Search

The quality of rolling bearings is vital for the working state and rotation accuracy of the shaft. Timely and accurately acquiring bearing status and early fault diagnosis can effectively prevent losses, making it highly practical. To improve the accuracy of bearing fault diagnosis, this paper proposes a CNN-LSTM bearing fault diagnosis model optimized by hybrid particle swarm optimization (HPSO). The HPSO algorithm has a strong global optimization ability and can effectively solve nonlinear and multivariate optimization problems. It is used to optimize and match the parameters of the CNN-LSTM model and dynamically find the optimal value of the parameters. This model overcomes the problem that the parameters of the CNN-LSTM model depend on empirical settings and cannot be adjusted dynamically. This model is used for bearing fault diagnosis, and the accuracy rate of fault diagnosis classification reaches 99.2%. Compared with the traditional CNN, LSTM, and CNN-LSTM models, the accuracy rates are increased by 6.6%, 9.2%, and 5%, respectively. At the same time, comparing the models with different optimization parameters shows that the model proposed in this paper has the highest accuracy. The experimental results verified the superiority of the HPSO algorithm to optimize model parameters and the feasibility and accuracy of the HPSO-CNN-LSTM model for bearing fault diagnosis. [ABSTRACT FROM AUTHOR]

Over the past decade, deep learning (DL) has been applied in a large number of optical sensors applications. DL algorithms can improve the accuracy and reduce the noise level in optical sensors. Optical sensors are considered as a promising technology for modern intelligent sensing platforms. These sensors are widely used in process monitoring, quality prediction, pollution, defence, security, and many other applications. However, they suffer major challenges such as the large generated datasets and low processing speeds for these data, including the high cost of these sensors. These challenges can be mitigated by integrating DL systems with optical sensor technologies. This paper presents recent studies integrating DL algorithms with optical sensor applications. This paper also highlights several directions for DL algorithms that promise a considerable impact on use for optical sensor applications. Moreover, this study provides new directions for the future development of related research. [ABSTRACT FROM AUTHOR]

Due to its capacity to gather vast, high-level data about human activity from wearable or stationary sensors, human activity recognition substantially impacts people's day-to-day lives. Multiple people and things may be seen acting in the video, dispersed throughout the frame in various places. Because of this, modeling the interactions between many entities in spatial dimensions is necessary for visual reasoning in the action recognition task. The main aim of this paper is to evaluate and map the current scenario of human actions in red, green, and blue videos, based on deep learning models. A residual network (ResNet) and a vision transformer architecture (ViT) with a semi-supervised learning approach are evaluated. The DINO (self-DIstillation with NO labels) is used to enhance the potential of the ResNet and ViT. The evaluated benchmark is the human motion database (HMDB51), which tries to better capture the richness and complexity of human actions. The obtained results for video classification with the proposed ViT are promising based on performance metrics and results from the recent literature. The results obtained using a bi-dimensional ViT with long short-term memory demonstrated great performance in human action recognition when applied to the HMDB51 dataset. The mentioned architecture presented 96.7 ± 0.35% and 41.0 ± 0.27% in terms of accuracy (mean ± standard deviation values) in the train and test phases of the HMDB51 dataset, respectively. [ABSTRACT FROM AUTHOR]

Although convolutional neural networks (CNNs) have produced great achievements in various fields, many scholars are still exploring better network models, since CNNs have an inherent limitation—that is, the remote modeling ability of convolutional kernels is limited. On the contrary, the transformer has been applied by many scholars to the field of vision, and although it has a strong global modeling capability, its close-range modeling capability is mediocre. While the foreground information to be segmented in medical images is usually clustered in a small interval in the image, the distance between different categories of foreground information is uncertain. Therefore, in order to obtain a perfect medical segmentation prediction graph, the network should not only have a strong learning ability for local details, but also have a certain distance modeling ability. To solve these problems, a remote feature exploration (RFE) module is proposed in this paper. The most important feature of this module is that remote elements can be used to assist in the generation of local features. In addition, in order to better verify the feasibility of the innovation in this paper, a new multi-organ segmentation dataset (MOD) was manually created. While both the MOD and Synapse datasets label eight categories of organs, there are some images in the Synapse dataset that label only a few categories of organs. The proposed method achieved 79.77% and 75.12% DSC on the Synapse and MOD datasets, respectively. Meanwhile, the HD95 (mm) scores were 21.75 on Synapse and 7.43 on the MOD dataset. [ABSTRACT FROM AUTHOR]

This paper proposes a real-time semantics-driven infrared and visible image fusion framework (RSDFusion). A novel semantics-driven image fusion strategy is introduced in image fusion to maximize the retention of significant information of the source image in the fusion image. First, a semantically segmented image of the source image is obtained using a pre-trained semantic segmentation model. Second, masks of significant targets are obtained from the semantically segmented image, and these masks are used to separate the targets in the source and fusion images. Finally, the local semantic loss of the separation target is designed and combined with the overall structural similarity loss of the image to instruct the network to extract appropriate features to reconstruct the fusion image. Experimental results show that the RSDFusion proposed in this paper outperformed other comparative methods on both subjective and objective evaluation of public datasets and that the main target of the source image is better preserved in the fusion image. [ABSTRACT FROM AUTHOR]

This paper proposes a speech recognition method based on a domain-specific language speech network (DSL-Net) and a confidence decision network (CD-Net). The method involves automatically training a domain-specific dataset, using pre-trained model parameters for migration learning, and obtaining a domain-specific speech model. Importance sampling weights were set for the trained domain-specific speech model, which was then integrated with the trained speech model from the benchmark dataset. This integration automatically expands the lexical content of the model to accommodate the input speech based on the lexicon and language model. The adaptation attempts to address the issue of out-of-vocabulary words that are likely to arise in most realistic scenarios and utilizes external knowledge sources to extend the existing language model. By doing so, the approach enhances the adaptability of the language model in new domains or scenarios and improves the prediction accuracy of the model. For domain-specific vocabulary recognition, a deep fully convolutional neural network (DFCNN) and a candidate temporal classification (CTC)-based approach were employed to achieve effective recognition of domain-specific vocabulary. Furthermore, a confidence-based classifier was added to enhance the accuracy and robustness of the overall approach. In the experiments, the method was tested on a proprietary domain audio dataset and compared with an automatic speech recognition (ASR) system trained on a large-scale dataset. Based on experimental verification, the model achieved an accuracy improvement from 82% to 91% in the medical domain. The inclusion of domain-specific datasets resulted in a 5% to 7% enhancement over the baseline, while the introduction of model confidence further improved the baseline by 3% to 5%. These findings demonstrate the significance of incorporating domain-specific datasets and model confidence in advancing speech recognition technology. [ABSTRACT FROM AUTHOR]

