture, where a dual-stream CNNs is employed in the encoder to separately extract spectral and local spatial information. The extracted features are then fused together to form a more complete representation of the input data. Subsequently, a linear projection-based multi-head self-attention mechanism is applied to capture global contextual information, allowing for comprehensive spatial information extraction while maintaining lightweight computation. To achieve better reconstruction performance, a model-free nonlinear mixing approach is adopted to enhance the model's universality, with the mixing model learned entirely from the data. Additionally, an initialization method based on endmember bundles is utilized to reduce interference from outliers and noise. Comparative results on real datasets against several state-of-the-art unmixing methods demonstrate the superior of the proposed approach. [ABSTRACT FROM AUTHOR]

Deep learning models have demonstrated potential in Condition-Based Monitoring (CBM) for rotating machinery, such as induction motors (IMs). However, their performance is significantly influenced by the size of the training dataset and the way signals are presented to the model. When trained on segmented signals over a fixed period, the model's accuracy can decline when tested on signals that differ from the training interval or are randomly sampled. Conversely, models utilizing data augmentation techniques exhibit better generalization to unseen conditions. This paper highlights the bias introduced by traditional training methods towards specific periodic waveform sampling and proposes a new method to augment phase current signals during training using a shifting window technique. This approach is considered as a practical approach for motor current augmentation and is shown to enhance classification accuracy and improved generalization when compared to existing techniques. [ABSTRACT FROM AUTHOR]

Magnetic field is one of the basic data for constructing a transformer digital twin. The finite element transient simulation takes a long time and cannot meet the real-time requirements of a digital twin. According to the nonlinear characteristics of the core and the timing characteristics of the magnetic field, this paper proposes a fast calculation method of the spatial magnetic field of the transformer, considering the nonlinear characteristics of the core. Firstly, based on the geometric and electrical parameters of the single-phase double-winding test transformer, the corresponding finite element simulation model is built. Secondly, the key parameters of the finite element model are parametrically scanned to obtain the nonlinear working condition data set of the test transformer. Finally, a deep learning network integrating a convolutional neural network (CNN) and a long short-term memory network (LSTM) is built to train the mapping relationship between winding voltage, current, and the spatial magnetic field so as to realize the rapid calculation of the transformer magnetic field. The results show that the calculation time of the deep learning model is greatly shortened compared with the finite element model, and the model calculation results are consistent with the experimental measurement results. [ABSTRACT FROM AUTHOR]

This paper presents a new edge detection process implemented in an embedded IoT device called Bee Smart Detection node to detect catastrophic apiary events. Such events include swarming, queen loss, and the detection of Colony Collapse Disorder (CCD) conditions. Two deep learning sub-processes are used for this purpose. The first uses a fuzzy multi-layered neural network of variable depths called fuzzy-stranded-NN to detect CCD conditions based on temperature and humidity measurements inside the beehive. The second utilizes a deep learning CNN model to detect swarming and queen loss cases based on sound recordings. The proposed processes have been implemented into autonomous Bee Smart Detection IoT devices that transmit their measurements and the detection results to the cloud over Wi-Fi. The BeeSD devices have been tested for easy-to-use functionality, autonomous operation, deep learning model inference accuracy, and inference execution speeds. The author presents the experimental results of the fuzzy-stranded-NN model for detecting critical conditions and deep learning CNN models for detecting swarming and queen loss. From the presented experimental results, the stranded-NN achieved accuracy results up to 95%, while the ResNet-50 model presented accuracy results up to 99% for detecting swarming or queen loss events. The ResNet-18 model is also the fastest inference speed replacement of the ResNet-50 model, achieving up to 93% accuracy results. Finally, cross-comparison of the deep learning models with machine learning ones shows that deep learning models can provide at least 3–5% better accuracy results. [ABSTRACT FROM AUTHOR]

The success of near-infrared spectroscopy (NIRS) analysis hinges on the precision and robustness of the calibration model. Shallow learning (SL) algorithms like partial least squares discriminant analysis (PLS-DA) often fall short in capturing the interrelationships between adjacent spectral variables, and the analysis results are easily affected by spectral noise, which dramatically limits the breadth and depth of applications of NIRS. Deep learning (DL) methods, with their capacity to discern intricate features from limited samples, have been progressively integrated into NIRS. In this paper, two discriminant analysis problems, including wheat kernels and Yali pears as examples, and several representative calibration models were used to research the robustness and effectiveness of the model. Additionally, this article proposed a near-infrared calibration model, which was based on the Gramian angular difference field method and coordinate attention convolutional neural networks (G-CACNNs). The research results show that, compared with SL, spectral preprocessing has a smaller impact on the analysis accuracy of consensus learning (CL) and DL, and the latter has the highest analysis accuracy in the modeling results using the original spectrum. The accuracy of G-CACNNs in two discrimination tasks was 98.48% and 99.39%. Finally, this research compared the performance of various models under noise to evaluate the robustness and noise resistance of the proposed method. [ABSTRACT FROM AUTHOR]

Falls among the elderly are a common and serious health risk that can lead to physical injuries and other complications. To promptly detect and respond to fall events, radar-based fall detection systems have gained widespread attention. In this paper, a deep learning model is proposed based on the frequency spectrum of radar signals, called the convolutional bidirectional long short-term memory (CB-LSTM) model. The introduction of the CB-LSTM model enables the fall detection system to capture both temporal sequential and spatial features simultaneously, thereby enhancing the accuracy and reliability of the detection. Extensive comparison experiments demonstrate that our model achieves an accuracy of 98.83% in detecting falls, surpassing other relevant methods currently available. In summary, this study provides effective technical support using the frequency spectrum and deep learning methods to monitor falls among the elderly through the design and experimental validation of a radar-based fall detection system, which has great potential for improving quality of life for the elderly and providing timely rescue measures. [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]

