Article
Chemistry, Multidisciplinary
Xiaochao Dang, Yanhong Bai, Zhanjun Hao, Gaoyuan Liu
Summary: This research proposes a deep spatiotemporal gesture recognition method based on Wi-Fi signals. By selecting gesture-sensitive antennas, denoising and segmenting gesture data, and extracting temporal and spatial features, high recognition accuracy is achieved.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Information Systems
Yi Zhang, Yue Zheng, Guidong Zhang, Kun Qian, Chen Qian, Zheng Yang
Summary: This article presents GaitSense, a Wi-Fi-based human identification system, that overcomes the unrealistic assumptions of existing Wi-Fi sensing approaches and improves the system's applicability in new deployment scenarios through transfer learning and data augmentation techniques.
ACM TRANSACTIONS ON SENSOR NETWORKS
(2022)
Article
Computer Science, Information Systems
Lei Zhang, Wenyuan Huang, Xiaoxia Jia, Xiaojie Fan, Xiaochen Fan, Liangyi Gong, Wenyuan Tao, Shiwen Mao
Summary: This article introduces Wi-Gym, a gymnastics activity assessment system that utilizes Wi-Fi technology to compare the dynamic channel state information for evaluating the quality of training. Domain adaptation is also employed to adapt to environmental changes. Experimental results validate the effectiveness and robustness of the proposed approach.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Theory & Methods
Chen Chen, Gang Zhou, Youfang Lin
Summary: The rapid development of wireless sensing based on Channel State Information (CSI) with WiFi devices has been observed in recent years. WiFi sensing has shown great potential in detection, recognition, and estimation applications. However, the challenge of ensuring sensing performance when exposing a pre-trained system to new domains without data collection and system retraining remains. This survey provides a comprehensive review of cross-domain WiFi sensing research efforts, including mathematical models of CSI, impact of different domains on CSI, and various algorithms for achieving high sensing accuracy in new domains.
ACM COMPUTING SURVEYS
(2023)
Article
Computer Science, Information Systems
Weiping Ge, Yichen Tian, Xiulong Liu, Xinyu Tong, Wenyu Qu, Zhenzhe Zhong, Haojie Chen
Summary: This article introduces CrossTrack, a device-free cross-link tracking system that utilizes commodity Wi-Fi. By detecting cross-link behavior, identifying cross-link position, and optimizing trajectory, CrossTrack reduces tracking errors significantly.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Mir Kanon Ara Jannat, Md. Shafiqul Islam, Sung-Hyun Yang, Hui Liu
Summary: This paper analyzes the relationship between human activities and Wi-Fi CSI signals and proposes an adaptive antenna elimination algorithm to improve recognition efficiency. Experimental results show that the recognition system achieved high classification accuracy using machine learning algorithms on two online datasets.
Article
Engineering, Electrical & Electronic
Isack Bulugu
Summary: Gesture recognition has various applications in human-computer interaction. With the widespread deployment of Wi-Fi devices, thanks to wireless communication, the Internet of Things, and the availability of data on Wi-Fi channel state information (CSI), most existing studies in CSI gesture recognition focus solely on known domains. This paper proposes a CSI cross-domain gesture recognition approach utilizing 3D convolutional neural networks to achieve cross-scene gesture recognition by extracting domain-independent features and combining them with a 3D convolutional neural network learning model. Experimental results demonstrate high recognition accuracy in both known and unknown scenes.
SIGNAL IMAGE AND VIDEO PROCESSING
(2023)
Article
Chemistry, Analytical
Chendan Dou, Hao Huan
Summary: This study utilizes channel state information collected by Wi-Fi devices to monitor respiration rate, designing a complete system through time-frequency analysis and multipath decomposition techniques. Experimental results demonstrate the system's high-precision respiratory monitoring capability in various environments.