Recently, convolutional neural networks (CNNs) have been widely used in image denoising, and their performance has been enhanced through residual learning. However, previous research mostly focused on optimizing the network architecture of CNNs, ignoring the limitations of the commonly used residual learning. This paper identifies two of its limitations, which are the neglect of image information and the lack of effective consideration of image self-similarity. To solve these limitations, this paper proposes a compositional denoising network (CDN), which contains two sub-paths, the image information path (IIP) and the noise estimation path (NEP), respectively. IIP is trained via an image-to-image method to extract image information. For NEP, it utilizes image self-similarity from the perspective of training. This similarity-based training method constrains NEP to output similar estimated noise distributions for different image patches with a specific kind of noise. Finally, image information and noise distribution information are comprehensively considered for image denoising. Experimental results indicate that CDN outperforms other CNN-based methods in both synthetic and real-world image denoising, achieving state-of-the-art performance. [ABSTRACT FROM AUTHOR]

This paper presents a novel deep-learning (DL)-based approach for classifying digitally modulated signals, which involves the use of capsule networks (CAPs) together with the cyclic cumulant (CC) features of the signals. These were blindly estimated using cyclostationary signal processing (CSP) and were then input into the CAP for training and classification. The classification performance and the generalization abilities of the proposed approach were tested using two distinct datasets that contained the same types of digitally modulated signals, but had distinct generation parameters. The results showed that the classification of digitally modulated signals using CAPs and CCs proposed in the paper outperformed alternative approaches for classifying digitally modulated signals that included conventional classifiers that employed CSP-based techniques, as well as alternative DL-based classifiers that used convolutional neural networks (CNNs) or residual networks (RESNETs) with the in-phase/quadrature (I/Q) data used for training and classification. [ABSTRACT FROM AUTHOR]

Rotating machinery is susceptible to harsh environmental interference, and fault signal features are challenging to extract, leading to difficulties in health status recognition. This paper proposes multi-scale hybrid features and improved convolutional neural networks (MSCCNN) health status identification methods for rotating machinery. Firstly, the rotating machinery vibration signal is decomposed into intrinsic modal components (IMF) using empirical wavelet decomposition, and multi-scale hybrid feature sets are constructed by simultaneously extracting time-domain, frequency-domain and time-frequency-domain features based on the original vibration signal and the intrinsic modal components it decomposes. Secondly, using correlation coefficients to select features sensitive to degradation, construct rotating machinery health indicators based on kernel principal component analysis and complete health state classification. Finally, a convolutional neural network model (MSCCNN) incorporating multi-scale convolution and hybrid attention mechanism modules is developed for health state identification of rotating machinery, and an improved custom loss function is applied to improve the superiority and generalization ability of the model. The bearing degradation data set of Xi'an Jiaotong University is used to verify the effectiveness of the model. The recognition accuracy of the model is 98.22%, which is 5.83%, 3.30%, 2.29%, 1.52%, and 4.31% higher than that of SVM, CNN, CNN + CBAM, MSCNN, and MSCCNN + conventional features, respectively. The PHM2012 challenge dataset is used to increase the number of samples to validate the model effectiveness, and the model recognition accuracy is 97.67%, which is 5.63%, 1.88%, 1.36%, 1.49%, and 3.69% higher compared to SVM, CNN, CNN + CBAM, MSCNN, and MSCCNN + conventional features methods, respectively. The MSCCNN model recognition accuracy is 98.67% when validated on the degraded dataset of the reducer platform. [ABSTRACT FROM AUTHOR]

Fault diagnosis is essential for high energy systems such as liquid rocket engines (LREs) due to harsh thermal and mechanical working environment. In this study, a novel method based on one-dimension Convolutional Neural Network (1D-CNN) and interpretable bidirectional Long Short-term Memory (LSTM) is proposed for intelligent fault diagnosis of LREs. 1D-CNN is responsible for extracting sequential signals collected from multi sensors. Then the interpretable LSTM is developed to model the extracted features, which contributes to modeling the temporal information. The proposed method was executed for fault diagnosis using the simulated measurement data of the LRE mathematical model. The results demonstrate the proposed algorithm outperforms other methods in terms of accuracy of fault diagnosis. Through experimental verification, the method proposed in this paper was compared with CNN, 1DCNN-SVM and CNN-LSTM in terms of LRE startup transient fault recognition performance. The model proposed in this paper had the highest fault recognition accuracy (97.39%). [ABSTRACT FROM AUTHOR]

Insulators are widely used in distribution network transmission lines and serve as critical components of the distribution network. The detection of insulator faults is essential to ensure the safe and stable operation of the distribution network. Traditional insulator detection methods often rely on manual identification, which is time-consuming, labor-intensive, and inaccurate. The use of vision sensors for object detection is an efficient and accurate detection method that requires minimal human intervention. Currently, there is a considerable amount of research on the application of vision sensors for insulator fault recognition in object detection. However, centralized object detection requires uploading data collected from various substations through vision sensors to a computing center, which may raise data privacy concerns and increase uncertainty and operational risks in the distribution network. Therefore, this paper proposes a privacy-preserving insulator detection method based on federated learning. An insulator fault detection dataset is constructed, and Convolutional Neural Network (CNN) and Multi-Layer Perceptron (MLP) models are trained within the federated learning framework for insulator fault detection. Most of the existing insulator anomaly detection methods use a centralized model training method, which has the advantage of achieving a target detection accuracy of over 90%, but the disadvantage is that the training process is prone to privacy leakage and lacks privacy protection capability. Compared with the existing insulator target detection methods, the proposed method can also achieve an insulator anomaly detection accuracy of more than 90% and provide effective privacy protection. Through experiments, we demonstrate the applicability of the federated learning framework for insulator fault detection and its ability to protect data privacy while ensuring test accuracy. [ABSTRACT FROM AUTHOR]

This paper presents a novel, autonomous learning system working in real-time for face recognition. Multiple convolutional neural networks for face recognition tasks are available; however, these networks need training data and a relatively long training process as the training speed depends on hardware characteristics. Pretrained convolutional neural networks could be useful for encoding face images (after classifier layers are removed). This system uses a pretrained ResNet50 model to encode face images from a camera and the Multinomial Naïve Bayes for autonomous training in the real-time classification of persons. Faces of several persons visible in a camera are tracked using special cognitive tracking agents who deal with machine learning models. After a face in a new position of the frame appears (in a place where there was no face in the previous frames), the system checks if it is novel or not using a novelty detection algorithm based on an SVM classifier; if it is unknown, the system automatically starts training. As a result of the conducted experiments, one can conclude that good conditions provide assurance that the system can learn the faces of a new person who appears in the frame correctly. Based on our research, we can conclude that the critical element of this system working is the novelty detection algorithm. If false novelty detection works, the system can assign two or more different identities or classify a new person into one of the existing groups. [ABSTRACT FROM AUTHOR]

With the rapid development of sensor technology, structural health monitoring data have tended to become more massive. Deep learning has advantages when handling big data, and has therefore been widely researched for diagnosing structural anomalies. However, for the diagnosis of different structural abnormalities, the model hyperparameters need to be adjusted according to different application scenarios, which is a complicated process. In this paper, a new strategy for building and optimizing 1D-CNN models is proposed that is suitable for diagnosing damage to different types of structure. This strategy involves optimizing hyperparameters with the Bayesian algorithm and improving model recognition accuracy using data fusion technology. Under the condition of sparse sensor measurement points, the entire structure is monitored, and the high-precision diagnosis of structural damage is performed. This method improves the applicability of the model to different structure detection scenarios, and avoids the shortcomings of traditional hyperparameter adjustment methods based on experience and subjectivity. In preliminary research on the simply supported beam test case, the efficient and accurate identification of parameter changes in small local elements was achieved. Furthermore, publicly available structural datasets were utilized to verify the robustness of the method, and a high identification accuracy rate of 99.85% was achieved. Compared with other methods described in the literature, this strategy shows significant advantages in terms of sensor occupancy rate, computational cost, and identification accuracy. [ABSTRACT FROM AUTHOR]