In recent years, single-source-data-based deep learning methods have made considerable strides in the field of fault diagnosis. Nevertheless, the extraction of useful information from multi-source data remains a challenge. In this paper, we propose a novel approach called the Genetic Simulated Annealing Optimization (GASA) method with a multi-source data convolutional neural network (MSCNN) for the fault diagnosis of rolling bearing. This method aims to identify bearing faults more accurately and make full use of multi-source data. Initially, the bearing vibration signal is transformed into a time–frequency graph using the continuous wavelet transform (CWT) and the signal is integrated with the motor current signal and fed into the network model. Then, a GASA-MSCNN fault diagnosis method is established to better capture the crucial information within the signal and identify various bearing health conditions. Finally, a rolling bearing dataset under different noisy environments is employed to validate the robustness of the proposed model. The experimental results demonstrate that the proposed method is capable of accurately identifying various types of rolling bearing faults, with an accuracy rate reaching up to 98% or higher even in variable noise environments. The experiments reveal that the new method significantly improves fault detection accuracy. [ABSTRACT FROM AUTHOR]

With the rapid advancement of the Internet of Things, network security has garnered increasing attention from researchers. Applying deep learning (DL) has significantly enhanced the performance of Network Intrusion Detection Systems (NIDSs). However, due to its complexity and "black box" problem, deploying DL-based NIDS models in practical scenarios poses several challenges, including model interpretability and being lightweight. Feature selection (FS) in DL models plays a crucial role in minimizing model parameters and decreasing computational overheads while enhancing NIDS performance. Hence, selecting effective features remains a pivotal concern for NIDSs. In light of this, this paper proposes an interpretable feature selection method for encrypted traffic intrusion detection based on SHAP and causality principles. This approach utilizes the results of model interpretation for feature selection to reduce feature count while ensuring model reliability. We evaluate and validate our proposed method on two public network traffic datasets, CICIDS2017 and NSL-KDD, employing both a CNN and a random forest (RF). Experimental results demonstrate superior performance achieved by our proposed method. [ABSTRACT FROM AUTHOR]

Poplar (Populus) trees play a vital role in various industries and in environmental sustainability. They are widely used for paper production, timber, and as windbreaks, in addition to their significant contributions to carbon sequestration. Given their economic and ecological importance, effective disease management is essential. Convolutional Neural Networks (CNNs), particularly adept at processing visual information, are crucial for the accurate detection and classification of plant diseases. This study introduces a novel dataset of manually collected images of diseased poplar leaves from Uzbekistan and South Korea, enhancing the geographic diversity and application of the dataset. The disease classes consist of "Parsha (Scab)", "Brown-spotting", "White-Gray spotting", and "Rust", reflecting common afflictions in these regions. This dataset will be made publicly available to support ongoing research efforts. Employing the advanced YOLOv8 model, a state-of-the-art CNN architecture, we applied a Contrast Stretching technique prior to model training in order to enhance disease detection accuracy. This approach not only improves the model's diagnostic capabilities but also offers a scalable tool for monitoring and treating poplar diseases, thereby supporting the health and sustainability of these critical resources. This dataset, to our knowledge, will be the first of its kind to be publicly available, offering a valuable resource for researchers and practitioners worldwide. [ABSTRACT FROM AUTHOR]

Plane wave imaging persists as a focal point of research due to its high frame rate and low complexity. However, in spite of these advantages, its performance can be compromised by several factors such as noise, speckle, and artifacts that affect the image quality and resolution. In this paper, we propose an attention-based complex convolutional residual U-Net to reconstruct improved in-phase/quadrature complex data from a single insonification acquisition that matches diverging wave imaging. Our approach introduces an attention mechanism to the complex domain in conjunction with complex convolution to incorporate phase information and improve the image quality matching images obtained using coherent compounding imaging. To validate the effectiveness of this method, we trained our network on a simulated phased array dataset and evaluated it using in vitro and in vivo data. The experimental results show that our approach improved the ultrasound image quality by focusing the network's attention on critical aspects of the complex data to identify and separate different regions of interest from background noise. [ABSTRACT FROM AUTHOR]

The vulnerability of modern neural networks to random noise and deliberate attacks has raised concerns about their robustness, particularly as they are increasingly utilized in safety- and security-critical applications. Although recent research efforts were made to enhance robustness through retraining with adversarial examples or employing data augmentation techniques, a comprehensive investigation into the effects of training data perturbations on model robustness remains lacking. This paper presents the first extensive empirical study investigating the influence of data perturbations during model retraining. The experimental analysis focuses on both random and adversarial robustness, following established practices in the field of robustness analysis. Various types of perturbations in different aspects of the dataset are explored, including input, label, and sampling distribution. Single-factor and multi-factor experiments are conducted to assess individual perturbations and their combinations. The findings provide insights into constructing high-quality training datasets for optimizing robustness and recommend the appropriate degree of training set perturbations that balance robustness and correctness, and contribute to understanding model robustness in deep learning and offer practical guidance for enhancing model performance through perturbed retraining, promoting the development of more reliable and trustworthy deep learning systems for safety-critical applications. [ABSTRACT FROM AUTHOR]