Dengue viruses are currently one of the deadliest mosquito-borne infectious diseases; there is no effective treatment, and a vaccine for dengue fever is not yet available. Therefore, monitoring and preventing virus transmission is currently the most effective controlling method. This study focuses on environmental traces of dengue transmission, and a low-cost portable drone system for dengue virus inspection based on water sources is presented, which is equipped with a drone, a water collector, a microfluidic chip, and an electrochemical impedance converter using an Arduino development broad and an Analog Devices AD5934 chip. Water samples are carried back by a drone with a water collector, which can be measured and analyzed outdoors, that is not required to be brought back to the laboratory. The concentration of 10- and 20-μg/cc dengue nonstructural protein 1 can be identified by impedance magnitude in the microfluidic chip using the bead-based biomarker technology. The presented novel device using a drone-based collector with a low-cost electrochemical impedance sensor may have great potential for the creation of dengue maps, becoming a valuable technique that is beneficial to trace dengue transmission. In the future, it may quickly identify differences in impedance spectroscopy between numerous viruses for environmental investigation.
{"title":"Drone Inspection System Based on the Electrochemical Impedance Detector by Dengue NS1 Biomarkers in Water Environments","authors":"Sung-Lin Tsai;Jiunn-Jye Wey;Szu-Chia Lai;You-Qian Lin;Chiao-Jou Chang;Pao-Cheng Huang","doi":"10.1109/LSENS.2024.3449342","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3449342","url":null,"abstract":"Dengue viruses are currently one of the deadliest mosquito-borne infectious diseases; there is no effective treatment, and a vaccine for dengue fever is not yet available. Therefore, monitoring and preventing virus transmission is currently the most effective controlling method. This study focuses on environmental traces of dengue transmission, and a low-cost portable drone system for dengue virus inspection based on water sources is presented, which is equipped with a drone, a water collector, a microfluidic chip, and an electrochemical impedance converter using an Arduino development broad and an Analog Devices AD5934 chip. Water samples are carried back by a drone with a water collector, which can be measured and analyzed outdoors, that is not required to be brought back to the laboratory. The concentration of 10- and 20-μg/cc dengue nonstructural protein 1 can be identified by impedance magnitude in the microfluidic chip using the bead-based biomarker technology. The presented novel device using a drone-based collector with a low-cost electrochemical impedance sensor may have great potential for the creation of dengue maps, becoming a valuable technique that is beneficial to trace dengue transmission. In the future, it may quickly identify differences in impedance spectroscopy between numerous viruses for environmental investigation.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142137590","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}
In this letter, we present an automated signal quality-aware frequency demodulation (FD)-based electrocardiogram (ECG)-derived respiration rate (FD-ECG-derived RR) estimation method with reduced false alarms under noisy ECG signals, which are unavoidable in resting and ambulatory health monitoring applications. The proposed FD-ECG-derived RR estimation method includes three major steps of signal quality checking to discard noisy ECG signals, respiratory-induced frequency variation (RIFV) waveform extraction using a frequency demodulation envelope detector by determining peaks of the derivative ECG waveform using a simple R-peak detector, and respiration rate estimation using the Fourier magnitude spectrum of the extracted RIFV waveform. On the standard Capnobase and BIDMC databases, the proposed FD-ECG-derived RR estimation method provides promising results with mean absolute error values of 5.01 and 5.37 breaths/min, respectively. The signal quality-aware RR estimation method used can reduce false alarm rate of 84.85 ${%}$ by discarding noisy ECG signals with quality assessment accuracy of 85.25 ${%}$ . The proposed simplistic method having lightweight signal processing approaches makes it suitable for real-time health monitoring applications.