Accurately detecting falls and providing clear directions for the fall can greatly assist medical staff in promptly developing rescue plans and reducing secondary injuries during transportation to the hospital. In order to facilitate portability and protect people's privacy, this paper presents a novel method for detecting fall direction during motion using the FMCW radar. We analyze the fall direction in motion based on the correlation between different motion states. The range–time (RT) features and Doppler–time (DT) features of the person from the motion state to the fallen state were obtained by using the FMCW radar. We analyzed the different features of the two states and used a two-branch convolutional neural network (CNN) to detect the falling direction of the person. In order to improve the reliability of the model, this paper presents a pattern feature extraction (PFE) algorithm that effectively eliminates noise and outliers in RT maps and DT maps. The experimental results show that the method proposed in this paper has an identification accuracy of 96.27% for different falling directions, which can accurately identify the falling direction and improve the efficiency of rescue. [ABSTRACT FROM AUTHOR]

Object detection is an essential component of autonomous mobile robotic systems, enabling robots to understand and interact with the environment. Object detection and recognition have made significant progress using convolutional neural networks (CNNs). Widely used in autonomous mobile robot applications, CNNs can quickly identify complicated image patterns, such as objects in a logistic environment. Integration of environment perception algorithms and motion control algorithms is a topic subjected to significant research. On the one hand, this paper presents an object detector to better understand the robot environment and the newly acquired dataset. The model was optimized to run on the mobile platform already on the robot. On the other hand, the paper introduces a model-based predictive controller to guide an omnidirectional robot to a particular position in a logistic environment based on an object map obtained from a custom-trained CNN detector and LIDAR data. Object detection contributes to a safe, optimal, and efficient path for the omnidirectional mobile robot. In a practical scenario, we deploy a custom-trained and optimized CNN model to detect specific objects in the warehouse environment. Then we evaluate, through simulation, a predictive control approach based on the detected objects using CNNs. Results are obtained in object detection using a custom-trained CNN with an in-house acquired data set on a mobile platform and in the optimal control for the omnidirectional mobile robot. [ABSTRACT FROM AUTHOR]

A significant majority of the population in India makes their living through agriculture. Different illnesses that develop due to changing weather patterns and are caused by pathogenic organisms impact the yields of diverse plant species. The present article analyzed some of the existing techniques in terms of data sources, pre-processing techniques, feature extraction techniques, data augmentation techniques, models utilized for detecting and classifying diseases that affect the plant, how the quality of images was enhanced, how overfitting of the model was reduced, and accuracy. The research papers for this study were selected using various keywords from peer-reviewed publications from various databases published between 2010 and 2022. A total of 182 papers were identified and reviewed for their direct relevance to plant disease detection and classification, of which 75 papers were selected for this review after exclusion based on the title, abstract, conclusion, and full text. Researchers will find this work to be a useful resource in recognizing the potential of various existing techniques through data-driven approaches while identifying plant diseases by enhancing system performance and accuracy. [ABSTRACT FROM AUTHOR]

Petrochemical equipment tracking is a fundamental and important technology in petrochemical industry security monitoring, equipment working risk analysis, and other applications. In complex scenes where the multiple pipelines present different directions and many kinds of equipment have huge scale and shape variation in seriously mutual occlusions captured by moving cameras, the accuracy and speed of petrochemical equipment tracking would be limited because of the false and missed tracking of equipment with extreme sizes and severe occlusion, due to image quality, equipment scale, light, and other factors. In this paper, a new multiple petrochemical equipment tracking method is proposed by combining an improved Yolov7 network with attention mechanism and small target perceive layer and a hybrid matching that incorporates deep feature and traditional texture and location feature. The model incorporates the advantages of channel and spatial attention module into the improved Yolov7 detector and Siamese neural network for similarity matching. The proposed model is validated on the self-built petrochemical equipment video data set and the experimental results show it achieves a competitive performance in comparison with the related state-of-the-art tracking algorithms. [ABSTRACT FROM AUTHOR]

Due to the complexity of electromechanical equipment and the difficulties in obtaining large-scale health monitoring datasets, as well as the long-tailed distribution of data, existing methods ignore certain characteristics of health monitoring data. In order to solve these problems, this paper proposes a method for the fault diagnosis of rolling bearings in electromechanical equipment based on an improved prototypical network—the weight prototypical networks (WPorNet). The main contributions of this paper are as follows: (1) the prototypical networks, which perform well on small-sample classification tasks, were improved by calculating the different levels of influence of support sample distributions in order to achieve the prototypical calculation. The change in sample influence was calculated using the Kullback–Leibler divergence of the sample distribution. The influence change in a specific sample can be measured by assessing how much the distribution changes in the absence of that sample; and (2) The Gramian Angular Field (GAF) algorithm was used to transform one-dimensional time series into two-dimensional vibration images, which greatly improved the application effect of the 2D convolutional neural network (CNN). Through experiments on MAFAULDA and CWRU bearing datasets, it was shown that this network effectively solves the shortcomings of a small number of valid samples and a long-tail distribution in health monitoring data, it enhances the dependency between the samples and the global data, it improves the model's feature extraction ability, and it enhances the accuracy of model classification. Compared with the prototypical network, the improved network model increased the performance of the 2-way 10-shot, 2-way 20-shot, and 2-way 50-shot classification tasks by 5.23%, 5.74%, and 4.37%, respectively, and it increased the performance of the 4-way 10-shot, 4-way 20-shot, and 4-way 50-shot classification tasks by 12.02%, 10.47%, and 4.66%, respectively. Experimental results show that the improved prototypical network model has higher sample classification accuracy and stronger anti-interference ability compared with traditional small-sample classification models. [ABSTRACT FROM AUTHOR]

Extracting high-accuracy landslide areas using deep learning methods from high spatial resolution remote sensing images is a hot topic in current research. However, the existing deep learning algorithms are affected by background noise and landslide scale effects during the extraction process, leading to poor feature extraction effects. To address this issue, this paper proposes an improved mask regions-based convolutional neural network (Mask R-CNN) model to identify the landslide distribution in unmanned aerial vehicles (UAV) images. The improvement of the model mainly includes three aspects: (1) an attention mechanism of the convolutional block attention module (CBAM) is added to the backbone residual neural network (ResNet). (2) A bottom-up channel is added to the feature pyramidal network (FPN) module. (3) The region proposal network (RPN) is replaced by guided anchoring (GA-RPN). Sanming City, China was selected as the study area for the experiments. The experimental results show that the improved model has a recall of 91.4% and an accuracy of 92.6%, which is 12.9% and 10.9% higher than the original Mask R-CNN model, respectively, indicating that the improved model is more effective in landslide extraction. [ABSTRACT FROM AUTHOR]

