Pub Date : 2025-10-28DOI: 10.1109/LSENS.2025.3626554
Runqi Zeng;Jiuzhou Zhang;Ling Shi
This letter presents a novel approach for human motion estimation using millimeter-wave (mmWave) radar, integrating the extended Kalman filter (EKF), convolutional neural network (CNN), and bidirectional long short-term memory (BiLSTM) networks. The proposed method addresses key challenges in mmWave radar systems, such as frame failures and background noise, by leveraging EKF to enhance tracking robustness and suppress noise. The CNN-BiLSTM classifier captures spatial and temporal features to accurately classify four human motions. Experimental results demonstrate the system's effectiveness, achieving high accuracy rates compared to existing literature. This work advances mmWave radar-based motion detection by introducing a novel 3-D state-space model and a hybrid EKF-CNN-BiLSTM framework, offering significant improvements over traditional signal processing and deep learning techniques.
{"title":"Optimized Human Motion Estimation Through Extended Kalman Filter in MmWave Radar","authors":"Runqi Zeng;Jiuzhou Zhang;Ling Shi","doi":"10.1109/LSENS.2025.3626554","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3626554","url":null,"abstract":"This letter presents a novel approach for human motion estimation using millimeter-wave (mmWave) radar, integrating the extended Kalman filter (EKF), convolutional neural network (CNN), and bidirectional long short-term memory (BiLSTM) networks. The proposed method addresses key challenges in mmWave radar systems, such as frame failures and background noise, by leveraging EKF to enhance tracking robustness and suppress noise. The CNN-BiLSTM classifier captures spatial and temporal features to accurately classify four human motions. Experimental results demonstrate the system's effectiveness, achieving high accuracy rates compared to existing literature. This work advances mmWave radar-based motion detection by introducing a novel 3-D state-space model and a hybrid EKF-CNN-BiLSTM framework, offering significant improvements over traditional signal processing and deep learning techniques.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 12","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145510183","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 : 2025-10-28DOI: 10.1109/LSENS.2025.3626380
Mo Yang;Weirong Nie;Baolin Cheng;Haiyue Ren;Yun Cao;Jiong Wang
This letter reports a novel active magnetic coupling actuator applied in a micro-electromechanical system safety and arming device to realize the relatively large displacements of the interrupter. The actuator consists of an active micro-electromagnetic coil and two passive permanent magnets. Permanent magnet 1, which is fixed to the interrupter, reaches the target position through the combined action of the micro-electromagnetic coil and permanent magnet 2. The dynamic behavior of the actuator is investigated by simulations and experiments. The results show that the driving principle is verified, and the interrupter successfully realizes the movement of relatively large displacements. The test results match well with the simulation results.
{"title":"A Novel Active Magnetic Coupling Actuator for Silicon-Based MEMS Safety and Arming Device","authors":"Mo Yang;Weirong Nie;Baolin Cheng;Haiyue Ren;Yun Cao;Jiong Wang","doi":"10.1109/LSENS.2025.3626380","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3626380","url":null,"abstract":"This letter reports a novel active magnetic coupling actuator applied in a micro-electromechanical system safety and arming device to realize the relatively large displacements of the interrupter. The actuator consists of an active micro-electromagnetic coil and two passive permanent magnets. Permanent magnet 1, which is fixed to the interrupter, reaches the target position through the combined action of the micro-electromagnetic coil and permanent magnet 2. The dynamic behavior of the actuator is investigated by simulations and experiments. The results show that the driving principle is verified, and the interrupter successfully realizes the movement of relatively large displacements. The test results match well with the simulation results.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 12","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145510220","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 a comparative investigation of the dynamic response performance of femtosecond-laser-inscribed fiber Bragg gratings (FBGs) in multimode cyclic transparent optical polymer (CYTOP) fiber and conventional silica fiber under controlled vibrational excitation. Both FBGs were inscribed with a femtosecond laser, producing Bragg reflection peaks centered at 1550 nm, and were coencapsulated in polydimethylsiloxane (PDMS) at the same physical location. The encapsulated sensors were mounted on a vibration platform, and their wavelength responses were tested over the frequency range of 0.1–100 Hz. CYTOP FBG exhibits superior response amplitude and frequency sensitivity compared to the silica FBG. Furthermore, a real vital sign monitoring experiment was conducted on the human chest to verify the practical applicability of the CYTOP FBG in dynamic biosensing. These findings demonstrate the potential of CYTOP FBG for high-sensitivity biomedical vibration monitoring.
