IEEE Access最新文献

{"title":"Ensuring Miners’ Safety in Underground Mines Through Edge Computing: Real-Time PPE Compliance Analysis Based on Pose Estimation","authors":"Mohamed Imam;Karim Baïna;Youness Tabii;El Mostafa Ressami;Youssef Adlaoui;Intissar Benzakour;François Bourzeix;El Hassan Abdelwahed","doi":"10.1109/ACCESS.2024.3470558","DOIUrl":"https://doi.org/10.1109/ACCESS.2024.3470558","url":null,"abstract":"Safety in underground mining is critically challenged by environmental conditions and the need for rigorous adherence to safety protocols. Draa Sfar, the deepest mine in Morocco, presents extreme conditions that test the effectiveness of Personal Protective Equipment (PPE) compliance. This study addresses the gaps in real-time safety monitoring and compliance in such challenging environments. The primary objective of this research is to enhance PPE compliance detection in underground mines using advanced computer vision techniques. The study aims to develop a system that not only detects PPE but also ensures its proper use through pose estimation. The study involved collecting and annotating a unique dataset from the Draa Sfar mine, characterized by its harsh environmental conditions. Pose estimation was performed using the newly developed You Only Live Once (YOLO) Pose v8 algorithm, tailored for miners in underground settings. For PPE detection—specifically helmets, safety vests, gloves, and boots—we employed and compared several models including YOLO v8, v9, v10, Real-Time Detection Transformer (RT-DETR), and YOLO World. PPE compliance was then assessed by integrating pose estimation keypoints to filter out false detections effectively. The integrated approach successfully identified and verified the use of PPE with high accuracy. Comparative analysis showed that newer versions of YOLO alongside RT-DETR provided substantial improvements in detection rates under varied lighting and spatial conditions prevalent in underground mines. The findings demonstrate that combining pose estimation with advanced object detection frameworks significantly enhances PPE compliance monitoring in underground mines. This dual approach reduces the risk of false positives and ensures a more reliable safety system. By improving the accuracy and reliability of safety equipment detection in one of the most challenging mining environments, this research contributes to reducing occupational hazards and enhancing miner safety. The implications extend to other high-risk industries where environmental conditions complicate safety monitoring.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"12 ","pages":"145721-145739"},"PeriodicalIF":3.4,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10704570","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Novel Impedance Estimation Method for Determining Voltage Unbalance Contributions Based on an Optimization Algorithm","authors":"Vinícius Henrique Farias Brito;José Carlos de Oliveira;Raquel Cristina Filiagi Gregory","doi":"10.1109/ACCESS.2024.3473790","DOIUrl":"https://doi.org/10.1109/ACCESS.2024.3473790","url":null,"abstract":"The problem of “unbalance responsibility-sharing” is a matter of great concern for utility and consumer entities due to the increase in voltage unbalances, especially in electrical distribution systems. This issue arises from the need to determine the individual contributions of the utility and the consumer to the total unbalance at the point of common coupling between the entities. In the literature, the Superposition Method stands out as an effective approach to solving this problem. However, this procedure requires utility and consumer negative-sequence impedances, which are difficult to obtain in real-life scenarios. There is a variety of impedance estimation methods to overcome this issue, with emphasis on non-invasive methods. According to the literature, some of these procedures have practical and accuracy limitations. Therefore, this paper proposes a novel non-invasive impedance estimation method, termed the Correlation Minimization Method (CMM), which is based, essentially, on an optimization algorithm. In addition, computational simulations and field tests were carried out to evaluate the performance of the proposed method in comparison with existing approaches. The results show that the proposed method performed satisfactorily, even in the most adverse situations.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"12 ","pages":"145944-145954"},"PeriodicalIF":3.4,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10704613","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DRL-Enabled Hierarchical Federated Learning Optimization for Data Heterogeneity Management in Multi-Access Edge Computing","authors":"Suhyun Cho;Sunhwan Lim;Joohyung Lee","doi":"10.1109/ACCESS.2024.3473008","DOIUrl":"https://doi.org/10.1109/ACCESS.2024.3473008","url":null,"abstract":"This paper designs a novel Hierarchical Federated Learning (HFL) management scheme, enabled by deep reinforcement learning (DRL), for multi-access edge computing (MEC) environments to accelerate convergence. To do this, the proposed scheme controls the number of local updates performed by mobile devices (MDs) and the number of intermediate aggregations at the MEC server before data is transmitted to the cloud for global aggregation. This optimization aims to i) mitigate the straggler effect by balancing training times between MEC and cloud servers, and ii) reduce the risk of overfitting by avoiding excessive reliance on faster MDs. Additionally, to improve the efficiency of DRL, Bayesian optimization is employed to initialize action values, thereby avoiding inefficient exploration of actions. Extensive simulations demonstrate that our proposed scheme outperforms various benchmarks in terms of test accuracy and training time.