{"title":"SCL-Fall: Reliable Fall Detection Using mmWave Radar With Supervised Contrastive Learning","authors":"Wenxuan Li;Dongheng Zhang;Yadong Li;Ruiyuan Song;Yang Hu;Qibin Sun;Yan Chen","doi":"10.1109/JSAS.2024.3481205","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3481205","url":null,"abstract":"Fall is a severe health threat for elders' health care. While existing systems could achieve promising performance under specific scenarios, the required computing resources are usually not affordable, which is not applicable for real-time detection. In this article, we propose SCL-Fall, a real-time fall detection system using millimeter wave signal with supervised contrastive learning, which can achieve impressive accuracy with low computation complexity. Specifically, we first extract the signal variation corresponding to human activity with spatial–temporal processing. We incorporate reweighting and denoising techniques in the signal processing process. To enhance the system performance and robustness, we perform data augmentation by shifting, flipping, extracting, and interpolating the signal. Finally, we design a lightweight convolutional neural network to achieve real-time fall detection. Extensive experimental results demonstrate that the proposed system could achieve state-of-the-art performance with limited computation complexity.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"237-248"},"PeriodicalIF":0.0,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10716775","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600359","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":"Adjusting Detectable Velocity Range in FMCW Radar Systems Through Selective Sampling","authors":"Seungheon Kwak;Dahyun Jeon;Seongwook Lee","doi":"10.1109/JSAS.2024.3479110","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3479110","url":null,"abstract":"In a frequency-modulated continuous wave (FMCW) radar system, a series of waveforms with frequencies that increase linearly over time is transmitted. Once the transmitted signal reaches the target and returns, sampling is applied to the received signal, followed by the Fourier transform for distance and velocity estimation. In general, the detectable velocity range depends on the duration of a single waveform in the FMCW radar systems. If the target moves at a velocity that exceeds the detectable velocity of the radar, accurate velocity estimation is impossible due to Doppler ambiguity. Therefore, in this article, we propose a method for adjusting the detectable velocity range using a selective sampling method. In the proposed method, velocity ambiguity can be resolved by dual processing the samples obtained along the time axis at different rates. When the proposed method is applied to targets beyond the detectable velocity range of a conventional FMCW radar system, it effectively resolves Doppler ambiguity, enabling efficient velocity estimation. Our method has been verified to be well-applicable to data obtained from both simulation and real-world measurements. The comparison of the estimated velocity using our method with the ground truth in real-world measurements indicates an error of 0.07 m/s. We expect our proposed method to contribute to resolving the issue of velocity estimation ambiguity in the FMCW radar systems.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"249-260"},"PeriodicalIF":0.0,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10715571","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636298","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}
Guannan Liu;Rende Xie;Shih-Hau Fang;Hsiao-Chun Wu;Kun Yan
{"title":"Novel Human-Posture Recognition System Based on Advanced Graph Convolutional Network Using Skeletal Data","authors":"Guannan Liu;Rende Xie;Shih-Hau Fang;Hsiao-Chun Wu;Kun Yan","doi":"10.1109/JSAS.2024.3475355","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3475355","url":null,"abstract":"Automatic human-posture or human-activity recognition is a very important research problem nowadays. In this work, we propose a novel human-posture recognition approach using the 3-D skeletal data acquired by the Kinect V2 sensor. The acquired skeletal data are first segmented using our recently proposed automatic-segmentation technique and each segment can be labeled with a particular kind of human-posture. We propose four different types of node feature matrices extracted from the segmented skeletal data, which can serve as the input features to the advanced graph convolutional network for multiclassification. The realworld experimental results demonstrate that our proposed novel human-posture recognition system can reach a very high average classification-accuracy of 91.56%. In addition, the ablation study of the effect of skeletal-graph variations on the recognition performance is also presented. The average classification-accuracy further reaches up to 92.33% when four confusing joint-nodes are removed from the skeletal graph. Our proposed novel human-posture recognition approach can be very useful for practical applications, such as human-computer interface, intelligent healthcare, robotics, etc.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"224-236"},"PeriodicalIF":0.0,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10706704","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565489","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":"Joint Design of Receiving Filters and Complementary set of Sequences for ISAC With Sidelobe Level Suppression","authors":"Kecheng Zhang;Jun Wu;Fuwang Dong;Shihang Lu;Xiang Li;Weijie Yuan","doi":"10.1109/JSAS.2024.3462687","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3462687","url":null,"abstract":"The integrated sensing and communication (ISAC) waveform with a low sidelobe level on all delay indices is important for probing targets in the ISAC scenario. In this article, we consider the problem of jointly designing receiving filters and unimodular complementary sets of sequences (CSS) by minimizing the weighted sum of complementary integrated sidelobe level (CISL) and ISAC interference term at the communication receiver. We propose an optimization algorithm based on the majorization minimization scheme to solve the formulated nonconvex problem with a promised convergence. Fast Fourier transform (FFT) operations are performed in each iteration to improve the computation efficiency. Simulation results demonstrate that the crosscorrelation between the optimized receiving filters and CSS can achieve very low autocorrelation sidelobe levels on all time delay indices. The proposed algorithm has better convergence performance and the same computation complexity compared to the gradient descent algorithm.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"211-223"},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10681468","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142555091","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}
