IEEE Journal of Selected Areas in Sensors最新文献

{"title":"A Convolutional Transformer Network for Anomaly Detection in Wireless Body Area Networks","authors":"Granth Bagadia;Shreea Bose;Chittaranjan Hota","doi":"10.1109/JSAS.2025.3572860","DOIUrl":"https://doi.org/10.1109/JSAS.2025.3572860","url":null,"abstract":"The wireless body area network (WBAN) integrates wearable devices and Internet of Things (IoT) sensors in the human body, enabling real-time monitoring of physiological parameters for improved healthcare. Ensuring accurate and reliable data transmission is crucial to maintain system performance. To address this, we propose a novel anomaly detection framework that uses a two-stage convolutional transformer network (ConvTransformer) architecture, specifically designed to handle both point anomalies and contextual anomalies. In the first stage, we trained a ConvTransformer model to distinguish between human data and point anomalies. These out-of-range values may indicate abrupt irregularities in individual sensor readings. After identifying and filtering out point anomalies, the second stage applies another ConvTransformer model to the remaining data to detect contextual anomalies. These are more complex and involve simultaneous irregularities in multiple physiological signals (for example, heart rate, body temperature, and electrocardiogram), which may suggest more significant health concerns. This two-stage detection approach ensures more precise and robust anomaly detection. The first model achieved 99.66% accuracy in detecting point anomalies, while the second model reached nearly 99.76% accuracy in identifying contextual anomalies, showcasing the efficiency of the ConvTransformer architecture in WBAN applications for detecting anomalies.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"2 ","pages":"185-198"},"PeriodicalIF":0.0,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11010886","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Electroencephalogram and Event-Related Potential in Mild Cognitive Impairment: Recent Developments in Signal Processing, Machine Learning, and Deep Learning","authors":"Hamed Azami;Mina Mirjalili;Tarek K. Rajji;Chien-Te Wu;Anne Humeau-Heurtier;Tzyy-Ping Jung;Chun-Shu Wei;Thanh-Tung Trinh;Yi-Hung Liu","doi":"10.1109/JSAS.2025.3552546","DOIUrl":"https://doi.org/10.1109/JSAS.2025.3552546","url":null,"abstract":"Mild cognitive impairment (MCI) is an early stage of non-age-related cognitive decline with an increased risk of progressing to dementia. Early detection of MCI is essential for implementing preventative strategies that can delay or prevent the onset of dementia, ultimately improving patient outcomes and reducing healthcare costs. Electroencephalograms (EEGs) and event-related potentials (ERPs) have shown significant promise in detecting MCI due to their affordability, real-time monitoring capabilities, and noninvasiveness. EEG provides continuous brain activity data, while ERPs offer insights into specific cognitive processes by analyzing brain responses to stimuli. These methods can complement each other in MCI diagnosis by providing a comprehensive view of overall brain function and detailed information on specific cognitive processes. However, EEG and ERP are susceptible to noise and interindividual variability, which can hinder their reliability. In addition, applying machine learning models on EEG or ERP for MCI detection presents challenges such as the risk of overfitting and difficulties in interpreting the underlying decision-making process. This review emphasizes recent advancements in signal processing and feature extraction methods applied to EEG and ERP data and explores the use of machine learning and deep learning techniques to enhance diagnostic accuracy and interpretative depth. By integrating these methodologies, the review highlights how EEG and ERP can contribute to a more effective understanding and monitoring of cognitive changes associated with MCI, underscoring the importance of early diagnosis for timely intervention and improved patient care. Finally, the review focuses on future research directions, including the development of advanced analytical techniques and multimodal integration approaches involving EEG and ERP to further improve diagnostic accuracy and clinical application.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"2 ","pages":"162-184"},"PeriodicalIF":0.0,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10930754","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143839832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advanced Sensor Configurations for High-Speed Autonomous Racing Vehicles","authors":"Manuel Mar;Vishnu Pandi Chellapandi;Liangqi Yuan;Ziran Wang;Eric Dietz","doi":"10.1109/JSAS.2025.3547283","DOIUrl":"https://doi.org/10.1109/JSAS.2025.3547283","url":null,"abstract":"Autonomous racing is a dynamic and challenging domain that not only pushes the limits of technology but also plays a crucial role in the advancement and fostering of greater acceptance of autonomous systems. This article thoroughly analyzes challenges and advances in the design and performance of autonomous racing vehicles, focusing on Roborace and the Indy Autonomous Challenge (IAC). This review compares sensor configurations, artificial intelligence techniques, architectural nuances, and performance metrics on these cutting-edge platforms. In Roborace, the evolution from Devbot 1.0 to Robocar and Devbot 2.0 is detailed, revealing insights into sensor configurations and performance outcomes. The examination extends to the IAC, which is dedicated to high-speed self-driving vehicles and emphasizes development trajectories and sensor adaptations. By reviewing these platforms, the analysis provides a valuable comparison of autonomous driving racing systems and sensor suites, contributing to a broader understanding of sensor architectures and the challenges faced.