{"title":"Dynamic Response Comparison of CYTOP and Silica Fiber Bragg Gratings for Vital Sign Monitoring","authors":"Yuchi Hu;Andreas Ioannou;Changqiu Yu;Kyriacos Kalli","doi":"10.1109/LSENS.2025.3625752","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3625752","url":null,"abstract":"In this letter, we present a comparative investigation of the dynamic response performance of femtosecond-laser-inscribed fiber Bragg gratings (FBGs) in multimode cyclic transparent optical polymer (CYTOP) fiber and conventional silica fiber under controlled vibrational excitation. Both FBGs were inscribed with a femtosecond laser, producing Bragg reflection peaks centered at 1550 nm, and were coencapsulated in polydimethylsiloxane (PDMS) at the same physical location. The encapsulated sensors were mounted on a vibration platform, and their wavelength responses were tested over the frequency range of 0.1–100 Hz. CYTOP FBG exhibits superior response amplitude and frequency sensitivity compared to the silica FBG. Furthermore, a real vital sign monitoring experiment was conducted on the human chest to verify the practical applicability of the CYTOP FBG in dynamic biosensing. These findings demonstrate the potential of CYTOP FBG for high-sensitivity biomedical vibration monitoring.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 12","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145560702","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}
Traditional radar imaging methods based on point target models fail to achieve ideal results for extended targets, while simultaneously using multiple models introduces redundancy. This letter first treats point targets and line segments as special cases of rectangular plate targets, unifying the three target types under a single scattering model based on rectangular plates. Subsequently, a two-step orthogonal matching pursuit (OMP) algorithm is proposed to achieve sparsity-driven radar imaging. In the first OMP step, an observation matrix is constructed using the ideal point target model and the observation geometry, enabling coarse estimation of target position parameters in a greedy manner. In the second step, a unified rectangular plate model is employed along with the positional information obtained from the first OMP step to reconstruct the observation matrix. This allows for the simultaneous greedy estimation of both the rectangular plate model parameters and positional parameters, thereby reconstructing the target structure. Finally, the effectiveness of the proposed algorithm is validated through simulated experiments and real anechoic chamber tests.
{"title":"Sparsity-Driven Radar Imaging Using Two-Step OMP With a Unified Rectangular Plate Model","authors":"Pucheng Li;Ziwen Wang;Yifan Wu;Linghao Li;Zhen Wang;Zegang Ding","doi":"10.1109/LSENS.2025.3624617","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3624617","url":null,"abstract":"Traditional radar imaging methods based on point target models fail to achieve ideal results for extended targets, while simultaneously using multiple models introduces redundancy. This letter first treats point targets and line segments as special cases of rectangular plate targets, unifying the three target types under a single scattering model based on rectangular plates. Subsequently, a two-step orthogonal matching pursuit (OMP) algorithm is proposed to achieve sparsity-driven radar imaging. In the first OMP step, an observation matrix is constructed using the ideal point target model and the observation geometry, enabling coarse estimation of target position parameters in a greedy manner. In the second step, a unified rectangular plate model is employed along with the positional information obtained from the first OMP step to reconstruct the observation matrix. This allows for the simultaneous greedy estimation of both the rectangular plate model parameters and positional parameters, thereby reconstructing the target structure. Finally, the effectiveness of the proposed algorithm is validated through simulated experiments and real anechoic chamber tests.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"10 1","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145705889","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}
Bisphenol S (BPS) is widely used by plastic manufacturers as a common substitute for Bisphenol A. BPS poses notable risks to human health due to its endocrine-disrupting effects. Therefore, a sensitive detection method for BPS is essential for public health. The objective of this letter is to validate the prediction capabilities of machine learning (ML) framework for an extended-gate field-effect transistor (EGFET)-based BPS biosensor. The dataset was generated from I–V characteristics, and additional features were extracted in terms of output conductance ($g_{text{DS}}$), transconductance ($g_{m}$), and transconductance efficiency ($g_{m}big /I_{text{DS}}$). The stacking ensemble learning approach was used with base learners and a meta model prior to hyperparameter optimization using Optuna architecture. The best ML classifier framework was obtained by evaluating standard performance measures, confusion matrix, and learning curve. Moreover, SHapley Additive exPlanations (SHAP) analysis was performed to determine the importance ranking of the features utilized for prediction. The proposed ML framework for EGFET-based biosensor efficiently predicts BPS concentrations with high accuracy (97.60%), precision (97.78%), recall (97.61%), and F1-score (97.62%). SHAP analysis revealed that $g_{m}big /I_{text{DS}}$ is the dominant feature in predicting BPS concentration.