Gearboxes are one of the most widely used speed and power transfer elements in rotating machinery. Highly accurate compound fault diagnosis of gearboxes is of great significance for the safe and reliable operation of rotating machinery systems. However, traditional compound fault diagnosis methods treat compound faults as an independent fault mode in the diagnosis process and cannot decouple them into multiple single faults. To address this problem, this paper proposes a gearbox compound fault diagnosis method. First, a multiscale convolutional neural network (MSCNN) is used as a feature learning model, which can effectively mine the compound fault information from vibration signals. Then, an improved hybrid attention module, named the channel–space attention module (CSAM), is proposed. It is embedded into the MSCNN to assign weights to multiscale features for enhancing the feature differentiation processing ability of the MSCNN. The new neural network is named CSAM-MSCNN. Finally, a multilabel classifier is used to output single or multiple labels for recognizing single or compound faults. The effectiveness of the method was verified with two gearbox datasets. The results show that the method possesses higher accuracy and stability than other models for gearbox compound fault diagnosis. [ABSTRACT FROM AUTHOR]

To solve the problem of low accuracy of pavement crack detection caused by natural environment interference, this paper designed a lightweight detection framework named PCDETR (Pavement Crack DEtection TRansformer) network, based on the fusion of the convolution features with the sequence features and proposed an efficient pavement crack detection method. Firstly, the scalable Swin-Transformer network and the residual network are used as two parallel channels of the backbone network to extract the long-sequence global features and the underlying visual local features of the pavement cracks, respectively, which are concatenated and fused to enrich the extracted feature information. Then, the encoder and decoder of the transformer detection framework are optimized; the location and category information of the pavement cracks can be obtained directly using the set prediction, which provided a low-code method to reduce the implementation complexity. The research result shows that the highest AP (Average Precision) of this method reaches 45.8% on the COCO dataset, which is significantly higher than that of DETR and its variants model Conditional DETR where the AP values are 36.9% and 42.8%, respectively. On the self-collected pavement crack dataset, the AP of the proposed method reaches 45.6%, which is 3.8% higher than that of Mask R-CNN (Region-based Convolution Neural Network) and 8.8% higher than that of Faster R-CNN. Therefore, this method is an efficient pavement crack detection algorithm. [ABSTRACT FROM AUTHOR]

Drowsiness poses a serious challenge to road safety and various in-cabin sensing technologies have been experimented with to monitor driver alertness. Cameras offer a convenient means for contactless sensing, but they may violate user privacy and require complex algorithms to accommodate user (e.g., sunglasses) and environmental (e.g., lighting conditions) constraints. This paper presents a lightweight convolution neural network that measures eye closure based on eye images captured by a wearable glass prototype, which features a hot mirror-based design that allows the camera to be installed on the glass temples. The experimental results showed that the wearable glass prototype, with the neural network in its core, was highly effective in detecting eye blinks. The blink rate derived from the glass output was highly consistent with an industrial gold standard EyeLink eye-tracker. As eye blink characteristics are sensitive measures of driver drowsiness, the glass prototype and the lightweight neural network presented in this paper would provide a computationally efficient yet viable solution for real-world applications. [ABSTRACT FROM AUTHOR]

Chronic wounds, are a worldwide health problem affecting populations and economies as a whole. With the increase in age-related diseases, obesity, and diabetes, the costs of chronic wound healing will further increase. Wound assessment should be fast and accurate in order to reduce possible complications and thus shorten the wound healing process. This paper describes an automatic wound segmentation based on a wound recording system built upon a 7-DoF robot arm with an attached RGB-D camera and high-precision 3D scanner. The developed system represents a novel combination of 2D and 3D segmentation, where the 2D segmentation is based on the MobileNetV2 classifier and the 3D component is based on the active contour model, which works on the 3D mesh to further refine the wound contour. The end output is the 3D model of only the wound surface without the surrounding healthy skin and geometric parameters in the form of perimeter, area, and volume. [ABSTRACT FROM AUTHOR]

Insect pests have always been one of the main hazards affecting crop yield and quality in traditional agriculture. An accurate and timely pest detection algorithm is essential for effective pest control; however, the existing approach suffers from a sharp performance drop when it comes to the pest detection task due to the lack of learning samples and models for small pest detection. In this paper, we explore and study the improvement methods of convolutional neural network (CNN) models on the Teddy Cup pest dataset and further propose a lightweight and effective agricultural pest detection method for small target pests, named Yolo-Pest, for the pest detection task in agriculture. Specifically, we tackle the problem of feature extraction in small sample learning with the proposed CAC3 module, which is built in a stacking residual structure based on the standard BottleNeck module. By applying a ConvNext module based on the vision transformer (ViT), the proposed method achieves effective feature extraction while keeping a lightweight network. Comparative experiments prove the effectiveness of our approach. Our proposal achieves 91.9% mAP0.5 on the Teddy Cup pest dataset, which outperforms the Yolov5s model by nearly 8% in mAP0.5. It also achieves great performance on public datasets, such as IP102, with a great reduction in the number of parameters. [ABSTRACT FROM AUTHOR]

In recent decades, many cities have become densely populated due to increased urbanization, and the transportation infrastructure system has been heavily used. The downtime of important parts of the infrastructure, such as tunnels and bridges, seriously affects the transportation system's efficiency. For this reason, a safe and reliable infrastructure network is necessary for the economic growth and functionality of cities. At the same time, the infrastructure is ageing in many countries, and continuous inspection and maintenance are necessary. Nowadays, detailed inspections of large infrastructure are almost exclusively performed by inspectors on site, which is both time-consuming and subject to human errors. However, the recent technological advancements in computer vision, artificial intelligence (AI), and robotics have opened up the possibilities of automated inspections. Today, semiautomatic systems such as drones and other mobile mapping systems are available to collect data and reconstruct 3D digital models of infrastructure. This significantly decreases the downtime of the infrastructure, but both damage detection and assessments of the structural condition are still manually performed, with a high impact on the efficiency and accuracy of the procedure. Ongoing research has shown that deep-learning methods, especially convolutional neural networks (CNNs) combined with other image processing techniques, can automatically detect cracks on concrete surfaces and measure their metrics (e.g., length and width). However, these techniques are still under investigation. Additionally, to use these data for automatically assessing the structure, a clear link between the metrics of the cracks and the structural condition must be established. This paper presents a review of the damage of tunnel concrete lining that is detectable with optical instruments. Thereafter, state-of-the-art autonomous tunnel inspection methods are presented with a focus on innovative mobile mapping systems for optimizing data collection. Finally, the paper presents an in-depth review of how the risk associated with cracks is assessed today in concrete tunnel lining. [ABSTRACT FROM AUTHOR]