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"2 ","pages":"136-149"},"PeriodicalIF":0.0,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10909132","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143845465","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sub-1 GHz Indoor RSSI-Based Localization: An Experimental Evaluation of Trilateration, Multilateration, and Machine Learning Fingerprinting Methods","authors":"Ben McPartlin;Mahmoud Wagih","doi":"10.1109/JSAS.2025.3545784","DOIUrl":"https://doi.org/10.1109/JSAS.2025.3545784","url":null,"abstract":"As wireless radiofrequency-based localization techniques continue to attract interest, a plethora of approaches including received signal strength indicator (RSSI) trilateration and multilateration, phase, time-of-arrival, and machine learning models have been explored for indoor localization. However, there has been no comprehensive experimental investigations that compared the accuracy of these methods in a practical Internet of Things (IoT) wireless sensor network. Herein, we present a holistic evaluation of localization techniques in an indoor smart home environment, based on off-the-shelf 868/915 MHz transceivers. First, the hardware limitations, such as the antenna and RSSI radiation patterns and the effects of multipath reflections are experimentally investigated, identifying the optimal node placement. A practical RSSI recording and forwarding scheme is proposed and implemented using microcontroller units, showing a frugal approach for joint sensing and communication, with under 420 ms cycle time. Using this testbed, we compare multilateration approaches for three and four receivers, in both line-of-sight (LOS) and non-LOS links, achieving between 46% and 89% room prediction accuracy, with a minimum mean error of 1.49 m. A machine learning-based approach, using multinomial logistic regression, is then reported with a peak room classification accuracy of 97%–100%, for 25–30 RSSI points. A comparison with state-of-the-art implementations is presented showing a high room localization accuracy at a low hardware complexity, demonstrating the feasibility of RSSI-only localization in resource-constrained IoT networks.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"2 ","pages":"121-135"},"PeriodicalIF":0.0,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10904145","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143761514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Scalable and Reliable Data Framework for Sensor-Enabled Virtual Power Plant Digital Twin","authors":"Amritpal Singh;Umit Demirbaga;Gagangeet Singh Aujla;Anish Jindal;Hongjian Sun;Jing Jiang","doi":"10.1109/JSAS.2025.3540956","DOIUrl":"https://doi.org/10.1109/JSAS.2025.3540956","url":null,"abstract":"Sensor-enabled distributed energy resources (DERs) provide various advantages, including a lower carbon footprint, yet effective management of millions of DERs is still an issue. Virtual power plants (VPP) can integrate several DERs into a unified operational digital twin to enable real-time monitoring, analysis, and control. VPP may utilize advanced solutions to improve operational efficiency by combining substantial measurement data from DERs. However, effectively managing the quantity and complexity of data flows, whether streaming data or high-impact low-frequency data, is essential in maintaining the performance of DERs at sustained levels. The vast amounts of diverse data generated from various DERs pose significant challenges for storage, processing, and resource management. This article proposes a comprehensive framework that employs a distributed big data cluster to ensure scalable and reliable data storage and utilizes a robust message broker system for efficient data queuing. In addition, we present innovative load-balancing strategies within the VPP digital twin system. A decision tree algorithm is implemented to calculate the forthcoming workload collected by various deployed sensors at various DERs. The required resources are identified per workload, and the numbers are forwarded to the orchestrator. The orchestrator scales up and down resources based on resource utilization suggested by the decision tree algorithm when the resources or nodes are insufficient to handle the sensor data, optimizing the utilization of computing resources. The framework also features a failure detection component that performs root cause analysis to provide actionable insights for system optimization. Experimental results show that this framework ensures high efficiency, reliability, and real-time operational capability in VPP digital twin by addressing critical challenges in data storage, streaming data analysis, and load balancing.