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"12 ","pages":"147209-147219"},"PeriodicalIF":3.4,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10704611","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142450900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Sensitivity-Based Algorithm Approach in Reconstructing Images in Electrical Impedance Tomography","authors":"Rose Anne D. Alas;Arrianne Crystal T. Velasco","doi":"10.1109/ACCESS.2024.3473616","DOIUrl":"https://doi.org/10.1109/ACCESS.2024.3473616","url":null,"abstract":"Electrical impedance tomography (EIT) is a medical imaging technique used to reconstruct images inside the domain of interest. EIT collects data on the boundary of the domain to infer the conductivity distribution inside the domain. The conductivity distribution will then be used to produce a tomographic image of the inside of the domain. This paper aims to recover geometric properties of a spherical perturbation in the conductivity inside a domain using sensitivity values of the electric potential on the boundary of the domain. The continuum model for EIT is first considered, as it holds more boundary information compared to other models of EIT. A change on the conductivity inside the domain is applied, and the impact on the electric potential is studied. The inverse EIT problem is then solved by formulating relations between the sensitivity values on the boundary and the geometric properties of the spherical perturbation: the radius and the projection onto the boundary and depth of its center. A reconstruction method using these relations is proposed and the method is examined by performing numerical simulations on different domains to model the head and the thorax. Lastly, the proposed method is applied to the complete electrode model of the EIT problem to analyze the performance of the method when the boundary data is limited on the electrodes.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"12 ","pages":"146560-146574"},"PeriodicalIF":3.4,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10704621","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142447035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Knee Osteoarthritis Diagnosis With Unimodal and Multi-Modal Neural Networks: Data From the Osteoarthritis Initiative","authors":"Xin Yu Teh;Pauline Shan Qing Yeoh;Tao Wang;Xiang Wu;Khairunnisa Hasikin;Khin Wee Lai","doi":"10.1109/ACCESS.2024.3472654","DOIUrl":"https://doi.org/10.1109/ACCESS.2024.3472654","url":null,"abstract":"Knee osteoarthritis (OA) is a prevalent musculoskeletal condition affecting millions worldwide, posing significant health and economic burdens. Characterized by the degeneration of joint cartilage, the progression of knee OA varies significantly among individuals, making its prediction a complex issue. Previous studies on automated knee OA diagnosis have primarily relied on unimodal data, often overlooking the valuable information present in multi-modal data. Multi-modal learning, which integrates information from various modalities, is increasingly recognized for its potential to enhance diagnostic performance in medical applications. However, such models incur a higher computational load due to the additional data required. This research investigates the feasibility of multi-modal neural networks in knee OA diagnosis by integrating structural demographic data with unstructured imaging data. Three deep learning unimodal models (InceptionV3, DIKO, and EfficientNetv2) were transformed into multi-modal architectures (MF_InceptionNet, MF_DIKO, and MF_Eff) to compare their diagnostic capabilities. The proposed multi-modal models share a common architecture, with unimodal models acting as image feature extraction backbones and separate embedding layers for demographic data. The image features and demographic embeddings are combined into a unified vector before classification. Extensive experiments were conducted to evaluate the performance of these models across different class categories and dataset sizes. MF_DIKO and InceptionV3 emerged as the best multi-modal and unimodal neural networks, respectively, with overall accuracies of 0.67 and 0.75 for 3-class severity classification. Contrary to existing literature, our findings reveal that unimodal neural networks using only imaging features outperform multi-modal networks, suggesting unimodal models might suffice in certain applications.