Arc fault detection using artificial intelligence: Challenges and benefits

Safe physical interaction with cobots: a multi-modal fusion approach for health monitoring

Health monitoring is a critical aspect of personalized healthcare, enabling early detection, and intervention for various medical conditions. The emergence of cloud-based robot-assisted systems has opened new possibilities for efficient and remote health monitoring. In this paper, we present a Transformer-based Multi-modal Fusion approach for health monitoring, focusing on the effects of cognitive workload, assessment of cognitive workload in human-machine collaboration, and acceptability in human-machine interactions. Additionally, we investigate biomechanical strain measurement and evaluation, utilizing wearable devices to assess biomechanical risks in working environments. Furthermore, we study muscle fatigue assessment during collaborative tasks and propose methods for improving safe physical interaction with cobots. Our approach integrates multi-modal data, including visual, audio, and sensor- based inputs, enabling a holistic assessment of an individual's health status. The core of our method lies in leveraging the powerful Transformer model, known for its ability to capture complex relationships in sequential data. Through effective fusion and representation learning, our approach extracts meaningful features for accurate health monitoring. Experimental results on diverse datasets demonstrate the superiority of our Transformer-based multi- modal fusion approach, outperforming existing methods in capturing intricate patterns and predicting health conditions. The significance of our research lies in revolutionizing remote health monitoring, providing more accurate, and personalized healthcare services.

A gait stability evaluation method based on wearable acceleration sensors

In this study, an accurate tool is provided for the evaluation of the effect of joint motion effect on gait stability. This quantitative gait evaluation method relies exclusively on the analysis of data acquired using acceleration sensors. First, the acceleration signal of lower limb motion is collected dynamically in real-time through the acceleration sensor. Second, an algorithm based on improved dynamic time warping (DTW) is proposed and used to calculate the gait stability index of the lower limbs. Finally, the effects of different joint braces on gait stability are analyzed. The experimental results show that the joint brace at the ankle and the knee reduces the range of motions of both ankle and knee joints, and a certain impact is exerted on the gait stability. In comparison to the ankle joint brace, the knee joint brace inflicts increased disturbance on the gait stability. Compared to the joint motion of the braced side, which showed a large deviation, the joint motion of the unbraced side was more similar to that of the normal walking process. In this paper, the quantitative evaluation algorithm based on DTW makes the results more intuitive and has potential application value in the evaluation of lower limb dysfunction, clinical training and rehabilitation.

Public health implications of computer-aided diagnosis and treatment technologies in breast cancer care

Breast cancer remains a significant public health issue, being a leading cause of cancer-related mortality among women globally. Timely diagnosis and efficient treatment are crucial for enhancing patient outcomes, reducing healthcare burdens and advancing community health. This systematic review, following the PRISMA guidelines, aims to comprehensively synthesize the recent advancements in computer-aided diagnosis and treatment for breast cancer. The study covers the latest developments in image analysis and processing, machine learning and deep learning algorithms, multimodal fusion techniques and radiation therapy planning and simulation. The results of the review suggest that machine learning, augmented and virtual reality and data mining are the three major research hotspots in breast cancer management. Moreover, this paper discusses the challenges and opportunities for future research in this field. The conclusion highlights the importance of computer-aided techniques in the management of breast cancer and summarizes the key findings of the review.

Adaptive nonsingular terminal sliding mode controller for PMSM drive system using modified extended state observer

In this study, a novel adaptive nonsingular terminal sliding mode (ANTSM) control frame combined with a modified extended state observer (MESO) is presented to enhance the anti-interference performance of the permanent magnet synchronous motor (PMSM) system. In the face of time-varying disturbances with unknown upper bounds, traditional nonsingular terminal sliding mode (NTSM) controllers typically utilize the large control gain to counteract the total disturbance, which will cause unsatisfactory control performances. To address this tough issue, an ANTSM control technique was constructed for the PMSM system by tuning the control gain automatically without overestimation. On this basis, the MESO was adopted to estimate the unknown total disturbance, whose estimation was offset to the ANTSM control input. By applying finite-time techniques, the estimation error will finite-time converge to zero. The proposed MESO has a more rapid estimation speed than the traditional extended state observer (ESO). Finally, the validity of the ANTSM + ESO composite control algorithm is confirmed by comprehensive experiments.