{"title":"Signal Quality-Aware Frequency Demodulation-Based ECG-Derived Respiration Rate Estimation Method With Reduced False Alarms","authors":"Aditya Nalwaya;M. Sabarimalai Manikandan;Ram Bilas Pachori","doi":"10.1109/LSENS.2024.3449328","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3449328","url":null,"abstract":"In this letter, we present an automated signal quality-aware frequency demodulation (FD)-based electrocardiogram (ECG)-derived respiration rate (FD-ECG-derived RR) estimation method with reduced false alarms under noisy ECG signals, which are unavoidable in resting and ambulatory health monitoring applications. The proposed FD-ECG-derived RR estimation method includes three major steps of signal quality checking to discard noisy ECG signals, respiratory-induced frequency variation (RIFV) waveform extraction using a frequency demodulation envelope detector by determining peaks of the derivative ECG waveform using a simple R-peak detector, and respiration rate estimation using the Fourier magnitude spectrum of the extracted RIFV waveform. On the standard Capnobase and BIDMC databases, the proposed FD-ECG-derived RR estimation method provides promising results with mean absolute error values of 5.01 and 5.37 breaths/min, respectively. The signal quality-aware RR estimation method used can reduce false alarm rate of 84.85\u0000<inline-formula><tex-math>${%}$</tex-math></inline-formula>\u0000 by discarding noisy ECG signals with quality assessment accuracy of 85.25\u0000<inline-formula><tex-math>${%}$</tex-math></inline-formula>\u0000. The proposed simplistic method having lightweight signal processing approaches makes it suitable for real-time health monitoring applications.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142143629","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}
Electromyogram (EMG) signals are recordings of the electrical activity in muscles, which are studied due to their informative nature regarding neuromuscular disorders. Analysis of EMG signals is invaluable for identifying various neuromuscular conditions. In this letter, an automatic singular spectrum analysis (Auto-SSA) and quantum convolutional neural network (QCNN)-based framework is proposed for the detection of amyotrophic lateral sclerosis (ALS) using EMG signals. The Auto-SSA effectively decomposes the EMG signals into reconstructed components, from which the particle swarm optimization extracts the most significant features. The QCNN classifies the extracted features for efficient ALS detection. The proposed framework outperforms the compared state-of-the-art ALS detection frameworks, achieving a testing accuracy of 98.50%. With the obtained performance, the proposed framework could be a valuable diagnostic tool for ALS neuromuscular conditions.
肌电图（EMG）信号是肌肉电活动的记录，由于其对神经肌肉疾病的信息量大，因此被广泛研究。肌电图信号分析对于识别各种神经肌肉疾病非常有价值。在这封信中，我们提出了一种基于自动奇异频谱分析（Auto-SSA）和量子卷积神经网络（QCNN）的框架，用于利用肌电图信号检测肌萎缩性脊髓侧索硬化症（ALS）。Auto-SSA 能有效地将肌电信号分解为重建分量，然后通过粒子群优化从中提取最重要的特征。QCNN 对提取的特征进行分类，从而实现高效的 ALS 检测。所提出的框架优于同类最先进的 ALS 检测框架，测试准确率达到 98.50%。鉴于所取得的性能，所提出的框架可以成为 ALS 神经肌肉病症的重要诊断工具。
{"title":"ALS Detection Framework Based on Automatic Singular Spectrum Analysis and Quantum Convolutional Neural Network From EMG Signals","authors":"Kiran Kumar Makam;Vivek Kumar Singh;Ram Bilas Pachori","doi":"10.1109/LSENS.2024.3449369","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3449369","url":null,"abstract":"Electromyogram (EMG) signals are recordings of the electrical activity in muscles, which are studied due to their informative nature regarding neuromuscular disorders. Analysis of EMG signals is invaluable for identifying various neuromuscular conditions. In this letter, an automatic singular spectrum analysis (Auto-SSA) and quantum convolutional neural network (QCNN)-based framework is proposed for the detection of amyotrophic lateral sclerosis (ALS) using EMG signals. The Auto-SSA effectively decomposes the EMG signals into reconstructed components, from which the particle swarm optimization extracts the most significant features. The QCNN classifies the extracted features for efficient ALS detection. The proposed framework outperforms the compared state-of-the-art ALS detection frameworks, achieving a testing accuracy of 98.50%. With the obtained performance, the proposed framework could be a valuable diagnostic tool for ALS neuromuscular conditions.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142143680","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}
Pub Date : 2024-08-26DOI: 10.1109/LSENS.2024.3450176
Asim Yousuf;Rehan Hafiz;Saqib Riaz;Muhammad Farooq;Kashif Riaz;Muhammad Mahboob Ur Rahman
This letter presents a novel method for inferior myocardial infarction (MI) detection using lead II of electrocardiogram (ECG). We evaluate our proposed method on a public dataset, namely, Physikalisch Technische Bundesanstalt (PTB) ECG dataset from PhysioNet. Under our proposed method, we first clean the noisy ECG signals using db4 wavelet, followed by an R-peak detection algorithm to segment the ECG signals into beats. We then translate the ECG timeseries dataset to an equivalent dataset of grayscale images using Gramian angular summation field (GASF) and Gramian angular difference field (GADF) operations. Subsequently, the grayscale images are fed into a custom 2-D convolutional neural network (CNN), which efficiently differentiates between a healthy subject and a subject with MI. Our proposed approach achieves an average classification accuracy of 99.68%, 99.80%, 99.82%, and 99.84% under GASF dataset with noise and baseline wander, GADF dataset with noise and baseline wander, GASF dataset with noise and baseline wander removed, and GADF dataset with noise and baseline wander removed, respectively. Most importantly, this work opens the floor for innovation in wearable devices to measure lead II ECG (e.g., by a smart watch worn on right wrist, along with a smart patch on left leg), in order to do accurate, real-time, and early detection of inferior wall MI.
