Search

This document is a summary of a special issue of the journal Sensors, titled "Emerging AI+X-Based Sensor and Networking Technologies including Selected Papers from ICGHIT 2022–2023." The special issue features selected papers from the 10th and 11th International Conferences on Green and Human Information Technology (ICGHITs), which were held in Korea and Thailand. The conferences focused on the theme of "Emerging Artificial Intelligent (AI)+X technology" and "Hyper Automation + Human AI" respectively. The selected papers cover various topics such as network security, routing protocols, signal detection, and clustering mechanisms, all incorporating AI-based methods. The issue also includes papers on topics like secure authentication, distance estimation in RFID systems, energy optimization in smart homes, blockchain technology, and radar signal detection. The authors emphasize the importance of both technology and humanity in advancing green and information technologies. [Extracted from the article]

The Internet of Things (IoT), projected to exceed 30 billion active device connections globally by 2025, presents an expansive attack surface. The frequent collection and dissemination of confidential data on these devices exposes them to significant security risks, including user information theft and denial-of-service attacks. This paper introduces a smart, network-based Intrusion Detection System (IDS) designed to protect IoT networks from distributed denial-of-service attacks. Our methodology involves generating synthetic images from flow-level traffic data of the Bot-IoT and the LATAM-DDoS-IoT datasets and conducting experiments within both supervised and self-supervised learning paradigms. Self-supervised learning is identified in the state of the art as a promising solution to replace the need for massive amounts of manually labeled data, as well as providing robust generalization. Our results showcase that self-supervised learning surpassed supervised learning in terms of classification performance for certain tests. Specifically, it exceeded the F1 score of supervised learning for attack detection by 4.83% and by 14.61% in accuracy for the multiclass task of protocol classification. Drawing from extensive ablation studies presented in our research, we recommend an optimal training framework for upcoming contrastive learning experiments that emphasize visual representations in the cybersecurity realm. This training approach has enabled us to highlight the broader applicability of self-supervised learning, which, in some instances, outperformed supervised learning transferability by over 5% in precision and nearly 1% in F1 score. [ABSTRACT FROM AUTHOR]

With the rapid development and widespread application of blockchain technology in recent years, smart contracts running on blockchains often face security vulnerability problems, resulting in significant economic losses. Unlike traditional programs, smart contracts cannot be modified once deployed, and vulnerabilities cannot be remedied. Therefore, the vulnerability detection of smart contracts has become a research focus. Most existing vulnerability detection methods are based on rules defined by experts, which are inefficient and have poor scalability. Although there have been studies using machine learning methods to extract contract features for vulnerability detection, the features considered are singular, and it is impossible to fully utilize smart contract information. In order to overcome the limitations of existing methods, this paper proposes a smart contract vulnerability detection method based on deep learning and multimodal decision fusion. This method also considers the code semantics and control structure information of smart contracts. It integrates the source code, operation code, and control-flow modes through the multimodal decision fusion method. The deep learning method extracts five features used to represent contracts and achieves high accuracy and recall rates. The experimental results show that the detection accuracy of our method for arithmetic vulnerability, re-entrant vulnerability, transaction order dependence, and Ethernet locking vulnerability can reach 91.6%, 90.9%, 94.8%, and 89.5%, respectively, and the detected AUC values can reach 0.834, 0.852, 0.886, and 0.825, respectively. This shows that our method has a good vulnerability detection effect. Furthermore, ablation experiments show that the multimodal decision fusion method contributes significantly to the fusion of different modalities. [ABSTRACT FROM AUTHOR]

In this paper, research was conducted on anomaly detection of wheel flats. In the railway sector, conducting tests with actual railway vehicles is challenging due to safety concerns for passengers and maintenance issues as it is a public industry. Therefore, dynamics software was utilized. Next, STFT (short-time Fourier transform) was performed to create spectrogram images. In the case of railway vehicles, control, monitoring, and communication are performed through TCMS, but complex analysis and data processing are difficult because there are no devices such as GPUs. Furthermore, there are memory limitations. Therefore, in this paper, the relatively lightweight models LeNet-5, ResNet-20, and MobileNet-V3 were selected for deep learning experiments. At this time, the LeNet-5 and MobileNet-V3 models were modified from the basic architecture. Since railway vehicles are given preventive maintenance, it is difficult to obtain fault data. Therefore, semi-supervised learning was also performed. At this time, the Deep One Class Classification paper was referenced. The evaluation results indicated that the modified LeNet-5 and MobileNet-V3 models achieved approximately 97% and 96% accuracy, respectively. At this point, the LeNet-5 model showed a training time of 12 min faster than the MobileNet-V3 model. In addition, the semi-supervised learning results showed a significant outcome of approximately 94% accuracy when considering the railway maintenance environment. In conclusion, considering the railway vehicle maintenance environment and device specifications, it was inferred that the relatively simple and lightweight LeNet-5 model can be effectively utilized while using small images. [ABSTRACT FROM AUTHOR]

Contributions in the Field of Image Techniques Five papers in this Special Issue deal with image processing, including face images, microscopic images, and infrared images. Nowadays, with numerous sensors placed everywhere around us, we can obtain signals collected from a variety of environment-based sensors, including the ones placed on the ground, cased in the air or water, etc. M. Geremek and K. Szklanny in [[9]] investigated deep learning based detection of genetic diseases from face images, for 15 genetic disorders associated with facial dysmorphism. Image and video data analyzed in the presented papers include microscope images and infrared images, as well as face images. [Extracted from the article]

Human Pose Estimation (HPE) has received considerable attention during the past years, improving its performance thanks to the use of Deep Learning, and introducing new interesting uses, such as its application in Sport and Physical Exercise (SPE). The aim of this systematic review is to analyze the literature related to the application of HPE in SPE, the available data, methods, performance, opportunities, and challenges. One reviewer applied different inclusion and exclusion criteria, as well as quality metrics, to perform the paper filtering through the paper databases. The Association for Computing Machinery Digital Library, Web of Science, and dblp included more than 500 related papers after the initial filtering, finally resulting in 20. In addition, research was carried out regarding the publicly available data related to this topic. It can be concluded that even if related public data can be found, much more data is needed to be able to obtain good performance in different contexts. In relation with the methods of the authors, the use of general purpose systems as base, such as Openpose, combined with other methods and adaptations to the specific use case can be found. Finally, the limitations, opportunities, and challenges are presented. [ABSTRACT FROM AUTHOR]