Application of conjugated materials in sports training

In recent years, with the rapid development of the sports industry, the quality of sports training products on the market is uneven. Problems such as inaccurate detection of athletes' physical indicators, low comfort of sportswear, and reduced satisfaction with sports equipment often occur. To this end, this article proposes to apply conjugated materials with excellent optical, electrical, thermal and other properties to sports training and sports products, by summarizing the properties of conjugated materials and their applications in sports training, explores the potential of conjugated materials in improving athletes' training effects, monitoring sports status, and improving sports equipment. This article rates the application of conjugated materials in sports training products in terms of comfort, waterproofness, portability, lightness, aesthetics and breathability. The results showed that the average scores of the 20 sports participants on sportswear were 9.0475, 9.0075, 9.01, 9.025, 9.0325 and 9.04 respectively; the average scores on sports shoes were 9.035, 9.055, 9.02, 9.085, 9.0175 and 8.9975 respectively. Research shows that applying conjugated materials to sports training can improve athletes' performance and contribute to the better development of sports.

Multi-view and multi-scale behavior recognition algorithm based on attention mechanism

Human behavior recognition plays a crucial role in the field of smart education. It offers a nuanced understanding of teaching and learning dynamics by revealing the behaviors of both teachers and students. In this study, to address the exigencies of teaching behavior analysis in smart education, we first constructed a teaching behavior analysis dataset called EuClass. EuClass contains 13 types of teacher/student behavior categories and provides multi-view, multi-scale video data for the research and practical applications of teacher/student behavior recognition. We also provide a teaching behavior analysis network containing an attention-based network and an intra-class differential representation learning module. The attention mechanism uses a two-level attention module encompassing spatial and channel dimensions. The intra-class differential representation learning module utilized a unified loss function to reduce the distance between features. Experiments conducted on the EuClass dataset and a widely used action/gesture recognition dataset, IsoGD, demonstrate the effectiveness of our method in comparison to current state-of-the-art methods, with the recognition accuracy increased by 1-2% on average.

Dimensional optimisation and an inverse kinematic solution method of a safety-enhanced remote centre of motion manipulator

BACKGROUND

With the expansion of minimally invasive surgery (MIS) applications in surgery, the remote centre of motion (RCM) manipulator requires a more flexible workspace to meet different operation requirements. Thus, the mechanical structure and motion control of the RCM manipulator play important roles.

METHODS

A multi-objective genetic algorithm was exploited to maximise the kinematic performance and obtain a compact structure of the RCM manipulator. An inverse kinematic solution method is proposed to meet task accuracy and kinematic singularity avoidance constraints for safety motion control.

RESULTS

Simulation results demonstrate that there are significant improvements in the reachable workspace inside the abdominal cavity, the flexibility of the workspace, kinematic performance, and compactness of the RCM manipulator. Experiments verify the feasibility of the prototype and the validity of the proposed inverse kinematic solution method.

CONCLUSIONS

This enhances the adaptability and safety of the RCM manipulator and provides potential prospects for MIS application.

Smoking behavior detection algorithm based on YOLOv8-MNC

Introduction

The detection of smoking behavior is an emerging field faced with challenges in identifying small, frequently occluded objects like cigarette butts using existing deep learning technologies. Such challenges have led to unsatisfactory detection accuracy and poor model robustness.

Methods

To overcome these issues, this paper introduces a novel smoking detection algorithm, YOLOv8-MNC, which builds on the YOLOv8 network and includes a specialized layer for small target detection. The YOLOv8-MNC algorithm employs three key strategies: (1) It utilizes NWD Loss to mitigate the effects of minor deviations in object positions on IoU, thereby enhancing training accuracy; (2) It incorporates the Multi-head Self-Attention Mechanism (MHSA) to bolster the network's global feature learning capacity; and (3) It implements the lightweight general up-sampling operator CARAFE, in place of conventional nearest-neighbor interpolation up-sampling modules, minimizing feature information loss during the up-sampling process.