Bearing defects are a common problem in rotating machines and equipment that can lead to unexpected downtime, costly repairs, and even safety hazards. Diagnosing bearing defects is crucial for preventative maintenance, and deep learning models have shown promising results in this field. On the other hand, the high complexity of these models can lead to high computational and data processing costs, making their practical implementation challenging. Recent studies have focused on optimizing these models by reducing their size and complexity, but these methods often compromise classification performance. This paper proposes a new approach that reduces the dimensionality of input data and optimizes the model structure simultaneously. A much lower input data dimension than that of existing deep learning models was achieved by downsampling the vibration sensor signals used for bearing defect diagnosis and constructing spectrograms. This paper introduces a lite convolutional neural network (CNN) model with fixed feature map dimensions that achieve high classification accuracy with low-dimensional input data. The vibration sensor signals used for bearing defect diagnosis were first downsampled to reduce the dimensionality of the input data. Next, spectrograms were constructed using the signals of the minimum interval. Experiments were conducted using the vibration sensor signals from the Case Western Reserve University (CWRU) dataset. The experimental results show that the proposed method could be highly efficient in terms of computation while maintaining outstanding classification performance. The results show that the proposed method outperformed a state-of-the-art model for bearing defect diagnosis under different conditions. This approach is not limited to the field of bearing failure diagnosis, but could be applied potentially to other fields that require the analysis of high-dimensional time series data. [ABSTRACT FROM AUTHOR]

The fault diagnosis of rolling bearings is critical for the reliability assurance of mechanical systems. The operating speeds of the rolling bearings in industrial applications are usually time-varying, and the monitoring data available are difficult to cover all the speeds. Though deep learning techniques have been well developed, the generalization capacity under different working speeds is still challenging. In this paper, a sound and vibration fusion method, named the fusion multiscale convolutional neural network (F-MSCNN), was developed with strong adaptation performance under speed-varying conditions. The F-MSCNN works directly on raw sound and vibration signals. A fusion layer and a multiscale convolutional layer were added at the beginning of the model. With comprehensive information, such as the input, multiscale features are learned for subsequent classification. An experiment on the rolling bearing test bed was carried out, and six datasets under various working speeds were constructed. The results show that the proposed F-MSCNN can achieve high accuracy with stable performance when the speeds of the testing set are the same as or different from the training set. A comparison with other methods on the same datasets also proves the superiority of F-MSCNN in speed generalization. The diagnosis accuracy improves by sound and vibration fusion and multiscale feature learning. [ABSTRACT FROM AUTHOR]

This paper proposes a joint estimation method for source number and DOA based on an improved convolutional neural network for unknown source number and undetermined DOA estimation. By analyzing the signal model, the paper designs a convolutional neural network model based on the existence of a mapping relationship between the covariance matrix and both the source number and DOA estimation. The model, which discards the pooling layer to avoid data loss and introduces the dropout method to improve generalization, takes the signal covariance matrix as input and the two branches of source number estimation and DOA estimation as outputs, and achieves the unfixed number of DOA estimation by filling in invalid values. Simulation experiments and analysis of the results show that the algorithm can effectively achieve the joint estimation of source number and DOA. Under the conditions of high SNR and a large snapshot number, both the proposed algorithm and the traditional algorithm have high estimation accuracy, while under the conditions of low SNR and a small snapshot, the algorithm is better than the traditional algorithm, and under the underdetermined conditions, where the traditional algorithm often fails, the algorithm can still achieve the joint estimation. [ABSTRACT FROM AUTHOR]

Deep Learning (DL) has provided a significant breakthrough in many areas of research and industry. The development of Convolutional Neural Networks (CNNs) has enabled the improvement of computer vision-based techniques, making the information gathered from cameras more useful. For this reason, recently, studies have been carried out on the use of image-based DL in some areas of people's daily life. In this paper, an object detection-based algorithm is proposed to modify and improve the user experience in relation to the use of cooking appliances. The algorithm can sense common kitchen objects and identify interesting situations for users. Some of these situations are the detection of utensils on lit hobs, recognition of boiling, smoking and oil in kitchenware, and determination of good cookware size adjustment, among others. In addition, the authors have achieved sensor fusion by using a cooker hob with Bluetooth connectivity, so it is possible to automatically interact with it via an external device such as a computer or a mobile phone. Our main contribution focuses on supporting people when they are cooking, controlling heaters, or alerting them with different types of alarms. To the best of our knowledge, this is the first time a YOLO algorithm has been used to control the cooktop by means of visual sensorization. Moreover, this research paper provides a comparison of the detection performance among different YOLO networks. Additionally, a dataset of more than 7500 images has been generated and multiple data augmentation techniques have been compared. The results show that YOLOv5s can successfully detect common kitchen objects with high accuracy and fast speed, and it can be employed for realistic cooking environment applications. Finally, multiple examples of the identification of interesting situations and how we act on the cooktop are presented. [ABSTRACT FROM AUTHOR]

As a fundamental but difficult topic in computer vision, 3D object segmentation has various applications in medical image analysis, autonomous vehicles, robotics, virtual reality, lithium battery image analysis, etc. In the past, 3D segmentation was performed using hand-made features and design techniques, but these techniques could not generalize to vast amounts of data or reach acceptable accuracy. Deep learning techniques have lately emerged as the preferred method for 3D segmentation jobs as a result of their extraordinary performance in 2D computer vision. Our proposed method used a CNN-based architecture called 3D UNET, which is inspired by the famous 2D UNET that has been used to segment volumetric image data. To see the internal changes of composite materials, for instance, in a lithium battery image, it is necessary to see the flow of different materials and follow the directions analyzing the inside properties. In this paper, a combination of 3D UNET and VGG19 has been used to conduct a multiclass segmentation of publicly available sandstone datasets to analyze their microstructures using image data based on four different objects in the samples of volumetric data. In our image sample, there are a total of 448 2D images, which are then aggregated as one 3D volume to examine the 3D volumetric data. The solution involves the segmentation of each object in the volume data and further analysis of each object to find its average size, area percentage, total area, etc. The open-source image processing package IMAGEJ is used for further analysis of individual particles. In this study, it was demonstrated that convolutional neural networks can be trained to recognize sandstone microstructure traits with an accuracy of 96.78% and an IOU of 91.12%. According to our knowledge, many prior works have applied 3D UNET for segmentation, but very few papers extend it further to show the details of particles in the sample. The proposed solution offers a computational insight for real-time implementation and is discovered to be superior to the current state-of-the-art methods. The result has importance for the creation of an approximately similar model for the microstructural analysis of volumetric data. [ABSTRACT FROM AUTHOR]

In-bed posture monitoring has become a prevalent area of research to help minimize the risk of pressure sore development and to increase sleep quality. This paper proposed 2D and 3D Convolutional Neural Networks, which are trained on images and videos of an open-access dataset consisting of 13 subjects' body heat maps captured from a pressure mat in 17 positions, respectively. The main goal of this paper is to detect the three main body positions: supine, left, and right. We compare the use of image and video data through 2D and 3D models in our classification. Since the dataset was imbalanced, three strategies were evaluated, i.e., down sampling, over sampling, and class weights. The best 3D model achieved accuracies of 98.90 ± 1.05% and 97.80 ± 2.14% for 5-fold and leave-one-subject-out (LOSO) cross validations, respectively. To compare the 3D model with 2D, four pre-trained 2D models were evaluated, where the best-performing model was the ResNet-18 with accuracies of 99.97 ± 0.03% for 5-fold and 99.62 ± 0.37% for LOSO. The proposed 2D and 3D models provided promising results for in-bed posture recognition and can be used in the future to further distinguish postures into more detailed subclasses. The outcome of this study can be used to remind caregivers at hospitals and long-term care facilitiesto reposition their patients if they do not reposition themselves naturally to prevent pressure ulcers. In addition, the evaluation of body postures and movements during sleep can help caregivers understand sleep quality. [ABSTRACT FROM AUTHOR]