{"title":"Data-driven Extended-gate Field-effect Transistor-based Biosensors for Bisphenol S Detection Using Machine Learning Framework","authors":"Rishikesh Datar;Neha Menon;Ashirbad Panda;Gautam Bacher","doi":"10.1109/LSENS.2025.3623925","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3623925","url":null,"abstract":"Bisphenol S (BPS) is widely used by plastic manufacturers as a common substitute for Bisphenol A. BPS poses notable risks to human health due to its endocrine-disrupting effects. Therefore, a sensitive detection method for BPS is essential for public health. The objective of this letter is to validate the prediction capabilities of machine learning (ML) framework for an extended-gate field-effect transistor (EGFET)-based BPS biosensor. The dataset was generated from <italic>I–V</i> characteristics, and additional features were extracted in terms of output conductance (<inline-formula><tex-math>$g_{text{DS}}$</tex-math></inline-formula>), transconductance (<inline-formula><tex-math>$g_{m}$</tex-math></inline-formula>), and transconductance efficiency (<inline-formula><tex-math>$g_{m}big /I_{text{DS}}$</tex-math></inline-formula>). The stacking ensemble learning approach was used with base learners and a meta model prior to hyperparameter optimization using Optuna architecture. The best ML classifier framework was obtained by evaluating standard performance measures, confusion matrix, and learning curve. Moreover, SHapley Additive exPlanations (SHAP) analysis was performed to determine the importance ranking of the features utilized for prediction. The proposed ML framework for EGFET-based biosensor efficiently predicts BPS concentrations with high accuracy (97.60%), precision (97.78%), recall (97.61%), and F1-score (97.62%). SHAP analysis revealed that <inline-formula><tex-math>$g_{m}big /I_{text{DS}}$</tex-math></inline-formula> is the dominant feature in predicting BPS concentration.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 12","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145455814","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}
Rice is one of the most important food crops, serving as a major carbohydrate source worldwide. With ongoing climatic changes, abiotic stress has emerged as a critical challenge to rice production. Among these, salinity stress caused by excess salt in soil significantly impacts rice growth, particularly during germination and reproductive stages. To address the need for a cost-effective analytical approach, we evaluated salt stress in Pusa Basmati 1 rice plants using in vivo and in vitro electrochemical impedance spectroscopy (EIS). In addition, morphological changes, such as reduced plant height, leaf dimensions, shoot thickness, and root development, were recorded under increasing salt concentrations. EIS data, interpreted using an equivalent circuit model, revealed systematic variations in impedance and admittance parameters correlating with salt-induced morphological alterations.