Results

Experimental results from a customized smoking behavior dataset demonstrate significant improvement in detection accuracy. The YOLOv8-MNC model achieved a detection accuracy of 85.887%, signifying a remarkable increase of 5.7% in the mean Average Precision (mAP@0.5) when compared to the previous algorithm.

Discussion

The YOLOv8-MNC algorithm represents a valuable step forward in resolving existing problems in smoking behavior detection. Its enhanced performance in both detection accuracy and robustness indicates potential applicability in related fields, thus illustrating a meaningful advancement in the sphere of smoking behavior detection. Future efforts will focus on refining this technique and exploring its application in broader contexts.

Elicitation of trustworthiness requirements for highly dexterous teleoperation systems with signal latency

Introduction

Teleoperated robotic manipulators allow us to bring human dexterity and cognition to hard-to-reach places on Earth and in space. In long-distance teleoperation, however, the limits of the speed of light results in an unavoidable and perceivable signal delay. The resultant disconnect between command, action, and feedback means that systems often behave unexpectedly, reducing operators' trust in their systems. If we are to widely adopt telemanipulation technology in high-latency applications, we must identify and specify what would make these systems trustworthy.

Methods

In this requirements elicitation study, we present the results of 13 interviews with expert operators of remote machinery from four different application areas-nuclear reactor maintenance, robot-assisted surgery, underwater exploration, and ordnance disposal-exploring which features, techniques, or experiences lead them to trust their systems.

Results

We found that across all applications, except for surgery, the top-priority requirement for developing trust is that operators must have a comprehensive engineering understanding of the systems' capabilities and limitations. The remaining requirements can be summarized into three areas: improving situational awareness, facilitating operator training, and familiarity, and easing the operator's cognitive load.

Discussion

While the inclusion of technical features to assist the operators was welcomed, these were given lower priority than non-technical, user-centric approaches. The signal delays in the participants' systems ranged from none perceived to 1 min, and included examples of successful dexterous telemanipulation for maintenance tasks with a 2 s delay. As this is comparable to Earth-to-orbit and Earth-to-Moon delays, the requirements discussed could be transferable to telemanipulation tasks in space.

Dual graph convolutional networks integrating affective knowledge and position information for aspect sentiment triplet extraction

Aspect Sentiment Triplet Extraction (ASTE) is a challenging task in natural language processing (NLP) that aims to extract triplets from comments. Each triplet comprises an aspect term, an opinion term, and the sentiment polarity of the aspect term. The neural network model developed for this task can enable robots to effectively identify and extract the most meaningful and relevant information from comment sentences, ultimately leading to better products and services for consumers. Most existing end-to-end models focus solely on learning the interactions between the three elements in a triplet and contextual words, ignoring the rich affective knowledge information contained in each word and paying insufficient attention to the relationships between multiple triplets in the same sentence. To address this gap, this study proposes a novel end-to-end model called the Dual Graph Convolutional Networks Integrating Affective Knowledge and Position Information (DGCNAP). This model jointly considers both the contextual features and the affective knowledge information by introducing the affective knowledge from SenticNet into the dependency graph construction of two parallel channels. In addition, a novel multi-target position-aware function is added to the graph convolutional network (GCN) to reduce the impact of noise information and capture the relationships between potential triplets in the same sentence by assigning greater positional weights to words that are in proximity to aspect or opinion terms. The experiment results on the ASTE-Data-V2 datasets demonstrate that our model outperforms other state-of-the-art models significantly, where the F1 scores on 14res, 14lap, 15res, and 16res are 70.72, 57.57, 61.19, and 69.58.