The survival rate for sudden cardiac arrest (SCA) is low, and patients with long-term risks of SCA are not adequately alerted. Understanding SCA's characteristics will be key to developing preventive strategies. Many lives could be saved if SCA's early onset could be detected or predicted. Monitoring heart signals continuously is essential for diagnosing sporadic cardiac dysfunction. An electrocardiogram (ECG) can be used to continuously monitor heart function without having to go to the hospital. A zeolite-based dry electrode can provide safe on-skin ECG acquisition while the subject is out-of-hospital and facilitate long-term monitoring. To the ECG signal, a low-power 1 μW read-out circuit was designed and implemented in our prior work. However, having long-term ECG monitoring outside the hospital, i.e., high battery life, and low power consumption while transmission and reception of ECG signal are crucial. This paper proposes a prototype with a 10-bit resolution ADC and nRF24L01 transceivers placed 5 m apart. The system uses the 2.4 GHz worldwide ISM frequency band with GFSK modulation to wirelessly transmit digitized ECG bits at 250 kbps data rate to a physician's computer (or similar) for continuous monitoring of ECG signals; the power consumption is only 11.2 mW and 4.62 mW during transmission and reception, respectively, with a low bit error rate of ≤0.1%. Additionally, a subject-wise cross-validated, three-fold, optimized convolutional neural network (CNN) model using the Physionet-SCA dataset was implemented on NVIDIA Jetson to identify the irregular heartbeats yielding an accuracy of 89% with a run time of 5.31 s. Normal beat classification has an F1 score of 0.94 and a ROC score of 0.886. Thus, this paper integrates the ECG acquisition and processing unit with low-power wireless transmission and CNN model to detect irregular heartbeats. [ABSTRACT FROM AUTHOR]

In the biometric field, vein identification is a vital process that is constrained by the invisibility of veins as well as other unique features. Moreover, users generally do not wish to have their personal information uploaded to the cloud, so edge computing has become popular for the sake of protecting user privacy. In this paper, we propose a low-complexity and lightweight convolutional neural network (CNN) and we design intellectual property (IP) for shortening the inference time in finger vein recognition. This neural network system can operate independently in client mode. After fetching the user's finger vein image via a near-infrared (NIR) camera mounted on an embedded system, vein features can be efficiently extracted by vein curving algorithms and user identification can be completed quickly. Better image quality and higher recognition accuracy can be obtained by combining several preprocessing techniques and the modified CNN. Experimental data were collected by the finger vein image capture equipment developed in our laboratory based on the specifications of similar products currently on the market. Extensive experiments demonstrated the practicality and robustness of the proposed finger vein identification system. [ABSTRACT FROM AUTHOR]

This study aims to optimize the object identification process, especially identifying trash in the house compound. Most object identification methods cannot distinguish whether the object is a real image (3D) or a photographic image on paper (2D). This is a problem if the detected object is moved from one place to another. If the object is 2D, the robot gripper only clamps empty objects. In this study, the Sequential_Camera_LiDAR (SCL) method is proposed. This method combines a Convolutional Neural Network (CNN) with LiDAR (Light Detection and Ranging), with an accuracy of ±2 mm. After testing 11 types of trash on four CNN architectures (AlexNet, VGG16, GoogleNet, and ResNet18), the accuracy results are 80.5%, 95.6%, 98.3%, and 97.5%. This result is perfect for object identification. However, it needs to be optimized using a LiDAR sensor to determine the object in 3D or 2D. Trash will be ignored if the fast scanning process with the LiDAR sensor detects non-real (2D) trash. If Real (3D), the trash object will be scanned in detail to determine the robot gripper position in lifting the trash object. The time efficiency generated by fast scanning is between 13.33% to 59.26% depending on the object's size. The larger the object, the greater the time efficiency. In conclusion, optimization using the combination of a CNN and a LiDAR sensor can identify trash objects correctly and determine whether the object is real (3D) or not (2D), so a decision may be made to move the trash object from the detection location. [ABSTRACT FROM AUTHOR]

Various relations existing in Electroencephalogram (EEG) data are significant for EEG feature representation. Thus, studies on the graph-based method focus on extracting relevancy between EEG channels. The shortcoming of existing graph studies is that they only consider a single relationship of EEG electrodes, which results an incomprehensive representation of EEG data and relatively low accuracy of emotion recognition. In this paper, we propose a fusion graph convolutional network (FGCN) to extract various relations existing in EEG data and fuse these extracted relations to represent EEG data more comprehensively for emotion recognition. First, the FGCN mines brain connection features on topology, causality, and function. Then, we propose a local fusion strategy to fuse these three graphs to fully utilize the valuable channels with strong topological, causal, and functional relations. Finally, the graph convolutional neural network is adopted to represent EEG data for emotion recognition better. Experiments on SEED and SEED-IV demonstrate that fusing different relation graphs are effective for improving the ability in emotion recognition. Furthermore, the emotion recognition accuracy of 3-class and 4-class is higher than that of other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Convolutional neural network (CNN)-based autonomous driving object detection algorithms have excellent detection results on conventional datasets, but the detector performance can be severely degraded in low-light foggy weather environments. Existing methods have difficulty in achieving a balance between low-light image enhancement and object detection. To alleviate this problem, this paper proposes a foggy traffic environment object detection framework, IDOD-YOLOV7. This network is based on joint optimal learning of image defogging module IDOD (AOD + SAIP) and YOLOV7 detection modules. Specifically, for low-light foggy images, we propose to improve the image quality by joint optimization of image defogging (AOD) and image enhancement (SAIP), where the parameters of the SAIP module are predicted by a miniature CNN network and the AOD module performs image defogging by optimizing the atmospheric scattering model. The experimental results show that the IDOD module not only improves the image defogging quality for low-light fog images but also achieves better results in objective evaluation indexes such as PSNR and SSIM. The IDOD and YOLOV7 learn jointly in an end-to-end manner so that object detection can be performed while image enhancement is executed in a weakly supervised manner. Finally, a low-light fogged traffic image dataset (FTOD) was built by physical fogging in order to solve the domain transfer problem. The training of IDOD-YOLOV7 network by a real dataset (FTOD) improves the robustness of the model. We performed various experiments to visually and quantitatively compare our method with several state-of-the-art methods to demonstrate its superiority over the others. The IDOD-YOLOV7 algorithm not only suppresses the artifacts of low-light fog images and improves the visual effect of images but also improves the perception of autonomous driving in low-light foggy environments. [ABSTRACT FROM AUTHOR]