Article
Chemistry, Analytical
Carlos M. Mesa-Cantillo, David Sanchez-Rodriguez, Itziar Alonso-Gonzalez, Miguel A. Quintana-Suarez, Carlos Ley-Bosch, Jesus B. Alonso-Hernandez
Summary: Recently, there has been a development of applications and services that utilize indoor location of people for security, navigation, and location-based services. Wi-Fi networks are widely deployed and security systems are in high demand. This study proposes a methodology to detect human presence using channel state information (CSI) in wireless communication networks based on the 802.11n standard. The methodology achieves an average accuracy above 90%, as validated through experiments in different environments.
Article
Chemistry, Multidisciplinary
Yajun Zhang, Bo Yuan, Zhixiong Yang, Zijian Li, Xu Liu
Summary: This study presents an independent gesture recognition method that is not affected by the environment or the direction of gesture drawing. It utilizes channel state information (CSI) extracted from Wi-Fi signals to capture human body action information. Through preprocessing and feature extraction, the method achieves gesture recognition classification using weighted k-nearest neighbor (KNN) classification. Experimental results show high accuracy for the recognition of the same gesture by different users and different gestures by the same user in the same environment. The experiments also outperform other methods in recognition results.
APPLIED SCIENCES-BASEL
(2023)
Article
Chemistry, Analytical
Tao Li, Chenqi Shi, Peihao Li, Pengpeng Chen
Summary: This paper proposes a novel gesture recognition system based on a smartphone, which breaks the limitations of existing WiFi-based gesture recognition and uses multiple methods to improve recognition accuracy.
Article
Chemistry, Analytical
Junyan Li, Kang Yin, Chengpei Tang
Summary: The study introduces a data augmentation method called window slicing, which slices the original data to increase the size of the dataset and effectively improve the recognition accuracy, as demonstrated in experiments.
Article
Engineering, Electrical & Electronic
Xiaolong Yang, Quanchen Li, Mu Zhou, Jiacheng Wang
Summary: In this article, indoor device-free positioning and tracking technology based on channel state information (CSI) collected by the bcm4366 Wi-Fi chip is implemented. A phase detection and compensation method is used to calibrate phase ambiguity, and a 3-D beamspace matrix pencil (BMP) algorithm is proposed to estimate the angle of arrival (AoA), time of flight (ToF), and Doppler frequency shift (DFS) of dynamic targets. Passive localization is achieved based on joint multiparameters.
IEEE SENSORS JOURNAL
(2023)
Article
Computer Science, Information Systems
Jianfei Yang, Xinyan Chen, Han Zou, Dazhuo Wang, Lihua Xie
Summary: Wi-Fi sensing technology has been proven superior in smart homes due to its cost-effectiveness and privacy-preserving nature. This article introduces AutoFi, a Wi-Fi sensing model based on a novel geometric self-supervised learning algorithm, which effectively utilizes randomly captured low-quality CSI samples and achieves cross-task knowledge transfer.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Rui Peng, Yafei Tian, Shengqian Han
Summary: Wireless sensing-based hand gesture recognition is a promising method for human-machine interaction in future integrated sensing and communication systems. However, most existing works focus on single user scenarios, and the simultaneous movement of multiple users leads to interference and overlap of dynamic channel responses. This article proposes a spatial beamforming approach to mitigate the mutual influence of multiuser hand gestures. By utilizing a preamble gesture scheme and Doppler variation feature, the proposed method accurately estimates the spatial channel of dynamic reflections and verifies the channel response belonging to hand movement. Thorough analysis of inter-user interference under various conditions and prototype experiments using LTE signals demonstrate the effectiveness of the interference suppression approach.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Automation & Control Systems