{"title":"Inferior Myocardial Infarction Detection From Lead II of ECG: A Gramian Angular Field-Based 2D-CNN Approach","authors":"Asim Yousuf;Rehan Hafiz;Saqib Riaz;Muhammad Farooq;Kashif Riaz;Muhammad Mahboob Ur Rahman","doi":"10.1109/LSENS.2024.3450176","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3450176","url":null,"abstract":"This letter presents a novel method for inferior myocardial infarction (MI) detection using lead II of electrocardiogram (ECG). We evaluate our proposed method on a public dataset, namely, Physikalisch Technische Bundesanstalt (PTB) ECG dataset from PhysioNet. Under our proposed method, we first clean the noisy ECG signals using db4 wavelet, followed by an R-peak detection algorithm to segment the ECG signals into beats. We then translate the ECG timeseries dataset to an equivalent dataset of grayscale images using Gramian angular summation field (GASF) and Gramian angular difference field (GADF) operations. Subsequently, the grayscale images are fed into a custom 2-D convolutional neural network (CNN), which efficiently differentiates between a healthy subject and a subject with MI. Our proposed approach achieves an average classification accuracy of 99.68%, 99.80%, 99.82%, and 99.84% under GASF dataset with noise and baseline wander, GADF dataset with noise and baseline wander, GASF dataset with noise and baseline wander removed, and GADF dataset with noise and baseline wander removed, respectively. Most importantly, this work opens the floor for innovation in wearable devices to measure lead II ECG (e.g., by a smart watch worn on right wrist, along with a smart patch on left leg), in order to do accurate, real-time, and early detection of inferior wall MI.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142160069","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}
Pub Date : 2024-08-22DOI: 10.1109/LSENS.2024.3447897
Hafiz Ahmed
High-performance control of permanent magnet synchronous motors (PMSMs) demands precise position information, but nonidealities and signal conversion issues may introduce a dc offset (DCO) in the motor position sensor output. This offset significantly degrades drive performance and efficiency. To address this, conventional state-machine-type algorithms adapt control bandwidths based on fault types. This letter introduces an intuitive decision logic (DL) for both forward and reverse motor operations, offering simplicity and ease of implementation. In contrast to complex signal processing methods, such as wavelet and Fourier transformation and neural network, the proposed lightweight DL can be efficiently implemented in a wide range of embedded devices. Experimental results using an industrial-grade PMSM servo motor across diverse operating conditions validate the efficacy of the proposed DL over long short-term memory network-based counterpart.