Deep learning (DL) has been frequently applied in the image reconstruction of electromagnetic tomography (EMT) in recent years. It offers the potential to achieve higher-quality image reconstruction. Among these, research on samples is relatively scarce. Samples are the cornerstone for both large and small models, which is easy to ignore. In this paper, a deep learning electromagnetic tomography (DL-EMT) model with nine elements is established. Complete simulation and experimental samples are obtained based on this model. On the sample sets, the reconstruction quality is observed by adjusting the size and configuration of the training set. The Mann–Whitney U test shows that beyond a certain point, the addition of more samples to the training data fed into the deep learning network does not result in an obvious improvement statistically in the quality of the reconstructed images. This paper proposes a CC-building method for optimizing a sample set. This method is based on the Pearson correlation coefficient calculation, aiming to establish a more effective sample base for DL-EMT image reconstruction. The statistical analysis shows that the CC-building method can significantly improve the image reconstruction effect in a small and moderate sample size. This method is also validated by experiments. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) is the underlying technology that has enabled connecting daily apparatus to the Internet and enjoying the facilities of smart services. IoT marketing is experiencing an impressive 16.7% growth rate and is a nearly USD 300.3 billion market. These eye-catching figures have made it an attractive playground for cybercriminals. IoT devices are built using resource-constrained architecture to offer compact sizes and competitive prices. As a result, integrating sophisticated cybersecurity features is beyond the scope of the computational capabilities of IoT. All of these have contributed to a surge in IoT intrusion. This paper presents an LSTM-based Intrusion Detection System (IDS) with a Dynamic Access Control (DAC) algorithm that not only detects but also defends against intrusion. This novel approach has achieved an impressive 97.16% validation accuracy. Unlike most of the IDSs, the model of the proposed IDS has been selected and optimized through mathematical analysis. Additionally, it boasts the ability to identify a wider range of threats (14 to be exact) compared to other IDS solutions, translating to enhanced security. Furthermore, it has been fine-tuned to strike a balance between accurately flagging threats and minimizing false alarms. Its impressive performance metrics (precision, recall, and F1 score all hovering around 97%) showcase the potential of this innovative IDS to elevate IoT security. The proposed IDS boasts an impressive detection rate, exceeding 98%. This high accuracy instills confidence in its reliability. Furthermore, its lightning-fast response time, averaging under 1.2 s, positions it among the fastest intrusion detection systems available. [ABSTRACT FROM AUTHOR]

Deep learning pervades heavy data-driven disciplines in research and development. The Internet of Things and sensor systems, which enable smart environments and services, are settings where deep learning can provide invaluable utility. However, the data in these systems are very often directly or indirectly related to people, which raises privacy concerns. Federated learning (FL) mitigates some of these concerns and empowers deep learning in sensor-driven environments by enabling multiple entities to collaboratively train a machine learning model without sharing their data. Nevertheless, a number of works in the literature propose attacks that can manipulate the model and disclose information about the training data in FL. As a result, there has been a growing belief that FL is highly vulnerable to severe attacks. Although these attacks do indeed highlight security and privacy risks in FL, some of them may not be as effective in production deployment because they are feasible only given special—sometimes impractical—assumptions. In this paper, we investigate this issue by conducting a quantitative analysis of the attacks against FL and their evaluation settings in 48 papers. This analysis is the first of its kind to reveal several research gaps with regard to the types and architectures of target models. Additionally, the quantitative analysis allows us to highlight unrealistic assumptions in some attacks related to the hyper-parameters of the model and data distribution. Furthermore, we identify fallacies in the evaluation of attacks which raise questions about the generalizability of the conclusions. As a remedy, we propose a set of recommendations to promote adequate evaluations. [ABSTRACT FROM AUTHOR]

An autonomous place recognition system is essential for scenarios where GPS is useless, such as underground tunnels. However, it is difficult to use existing algorithms to fully utilize the small number of effective features in underground tunnel data, and recognition accuracy is difficult to guarantee. In order to solve this challenge, an efficient point cloud position recognition algorithm, named Dual-Attention Transformer Network (DAT-Net), is proposed in this paper. The algorithm firstly adopts the farthest point downsampling module to eliminate the invalid redundant points in the point cloud data and retain the basic shape of the point cloud, which reduces the size of the point cloud and, at the same time, reduces the influence of the invalid point cloud on the data analysis. After that, this paper proposes the dual-attention Transformer module to facilitate local information exchange by utilizing the multi-head self-attention mechanism. It extracts local descriptors and integrates highly discriminative global descriptors based on global context with the help of a feature fusion layer to obtain a more accurate and robust global feature representation. Experimental results show that the method proposed in this paper achieves an average F 1 score of 0.841 on the SubT-Tunnel dataset and outperforms many existing state-of-the-art algorithms in recognition accuracy and robustness tests. [ABSTRACT FROM AUTHOR]

Aiming at the problems of the poor recognition effect and low recognition rate of the existing methods in the process of belt deviation detection, this paper proposes a real-time belt deviation detection method. Firstly, ResNet18 combined with the attention mechanism module is used as a feature extraction network to enhance the features in the belt edge region and suppress the features in other regions. Then, the extracted features are used to predict the approximate locations of the belt edges using a classifier based on the contextual information on the fully connected layer. Next, the improved gradient equation is used as a structural loss in the model training stage to make the model prediction value closer to the target value. Then, the authors of this paper use the least squares method to fit the set of detected belt edge line points to obtain the accurate belt edge straight line. Finally, the deviation threshold is set according to the requirements of the safety production code, and the fitting results are compared with the threshold to achieve the belt deviation detection. Comparisons are made with four other methods: ultrafast structure-aware deep lane detection, end-to-end wireframe parsing, LSD, and the Hough transform. The results show that the proposed method is the fastest at 41 frames/sec; the accuracy is improved by 0.4%, 13.9%, 45.9%, and 78.8% compared to the other four methods; and the F1-score index is improved by 0.3%, 10.2%, 32.6%, and 72%, respectively, which meets the requirements of practical engineering applications. The proposed method can be used for intelligent monitoring and control in coal mines, logistics and transport industries, and other scenarios requiring belt transport. [ABSTRACT FROM AUTHOR]

Noncontact heart rate monitoring techniques based on millimeter-wave radar have advantages in unique medical scenarios. However, the accuracy of the existing noncontact heart rate estimation methods is still limited by interference, such as DC offsets, respiratory harmonics, and environmental noise. Additionally, these methods still require longer observation times. Most deep learning methods related to heart rate estimation still need to collect more heart rate marker data for training. To address the above problems, this paper introduces a radar signal-based heart rate estimation network named the "masked phase autoencoders with a vision transformer network" (MVN). This network is grounded on masked autoencoders (MAEs) for self-supervised pretraining and a vision transformer (ViT) for transfer learning. During the phase preprocessing stage, phase differencing and interpolation smoothing are performed on the input phase signal. In the self-supervised pretraining step, masked self-supervised training is performed on the phase signal using the MAE network. In the transfer learning stage, the encoder segment of the MAE network is integrated with the ViT network to enable transfer learning using labeled heart rate data. The innovative MVN offers a dual advantage—it not only reduces the cost associated with heart rate data acquisition but also adeptly addresses the issue of respiratory harmonic interference, which is an improvement over conventional signal processing methods. The experimental results show that the process in this paper improves the accuracy of heart rate estimation while reducing the requisite observation time. [ABSTRACT FROM AUTHOR]

Machine learning (ML) has a well-established reputation for successfully enabling automation through its scalable predictive power. Industry 4.0 encapsulates a new stage of industrial processes and value chains driven by smart connection and automation. Large-scale problems within these industrial settings are a prime example of an environment that can benefit from ML. However, a clear view of how ML currently intersects with industry 4.0 is difficult to grasp without reading an infeasible number of papers. This systematic review strives to provide such a view by gathering a collection of 45,783 relevant papers from Scopus and Web of Science and analysing it with BERTopic. We analyse the key topics to understand what industry applications receive the most attention and which ML methods are used the most. Moreover, we manually reviewed 17 white papers of consulting firms to compare the academic landscape to an industry perspective. We found that security and predictive maintenance were the most common topics, CNNs were the most used ML method and industry companies, at the moment, generally focus more on enabling successful adoption rather than building better ML models. The academic topics are meaningful and relevant but technology focused on making ML adoption easier deserves more attention. [ABSTRACT FROM AUTHOR]