Imaging is one of the main tools of modern astronomy—many images are collected each day, and they must be processed. Processing such a large amount of images can be complex, time-consuming, and may require advanced tools. One of the techniques that may be employed is artificial intelligence (AI)-based image detection and classification. In this paper, the research is focused on developing such a system for the problem of the Magellan dataset, which contains 134 satellite images of Venus's surface with individual volcanoes marked with circular labels. Volcanoes are classified into four classes depending on their features. In this paper, the authors apply the You-Only-Look-Once (YOLO) algorithm, which is based on a convolutional neural network (CNN). To apply this technique, the original labels are first converted into a suitable YOLO format. Then, due to the relatively small number of images in the dataset, deterministic augmentation techniques are applied. Hyperparameters of the YOLO network are tuned to achieve the best results, which are evaluated as mean average precision (mAP@0.5) for localization accuracy and F1 score for classification accuracy. The experimental results using cross-vallidation indicate that the proposed method achieved 0.835 mAP@0.5 and 0.826 F1 scores, respectively. [ABSTRACT FROM AUTHOR]

Removing redundant features and improving classifier performance necessitates the use of meta-heuristic and deep learning (DL) algorithms in feature selection and classification problems. With the maturity of DL tools, many data-driven polarimetric synthetic aperture radar (POLSAR) representation models have been suggested, most of which are based on deep convolutional neural networks (DCNNs). In this paper, we propose a hybrid approach of a new multi-objective binary chimp optimization algorithm (MOBChOA) and DCNN for optimal feature selection. We implemented the proposed method to classify POLSAR images from San Francisco, USA. To do so, we first performed the necessary preprocessing, including speckle reduction, radiometric calibration, and feature extraction. After that, we implemented the proposed MOBChOA for optimal feature selection. Finally, we trained the fully connected DCNN to classify the pixels into specific land-cover labels. We evaluated the performance of the proposed MOBChOA-DCNN in comparison with nine competitive methods. Our experimental results with the POLSAR image datasets show that the proposed architecture had a great performance for different important optimization parameters. The proposed MOBChOA-DCNN provided fewer features (27) and the highest overall accuracy. The overall accuracy values of MOBChOA-DCNN on the training and validation datasets were 96.89% and 96.13%, respectively, which were the best results. The overall accuracy of SVM was 89.30%, which was the worst result. The results of the proposed MOBChOA on two real-world benchmark problems were also better than the results with the other methods. Furthermore, it was shown that the MOBChOA-DCNN performed better than methods from previous studies. [ABSTRACT FROM AUTHOR]

The popularity and demand for high-quality date palm fruits (Phoenix dactylifera L.) have been growing, and their quality largely depends on the type of handling, storage, and processing methods. The current methods of geometric evaluation and classification of date palm fruits are characterised by high labour intensity and are usually performed mechanically, which may cause additional damage and reduce the quality and value of the product. Therefore, non-contact methods are being sought based on image analysis, with digital solutions controlling the evaluation and classification processes. The main objective of this paper is to develop an automatic classification model for varieties of date palm fruits using a convolutional neural network (CNN) based on two fundamental criteria, i.e., colour difference and evaluation of geometric parameters of dates. A CNN with a fixed architecture was built, marked as DateNET, consisting of a system of five alternating Conv2D, MaxPooling2D, and Dropout classes. The validation accuracy of the model presented in this study depended on the selection of classification criteria. It was 85.24% for fruit colour-based classification and 87.62% for the geometric parameters only; however, it increased considerably to 93.41% when both the colour and geometry of dates were considered. [ABSTRACT FROM AUTHOR]

Automatic extraction of building contours from high-resolution images is of great significance in the fields of urban planning, demographics, and disaster assessment. Network models based on convolutional neural network (CNN) and transformer technology have been widely used for semantic segmentation of buildings from high resolution remote sensing images (HRSI). However, the fixed geometric structure and the local receptive field of the convolutional kernel are not good at global feature extraction, and the transformer technique with self-attention mechanism introduces computational redundancies and extracts local feature details poorly in the process of modeling the global contextual information. In this paper, a dual-branch fused reconstructive transformer network, DFRTNet, is proposed for efficient and accurate building extraction. In the encoder, the traditional transformer is reconfigured by designing the local and global feature extraction module (LGFE); the branch of global feature extraction (GFE) performs dynamic range attention (DRA) based on the idea of top-k attention for extracting global features; furthermore, the branch of local feature extraction (LFE) is used to obtain fine-grained features. The multilayer perceptron (MLP) is employed to efficiently fuse the local and global features. In the decoder, a simple channel attention module (CAM) is used in the up-sampling part to enhance channel dimension features. Our network achieved the best segmentation accuracy on both the WHU and Massachusetts building datasets when compared to other mainstream and state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This paper proposed a real-time fault diagnostic method for hydraulic systems using data collected from multiple sensors. The method is based on a proposed multi-sensor convolutional neural network (MS-CNN) that incorporates feature extraction, sensor selection, and fault diagnosis into an end-to-end model. Both the sensor selection process and fault diagnosis process are based on abstract fault-related features learned by a CNN deep learning model. Therefore, compared with the traditional sensor-and-feature selection method, the proposed MS-CNN can find the sensor channels containing higher-level fault-related features, which provides two advantages for diagnosis. First, the sensor selection can reduce the redundant information and improve the diagnostic performance of the model. Secondly, the reduced number of sensors simplifies the model, reducing communication burden and computational complexity. These two advantages make the MS-CNN suitable for real-time hydraulic system fault diagnosis, in which the multi-sensor feature extraction and the computation speed are both significant. The proposed MS-CNN approach is evaluated experimentally on an electric-hydraulic subsea control system test rig and an open-source dataset. The proposed method shows obvious superiority in terms of both diagnosis accuracy and computational speed when compared with traditional CNN models and other state-of-the-art multi-sensor diagnostic methods. [ABSTRACT FROM AUTHOR]

Human action recognition (HAR) is a rapidly growing field with numerous applications in various domains. HAR involves the development of algorithms and techniques to automatically identify and classify human actions from video data. Accurate recognition of human actions has significant implications in fields such as surveillance and sports analysis and in the health care domain. This paper presents a study on the design and development of an imitation detection system using an HAR algorithm based on deep learning. This study explores the use of deep learning models, such as a single-frame convolutional neural network (CNN) and pretrained VGG-16, for the accurate classification of human actions. The proposed models were evaluated using a benchmark dataset, KTH. The performance of these models was compared with that of classical classifiers, including K-Nearest Neighbors, Support Vector Machine, and Random Forest. The results showed that the VGG-16 model achieved higher accuracy than the single-frame CNN, with a 98% accuracy rate. [ABSTRACT FROM AUTHOR]

Target detection has always been a hotspot in image processing/computer vision research, and small-target detection is a frequently encountered problem in the field of target detection. With the continuous innovation of target detection technology, people always hope that the detection of small targets can reach the real-time accuracy of large-target detection. In this paper, a small-target detection model based on dual-core convolutional neural networks (CNN) is proposed, which is mainly used for the intelligent detection of books in the production line of printed books. The model is mainly composed of two modules, including a region prediction module and suspicious target search module. The region prediction module uses a CNN to predict suspicious region blocks in a large context. The suspicious target search module uses a different CNN from the above to find tiny targets in the predicted region blocks. Comparative testing of four small book target samples using this model shows that this model has better book small-target detection accuracy compared to other models. [ABSTRACT FROM AUTHOR]