{"title":"Measurement Offset Fault Detection Logic for PMSM Position Sensor","authors":"Hafiz Ahmed","doi":"10.1109/LSENS.2024.3447897","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3447897","url":null,"abstract":"High-performance control of permanent magnet synchronous motors (PMSMs) demands precise position information, but nonidealities and signal conversion issues may introduce a dc offset (DCO) in the motor position sensor output. This offset significantly degrades drive performance and efficiency. To address this, conventional state-machine-type algorithms adapt control bandwidths based on fault types. This letter introduces an intuitive decision logic (DL) for both forward and reverse motor operations, offering simplicity and ease of implementation. In contrast to complex signal processing methods, such as wavelet and Fourier transformation and neural network, the proposed lightweight DL can be efficiently implemented in a wide range of embedded devices. Experimental results using an industrial-grade PMSM servo motor across diverse operating conditions validate the efficacy of the proposed DL over long short-term memory network-based counterpart.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142137554","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}
Pub Date : 2024-08-21DOI: 10.1109/LSENS.2024.3445324
Jatin Rana;Anuj K. Sharma;Yogendra Kumar Prajapati
This letter illustrates the successful application of machine learning (ML) models with explainable artificial intelligence (XAI) to enhance the efficacy of a surface plasmon resonance (SPR)-based fiber-optic sensor device (FOSD). The investigation also examines the correlation between the sensor's figure of merit (FoM) and the following variables: light wavelength (λ), sensing region length, metal layer thickness, and refractive index (RI) of surrounding (i.e., sensing or analyte) medium. The study established that the FoM datasets were consistent with various boosting algorithms, such as XGBoost, CatBoost, etc. Incorporating these algorithms into datasets with a λ-resolution of 1 nm led to enhanced FoM magnitudes. The dataset comprises 32 768 data points, each of which falls within one of 15 distinct thickness values and 25 distinct sensing length values. The selected CatBoost ML model exhibits a high level of consistency with the data in terms of trend matching, with all other evaluation parameters lying within acceptable ranges. Furthermore, we have implemented XAI to gain a more comprehensive understanding of the model's internal mechanism in relation to FoM prediction. The results from the shapley additive explanations (SHAP) method indicate that analyte RI and λ play significantly bigger role in dictating the FoM of the SPR-based FOSD. This study emphasizes that the efficient finalization of sensor design and improved sensing performance can be achieved by selecting an appropriate ML model along with XAI and implementing it on a variety of FOSD datasets.
{"title":"Intervention of Machine Learning and Explainable Artificial Intelligence in Fiber-Optic Sensor Device Data for Systematic and Comprehensive Performance Optimization","authors":"Jatin Rana;Anuj K. Sharma;Yogendra Kumar Prajapati","doi":"10.1109/LSENS.2024.3445324","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3445324","url":null,"abstract":"This letter illustrates the successful application of machine learning (ML) models with explainable artificial intelligence (XAI) to enhance the efficacy of a surface plasmon resonance (SPR)-based fiber-optic sensor device (FOSD). The investigation also examines the correlation between the sensor's figure of merit (FoM) and the following variables: light wavelength (λ), sensing region length, metal layer thickness, and refractive index (RI) of surrounding (i.e., sensing or analyte) medium. The study established that the FoM datasets were consistent with various boosting algorithms, such as XGBoost, CatBoost, etc. Incorporating these algorithms into datasets with a λ-resolution of 1 nm led to enhanced FoM magnitudes. The dataset comprises 32 768 data points, each of which falls within one of 15 distinct thickness values and 25 distinct sensing length values. The selected CatBoost ML model exhibits a high level of consistency with the data in terms of trend matching, with all other evaluation parameters lying within acceptable ranges. Furthermore, we have implemented XAI to gain a more comprehensive understanding of the model's internal mechanism in relation to FoM prediction. The results from the shapley additive explanations (SHAP) method indicate that analyte RI and λ play significantly bigger role in dictating the FoM of the SPR-based FOSD. This study emphasizes that the efficient finalization of sensor design and improved sensing performance can be achieved by selecting an appropriate ML model along with XAI and implementing it on a variety of FOSD datasets.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142169731","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}
Pub Date : 2024-08-21DOI: 10.1109/LSENS.2024.3447091
Pallab K. Choudhury;Élie Awwad
An in-band integration strategy is proposed by inserting a sensing probe signal over communication data by modulating the same wavelength channel for next-generation optical access network targeting wavelength-division multiplexing (WDM) point-to-point links. The integration is done by exploring the dc-balanced property of a Manchester-coded signal allowing an effective reduction of low-frequency components to accommodate an in-band Golay-coded lower frequency signal that acts as a sensing probe. The system is demonstrated for 10-Gb/s downstream data over a 20-km fiber with a simple direct-detection receiver in a mobile- or enterprise-fronthaul-based WDM link. Differential-phase-sensitive optical time-domain reflectometry is used to locate external perturbations by using the Golay-coded signal for channel estimation and a coherent receiver at the central office. The presented results show that the downstream data can be successfully retrieved from the integrated signal within a pre-forward error correction bit error rate limit of 10 −3 maintaining enough input optical power budget at the receiver side. Moreover, the backscattered signal is analyzed for accurate detection of two simultaneous events applied over the fiber maintaining a sensing spatial resolution of 2.1 m and a maximum acoustic bandwidth of 381 Hz with a strain sensitivity down to 15 nϵ pp (peak to peak).