This paper discusses optimizing desktop image quality and bandwidth consumption in remote IoT GUI desktop scenarios. Remote desktop tools, which are crucial for work efficiency, typically employ image compression techniques to manage bandwidth. Although JPEG is widely used for its efficiency in eliminating redundancy, it can introduce quality loss with increased compression. Recently, deep learning-based compression techniques have emerged, challenging traditional methods like JPEG. This study introduces an optimized RFB (Remote Frame Buffer) protocol based on a convolutional neural network (CNN) image compression algorithm, focusing on human visual perception in desktop image processing. The improved RFB protocol proposed in this paper, compared to the unoptimized RFB protocol, can save 30–80% of bandwidth consumption and enhances remote desktop image quality, as evidenced by improved PSNR and MS-SSIM values between the remote desktop image and the original image, thus providing superior desktop image transmission quality. [ABSTRACT FROM AUTHOR]

In cases with a large number of sensors and complex spatial distribution, correctly learning the spatial characteristics of the sensors is vital for structural damage identification. Graph convolutional neural networks (GCNs), unlike other methods, have the ability to learn the spatial characteristics of the sensors, which is targeted at the above problems in structural damage identification. However, under the influence of environmental interference, sensor instability, and other factors, part of the vibration signal can easily change its fundamental characteristics, and there is a possibility of misjudging structural damage. Therefore, on the basis of building a high-performance graphical convolutional deep learning model, this paper considers the integration of data fusion technology in the model decision-making layer and proposes a single-model decision-making fusion neural network (S_DFNN) model. Through experiments involving the frame model and the self-designed cable-stayed bridge model, it is concluded that this method has a better performance of damage recognition for different structures, and the accuracy is improved based on a single model and has good damage recognition performance. The method has better damage identification performance in different structures, and the accuracy rate is improved based on the single model, which has a very good damage identification effect. It proves that the structural damage diagnosis method proposed in this paper with data fusion technology combined with deep learning has a strong generalization ability and has great potential in structural damage diagnosis. [ABSTRACT FROM AUTHOR]

With the wide application of direct sequence spread spectrum (DSSS) signals, the comprehensive performance of DSSS communication systems has been continuously improved, making the electronic reconnaissance link in communication countermeasures more difficult. Electronic reconnaissance technology, as the fundamental means of modern electronic warfare, mainly includes signal detection, recognition, and parameter estimation. At present, research on DSSS detection algorithms is mostly based on the correlation characteristics of DSSS signals, and autocorrelation algorithm is the most mature and widely used method in practical engineering. With the continuous development of deep learning, deep-learning-based methods have gradually been introduced to replace traditional algorithms in the field of signal processing. This paper proposes a spread spectrum signal detection method based on convolutional neural network (CNN). Through experimental analysis, the detection performance of the CNN model proposed in this paper on DSSS signals in various situations has been compared and analyzed with traditional autocorrelation detection methods for different signal-to-noise ratios. The experiments verified the estimation performance of the model in this paper under different signal-to-noise ratios, different spreading code lengths, different spreading code types, and different modulation methods and compared it with the autocorrelation detection algorithm. It was found that the detection performance of the model in this paper was higher than that of the autocorrelation detection method, and the overall performance was improved by 4 dB. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG)-based brain–computer interfaces (BCIs) provide a novel approach for controlling external devices. BCI technologies can be important enabling technologies for people with severe mobility impairment. Endogenous paradigms, which depend on user-generated commands and do not need external stimuli, can provide intuitive control of external devices. This paper discusses BCIs to control various physical devices such as exoskeletons, wheelchairs, mobile robots, and robotic arms. These technologies must be able to navigate complex environments or execute fine motor movements. Brain control of these devices presents an intricate research problem that merges signal processing and classification techniques with control theory. In particular, obtaining strong classification performance for endogenous BCIs is challenging, and EEG decoder output signals can be unstable. These issues present myriad research questions that are discussed in this review paper. This review covers papers published until the end of 2021 that presented BCI-controlled dynamic devices. It discusses the devices controlled, EEG paradigms, shared control, stabilization of the EEG signal, traditional machine learning and deep learning techniques, and user experience. The paper concludes with a discussion of open questions and avenues for future work. [ABSTRACT FROM AUTHOR]

The purpose of image dehazing is to remove the interference from weather factors in degraded images and enhance the clarity and color saturation of images to maximize the restoration of useful features. Single image dehazing is one of the most important tasks in the field of image restoration. In recent years, due to the progress of deep learning, single image dehazing has made great progress. With the success of Transformer in advanced computer vision tasks, some research studies also began to apply Transformer to image dehazing tasks and obtained surprising results. However, both the deconvolution-neural-network-based dehazing algorithm and Transformer based dehazing algorithm magnify their advantages and disadvantages separately. Therefore, this paper proposes a novel Transformer–Convolution fusion dehazing network (TCFDN), which uses Transformer's global modeling ability and convolutional neural network's local modeling ability to improve the dehazing ability. In the Transformer–Convolution fusion dehazing network, the classic self-encoder structure is used. This paper proposes a Transformer–Convolution hybrid layer, which uses an adaptive fusion strategy to make full use of the Swin-Transformer and convolutional neural network to extract and reconstruct image features. On the basis of previous research, this layer further improves the ability of the network to remove haze. A series of contrast experiments and ablation experiments not only proved that the Transformer–Convolution fusion dehazing network proposed in this paper exceeded the more advanced dehazing algorithm, but also provided solid and powerful evidence for the basic theory on which it depends. [ABSTRACT FROM AUTHOR]

The decision-making algorithm serves as a fundamental component for advancing the level of autonomous driving. The end-to-end decision-making algorithm has a strong ability to process the original data, but it has grave uncertainty. However, other learning-based decision-making algorithms rely heavily on ideal state information and are entirely unsuitable for autonomous driving tasks in real-world scenarios with incomplete global information. Addressing this research gap, this paper proposes a stable hierarchical decision-making framework with images as the input. The first step of the framework is a model-based data encoder that converts the input image data into a fixed universal data format. Next is a state machine based on a time series Graph Convolutional Network (GCN), which is used to classify the current driving state. Finally, according to the state's classification, the corresponding rule-based algorithm is selected for action generation. Through verification, the algorithm demonstrates the ability to perform autonomous driving tasks in different traffic scenarios without relying on global network information. Comparative experiments further confirm the effectiveness of the hierarchical framework, model-based image data encoder, and time series GCN. [ABSTRACT FROM AUTHOR]

Mobile crowdsensing (MCS) systems rely on the collective contribution of sensor data from numerous mobile devices carried by participants. However, the open and participatory nature of MCS renders these systems vulnerable to adversarial attacks or data poisoning attempts where threat actors can inject malicious data into the system. There is a need for a detection system that mitigates malicious sensor data to maintain the integrity and reliability of the collected information. This paper addresses this issue by proposing an adaptive and robust model for detecting malicious data in MCS scenarios involving sensor data from mobile devices. The proposed model incorporates an adaptive learning mechanism that enables the TCN-based model to continually evolve and adapt to new patterns, enhancing its capability to detect novel malicious data as threats evolve. We also present a comprehensive evaluation of the proposed model's performance using the SherLock datasets, demonstrating its effectiveness in accurately detecting malicious sensor data and mitigating potential threats to the integrity of MCS systems. Comparative analysis with existing models highlights the performance of the proposed TCN-based model in terms of detection accuracy, with an accuracy score of 98%. Through these contributions, the paper aims to advance the state of the art in ensuring the trustworthiness and security of MCS systems, paving the way for the development of more reliable and robust crowdsensing applications. [ABSTRACT FROM AUTHOR]