{"title":"In Vitro and In Vivo EIS-Based Analysis and Validation of Salt Stress Response in Pusa Basmati 1 Rice","authors":"Sohom Adhikari;Rishikesh Datar;Sandhya Mehrotra;Rajesh Mehrotra;Gautam Bacher","doi":"10.1109/LSENS.2025.3623927","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3623927","url":null,"abstract":"Rice is one of the most important food crops, serving as a major carbohydrate source worldwide. With ongoing climatic changes, abiotic stress has emerged as a critical challenge to rice production. Among these, salinity stress caused by excess salt in soil significantly impacts rice growth, particularly during germination and reproductive stages. To address the need for a cost-effective analytical approach, we evaluated salt stress in Pusa Basmati 1 rice plants using in vivo and in vitro electrochemical impedance spectroscopy (EIS). In addition, morphological changes, such as reduced plant height, leaf dimensions, shoot thickness, and root development, were recorded under increasing salt concentrations. EIS data, interpreted using an equivalent circuit model, revealed systematic variations in impedance and admittance parameters correlating with salt-induced morphological alterations.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 12","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145674713","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 : 2025-10-20DOI: 10.1109/LSENS.2025.3622198
Naveed Iqbal;Muhammad Khalid;Ajmal Khan;Zeeshan Kaleem;Adil H. Khan
The real-time use of wireless sensor networks has become increasingly popular due to their attractive features. However, energy management becomes a critical factor in these networks, especially during deployment, because each sensor node has limited battery capacity. While wireless sensors offer advantages, transmitting massive volumes from numerous sensors to a central data center wirelessly presents a significant hurdle. In this work, the focus is on the seismic sensor (geophone), and the challenge lies in transmitting hundreds of recordings per geophone through narrowband channels without overloading the data center or the sensors themselves. This motivates our proposed method, DeepWave, a lightweight and standalone compressive sensing approach designed specifically for in-field data acquisition. This study presents an effective method for compressing seismic data in the field, followed by the utilization of the wavelet transform and integration with a convolutional neural network (CNN) for recovery at a later stage. The sparsity-aware schematic, DeepWave, is proposed for compressed data recovery and compared with benchmarking techniques. A key strength of this method is that it is general and works with any underlying data statistics, allowing it to adapt to a wide range of exploration and sensing scenarios. Our findings indicate that this CNN-based approach achieves an effective balance between data compression (93.75% compression percentage) and signal fidelity ( dB normalized mean-square error) on the evaluated dataset.
{"title":"DeepWave: A Wavelet-Based Technique for Compressing In-Field Sensors Data","authors":"Naveed Iqbal;Muhammad Khalid;Ajmal Khan;Zeeshan Kaleem;Adil H. Khan","doi":"10.1109/LSENS.2025.3622198","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3622198","url":null,"abstract":"The real-time use of wireless sensor networks has become increasingly popular due to their attractive features. However, energy management becomes a critical factor in these networks, especially during deployment, because each sensor node has limited battery capacity. While wireless sensors offer advantages, transmitting massive volumes from numerous sensors to a central data center wirelessly presents a significant hurdle. In this work, the focus is on the seismic sensor (geophone), and the challenge lies in transmitting hundreds of recordings per geophone through narrowband channels without overloading the data center or the sensors themselves. This motivates our proposed method, DeepWave, a lightweight and standalone compressive sensing approach designed specifically for in-field data acquisition. This study presents an effective method for compressing seismic data in the field, followed by the utilization of the wavelet transform and integration with a convolutional neural network (CNN) for recovery at a later stage. The sparsity-aware schematic, DeepWave, is proposed for compressed data recovery and compared with benchmarking techniques. A key strength of this method is that it is general and works with any underlying data statistics, allowing it to adapt to a wide range of exploration and sensing scenarios. Our findings indicate that this CNN-based approach achieves an effective balance between data compression (93.75% compression percentage) and signal fidelity ( dB normalized mean-square error) on the evaluated dataset.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 12","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145778235","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 : 2025-10-20DOI: 10.1109/LSENS.2025.3624027
Yahya Abbass;Silvana Miranda Montenegro;Fabio Egle;Moustafa Saleh;Maurizio Valle;Claudio Castellini
During muscle contractions, force distributions are generated on muscle surfaces due to muscle activity, which is applicable for control in a human–machine interface. It has been proven that the force distribution from the corresponding body motions can be recorded utilizing the so-called Force Myography (FMG). Flexible piezoelectric sensors with attractive sensing properties have been widely used in several areas to detect force variations through wearable devices. In this letter, we developed an FMG armband composed of high-density (24 sensors) piezoelectric electronic skin and multichannel embedded electronics. The FMG armband was used to recognize eleven hand and wrist gestures performed by able-bodied subjects. To do this, two signal-processing approaches (front-end approach and feature-based approach) were developed to process the FMG patterns and extract the proper features. The processed FMG patterns were evaluated and identified by employing various classical machine learning algorithms, and an average gesture recognition accuracy of 98% for wrist gestures was obtained. This letter demonstrates the feasibility of using high-density piezoelectric skin for FMG and leads to alternative methods for gesture recognition in biomedical applications.