{"title":"In-Band Sensing and Communication for Optical Access Networks Using Δϕ-OTDR With Simplified Transceivers","authors":"Pallab K. Choudhury;Élie Awwad","doi":"10.1109/LSENS.2024.3447091","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3447091","url":null,"abstract":"An in-band integration strategy is proposed by inserting a sensing probe signal over communication data by modulating the same wavelength channel for next-generation optical access network targeting wavelength-division multiplexing (WDM) point-to-point links. The integration is done by exploring the dc-balanced property of a Manchester-coded signal allowing an effective reduction of low-frequency components to accommodate an in-band Golay-coded lower frequency signal that acts as a sensing probe. The system is demonstrated for 10-Gb/s downstream data over a 20-km fiber with a simple direct-detection receiver in a mobile- or enterprise-fronthaul-based WDM link. Differential-phase-sensitive optical time-domain reflectometry is used to locate external perturbations by using the Golay-coded signal for channel estimation and a coherent receiver at the central office. The presented results show that the downstream data can be successfully retrieved from the integrated signal within a pre-forward error correction bit error rate limit of 10\u0000<sup>−3</sup>\u0000 maintaining enough input optical power budget at the receiver side. Moreover, the backscattered signal is analyzed for accurate detection of two simultaneous events applied over the fiber maintaining a sensing spatial resolution of 2.1 m and a maximum acoustic bandwidth of 381 Hz with a strain sensitivity down to 15 nϵ\u0000<sub>pp</sub>\u0000 (peak to peak).","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142160005","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}
Discrete hand-gesture recognition using sensors built into wrist-wearable devices could enable always-available input across a wide range of ubiquitous environments. For example, a user could flick their wrist to dismiss a phone call or tap their thumb and index fingers together to make a selection in mixed reality. To move toward such applications, this work evaluates a new multimodal commercially available device (the BioPoint by SIFI Labs ) for recognizing seven dynamic hand gestures. Three sensors were evaluated, including a single channel of electromyography (EMG), a three-axis accelerometer (ACC), and photoplethysmography (PPG). Using a deep LSTM-based network, the relative performance of each sensor and all possible combinations were compared for their gesture classification abilities. The results show that the combination of all sensors led to the highest classification accuracy ( $>$ 96%), significantly outperforming the individual performance of each sensor (p $< $ 0.05). In addition, the fusion of all sensors significantly improved performance across days (p $< $ 0.05) and was significantly more resilient when classifying gestures elicited in unseen limb positions (p $< $ 0.05). These results highlight the complementary benefits of fusing EMG, ACC, and PPG signals as a viable path forward for the reliable recognition of discrete event-driven gestures using wrist-based wearables.
{"title":"Discrete Gesture Recognition Using Multimodal PPG, IMU, and Single-Channel EMG Recorded at the Wrist","authors":"Ethan Eddy;Evan Campbell;Ulysse Côté-Allard;Scott Bateman;Erik Scheme","doi":"10.1109/LSENS.2024.3447240","DOIUrl":"https://doi.org/10.1109/LSENS.2024.3447240","url":null,"abstract":"Discrete hand-gesture recognition using sensors built into wrist-wearable devices could enable always-available input across a wide range of ubiquitous environments. For example, a user could flick their wrist to dismiss a phone call or tap their thumb and index fingers together to make a selection in mixed reality. To move toward such applications, this work evaluates a new multimodal commercially available device (the \u0000<italic>BioPoint</i>\u0000 by \u0000<italic>SIFI Labs</i>\u0000) for recognizing seven dynamic hand gestures. Three sensors were evaluated, including a single channel of electromyography (EMG), a three-axis accelerometer (ACC), and photoplethysmography (PPG). Using a deep LSTM-based network, the relative performance of each sensor and all possible combinations were compared for their gesture classification abilities. The results show that the combination of all sensors led to the highest classification accuracy (\u0000<inline-formula><tex-math>$>$</tex-math></inline-formula>\u000096%), significantly outperforming the individual performance of each sensor (p \u0000<inline-formula><tex-math>$< $</tex-math></inline-formula>\u0000 0.05). In addition, the fusion of all sensors significantly improved performance across days (p \u0000<inline-formula><tex-math>$< $</tex-math></inline-formula>\u0000 0.05) and was significantly more resilient when classifying gestures elicited in unseen limb positions (p \u0000<inline-formula><tex-math>$< $</tex-math></inline-formula>\u0000 0.05). These results highlight the complementary benefits of fusing EMG, ACC, and PPG signals as a viable path forward for the reliable recognition of discrete event-driven gestures using wrist-based wearables.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142123028","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：