The cooperative, connected, and automated mobility (CCAM) infrastructure plays a key role in understanding and enhancing the environmental perception of autonomous vehicles (AVs) driving in complex urban settings. However, the deployment of CCAM infrastructure necessitates the efficient selection of the computational processing layer and deployment of machine learning (ML) and deep learning (DL) models to achieve greater performance of AVs in complex urban environments. In this paper, we propose a computational framework and analyze the effectiveness of a custom-trained DL model (YOLOv8) when deployed in diverse devices and settings at the vehicle-edge-cloud-layered architecture. Our main focus is to understand the interplay and relationship between the DL model's accuracy and execution time during deployment at the layered framework. Therefore, we investigate the trade-offs between accuracy and time by the deployment process of the YOLOv8 model over each layer of the computational framework. We consider the CCAM infrastructures, i.e., sensory devices, computation, and communication at each layer. The findings reveal that the performance metrics results (e.g., 0.842 mAP@0.5) of deployed DL models remain consistent regardless of the device type across any layer of the framework. However, we observe that inference times for object detection tasks tend to decrease when the DL model is subjected to different environmental conditions. For instance, the Jetson AGX (non-GPU) outperforms the Raspberry Pi (non-GPU) by reducing inference time by 72%, whereas the Jetson AGX Xavier (GPU) outperforms the Jetson AGX ARMv8 (non-GPU) by reducing inference time by 90%. A complete average time comparison analysis for the transfer time, preprocess time, and total time of devices Apple M2 Max, Intel Xeon, Tesla T4, NVIDIA A100, Tesla V100, etc., is provided in the paper. Our findings direct the researchers and practitioners to select the most appropriate device type and environment for the deployment of DL models required for production. [ABSTRACT FROM AUTHOR]

The effective identification and mitigation of non-line-of-sight (NLOS) ranging errors are essential for achieving high-precision positioning and navigation with ultra-wideband (UWB) technology in harsh indoor environments. In this paper, an efficient UWB ranging-error mitigation strategy that uses novel channel impulse response parameters based on the results of a two-step NLOS identification, composed of a decision tree and feedforward neural network, is proposed to realize indoor locations. NLOS ranging errors are classified into three types, and corresponding mitigation strategies and recall mechanisms are developed, which are also extended to partial line-of-sight (LOS) errors. Extensive experiments involving three obstacles (humans, walls, and glass) and two sites show an average NLOS identification accuracy of 95.05%, with LOS/NLOS recall rates of 95.72%/94.15%. The mitigated LOS errors are reduced by 50.4%, while the average improvement in the accuracy of the three types of NLOS ranging errors is 61.8%, reaching up to 76.84%. Overall, this method achieves a reduction in LOS and NLOS ranging errors of 25.19% and 69.85%, respectively, resulting in a 54.46% enhancement in positioning accuracy. This performance surpasses that of state-of-the-art techniques, such as the convolutional neural network (CNN), long short-term memory–extended Kalman filter (LSTM-EKF), least-squares–support vector machine (LS-SVM), and k-nearest neighbor (K-NN) algorithms. [ABSTRACT FROM AUTHOR]

Due to the complexity of real optical flow capture, the existing research still has not performed real optical flow capture of infrared (IR) images with the production of an optical flow based on IR images, which makes the research and application of deep learning-based optical flow computation limited to the field of RGB images only. Therefore, in this paper, we propose a method to produce an optical flow dataset of IR images. We utilize the RGB-IR cross-modal image transformation network to rationally transform existing RGB image optical flow datasets. The RGB-IR cross-modal image transformation is based on the improved Pix2Pix implementation, and in the experiments, the network is validated and evaluated using the RGB-IR aligned bimodal dataset M3FD. Then, RGB-IR cross-modal transformation is performed on the existing RGB optical flow dataset KITTI, and the optical flow computation network is trained using the IR images generated by the transformation. Finally, the computational results of the optical flow computation network before and after training are analyzed based on the RGB-IR aligned bimodal data. [ABSTRACT FROM AUTHOR]

In substation lightning rod meter reading data taking, the classical object detection model is not suitable for deployment in substation monitoring hardware devices due to its large size, large number of parameters, and slow detection speed, while is difficult to balance detection accuracy and real-time requirements with the existing lightweight object detection model. To address this problem, this paper constructs a lightweight object detection algorithm, YOLOv5-Meter Reading Lighting (YOLOv5-MRL), based on the improved YOLOv5 model's speed while maintaining accuracy. Then, the YOLOv5s are pruned based on the convolutional kernel channel soft pruning algorithm, which greatly reduces the number of parameters in the YOLOv5-MRL model while maintaining a certain accuracy loss. Finally, in order to facilitate the dial reading, the dial external circle fitting method is proposed to calculate the dial reading using the circular angle algorithm. The experimental results on the self-built dataset show that the YOLOv5-MRL object detection model achieves a mean average precision of 96.9%, a detection speed of 5 ms/frame, and a model weight size of 5.5 MB, making it better than other advanced dial reading models. [ABSTRACT FROM AUTHOR]

Livestock's live body dimensions are a pivotal indicator of economic output. Manual measurement is labor-intensive and time-consuming, often eliciting stress responses in the livestock. With the advancement of computer technology, the techniques for livestock live body dimension measurement have progressed rapidly, yielding significant research achievements. This paper presents a comprehensive review of the recent advancements in livestock live body dimension measurement, emphasizing the crucial role of computer-vision-based sensors. The discussion covers three main aspects: sensing data acquisition, sensing data processing, and sensing data analysis. The common techniques and measurement procedures in, and the current research status of, live body dimension measurement are introduced, along with a comparative analysis of their respective merits and drawbacks. Livestock data acquisition is the initial phase of live body dimension measurement, where sensors are employed as data collection equipment to obtain information conducive to precise measurements. Subsequently, the acquired data undergo processing, leveraging techniques such as 3D vision technology, computer graphics, image processing, and deep learning to calculate the measurements accurately. Lastly, this paper addresses the existing challenges within the domain of livestock live body dimension measurement in the livestock industry, highlighting the potential contributions of computer-vision-based sensors. Moreover, it predicts the potential development trends in the realm of high-throughput live body dimension measurement techniques for livestock. [ABSTRACT FROM AUTHOR]

Currently, in most traditional VSLAM (visual SLAM) systems, static assumptions result in a low accuracy in dynamic environments, or result in a new and higher level of accuracy but at the cost of sacrificing the real–time property. In highly dynamic scenes, balancing a high accuracy and a low computational cost has become a pivotal requirement for VSLAM systems. This paper proposes a new VSLAM system, balancing the competitive demands between positioning accuracy and computational complexity and thereby further improving the overall system properties. From the perspective of accuracy, the system applies an improved lightweight target detection network to quickly detect dynamic feature points while extracting feature points at the front end of the system, and only feature points of static targets are applied for frame matching. Meanwhile, the attention mechanism is integrated into the target detection network to continuously and accurately capture dynamic factors to cope with more complex dynamic environments. From the perspective of computational expense, the lightweight network Ghostnet module is applied as the backbone network of the target detection network YOLOv5s, significantly reducing the number of model parameters and improving the overall inference speed of the algorithm. Experimental results on the TUM dynamic dataset indicate that in contrast with the ORB–SLAM3 system, the pose estimation accuracy of the system improved by 84.04%. In contrast with dynamic SLAM systems such as DS–SLAM and DVO SLAM, the system has a significantly improved positioning accuracy. In contrast with other VSLAM algorithms based on deep learning, the system has superior real–time properties while maintaining a similar accuracy index. [ABSTRACT FROM AUTHOR]