MUNIX repeatability evaluation method based on FastICA demixing

To enhance the reproducibility of motor unit number index (MUNIX) for evaluating neurological disease progression, this paper proposes a negative entropy-based fast independent component analysis (FastICA) demixing method to assess MUNIX reproducibility in the presence of inter-channel mixing of electromyography (EMG) signals acquired by high-density electrodes. First, composite surface EMG (sEMG) signals were obtained using high-density surface electrodes. Second, the FastICA algorithm based on negative entropy was employed to determine the orthogonal projection matrix that minimizes the negative entropy of the projected signal and effectively separates mixed sEMG signals. Finally, the proposed experimental approach was validated by introducing an interrelationship criterion to quantify independence between adjacent channel EMG signals, measuring MUNIX repeatability using coefficient of variation (CV), and determining motor unit number and size through MUNIX. Results analysis shows that the inclusion of the full (128) channel sEMG information leads to a reduction in CV value by $1.5 \pm 0.1$ and a linear decline in CV value with an increase in the number of channels. The correlation between adjacent channels in participants decreases by $0.12 \pm 0.05$ as the number of channels gradually increases. The results demonstrate a significant reduction in the number of interrelationships between sEMG signals following negative entropy-based FastICA processing, compared to the mixed sEMG signals. Moreover, this decrease in interrelationships becomes more pronounced with an increasing number of channels. Additionally, the CV of MUNIX gradually decreases with an increase in the number of channels, thereby optimizing the issue of abnormal MUNIX repeatability patterns and further enhancing the reproducibility of MUNIX based on high-density surface EMG signals.

Autonomous driving controllers with neuromorphic spiking neural networks

Autonomous driving is one of the hallmarks of artificial intelligence. Neuromorphic (brain-inspired) control is posed to significantly contribute to autonomous behavior by leveraging spiking neural networks-based energy-efficient computational frameworks. In this work, we have explored neuromorphic implementations of four prominent controllers for autonomous driving: pure-pursuit, Stanley, PID, and MPC, using a physics-aware simulation framework. We extensively evaluated these models with various intrinsic parameters and compared their performance with conventional CPU-based implementations. While being neural approximations, we show that neuromorphic models can perform competitively with their conventional counterparts. We provide guidelines for building neuromorphic architectures for control and describe the importance of their underlying tuning parameters and neuronal resources. Our results show that most models would converge to their optimal performances with merely 100-1,000 neurons. They also highlight the importance of hybrid conventional and neuromorphic designs, as was suggested here with the MPC controller. This study also highlights the limitations of neuromorphic implementations, particularly at higher (> 15 m/s) speeds where they tend to degrade faster than in conventional designs.

Preoperative Planning Framework for Robot-Assisted Dental Implant Surgery: Finite-Parameter Surrogate Model and Optimization of Instrument Placement

For robot-assisted dental implant surgery, it is necessary to feed the instrument into a specified position to perform surgery. To improve safety and efficiency, a preoperative planning framework, including a finite-parameter surrogate model (FPSM) and an automatic instrument-placement method, is proposed in this paper. This framework is implemented via two-stage optimization. In the first stage, a group of closed curves in polar coordinates is used to represent the oral cavity. By optimizing a finite number of parameters for these curves, the oral structure is simplified to form the FPSM. In the second stage, the FPSM serves as a fast safety estimator with which the target position/orientation of the instrument for the feeding motion is automatically determined through particle swarm optimization (PSO). The optimized feeding target can be used to generate a virtual fixture (VF) to avoid undesired operations and to lower the risk of collision. This proposed framework has the advantages of being safe, fast, and accurate, overcoming the computational burden and insufficient real-time performance of complex 3D models. The framework has been developed and tested, preliminarily verifying its feasibility, efficiency, and effectiveness.

Metric networks for enhanced perception of non-local semantic information

Introduction

Metric learning, as a fundamental research direction in the field of computer vision, has played a crucial role in image matching. Traditional metric learning methods aim at constructing two-branch siamese neural networks to address the challenge of image matching, but they often overlook to cross-source and cross-view scenarios.

Methods

In this article, a multi-branch metric learning model is proposed to address these limitations. The main contributions of this work are as follows: Firstly, we design a multi-branch siamese network model that enhances measurement reliability through information compensation among data points. Secondly, we construct a non-local information perception and fusion model, which accurately distinguishes positive and negative samples by fusing information at different scales. Thirdly, we enhance the model by integrating semantic information and establish an information consistency mapping between multiple branches, thereby improving the robustness in cross-source and cross-view scenarios.