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"2 ","pages":"108-120"},"PeriodicalIF":0.0,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10896574","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143698265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Survey on Digital Twins: Enabling Technologies, Use Cases, Application, Open Issues, and More","authors":"Vikas Hassija;Vinay Chamola;Rajdipta De;Soham Das;Arjab Chakrabarti;Kuldip Singh Sangwan;Amit Pandey","doi":"10.1109/JSAS.2024.3523856","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3523856","url":null,"abstract":"Digital Twins, sophisticated digital replicas of physical entities, have been gaining significant attention, especially after NASA's endorsement, and are poised to revolutionize numerous fields, such as medicine and construction. These advanced models offer dynamic, real-time simulations, leveraging enabling technologies, such as artificial intelligence, machine learning, IoT, cloud computing, and Big Data analytics to enhance their functionality and applicability. In the medical field, Digital Twins facilitate personalized treatment plans and predictive maintenance of medical equipment by simulating human organs with precision. In construction, they enable efficient building design and urban planning, optimizing resource use, and reducing costs through predictive maintenance. Startups are innovatively employing Digital Twins in various sectors, from smart cities—where they optimize traffic flow, energy consumption, and waste management—to industrial machinery, ensuring predictive maintenance and minimizing downtime. This survey delves into the diverse use cases, market potential, and challenges of Digital Twins, such as data security and interoperability, while emphasizing their transformative impact on industries. The future prospects are promising, with continuous advancements in AI, ML, IoT, and cloud computing driving further expansion and application of Digital Twin technologies.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"2 ","pages":"84-107"},"PeriodicalIF":0.0,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10818423","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FallAware: An Explainable Learning Approach to Robust Fall Detection With WiFi","authors":"Sai Deepika Regani;Beibei Wang;Yuqian Hu;Guozhen Zhu;K. J. Ray Liu","doi":"10.1109/JSAS.2024.3520517","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3520517","url":null,"abstract":"Indoor falls have proved fatal to many people due to a lack of timely assistance. Existing approaches for fall detection using cameras and wearable devices intrude on privacy and cause inconvenience. Passive sensing approaches using radar have limited coverage and demand dense deployment. Current solutions using commercial off-the-shelf (COTS) WiFi devices are either environment-dependent or lack extensive testing in real environments to confidently assess false alarm rates. In this work, we propose a fusion approach to detect falls with COTS WiFi, where we leverage signal processing techniques to extract environment-independent features, and use a neural network to detect differentiating patterns in those features. We designed a lightweight long short-term memory-based neural network with only 21 k parameters that can easily be deployed on edge devices. We further provide a framework to explain the network's behavior that supports a calibration-free design. Our proposed <italic>FallAware</i> system's detection performance has been extensively tested on <inline-formula><tex-math>$sim$</tex-math></inline-formula>2400 falls gathered from over 25 volunteers in 5 different environments. In addition, we conducted long-term false alarm testing in 6 diverse environments for a total duration of 21 months. The results show that <italic>FallAware</i> can detect falls with an average detection rate of 94.1% in unseen environments with <inline-formula><tex-math>$&lt; $</tex-math></inline-formula>5 false alarms per month in single-person occupancy homes.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"2 ","pages":"71-83"},"PeriodicalIF":0.0,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10810750","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Nonparametric Multitarget Data Association and Tracking for Multistatic Radars","authors":"S. Sruti;K. Giridhar","doi":"10.1109/JSAS.2024.3517513","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3517513","url":null,"abstract":"Multistatic radar systems provide better detection performance for stealth airborne platforms and are resilient to single-point failures. However, when multiple targets are present over the radar surveillance region, incorrect target associations to the measurements could create ghost targets. Computationally efficient and accurate de-ghosting and tracking multiple targets are critical tasks in real-time distributed radar systems. By exploiting the geometry of the measurement model in the association