Tunnel cracks are the main factors that cause damage and collapse of tunnel structures. How to detect tunnel cracks efficiently and avoid safety accidents caused by tunnel cracks effectively is a research hotspot at present. In order to meet the need for efficient detection of tunnel cracks, the tunnel crack detection method based on improved Retinex and deep learning is proposed in this paper. The tunnel crack images collected by optical imaging equipment are used to improve the contrast information of tunnel crack images using the image enhancement algorithm, and this image enhancement algorithm has the function of multi-scale Retinex decomposition with improved central filtering. An improved VGG19 network model is constructed to achieve efficient segmentation of tunnel crack images through deep learning methods and then form the segmented binary image. The Zhang–Suen fast parallel-thinning method is used to obtain the skeleton map of the single-layer pixel, and the length and width information of the tunnel cracks are obtained. The feasibility and effectiveness of the proposed method are verified by experiments. Compared with other methods in the literature, the maximum deviation in the length of the tunnel crack is about 5 mm, and the maximum deviation in the width of the tunnel crack is about 0.8 mm. The experimental results show that the proposed method has a shorter detection time and higher detection accuracy. The research results of this paper can provide a strong basis for the health evaluation of tunnels. [ABSTRACT FROM AUTHOR]

The conventional trust model employed in satellite network security routing algorithms exhibits limited accuracy in detecting malicious nodes and lacks adaptability when confronted with unknown attacks. To address this challenge, this paper introduces a secure satellite network routing technology founded on deep learning and trust management. The approach embraces the concept of distributed trust management, resulting in all satellite nodes in this paper being equipped with trust management and anomaly detection modules for assessing the security of neighboring nodes. In a more detailed breakdown, this technology commences by preprocessing the communication behavior of satellite network nodes using D–S evidence theory, effectively mitigating interference factors encountered during the training of VAE modules. Following this preprocessing step, the trust vector, which has undergone prior processing, is input into the VAE module. Once the VAE module's training is completed, the satellite network can assess safety factors by employing the safety module during the collection of trust evidence. Ultimately, these security factors can be integrated with the pheromone component within the ant colony algorithm to guide the ants in discovering pathways. Simulation results substantiate that the proposed satellite network secure routing algorithm effectively counters the impact of malicious nodes on data transmission within the network. When compared to the traditional trust management model of satellite network secure routing algorithms, the algorithm demonstrates enhancements in average end-to-end delay, packet loss rate, and throughput. [ABSTRACT FROM AUTHOR]

Background: Digital clinical measures collected via various digital sensing technologies such as smartphones, smartwatches, wearables, and ingestible and implantable sensors are increasingly used by individuals and clinicians to capture the health outcomes or behavioral and physiological characteristics of individuals. Time series classification (TSC) is very commonly used for modeling digital clinical measures. While deep learning models for TSC are very common and powerful, there exist some fundamental challenges. This review presents the non-deep learning models that are commonly used for time series classification in biomedical applications that can achieve high performance. Objective: We performed a systematic review to characterize the techniques that are used in time series classification of digital clinical measures throughout all the stages of data processing and model building. Methods: We conducted a literature search on PubMed, as well as the Institute of Electrical and Electronics Engineers (IEEE), Web of Science, and SCOPUS databases using a range of search terms to retrieve peer-reviewed articles that report on the academic research about digital clinical measures from a five-year period between June 2016 and June 2021. We identified and categorized the research studies based on the types of classification algorithms and sensor input types. Results: We found 452 papers in total from four different databases: PubMed, IEEE, Web of Science Database, and SCOPUS. After removing duplicates and irrelevant papers, 135 articles remained for detailed review and data extraction. Among these, engineered features using time series methods that were subsequently fed into widely used machine learning classifiers were the most commonly used technique, and also most frequently achieved the best performance metrics (77 out of 135 articles). Statistical modeling (24 out of 135 articles) algorithms were the second most common and also the second-best classification technique. Conclusions: In this review paper, summaries of the time series classification models and interpretation methods for biomedical applications are summarized and categorized. While high time series classification performance has been achieved in digital clinical, physiological, or biomedical measures, no standard benchmark datasets, modeling methods, or reporting methodology exist. There is no single widely used method for time series model development or feature interpretation, however many different methods have proven successful. [ABSTRACT FROM AUTHOR]

Motion blur recovery is a common method in the field of remote sensing image processing that can effectively improve the accuracy of detection and recognition. Among the existing motion blur recovery methods, the algorithms based on deep learning do not rely on a priori knowledge and, thus, have better generalizability. However, the existing deep learning algorithms usually suffer from feature misalignment, resulting in a high probability of missing details or errors in the recovered images. This paper proposes an end-to-end generative adversarial network (SDD-GAN) for single-image motion deblurring to address this problem and to optimize the recovery of blurred remote sensing images. Firstly, this paper applies a feature alignment module (FAFM) in the generator to learn the offset between feature maps to adjust the position of each sample in the convolution kernel and to align the feature maps according to the context; secondly, a feature importance selection module is introduced in the generator to adaptively filter the feature maps in the spatial and channel domains, preserving reliable details in the feature maps and improving the performance of the algorithm. In addition, this paper constructs a self-constructed remote sensing dataset (RSDATA) based on the mechanism of image blurring caused by the high-speed orbital motion of satellites. Comparative experiments are conducted on self-built remote sensing datasets and public datasets as well as on real remote sensing blurred images taken by an in-orbit satellite (CX-6(02)). The results show that the algorithm in this paper outperforms the comparison algorithm in terms of both quantitative evaluation and visual effects. [ABSTRACT FROM AUTHOR]

Automatic power line extraction from aerial images of unmanned aerial vehicles is one of the key technologies of power line inspection. However, the faint power line targets and complex image backgrounds make the extraction of power lines a greater challenge. In this paper, a new power line extraction method is proposed, which has two innovative points. Innovation point one, based on the introduction of the Mask RCNN network algorithm, proposes a block extraction strategy to realize the preliminary extraction of power lines with the idea of "part first and then the whole". This strategy globally reduces the anchor frame size, increases the proportion of power lines in the feature map, and reduces the accuracy degradation caused by the original negative anchor frames being misclassified as positive anchor frames. Innovation point two, the proposed connected domain group fitting algorithm solves the problem of broken and mis-extracted power lines even after the initial extraction and solves the problem of incomplete extraction of power lines by background texture interference. Through experiments on 60 images covering different complex image backgrounds, the performance of the proposed method far exceeds that of commonly used methods such as LSD, Yolact++, and Mask RCNN. DSCPL, TPR, precision, and accuracy are as high as 73.95, 81.75, 69.28, and 99.15, respectively, while FDR is only 30.72. The experimental results show that the proposed algorithm has good performance and can accomplish the task of power line extraction under complex image backgrounds. The algorithm in this paper solves the main problems of power line extraction and proves the feasibility of the algorithm in other scenarios. In the future, the dataset will be expanded to improve the performance of the algorithm in different scenarios. [ABSTRACT FROM AUTHOR]