Results

Experimental tests which demonstrate the effectiveness of the proposed method are carried out under various conditions, including homologous, heterogeneous, multi-view, and crossview scenarios. Compared to the state-of-the-art comparison algorithms, our proposed algorithm achieves an improvement of ~1, 2, 1, and 1% in terms of similarity measurement Recall@10, respectively, under these four conditions.

Discussion

In addition, our work provides an idea for improving the crossscene application ability of UAV positioning and navigation algorithm.

Comparison of machine learning approaches for near-fall-detection with motion sensors

Introduction

Falls are one of the most common causes of emergency hospital visits in older people. Early recognition of an increased fall risk, which can be indicated by the occurrence of near-falls, is important to initiate interventions.

Methods

In a study with 87 subjects we simulated near-fall events on a perturbation treadmill and recorded them with inertial measurement units (IMU) at seven different positions. We investigated different machine learning models for the near-fall detection including support vector machines, AdaBoost, convolutional neural networks, and bidirectional long short-term memory networks. Additionally, we analyzed the influence of the sensor position on the classification results.

Results

The best results showed a DeepConvLSTM with an F1 score of 0.954 (precision 0.969, recall 0.942) at the sensor position "left wrist."

Discussion

Since these results were obtained in the laboratory, the next step is to evaluate the suitability of the classifiers in the field.

A Novel Sensor Fusion Approach for Precise Hand Tracking in Virtual Reality-Based Human-Computer Interaction

The rapidly evolving field of Virtual Reality (VR)-based Human-Computer Interaction (HCI) presents a significant demand for robust and accurate hand tracking solutions. Current technologies, predominantly based on single-sensing modalities, fall short in providing comprehensive information capture due to susceptibility to occlusions and environmental factors. In this paper, we introduce a novel sensor fusion approach combined with a Long Short-Term Memory (LSTM)-based algorithm for enhanced hand tracking in VR-based HCI. Our system employs six Leap Motion controllers, two RealSense depth cameras, and two Myo armbands to yield a multi-modal data capture. This rich data set is then processed using LSTM, ensuring the accurate real-time tracking of complex hand movements. The proposed system provides a powerful tool for intuitive and immersive interactions in VR environments.

Artificial intelligence for video game visualization, advancements, benefits and challenges

In recent years, the field of artificial intelligence (AI) has witnessed remarkable progress and its applications have extended to the realm of video games. The incorporation of AI in video games enhances visual experiences, optimizes gameplay and fosters more realistic and immersive environments. In this review paper, we systematically explore the diverse applications of AI in video game visualization, encompassing machine learning algorithms for character animation, terrain generation and lighting effects following the PRISMA guidelines as our review methodology. Furthermore, we discuss the benefits, challenges and ethical implications associated with AI in video game visualization as well as the potential future trends. We anticipate that the future of AI in video gaming will feature increasingly sophisticated and realistic AI models, heightened utilization of machine learning and greater integration with other emerging technologies leading to more engaging and personalized gaming experiences.

Artificial intelligence techniques for ground fault line selection in power systems: State-of-the-art and research challenges

In modern power systems, efficient ground fault line selection is crucial for maintaining stability and reliability within distribution networks, especially given the increasing demand for energy and integration of renewable energy sources. This systematic review aims to examine various artificial intelligence (AI) techniques employed in ground fault line selection, encompassing artificial neural networks, support vector machines, decision trees, fuzzy logic, genetic algorithms, and other emerging methods. This review separately discusses the application, strengths, limitations, and successful case studies of each technique, providing valuable insights for researchers and professionals in the field. Furthermore, this review investigates challenges faced by current AI approaches, such as data collection, algorithm performance, and real-time requirements. Lastly, the review highlights future trends and potential avenues for further research in the field, focusing on the promising potential of deep learning, big data analytics, and edge computing to further improve ground fault line selection in distribution networks, ultimately enhancing their overall efficiency, resilience, and adaptability to evolving demands.