This paper proposes fault diagnosis methods aimed at proactively preventing potential safety issues in robot systems, particularly human coexistence robots (HCRs) used in industrial environments. The data were collected from durability tests of the driving module for HCRs, gathering time-series vibration data until the module failed. In this study, to apply classification methods in the absence of post-failure data, the initial 50% of the collected data were designated as the normal section, and the data from the 10 h immediately preceding the failure were selected as the fault section. To generate additional data for the limited fault dataset, the Wasserstein generative adversarial networks with gradient penalty (WGAN-GP) model was utilized and residual connections were added to the generator to maintain the basic structure while preventing the loss of key features of the data. Considering that the performance of image encoding techniques varies depending on the dataset type, this study applied and compared five image encoding methods and four CNN models to facilitate the selection of the most suitable algorithm. The time-series data were converted into image data using image encoding techniques including recurrence plot, Gramian angular field, Markov transition field, spectrogram, and scalogram. These images were then applied to CNN models, including VGGNet, GoogleNet, ResNet, and DenseNet, to calculate the accuracy of fault diagnosis and compare the performance of each model. The experimental results demonstrated significant improvements in diagnostic accuracy when employing the WGAN-GP model to generate fault data, and among the image encoding techniques and convolutional neural network models, spectrogram and DenseNet exhibited superior performance, respectively. [ABSTRACT FROM AUTHOR]

In this paper, an event-driven wireless sensor node is proposed and demonstrated. The primary design objective is to devise a wireless sensor node with miniaturization, integration, and high-accuracy recognition ability. The proposed wireless sensor node integrates two vibration-threshold-triggered energy harvesters that sense and power a threshold voltage control circuit for power management, a microcontroller unit (MCU) for system control, a one-dimensional convolutional neural network (1D-CNN) environment data analysis and vibration events distribution, and a radio frequency (RF) digital baseband transmitter with IEEE 802.15.4-/.6 protocols. The dimensions of the wireless sensor node are 4 × 2 × 1 cm3. Finally, the proposed wireless sensor node was fabricated and tested. The alarming time for detecting the vibration event is less than 6 s. The measured recognition accuracy of three events (knock, shake, and heat) is over 97.5%. The experimental results showed that the proposed integrated wireless sensor node is very suitable for wireless environmental monitoring systems. [ABSTRACT FROM AUTHOR]

Recent advances in wearable systems have made inertial sensors, such as accelerometers and gyroscopes, compact, lightweight, multimodal, low-cost, and highly accurate. Wearable inertial sensor-based multimodal human activity recognition (HAR) methods utilize the rich sensing data from embedded multimodal sensors to infer human activities. However, existing HAR approaches either rely on domain knowledge or fail to address the time-frequency dependencies of multimodal sensor signals. In this paper, we propose a novel method called deep wavelet convolutional neural networks (DWCNN) designed to learn features from the time-frequency domain and improve accuracy for multimodal HAR. DWCNN introduces a framework that combines continuous wavelet transforms (CWT) with enhanced deep convolutional neural networks (DCNN) to capture the dependencies of sensing signals in the time-frequency domain, thereby enhancing the feature representation ability for multiple wearable inertial sensor-based HAR tasks. Within the CWT, we further propose an algorithm to estimate the wavelet scale parameter. This helps enhance the performance of CWT when computing the time-frequency representation of the input signals. The output of the CWT then serves as input for the proposed DCNN, which consists of residual blocks for extracting features from different modalities and attention blocks for fusing these features of multimodal signals. We conducted extensive experiments on five benchmark HAR datasets: WISDM, UCI-HAR, Heterogeneous, PAMAP2, and UniMiB SHAR. The experimental results demonstrate the superior performance of the proposed model over existing competitors. [ABSTRACT FROM AUTHOR]

The presented paper investigates the problem of endoscopic bleeding detection in endoscopic videos in the form of a binary image classification task. A set of definitions of high-level visual features of endoscopic bleeding is introduced, which incorporates domain knowledge from the field. The high-level features are coupled with respective feature descriptors, enabling automatic capture of the features using image processing methods. Each of the proposed feature descriptors outputs a feature activation map in the form of a grayscale image. Acquired feature maps can be appended in a straightforward way to the original color channels of the input image and passed to the input of a convolutional neural network during the training and inference steps. An experimental evaluation is conducted to compare the classification ROC AUC of feature-extended convolutional neural network models with baseline models using regular color image inputs. The advantage of feature-extended models is demonstrated for the Resnet and VGG convolutional neural network architectures. [ABSTRACT FROM AUTHOR]

The problem of registering point clouds in scenarios with low overlap is explored in this study. Previous methodologies depended on having a sufficient number of repeatable keypoints to extract correspondences, making them less effective in partially overlapping environments. In this paper, a novel learning network is proposed to optimize correspondences in sparse keypoints. Firstly, a multi-layer channel sampling mechanism is suggested to enhance the information in point clouds, and keypoints were filtered and fused at multi-layer resolutions to form patches through feature weight filtering. Moreover, a template matching module is devised, comprising a self-attention mapping convolutional neural network and a cross-attention network. This module aims to match contextual features and refine the correspondence in overlapping areas of patches, ultimately enhancing correspondence accuracy. Experimental results demonstrate the robustness of our model across various datasets, including ModelNet40, 3DMatch, 3DLoMatch, and KITTI. Notably, our method excels in low-overlap scenarios, showcasing superior performance. [ABSTRACT FROM AUTHOR]

With the recent rise in violent crime, the real-time situation analysis capabilities of the prevalent closed-circuit television have been employed for the deterrence and resolution of criminal activities. Anomaly detection can identify abnormal instances such as violence within the patterns of a specified dataset; however, it faces challenges in that the dataset for abnormal situations is smaller than that for normal situations. Herein, using datasets such as UBI-Fights, RWF-2000, and UCSD Ped1 and Ped2, anomaly detection was approached as a binary classification problem. Frames extracted from each video with annotation were reconstructed into a limited number of images of 3 × 3 , 4 × 3 , 4 × 4 , 5 × 3 sizes using the method proposed in this paper, forming an input data structure similar to a light field and patch of vision transformer. The model was constructed by applying a convolutional block attention module that included channel and spatial attention modules to a residual neural network with depths of 10, 18, 34, and 50 in the form of a three-dimensional convolution. The proposed model performed better than existing models in detecting abnormal behavior such as violent acts in videos. For instance, with the undersampled UBI-Fights dataset, our network achieved an accuracy of 0.9933, a loss value of 0.0010, an area under the curve of 0.9973, and an equal error rate of 0.0027. These results may contribute significantly to solve real-world issues such as the detection of violent behavior in artificial intelligence systems using computer vision and real-time video monitoring. [ABSTRACT FROM AUTHOR]