Zhenyuan Zhang, Xiaojie Wang, Darong Huang, Xin Fang, Mu Zhou, Bo Mi
Summary: This article presents an integrated detection and tracking (iDT) method for multipedestrian trajectory tracking under low signal-to-noise ratio (SNR) conditions. By jointly addressing the detection and tracking, continuous and accurate detection and tracking are ensured in low SNR conditions. The Bayesian framework is tailored with a multipedestrian evolutionary indicator to track all targets simultaneously. Experimental results show that iDT has unique advantages in low-observable multipedestrian tracking compared to traditional methods.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Electrical & Electronic
Jiacheng Wang, Hongyang Du, Zengshan Tian, Dusit Niyato, Jiawen Kang, Xuemin Shen
Summary: This paper proposes a semantic transmission framework for transmitting sensing information from the physical world to Metaverse. By defining semantic bases and achieving semantic encoding of sensing data, the amount of transmitted data is significantly reduced. Experimental results show that the encoded data is about 27.87% of the original data, while maintaining sensing performance.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2023)
Editorial Material
Chemistry, Analytical
Ying-Ren Chien, Mu Zhou, Ao Peng, Ni Zhu, Joaquin Torres-Sospedra
Article
Chemistry, Multidisciplinary
Yannan Zhang, Mingchao Sun, Yueming Song, Chong Zhang, Miaolei Zhou
Summary: In this research, a Hammerstein model is developed to depict the rate-dependent hysteresis of Piezo-actuated stage (P-AS), and a hysteresis compensator based on the inverse Bouc-Wen model is designed to compensate for the static hysteresis of P-AS. An improved differential evolution algorithm and a least-squares algorithm are used for model identification. A hybrid adaptive control approach based on the hysteresis compensator is adopted to increase the control accuracy, and the stability of the closed-loop system is analyzed using Lyapunov stability theory. Experimental results confirm the effectiveness of the proposed control approach for accurate positioning of P-AS.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Xin Liu, Min Jia, Mu Zhou, Bin Wang, Tariq S. Durrani
Summary: The lack of spectrum resources has become a key technical bottleneck for the development of Industrial Internet of Things (IIoT), as the 2.4-GHz unlicensed frequency band it utilizes is heavily used by other communication systems. The proposed integrated cooperative spectrum sensing and access control model aims to improve the transmission performance of Cognitive IIoT (CIIoT) while ensuring a high detection probability and controlling interference to primary users (PU). The optimization problem is solved by jointly optimizing spectrum sensing and access control parameters, and a simultaneous CSS and access control model is also presented to increase communication time.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Engineering, Mechanical
Yewei Yu, Chen Zhang, Wenjing Cao, Xiaoliang Huang, Xiuyu Zhang, Miaolei Zhou
Summary: The magnetic shape memory alloy based actuator (MSMA-BA) is crucial for high-precision positioning systems due to its high precision, low energy consumption, and large stroke. However, the inherent hysteresis of the MSMA material significantly affects the positioning accuracy of the MSMA-BA. This study proposes a multi meta-model approach combining the nonlinear auto-regressive moving average with exogenous inputs (NARMAX) and Bouc-Wen (BW) models to describe the complex dynamic hysteresis of the MSMA-BA. The experiments conducted on the MSMA-BA demonstrate the validity of the proposed control scheme.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Telecommunications
Xin Liu, Zechen Liu, Mu Zhou
Summary: In this paper, a green multi-UAV assisted IoT system based on non-orthogonal multiple access (NOMA) is proposed to improve energy efficiency and fairness among UAVs. By optimizing communication scheduling, transmit power allocation, and UAV trajectory, the minimum energy efficiency of the UAVs is maximized.