process, we propose a novel and efficient data association approach followed by a tracking algorithm in this work. It utilizes the time-of-arrival and bistatic Doppler frequency measurements of the targets with respect to different transmitter–receiver pairs to accurately determine and track the 3-D positions and velocities of the targets. The proposed approach is nonparametric as it does not need any assumption on the initial states or the number of targets and their motion models, but only uses the knowledge of the geometry of the terrestrial radar sensors. This nonparametric data association and tracking (NPDAT) algorithm is tested with multiple targets in two significant scenarios. First, all the targets are simultaneously present in the region, and then, targets arrive and depart the region based on a random arrival pattern. Our approach precisely tracks targets even during crossover and also tracks fast-maneuvering targets. This NPDAT algorithm is compared with popular existing methods and is shown to exhibit superior performance in estimation accuracy and maneuvering target tracking ability, even while enjoying a significantly lower time and implementation complexity.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"2 ","pages":"28-39"},"PeriodicalIF":0.0,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10803016","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142912561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SrcSense: Robust WiFi-Based Motion Source Recognition via Signal-Informed Deep Learning","authors":"Guozhen Zhu;Beibei Wang;Weihang Gao;Yuqian Hu;Chenshu Wu;K. J. Ray Liu","doi":"10.1109/JSAS.2024.3517514","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3517514","url":null,"abstract":"As WiFi has become a ubiquitous medium for communication, its role in sensing applications has expanded. However, the current WiFi sensing applications are limited by their assumption that any detected motion signifies human activity, overlooking the potential impact of nonhuman subjects. Existing attempts to recognize the interference from nonhuman motion impose stringent requirements regarding device positioning, data quality, environmental complexity, and nonhuman subject categories. In this study, we design a robust deep learning framework, SrcSense (“<bold>S</b>ou<bold>rc</b>e <bold>Sense</b>”), to recognize the motion source with WiFi signals through the wall. SrcSense extracts environment-independent features from single-link WiFi. We investigate the performance of popular deep neural networks and explore the efficacy of transferring pretrained models to WiFi sensing tasks. We implement SrcSense and evaluate the performance in five real-world complex environments with commodity WiFi devices. With a challenging dataset considering large pets, diverse human activities and multiple subjects coexisting cases, SrcSense achieves an average validation accuracy of 95.84% across five distinct environments and an average testing accuracy of 91.71% in unseen environments without further model training or parameter tuning. By accumulating 20 s of WiFi data, SrcSense can achieve an elevated recognition accuracy of 99.77% with ResNet-50. These results underline the robustness of our approach and its readiness for integration into ubiquitous intelligent Internet of Things (IoT) systems and applications.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"2 ","pages":"40-53"},"PeriodicalIF":0.0,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10803907","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142975940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Comprehensive Planning Framework for Connected Elevated LiDAR Sensors","authors":"Nawfal Guefrachi;Michael C. Lucic;Mohammad Yassen;Hakim Ghazzai;Ahmad Alsharoa","doi":"10.1109/JSAS.2024.3506478","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3506478","url":null,"abstract":"The combination of mobile edge computing (MEC) and sensing technologies, such as light detection and ranging (LiDAR), offers a viable path toward enhancing autonomous vehicle navigation and traffic monitoring in the context of intelligent transportation systems. In order to meet these needs, this article offers a methodology that investigates the use of elevated LiDAR (ELiD) and its integration with MEC. Our work focuses on two main challenges: optimizing the placement of ELiDs to ensure extensive urban coverage and minimizing network latency by efficiently routing data to MEC servers. By proposing a heuristic for real-time task allocation, we aim to enhance safety and operational efficiency in smart cities. Our findings show a modest optimality gap where the heuristic achieves a balance between computational efficiency and minimized cloud dependency, albeit at the cost of a marginally increased latency, highlighting the nuanced tradeoffs in edge-to-cloud task distribution for efficient LiDAR data processing in smart cities.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"2 ","pages":"54-70"},"PeriodicalIF":0.0,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10767283","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142975941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}