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"12 ","pages":"146698-146717"},"PeriodicalIF":3.4,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10704620","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142447232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"HgbNet: Predicting Hemoglobin Level/Anemia Degree From Irregular EHR","authors":"Zhuo Zhi;Moe Elbadawi;Adam Daneshmend;Mine Orlu;Abdul Basit;Andreas Demosthenous;Miguel Rodrigues","doi":"10.1109/ACCESS.2024.3473693","DOIUrl":"https://doi.org/10.1109/ACCESS.2024.3473693","url":null,"abstract":"Predicting a patient’s hemoglobin level or degree of anemia using Electronic Health Records (EHRs) is a non-invasive and rapid approach. However, it presents challenges due to the irregular multivariate time series nature of EHRs, which often contain significant amounts of missing values and irregular time intervals. To address these issues, we introduce HgbNet, a model specifically designed to process irregular EHR data. HgbNet incorporates a NanDense layer with a missing indicator to handle missing values. Inspired by clinicians’ decision-making processes, the model employs three kinds of attention mechanisms to account for both local irregularity and global irregularity. We evaluate the proposed method using two real-world datasets across two use cases. HgbNet outperforms the best baseline results across all test scenarios, achieving an R2 score of \u0000<inline-formula> <tex-math>$0.867~pm $ </tex-math></inline-formula>\u0000 0.003 and \u0000<inline-formula> <tex-math>$0.861~pm $ </tex-math></inline-formula>\u0000 0.003 for hemoglobin level prediction, and an F1 score of \u0000<inline-formula> <tex-math>$0.855~pm $ </tex-math></inline-formula>\u0000 0.005 and \u0000<inline-formula> <tex-math>$0.843~pm $ </tex-math></inline-formula>\u0000 0.005 for anemia degree prediction under usecase 1 across two datasets. Additionally, we analyze the effect of the length of irregular time intervals on prediction performance and improve HgbNet’s performance at long intervals in usecase 2. These findings highlight the feasibility of estimating hemoglobin levels and anemia degree from EHR data, positioning HgbNet as an effective non-invasive anemia diagnosis solution that could potentially enhance the quality of life for millions of affected individuals worldwide.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"12 ","pages":"144837-144854"},"PeriodicalIF":3.4,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10704680","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408858","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Algorithms for Routing and Spectrum Allocation in Elastic Optical Networks: A Taxonomy","authors":"César F. Bogado-Martínez;Diego P. Pinto-Roa;Benjamín Barán","doi":"10.1109/ACCESS.2024.3472651","DOIUrl":"https://doi.org/10.1109/ACCESS.2024.3472651","url":null,"abstract":"Elastic Optical Networks (EONs) increase the transport capacity of standard optical networks, and have been proposed as a short-term solution to satisfy the dynamic demands of service quality requirements. To this end, the development of algorithms to better facilitate Routing and Spectrum Allocation (RSA) is envisaged to have a critical impact on the performance of EON. Given the abundance of RSA algorithms, this study presents the unique challenge of organizing and classifying them meaningfully to understand and select the most suitable approach for the corresponding niche service quality requirements. This study proposes a novel taxonomy structure for grouping RSA algorithms based on the following criteria: (1) resource assignment policies, (2) flexibility type, (3) traffic type, (4) optimization approaches, (5) number of objective functions, and (6) problem separability. Finally, the contributions of this study are twofold: it presents a state-of-the-art taxonomy framework that organizes existing published works based on a set of predetermined criteria, and explores research opportunities involving RSA algorithms to realize the full potential of EONs in telecommunications.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"12 ","pages":"145619-145636"},"PeriodicalIF":3.4,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10704675","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"STPAS: Spatial-Temporal Filtering-Based Perception and Analysis System for Precision Aerial Spraying","authors":"Jaehwi Seol;Changjo Kim;Eunji Ju;Hyoung Il Son","doi":"10.1109/ACCESS.2024.3473538","DOIUrl":"https://doi.org/10.1109/ACCESS.2024.3473538","url":null,"abstract":"This study proposes a perception and analysis method for precise aerial spraying based on three-dimensional (3D) deep learning. Point cloud data for water droplets are acquired using 3D LiDAR, and the PointNet++ deep learning model is trained to classify and segment the spray pattern. Spatial-temporal data are processed for the segmented point cloud data. The spray from each nozzle is clustered through spatial data processing, and clustering is based on this information. This approach allows each nozzle to be distinguished and mapped. Processing temporal data compensates for unsensed or noisy data points and predicts the water droplet trajectories, enhancing the spray data. This method more accurately measures the shape of water droplets. Experiments altering the flight conditions of unmanned aerial vehicles (UAVs) were conducted to assess the proposed framework, demonstrating that processing is feasible in the onboard system of the UAV. The proposed method has potential application in control systems for precise spraying in the future.