Mahmoud T. Kabir;Anna Gaydamaka;Abdullahi Mohammad;Dmitri Moltchanov;Bo Tan
{"title":"The Complete Pareto Points for In-Band Full Duplex Integrated Sensing and Communication Systems","authors":"Mahmoud T. Kabir;Anna Gaydamaka;Abdullahi Mohammad;Dmitri Moltchanov;Bo Tan","doi":"10.1109/JSAS.2024.3458888","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3458888","url":null,"abstract":"In this article, we investigate beamforming and transmit power optimization for in-band full-duplex integrated sensing and communications (FD-ISAC) systems. Our focus is on an FD-ISAC base station (BS) that simultaneously communicates with both downlink (DL) and uplink (UL) communication users (CUs) while detecting a target. Existing FD-ISAC studies typically: 1) consider either DL or UL users, not both, leading to additional interference; 2) neglect radar signal-to-interference-plus-noise ratio (SINR) as a performance metric; or 3) address single-objective optimization, focusing on either communication or radar performance. We formulate the problem as a weighted multiobjective optimization, balancing the achievable sum rate for CUs and the received radar SINR–two inherently conflicting objectives. To solve this nonconvex problem, we propose two solutions: A complexity-oriented design (COD) utilizing convex transformations and relaxations. And a performance-oriented design (POD) leveraging single-objective solutions to address the multiobjective formulation. Numerical evaluations demonstrate that both methods achieve comparable performance for CUs and radar. However, COD performs better for radar, while POD is superior for CUs, especially with a higher number of BS antennas. COD also has lower computational complexity. Our proposed FD-ISAC schemes outperform existing half-duplex (HD) ISAC schemes by approximately 6 dB for radar SINR and 8 bits/s/Hz for CU rate.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"198-210"},"PeriodicalIF":0.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10678876","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142555092","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}
Chenhao Luo;Aimin Tang;Fei Gao;Jianguo Liu;Xudong Wang
{"title":"Channel Modeling Framework for Both Communications and Bistatic Sensing Under 3GPP Standard","authors":"Chenhao Luo;Aimin Tang;Fei Gao;Jianguo Liu;Xudong Wang","doi":"10.1109/JSAS.2024.3451411","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3451411","url":null,"abstract":"Integrated sensing and communications (ISAC) is considered a promising technology in the beyond 5G/6G networks. The channel model is essential for an ISAC system to evaluate the communication and sensing performance. Most existing channel modeling studies focus on the monostatic ISAC channel. In this article, the channel modeling framework for bistatic ISAC is considered. The proposed channel modeling framework extends the current 3GPP channel modeling framework and ensures the compatibility with the communication channel model. To support the bistatic sensing function, several key features for sensing are added. First, more clusters with weaker power are generated and retained to characterize the potential sensing targets. Second, the target model can be either deterministic or statistical, based on different sensing scenarios. Furthermore, for the statistical case, different reflection models are employed in the generation of rays, taking into account spatial coherence. The effectiveness of the proposed bistatic ISAC channel model framework is validated by both ray tracing simulations and experiment studies. The compatibility with the 3GPP communication channel model and how to use this framework for sensing evaluation are also demonstrated.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"166-176"},"PeriodicalIF":0.0,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10659127","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142275014","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}
Zhe Chen;Chao Hu;Tianyue Zheng;Hangcheng Cao;Yanbing Yang;Yen Chu;Hongbo Jiang;Jun Luo
{"title":"ISAC-Fi: Enabling Full-Fledged Monostatic Sensing Over Wi-Fi Communication","authors":"Zhe Chen;Chao Hu;Tianyue Zheng;Hangcheng Cao;Yanbing Yang;Yen Chu;Hongbo Jiang;Jun Luo","doi":"10.1109/JSAS.2024.3443248","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3443248","url":null,"abstract":"Although Wi-Fi communications have been exploited for sensing purpose for over a decade, the \u0000<italic>bistatic</i>\u0000 or \u0000<italic>multistatic</i>\u0000 nature of Wi-Fi still poses multiple challenges, hampering real-life deployment of \u0000<italic>integrated sensing and communication</i>\u0000 (ISAC) within the Wi-Fi framework. In this article, we aim to redesign Wi-Fi so that \u0000<italic>monostatic</i>\u0000 sensing (mimicking radar) can be achieved over the multistatic communication infrastructure. Specifically, we propose, design, and implement ISAC-Fi as an ISAC-ready Wi-Fi prototype. We first present a novel self-interference cancellation scheme, in order to extract reflected (radio frequency) signals for sensing purpose in the face of transmissions. We then subtly revise the existing Wi-Fi framework so as to seamlessly operate monostatic sensing under the Wi-Fi communication standard. Finally, we offer two ISAC-Fi designs: 1) a Universal Software Radio Peripheral (USRP)-based design emulates a totally redesigned ISAC-Fi device and 2) another plug-and-play design allows for backward compatibility by attaching an extra module to an arbitrary Wi-Fi device. We perform extensive experiments to validate the efficacy of ISAC-Fi and also to demonstrate its superiority over existing Wi-Fi sensing proposals.