Deep learning technology has advanced rapidly and has started to be applied for the detection of welding defects. In the manufacturing process of power batteries for new energy vehicles, welding defects may occur due to the high directivity, convergence, and penetration of the laser beam. The accuracy of deep learning prediction relies heavily on big data, but balanced big data of welding defects is hard to acquire at the battery production site. In this paper, the authors construct a dataset named RIAM, which consists of images captured from an industrial environment for laser welding of power battery modules. RIAM contains four types of images: Normality, Lack of fusion, Surface porosity, and Scaled surface. The characteristics of RIAM are carefully considered in the application scenarios. Moreover, this paper proposes a gradient-based unsupervised model named Grad-MobileNet, which can be trained with only a few normal images and can extract the feature gradients of the input images. Welding defects can then be classified by the gradient distribution. This model is based on MobileNetV3, which is a lightweight convolutional neural network (CNN), and achieves 99% accuracy, which is higher than the accuracy expected from supervised learning. [ABSTRACT FROM AUTHOR]

Dragon fruit is one of the most popular fruits in China and Southeast Asia. It, however, is mainly picked manually, imposing high labor intensity on farmers. The hard branches and complex postures of dragon fruit make it difficult to achieve automated picking. For picking dragon fruits with diverse postures, this paper proposes a new dragon fruit detection method, not only to identify and locate the dragon fruit, but also to detect the endpoints that are at the head and root of the dragon fruit, which can provide more visual information for the dragon fruit picking robot. First, YOLOv7 is used to locate and classify the dragon fruit. Then, we propose a PSP-Ellipse method to further detect the endpoints of the dragon fruit, including dragon fruit segmentation via PSPNet, endpoints positioning via an ellipse fitting algorithm and endpoints classification via ResNet. To test the proposed method, some experiments are conducted. In dragon fruit detection, the precision, recall and average precision of YOLOv7 are 0.844, 0.924 and 0.932, respectively. YOLOv7 also performs better compared with some other models. In dragon fruit segmentation, the segmentation performance of PSPNet on dragon fruit is better than some other commonly used semantic segmentation models, with the segmentation precision, recall and mean intersection over union being 0.959, 0.943 and 0.906, respectively. In endpoints detection, the distance error and angle error of endpoints positioning based on ellipse fitting are 39.8 pixels and 4.3°, and the classification accuracy of endpoints based on ResNet is 0.92. The proposed PSP-Ellipse method makes a great improvement compared with two kinds of keypoint regression method based on ResNet and UNet. Orchard picking experiments verified that the method proposed in this paper is effective. The detection method proposed in this paper not only promotes the progress of the automatic picking of dragon fruit, but it also provides a reference for other fruit detection. [ABSTRACT FROM AUTHOR]

Recent advances in sensor technology are expected to lead to a greater use of wireless sensor networks (WSNs) in industry, logistics, healthcare, etc. On the other hand, advances in artificial intelligence (AI), machine learning (ML), and deep learning (DL) are becoming dominant solutions for processing large amounts of data from edge-synthesized heterogeneous sensors and drawing accurate conclusions with better understanding of the situation. Integration of the two areas WSN and AI has resulted in more accurate measurements, context-aware analysis and prediction useful for smart sensing applications. In this paper, a comprehensive overview of the latest developments in context-aware intelligent systems using sensor technology is provided. In addition, it also discusses the areas in which they are used, related challenges, motivations for adopting AI solutions, focusing on edge computing, i.e., sensor and AI techniques, along with analysis of existing research gaps. Another contribution of this study is the use of a semantic-aware approach to extract survey-relevant subjects. The latter specifically identifies eleven main research topics supported by the articles included in the work. These are analyzed from various angles to answer five main research questions. Finally, potential future research directions are also discussed. [ABSTRACT FROM AUTHOR]

The continuously increasing number of mobile devices actively being used in the world amounted to approximately 6.8 billion by 2022. Consequently, this implies a substantial increase in the amount of personal data collected, transported, processed, and stored. The authors of this paper designed and implemented an integrated personal health data management system, which considers data-driven software and hardware sensors, comprehensive data privacy techniques, and machine-learning-based algorithmic models. It was determined that there are very few relevant and complete surveys concerning this specific problem. Therefore, the current scientific research was considered, and this paper comprehensively analyzes the importance of deep learning techniques that are applied to the overall management of data collected by data-driven soft sensors. This survey considers aspects that are related to demographics, health and body parameters, and human activity and behaviour pattern detection. Additionally, the relatively complex problem of designing and implementing data privacy mechanisms, while ensuring efficient data access, is also discussed, and the relevant metrics are presented. The paper concludes by presenting the most important open research questions and challenges. The paper provides a comprehensive and thorough scientific literature survey, which is useful for any researcher or practitioner in the scope of data-driven soft sensors and privacy techniques, in relation to the relevant machine-learning-based models. [ABSTRACT FROM AUTHOR]

As the demand for Internet access increases, malicious traffic on the Internet has soared also. In view of the fact that the existing malicious-traffic-identification methods suffer from low accuracy, this paper proposes a malicious-traffic-identification method based on contrastive learning. The proposed method is able to overcome the shortcomings of traditional methods that rely on labeled samples and is able to learn data feature representations carrying semantic information from unlabeled data, thus improving the model accuracy. In this paper, a new malicious traffic feature extraction model based on a Transformer is proposed. Employing a self-attention mechanism, the proposed feature extraction model can extract the bytes features of malicious traffic by performing calculations on the malicious traffic, thereby realizing the efficient identification of malicious traffic. In addition, a bidirectional GLSTM is introduced to extract the timing features of malicious traffic. The experimental results show that the proposed method is superior to the latest published methods in terms of accuracy and F1 score. [ABSTRACT FROM AUTHOR]

The Convolutional Neural Network (CNN) is one of the widely used deep learning models that offers the chance to boost farming productivity through autonomous inference of field conditions. In this paper, CNN is connected to a Support Vector Machine (SVM) to form a new model CNN-SVM; the CNN models chosen are ResNet-50 and VGG16 and the CNN-SVM models formed are ResNet-50-SVM and VGG16-SVM. The method consists of two parts: ResNet-50 and VGG16 for feature extraction and SVM for classification. This paper uses the public multi-class weeds dataset DeepWeeds for training and testing. The proposed ResNet-50-SVM and VGG16-SVM approaches achieved 97.6% and 95.9% recognition accuracies on the DeepWeeds dataset, respectively. The state-of-the-art networks (VGG16, ResNet-50, GoogLeNet, Densenet-121, and PSO-CNN) with the same dataset are accurate at 93.2%, 96.1%, 93.6%, 94.3%, and 96.9%, respectively. In comparison, the accuracy of the proposed methods has been improved by 1.5% and 2.7%, respectively. The proposed ResNet-50-SVM and the VGG16-SVM weed classification approaches are effective and can achieve high recognition accuracy. [ABSTRACT FROM AUTHOR]