IEEE TRANSACTIONS ON GREEN COMMUNICATIONS AND NETWORKING
(2023)
Article
Engineering, Electrical & Electronic
Xiaolong Yang, Quanchen Li, Mu Zhou, Jiacheng Wang
Summary: In this article, indoor device-free positioning and tracking technology based on channel state information (CSI) collected by the bcm4366 Wi-Fi chip is implemented. A phase detection and compensation method is used to calibrate phase ambiguity, and a 3-D beamspace matrix pencil (BMP) algorithm is proposed to estimate the angle of arrival (AoA), time of flight (ToF), and Doppler frequency shift (DFS) of dynamic targets. Passive localization is achieved based on joint multiparameters.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Yewei Yu, Chen Zhang, En Wang, Miaolei Zhou
Summary: In this study, a composite model combining an improved fractional-order Bouc-Wen model and a nonlinear auto-regressive moving average with exogenous inputs (NARMAX) model is proposed to describe the hysteresis in MSMA-based actuators. A neural network adaptive control method is used to improve the positioning accuracy of the actuator, considering the effect of time delay on the system performance. Experimental studies validate the effectiveness of the proposed modeling and control schemes.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2023)
Article
Automation & Control Systems
Chen Zhang, Yewei Yu, Miaolei Zhou
Summary: This study considers the problem of finite-time adaptive output feedback quantized control for nonstrict-feedback nonlinear systems with unknown hysteresis and time delays. An estimated inverse compensator (EIC) is constructed to compensate for the hysteresis, while a Lyapunov-Krasovskii functional is used to handle the uncertainties of time delays. However, applying the quantized signal directly to the hysteretic system leads to degraded system performance. To overcome this issue, a new composite quantizer is proposed, which consists of an adaptive state-estimation filter and a modified hysteretic quantizer. The former facilitates state approximation by incorporating feedback information, while the latter regulates the communication rate. With the proposed EIC-FPAQC scheme, the closed-loop systems achieve semiglobal practical finite-time stability, and the tracking error can be guaranteed within a predefined accuracy. Experimental results on a piezoelectric-driven micropositioning stage demonstrate the effectiveness of the proposed method.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2023)
Article
Environmental Sciences
Zuoliang Yin, Huaizhi Wen, Wei Nie, Mu Zhou
Summary: This paper proposes a method for indoor localization of mobile robots based on a depth camera. ORB feature points are extracted from images, feature matching is performed between adjacent frames, and the Iterative Closest Point (ICP) algorithm is used to estimate the camera's pose, achieving localization. Experimental results show that the average accuracy of the proposed algorithm is 0.027 m, meeting the needs of indoor localization for mobile robots.
Article
Computer Science, Information Systems
Qiaolin Pu, Xin Lan, Mu Zhou, Joseph Kee-Yin Ng, Yong Ma, Hengjie Xiang
Summary: This article addresses the indoor localization problem using compression sensing theory for sparse localization in WLANs. It proposes an adaptive clustering algorithm and an improved measurement matrix model to improve localization accuracy and reduce storage space.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Yong Wang, Huishi Xia, Mu Zhou, Liangbo Xie, Wei He
Summary: This article proposes a method for denoise and target recognition of entangled optical quantum imaging systems. The RestoreCGAN is designed to restore and reconstruct the missing edge contour structure of the target, and the TSFFCNet is designed to extract deep semantic features and shallow features for target recognition. Experimental results show that RestoreCGAN outperforms the state-of-the-art methods in terms of both peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). Moreover, the recognition accuracy of the RestoreCGAN in combination with the TSFFCNet reaches 97.42%. This proves that the deep-learning method is effective for denoise and target recognition of entangled optical quantum imaging systems.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Electrical & Electronic
Qiaolin Pu, Youkun Chen, Mu Zhou, Joseph Kee-Yin Ng, Jinyu Zhang
Summary: This article proposes an indoor Wi-Fi localization scheme by introducing improved contrastive learning and a parallel fusion network. The proposed scheme outperforms others and improves location accuracy by about 22%.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Electrical & Electronic
Mu Zhou, Qian Wang, Liangbo Xie, Yong Ma, Wei He
Summary: This study proposes a passive target positioning method based on entangled light quantum, which utilizes quantum entangled states to detect and localize targets, providing high accuracy and anti-interference positioning services. By converting the continuous light energy into the discrete photon number, calculating detection probabilities, and establishing a CFAR detection model, the proposed method achieves highly sensitive target detection and accurate positioning. This method demonstrates high detection probability and low positioning error.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)