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"139-153"},"PeriodicalIF":0.0,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10636274","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142143600","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":"UAV-Aided Localization and Communication: Joint Frame Structure, Beamwidth, and Power Allocation","authors":"Tianhao Liang;Tingting Zhang;Sheng Zhou;Wentao Liu;Dong Li;Qinyu Zhang","doi":"10.1109/JSAS.2024.3439272","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3439272","url":null,"abstract":"In wireless sensors networks, integrating localization and communication technique is crucial for efficient spectrum and hardware utilizations. In this article, we present a novel framework of the unmanned aerial vehicle (UAV)-aided localization and communication for ground node (GN), where the average spectral efficiency (SE) is used to reveal the intricate relationship among the frame structure, channel estimation error, and localization accuracy. In particular, we first derive the lower bounds for channel estimation error and the 3-D location prediction error, respectively. Leveraging these comprehensive analysis, we formulate a problem to maximize the average SE in the UAV–GN communication, where the frame structure, beamwidth, and power allocation can be jointly optimized. Subsequently, we propose an efficient iterative algorithm to address this nonconvex problem with closed-form expressions for beamwidth design and power allocation. Numerical results demonstrate that the performance of our proposed method can approach the upper bound with low complexity, and achieve over 70% performance gain compared with communication-only benchmarks. In addition, the analysis highlights the dominated impacts of the Doppler effect on the average SE.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"154-165"},"PeriodicalIF":0.0,"publicationDate":"2024-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10623800","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142169697","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":"Selecting and Evaluating Key MDS-UPDRS Activities Using Wearable Devices for Parkinson's Disease Self-Assessment","authors":"Yuting Zhao;Xulong Wang;Xiyang Peng;Ziheng Li;Fengtao Nan;Menghui Zhou;Jun Qi;Yun Yang;Zhong Zhao;Lida Xu;Po Yang","doi":"10.1109/JSAS.2024.3432714","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3432714","url":null,"abstract":"Parkinson's disease (PD) is a complex neurodegenerative disease in the elderly. This disease has no cure, but assessing these motor symptoms will help slow down that progression. Inertial sensing-based wearable devices, such as mobile phones and smartwatches have been widely employed to analyze the condition of PD patients. However, most studies purely focused on a single activity or symptom, which may ignore the correlation between activities and complementary characteristics. In this article, a novel technical pipeline is proposed for fine-grained classification of PD severity grades, which identify the most representative activities. We also propose a multiactivities combination scheme based on MDS-UPDRS. Utilizing this scheme, symptom-related and complementary activities are captured. We collected 85 PD subjects of different severity grades using a single wrist sensor. Our best results demonstrate F1 scores of 95.75\u0000<inline-formula><tex-math>$%$</tex-math></inline-formula>\u0000 for PD diagnosis and the fine-grained classification accuracy of PD disease grade is 82.41\u0000<inline-formula><tex-math>$%$</tex-math></inline-formula>\u0000 when combing four activities which improved by 11.02\u0000<inline-formula><tex-math>$%$</tex-math></inline-formula>\u0000 over a single activity. The experiments and theoretical analyses can serve as a useful foundation for future investigations into the effect of proposed solutions for PD diagnosis in uncontrolled environment setup, ultimately leading to self-PD assessment in the home environment.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"177-189"},"PeriodicalIF":0.0,"publicationDate":"2024-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10607854","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142408788","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}
Lifan Xu;Shunqiao Sun;Yimin D. Zhang;Athina P. Petropulu
{"title":"Reconfigurable Beamforming for Automotive Radar Sensing and Communication: A Deep Reinforcement Learning Approach","authors":"Lifan Xu;Shunqiao Sun;Yimin D. Zhang;Athina P. Petropulu","doi":"10.1109/JSAS.2024.3431462","DOIUrl":"https://doi.org/10.1109/JSAS.2024.3431462","url":null,"abstract":"In this article, we present a novel low-cost, dual-function radar-communication system that addresses dynamic environments such as those arising in automotive applications. The low cost is achieved by using a sparse phased arrays equipped with quantized double-phase shifters. The operation in dynamic environments is achieved via a deep reinforcement learning (DRL) approach that adaptively selects a small subset of transmit antennas and adjusts the phase shifters such that the transmitted energy is concentrated on the communication user and the target of interest, while the interference to other radars is reduced. The action space in the DRL approach increases fast with the number of antennas and the number of bits used in quantization, and as a result the complexity of the design problem grows exponentially. To tackle the resulting curse of dimensionality in the action space, we adopt the Wolpertinger strategy, which incorporates the nearest neighborhood component to project the vast action space into a smaller, more manageable space while maintaining the desired performance. Numerical results demonstrate the feasibility of our proposed method.","PeriodicalId":100622,"journal":{"name":"IEEE Journal of Selected Areas in Sensors","volume":"1 ","pages":"124-138"},"PeriodicalIF":0.0,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10605037","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141991486","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}