In order to more effectively monitor and interfere with enemy signals, it is particularly important to accurately and efficiently identify the intercepted signals and estimate their parameters in the increasingly complex electromagnetic environment. Therefore, in non-cooperative situations, it is of great practical significance to study how to accurately detect direct sequence spread spectrum (DSSS) signals in real time and estimate their parameters. The traditional time-delay correlation algorithm encounters the challenges such as peak energy leakage and false peak interference. As an alternative, this paper introduces a Pseudo-Noise (PN) code period estimation method utilizing a one-dimensional (1D) convolutional neural network based on the residual network (CNN-ResNet). This method transforms the problem of spread spectrum code period estimation into a multi-classification problem of spread spectrum code length estimation. Firstly, the In-phase/Quadrature(I/Q) two-way of the received DSSS signals is directly input into the CNN-ResNet model, which will automatically learn the characteristics of the DSSS signal with different PN code lengths and then estimate the PN code length. Simulation experiments are conducted using a data set with DSSS signals ranging from −20 to 10 dB in terms of signal-to-noise ratios (SNRs). Upon training and verifying the model using BPSK modulation, it is then put to the test with QPSK-modulated signals, and the estimation performance was analyzed through metrics such as loss function, accuracy rate, recall rate, and confusion matrix. The results demonstrate that the 1D CNN-ResNet proposed in this paper is capable of effectively estimating the PN code period of the non-cooperative DSSS signal, exhibiting robust generalization abilities. [ABSTRACT FROM AUTHOR]

Image inpainting is an active area of research in image processing that focuses on reconstructing damaged or missing parts of an image. The advent of deep learning has greatly advanced the field of image restoration in recent years. While there are many existing methods that can produce high-quality restoration results, they often struggle when dealing with images that have large missing areas, resulting in blurry and artifact-filled outcomes. This is primarily because of the presence of invalid information in the inpainting region, which interferes with the inpainting process. To tackle this challenge, the paper proposes a novel approach called separable mask update convolution. This technique automatically learns and updates the mask, which represents the missing area, to better control the influence of invalid information within the mask area on the restoration results. Furthermore, this convolution method reduces the number of network parameters and the size of the model. The paper also introduces a regional normalization technique that collaborates with separable mask update convolution layers for improved feature extraction, thereby enhancing the quality of the restored image. Experimental results demonstrate that the proposed method performs well in restoring images with large missing areas and outperforms state-of-the-art image inpainting methods significantly in terms of image quality. [ABSTRACT FROM AUTHOR]

Smart living, an increasingly prominent concept, entails incorporating sophisticated technologies in homes and urban environments to elevate the quality of life for citizens. A critical success factor for smart living services and applications, from energy management to healthcare and transportation, is the efficacy of human action recognition (HAR). HAR, rooted in computer vision, seeks to identify human actions and activities using visual data and various sensor modalities. This paper extensively reviews the literature on HAR in smart living services and applications, amalgamating key contributions and challenges while providing insights into future research directions. The review delves into the essential aspects of smart living, the state of the art in HAR, and the potential societal implications of this technology. Moreover, the paper meticulously examines the primary application sectors in smart living that stand to gain from HAR, such as smart homes, smart healthcare, and smart cities. By underscoring the significance of the four dimensions of context awareness, data availability, personalization, and privacy in HAR, this paper offers a comprehensive resource for researchers and practitioners striving to advance smart living services and applications. The methodology for this literature review involved conducting targeted Scopus queries to ensure a comprehensive coverage of relevant publications in the field. Efforts have been made to thoroughly evaluate the existing literature, identify research gaps, and propose future research directions. The comparative advantages of this review lie in its comprehensive coverage of the dimensions essential for smart living services and applications, addressing the limitations of previous reviews and offering valuable insights for researchers and practitioners in the field. [ABSTRACT FROM AUTHOR]

This article proposes a CBAM-ASPP-SqueezeNet model based on the attention mechanism and atrous spatial pyramid pooling (CBAM-ASPP) to solve the problem of robot multi-target grasping detection. Firstly, the paper establishes and expends a multi-target grasping dataset, as well as introduces and uses transfer learning to conduct network pre-training on the single-target dataset and slightly modify the model parameters using the multi-target dataset. Secondly, the SqueezeNet model is optimized and improved using the attention mechanism and atrous spatial pyramid pooling module. The paper introduces the attention mechanism network to weight the transmitted feature map in the channel and spatial dimensions. It uses a variety of parallel operations of atrous convolution with different atrous rates to increase the size of the receptive field and preserve features from different ranges. Finally, the CBAM-ASPP-SqueezeNet algorithm is verified using the self-constructed, multi-target capture dataset. When the paper introduces transfer learning, the various indicators converge after training 20 epochs. In the physical grabbing experiment conducted by Kinova and SIASUN Arm, a network grabbing success rate of 93% was achieved. [ABSTRACT FROM AUTHOR]

This survey provides a comprehensive overview of traditional techniques and deep learning-based methodologies for monocular visual odometry (VO), with a focus on displacement measurement applications. This paper outlines the fundamental concepts and general procedures for VO implementation, including feature detection, tracking, motion estimation, triangulation, and trajectory estimation. This paper also explores the research challenges inherent in VO implementation, including scale estimation and ground plane considerations. The scientific literature is rife with diverse methodologies aiming to overcome these challenges, particularly focusing on the problem of accurate scale estimation. This issue has been typically addressed through the reliance on knowledge regarding the height of the camera from the ground plane and the evaluation of feature movements on that plane. Alternatively, some approaches have utilized additional tools, such as LiDAR or depth sensors. This survey of approaches concludes with a discussion of future research challenges and opportunities in the field of monocular visual odometry. [ABSTRACT FROM AUTHOR]

Stress has emerged as a major concern in modern society, significantly impacting human health and well-being. Statistical evidence underscores the extensive social influence of stress, especially in terms of work-related stress and associated healthcare costs. This paper addresses the critical need for accurate stress detection, emphasising its far-reaching effects on health and social dynamics. Focusing on remote stress monitoring, it proposes an efficient deep learning approach for stress detection from facial videos. In contrast to the research on wearable devices, this paper proposes novel Hybrid Deep Learning (DL) networks for stress detection based on remote photoplethysmography (rPPG), employing (Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), 1D Convolutional Neural Network (1D-CNN)) models with hyperparameter optimisation and augmentation techniques to enhance performance. The proposed approach yields a substantial improvement in accuracy and efficiency in stress detection, achieving up to 95.83% accuracy with the UBFC-Phys dataset while maintaining excellent computational efficiency. The experimental results demonstrate the effectiveness of the proposed Hybrid DL models for rPPG-based-stress detection. [ABSTRACT FROM AUTHOR]

Deep learning technology can improve sensing efficiency and has the ability to discover potential patterns in data; the efficiency of user behavior recognition in the field of smart homes has been further improved, making the recognition process more intelligent and humanized. This paper analyzes the optical sensors commonly used in smart homes and their working principles through case studies and explores the technical framework of user behavior recognition based on optical sensors. At the same time, CiteSpace (Basic version 6.2.R6) software is used to visualize and analyze the related literature, elaborate the main research hotspots and evolutionary changes of optical sensor-based smart home user behavior recognition, and summarize the future research trends. Finally, fully utilizing the advantages of cloud computing technology, such as scalability and on-demand services, combining typical life situations and the requirements of smart home users, a smart home data collection and processing technology framework based on elderly fall monitoring scenarios is designed. Based on the comprehensive research results, the application and positive impact of optical sensors in smart home user behavior recognition were analyzed, and inspiration was provided for future smart home user experience research. [ABSTRACT FROM AUTHOR]

