Pub Date : 2024-09-10DOI: 10.1109/LSENS.2024.3453558
V. Mallikarjuna Reddy M;P. S. Pandian;Karthick P A
Recent advancements and developments in the field of rehabi- litation lead to the invention of myoelectric control interfaces for patients with disabilities. However, decoding the motion intent from the surface electromyography (sEMG) signals of hamstrings and quadriceps is challenging due to its complex mechanics associated with weight bearing joints and stochastic, nonstationary, and multicomponent behavior of signals. In this letter, a novel approach is proposed for multiclass gait phase classification during level walking using temporal convolutional network (TCN) of sEMG signals. For this purpose, sEMG and inertial measurement unit (IMU) data were recorded concurrently from 20 healthy participants during level walking on treadmill at a speed of 2.5 km/h. sEMG were collected from the muscles, namely, rectus femoris (RF), vastus lateralis (VL), biceps femoris (BF), and semitendinosus (SEM). The IMU measurements of knee flexion/extension data are utilized for labeling the four phases of gait cycle. The root mean square of sEMG epochs is used to design the TCN framework. The results show that the proposed framework has the ability to differentiate the four classes of gait with a maximum accuracy of 86.00% using the myoelectric activity from all the four muscles. The information from the muscle pairs SEM and VL, and RF and BF, yielded the correct detection rate of 83.00% and 84.00%, respectively. In addition, the accuracy is also improved by 6% with TCN when we compare accuracy obtained through convolutional neural network architecture. The findings suggest that the proposed approach is effective in decoding the motion intent of lower limb muscles, which may lead to the development of precise movement control of lower limb prosthesis.
{"title":"Multiclass Gait Phase Classification From the Temporal Convolutional Network of Wireless Surface Electromyography Measurements","authors":"V. Mallikarjuna Reddy M;P. S. Pandian;Karthick P A","doi":"10.1109/LSENS.2024.3453558","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3453558","url":null,"abstract":"Recent advancements and developments in the field of rehabi- litation lead to the invention of myoelectric control interfaces for patients with disabilities. However, decoding the motion intent from the surface electromyography (sEMG) signals of hamstrings and quadriceps is challenging due to its complex mechanics associated with weight bearing joints and stochastic, nonstationary, and multicomponent behavior of signals. In this letter, a novel approach is proposed for multiclass gait phase classification during level walking using temporal convolutional network (TCN) of sEMG signals. For this purpose, sEMG and inertial measurement unit (IMU) data were recorded concurrently from 20 healthy participants during level walking on treadmill at a speed of 2.5 km/h. sEMG were collected from the muscles, namely, rectus femoris (RF), vastus lateralis (VL), biceps femoris (BF), and semitendinosus (SEM). The IMU measurements of knee flexion/extension data are utilized for labeling the four phases of gait cycle. The root mean square of sEMG epochs is used to design the TCN framework. The results show that the proposed framework has the ability to differentiate the four classes of gait with a maximum accuracy of 86.00% using the myoelectric activity from all the four muscles. The information from the muscle pairs SEM and VL, and RF and BF, yielded the correct detection rate of 83.00% and 84.00%, respectively. In addition, the accuracy is also improved by 6% with TCN when we compare accuracy obtained through convolutional neural network architecture. The findings suggest that the proposed approach is effective in decoding the motion intent of lower limb muscles, which may lead to the development of precise movement control of lower limb prosthesis.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142274963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Millimeter-wave (MMW) radar imaging technology has advanced significantly, providing high-resolution images crucial for various self-driving applications. This letter presents a novel approach for extracting road surfaces within a vehicle's lane using MMW radar imagery. First, the zonal connected area detection algorithm with sliding windows effectively detects feature points in the radar images. Second, the feature point classification algorithm, utilizing horizontal offset values, preliminarily identifies the feature points for the vehicle's lane boundary. Finally, the feature points are refined based on horizontal density, followed by boundary fitting to extract the road surface accurately. Experiments were conducted on three different scenarios and three distinct datasets to verify the effectiveness and generalization ability of the algorithm.
{"title":"Vehicle Road Lane Extraction Using Millimeter-Wave Radar Imagery for Self-Driving Applications","authors":"Weixue Liu;Yuexia Wang;Jiajia Shi;Quan Shi;Zhihuo Xu","doi":"10.1109/LSENS.2024.3456120","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3456120","url":null,"abstract":"Millimeter-wave (MMW) radar imaging technology has advanced significantly, providing high-resolution images crucial for various self-driving applications. This letter presents a novel approach for extracting road surfaces within a vehicle's lane using MMW radar imagery. First, the zonal connected area detection algorithm with sliding windows effectively detects feature points in the radar images. Second, the feature point classification algorithm, utilizing horizontal offset values, preliminarily identifies the feature points for the vehicle's lane boundary. Finally, the feature points are refined based on horizontal density, followed by boundary fitting to extract the road surface accurately. Experiments were conducted on three different scenarios and three distinct datasets to verify the effectiveness and generalization ability of the algorithm.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142235827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Internet of Things (IoT) relies on accurate distance estimation between devices, crucial for localization in various applications. While received signal strength indicator (RSSI)-based ranging lacks precision and time-of-flight narrow band systems perform poorly, phase-based ranging emerges as the preferred choice for Bluetooth Low Energy (BLE). Infineon's BLE prototype and its performance with a novel processing pipeline based on the minimum variance distortionless response (MVDR) algorithm are presented in this letter. Our pipeline comprises subalgorithms for preprocessing, scene identification, feature selection, feature engineering, and postprocessing. Preprocessing includes zero distance calibration, low-pass filtering, and time history averaging. Scene identification adapts parameters to environmental conditions. MVDR algorithms enable high-resolution feature transformation to project the residual phase correction term to the range domain. Postprocessing includes a tracker and data-dependent adaptation. Postprocessing in conjunction with feature selection tracks the line of sight path, minimizing distance jitter. Our proposed pipeline achieves a $text{90}{%}$