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"12 ","pages":"145997-146008"},"PeriodicalIF":3.4,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10704678","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408971","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing EEG Signal Classification With a Novel Random Subset Channel Selection Approach: Applications in Taste, Odor, and Motor Imagery Analysis","authors":"Amir Naser;Önder Aydemir","doi":"10.1109/ACCESS.2024.3473810","DOIUrl":"https://doi.org/10.1109/ACCESS.2024.3473810","url":null,"abstract":"This study uses various datasets to evaluate the performance of feature extraction and classification methods for EEG signals. The EEG signals analyzed in this research are based on taste, odor, and motor imagery, employing novel methods to interpret these complex signals accurately. Three datasets were used in this study: taste-based EEG signals from 10 healthy subjects, odor-based EEG signals from 5 subjects, and motor imagery EEG data from 29 subjects. Feature extraction methods such as Hilbert Transform (HT) for taste, Wavelet Packet Decomposition (WPD) for odor, and HT for motor imagery were applied. Sequential forward and backward search methods were compared with a newly proposed Random Subset Channel Selection (RSCS) method to determine the most effective channels. For the taste dataset, using the RSCS method, an average classification accuracy of 82% was achieved with a significant reduction in the number of channels, demonstrating a 37.9% improvement over using all channels. In the odor dataset, the proposed method achieved an average accuracy of 99.28% for open-nose conditions and 97.49% for closed-nose conditions, with an 86.3% improvement in classification accuracy and an 89.09% reduction in computational complexity. The RSCS method achieved an average accuracy of 81.56% for the motor imagery dataset, showing superior performance compared to sequential methods. The proposed RSCS method outperforms traditional sequential methods by improving classification accuracy and reducing computational complexity across different types of EEG datasets. This method holds promise for enhancing BCI system performance, significantly improving the detection and early diagnosis of neurological conditions.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"12 ","pages":"145608-145618"},"PeriodicalIF":3.4,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10704658","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FranSys—A Fast Non-Autoregressive Recurrent Neural Network for Multi-Step Ahead Prediction","authors":"Daniel O. M. Weber;Clemens Gühmann;Thomas Seel","doi":"10.1109/ACCESS.2024.3473014","DOIUrl":"https://doi.org/10.1109/ACCESS.2024.3473014","url":null,"abstract":"Neural network-based nonlinear system identification is crucial for various multi-step ahead prediction tasks, including model predictive control and digital twins. These applications demand models that are not only accurate but also efficient in training and deployment. While current state-of-the-art neural network-based methods can identify accurate models, they often become prohibitively slow when scaled to achieve high accuracy, limiting their use in resource-constrained or time-critical applications. We propose FranSys, a Fast recurrent neural network-based method for multi-step ahead prediction in non-autoregressive System Identification. FranSys comprises three key innovations: 1) the first non-autoregressive RNN model structure for multi-step ahead prediction that enables much faster training and inference compared to autoregressive RNNs by separating state estimation and prediction into two specialized sub-models, 2) a state distribution alignment training technique that enhances generalizability and 3) a prediction horizon scheduling method that accelerates training by progressively increasing the prediction horizon. We evaluate FranSys on three publicly available benchmark datasets representing diverse systems, comparing its speed and accuracy against state-of-the-art RNN-based multi-step ahead prediction methods. The evaluation includes various prediction horizons, model sizes, and hyperparameter optimization settings, using both our own implementations and those from related work. Results demonstrate that FranSys is 10 to 100 times faster in training and inference with the same and often higher accuracy on test data than state-of-the-art RNN-based multi-step ahead prediction methods, particularly with long prediction horizons. This substantial speed improvement enables the application of larger neural network-based models with longer prediction horizons on resource-constrained systems in time-critical tasks, such as model predictive control and online learning of digital twins. The code of FranSys is publicly available.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"12 ","pages":"145130-145147"},"PeriodicalIF":3.4,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10704623","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142409000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}