In recent years, radar emitter signal recognition has enjoyed a wide range of applications in electronic support measure systems and communication security. More and more deep learning algorithms have been used to improve the recognition accuracy of radar emitter signals. However, complex deep learning algorithms and data preprocessing operations have a huge demand for computing power, which cannot meet the requirements of low power consumption and high real-time processing scenarios. Therefore, many research works have remained in the experimental stage and cannot be actually implemented. To tackle this problem, this paper proposes a resource reuse computing acceleration platform based on field programmable gate arrays (FPGA), and implements a one-dimensional (1D) convolutional neural network (CNN) and long short-term memory (LSTM) neural network (NN) model for radar emitter signal recognition, directly targeting the intermediate frequency (IF) data of radar emitter signal for classification and recognition. The implementation of the 1D-CNN-LSTM neural network on FPGA is realized by multiplexing the same systolic array to accomplish the parallel acceleration of 1D convolution and matrix vector multiplication operations. We implemented our network on Xilinx XCKU040 to evaluate the effectiveness of our proposed solution. Our experiments show that the system can achieve 7.34 giga operations per second (GOPS) data throughput with only 5.022 W power consumption when the radar emitter signal recognition rate is 96.53%, which greatly improves the energy efficiency ratio and real-time performance of the radar emitter recognition system. [ABSTRACT FROM AUTHOR]

Surgery is a common first-line treatment for many types of disease, including cancer. Mortality rates after general elective surgery have seen significant decreases whilst postoperative complications remain a frequent occurrence. Preoperative assessment tools are used to support patient risk stratification but do not always provide a precise and accessible assessment. Wearable sensors (WS) provide an accessible alternative that offers continuous monitoring in a non-clinical setting. They have shown consistent uptake across the perioperative period but there has been no review of WS as a preoperative assessment tool. This paper reviews the developments in WS research that have application to the preoperative period. Accelerometers were consistently employed as sensors in research and were frequently combined with photoplethysmography or electrocardiography sensors. Pre-processing methods were discussed and missing data was a common theme; this was dealt with in several ways, commonly by employing an extraction threshold or using imputation techniques. Research rarely processed raw data; commercial devices that employ internal proprietary algorithms with pre-calculated heart rate and step count were most commonly employed limiting further feature extraction. A range of machine learning models were used to predict outcomes including support vector machines, random forests and regression models. No individual model clearly outperformed others. Deep learning proved successful for predicting exercise testing outcomes but only within large sample-size studies. This review outlines the challenges of WS and provides recommendations for future research to develop WS as a viable preoperative assessment tool. [ABSTRACT FROM AUTHOR]

This paper proposes a new approach to defect detection system design focused on exact damaged areas demonstrated through visual data containing gear wheel images. The main advantage of the system is the capability to detect a wide range of patterns of defects occurring in datasets. The methodology is built on three processes that combine different approaches from unsupervised and supervised methods. The first step is a search for anomalies, which is performed by defining the correct areas on the controlled object by using the autoencoder approach. As a result, the differences between the original and autoencoder-generated images are obtained. These are divided into clusters using the clustering method (DBSCAN). Based on the clusters, the regions of interest are subsequently defined and classified using the pre-trained Xception network classifier. The main result is a system capable of focusing on exact defect areas using the sequence of unsupervised learning (autoencoder)–unsupervised learning (clustering)–supervised learning (classification) methods (U2S-CNN). The outcome with tested samples was 177 detected regions and 205 occurring damaged areas. There were 108 regions detected correctly, and 69 regions were labeled incorrectly. This paper describes a proof of concept for defect detection by highlighting exact defect areas. It can be thus an alternative to using detectors such as YOLO methods, reconstructors, autoencoders, transformers, etc. [ABSTRACT FROM AUTHOR]

Currently, aeroplane images captured by camera sensors are characterized by their small size and intricate backgrounds, posing a challenge for existing deep learning algorithms in effectively detecting small targets. This paper incorporates the RFBNet (a coordinate attention mechanism) and the SIOU loss function into the YOLOv5 algorithm to address this issue. The result is developing the model for aeroplane and undercarriage detection. The primary goal is to synergize camera sensors with deep learning algorithms, improving image capture precision. YOLOv5-RSC enhances three aspects: firstly, it introduces the receptive field block based on the backbone network, increasing the size of the receptive field of the feature map, enhancing the connection between shallow and deep feature maps, and further improving the model's utilization of feature information. Secondly, the coordinate attention mechanism is added to the feature fusion network to assist the model in more accurately locating the targets of interest, considering attention in the channel and spatial dimensions. This enhances the model's attention to key information and improves detection precision. Finally, the SIoU bounding box loss function is adopted to address the issue of IoU's insensitivity to scale and increase the speed of model bounding box convergence. Subsequently, the Basler camera experimental platform was constructed for experimental verification. The results demonstrate that the AP values of the YOLOv5-RSC detection model for aeroplane and undercarriage are 92.4% and 80.5%, respectively. The mAP value is 86.4%, which is 2.0%, 5.4%, and 3.7% higher than the original YOLOv5 algorithm, respectively, with a detection speed reaching 89.2 FPS. These findings indicate that the model exhibits high detection precision and speed, providing a valuable reference for aeroplane undercarriage detection. [ABSTRACT FROM AUTHOR]

Due to the difficulty in generating a 6-Degree-of-Freedom (6-DoF) object pose estimation dataset, and the existence of domain gaps between synthetic and real data, existing pose estimation methods face challenges in improving accuracy and generalization. This paper proposes a methodology that employs higher quality datasets and deep learning-based methods to reduce the problem of domain gaps between synthetic and real data and enhance the accuracy of pose estimation. The high-quality dataset is obtained from Blenderproc and it is innovatively processed using bilateral filtering to reduce the gap. A novel attention-based mask region-based convolutional neural network (R-CNN) is proposed to reduce the computation cost and improve the model detection accuracy. Meanwhile, an improved feature pyramidal network (iFPN) is achieved by adding a layer of bottom-up paths to extract the internalization of features of the underlying layer. Consequently, a novel convolutional block attention module–convolutional denoising autoencoder (CBAM–CDAE) network is proposed by presenting channel attention and spatial attention mechanisms to improve the ability of AE to extract images' features. Finally, an accurate 6-DoF object pose is obtained through pose refinement. The proposed approach is compared to other models using the T-LESS and LineMOD datasets. Comparison results demonstrate the proposed approach outperforms the other estimation models. [ABSTRACT FROM AUTHOR]

Wi-Fi-based human activity recognition has attracted significant attention. Deep learning methods are widely used to achieve feature representation and activity sensing. While more learnable parameters in the neural networks model lead to richer feature extraction, it results in significant resource consumption, rendering the model unsuitable for lightweight Internet of Things (IoT) devices. Furthermore, the sensing performance heavily relies on the quality and quantity of data, which is a time-consuming and labor-intensive task. Therefore, there is a need to explore methods that reduce the dependence on the quality and quantity of the dataset while ensuring recognition performance and decreasing model complexity to adapt to ubiquitous lightweight IoT devices. In this paper, we propose a novel Lightweight-Complex Temporal Convolution Network (L-CTCN) for human activity recognition. Specifically, this approach effectively combines complex convolution with a Temporal Convolution Network (TCN). Complex convolution can extract richer information from limited raw complex data, reducing the reliance on the quality and quantity of training samples. Based on the designed TCN framework with 1D convolution and residual blocks, the proposed model can achieve lightweight human activity recognition. Extensive experiments verify the effectiveness of the proposed method. We can achieve an average recognition accuracy of 96.6% with only 0.17 M parameter size. This method performs well under conditions of low sampling rates and a low number of subcarriers and samples. [ABSTRACT FROM AUTHOR]