{"title":"A Case Study: FMG-based Gesture Recognition using High-Density Piezoelectric Electronic Skin and Machine Learning","authors":"Yahya Abbass;Silvana Miranda Montenegro;Fabio Egle;Moustafa Saleh;Maurizio Valle;Claudio Castellini","doi":"10.1109/LSENS.2025.3624027","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3624027","url":null,"abstract":"During muscle contractions, force distributions are generated on muscle surfaces due to muscle activity, which is applicable for control in a human–machine interface. It has been proven that the force distribution from the corresponding body motions can be recorded utilizing the so-called Force Myography (FMG). Flexible piezoelectric sensors with attractive sensing properties have been widely used in several areas to detect force variations through wearable devices. In this letter, we developed an FMG armband composed of high-density (24 sensors) piezoelectric electronic skin and multichannel embedded electronics. The FMG armband was used to recognize eleven hand and wrist gestures performed by able-bodied subjects. To do this, two signal-processing approaches (front-end approach and feature-based approach) were developed to process the FMG patterns and extract the proper features. The processed FMG patterns were evaluated and identified by employing various classical machine learning algorithms, and an average gesture recognition accuracy of 98% for wrist gestures was obtained. This letter demonstrates the feasibility of using high-density piezoelectric skin for FMG and leads to alternative methods for gesture recognition in biomedical applications.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 12","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11208780","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145510185","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}
Pub Date : 2025-10-17DOI: 10.1109/LSENS.2025.3622924
Kamal Singh;Nitin Singha;Anuj K Sharma;Swati Bhalaik;Chirag Kumar
An effective electrode selection strategy is crucial in motor imagery (MI)-based brain–computer interfaces (BCIs) to maintain competitive performance while reducing the number of electrodes and overall computational complexity. This study introduces a novel electrode selection method based on signal power and evaluates its impact on MI task classification using the BCI Competition IV-2a dataset. Electrodes were systematically reduced by selecting those with the highest signal power. The proposed method was evaluated using state-of-the-art deep learning models, EEGNet, ShallowConvNet, and DeepConvNet, with classification accuracy and F1-score as performance metrics. EEGNet, with all electrodes, achieved an average accuracy of 69.30% and an average F1-score of 0.6910. As the number of electrodes was progressively reduced, performance declined gradually, with a noticeable drop observed after a 50% reduction. Notably, even with 50% fewer electrodes, accuracy remained within 8.59% of the full-electrode configuration. Topographic analysis showed that electrodes near the motor cortex, exhibiting higher signal power, were most critical for classification. In contrast, peripheral electrodes with lower signal power were less informative and could be removed, demonstrating the effectiveness of the proposed method. Similar trends were observed for ShallowConvNet and DeepConvNet, further confirming the method’s generalizability. This approach provides a promising direction for developing more practical, faster, cost-effective, and resource-efficient BCI systems.
{"title":"Optimized EEG Sensor Electrode Configuration for Motor Imagery Decoding With Minimal Accuracy Loss and Reduced Cost","authors":"Kamal Singh;Nitin Singha;Anuj K Sharma;Swati Bhalaik;Chirag Kumar","doi":"10.1109/LSENS.2025.3622924","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3622924","url":null,"abstract":"An effective electrode selection strategy is crucial in motor imagery (MI)-based brain–computer interfaces (BCIs) to maintain competitive performance while reducing the number of electrodes and overall computational complexity. This study introduces a novel electrode selection method based on signal power and evaluates its impact on MI task classification using the BCI Competition IV-2a dataset. Electrodes were systematically reduced by selecting those with the highest signal power. The proposed method was evaluated using state-of-the-art deep learning models, EEGNet, ShallowConvNet, and DeepConvNet, with classification accuracy and F1-score as performance metrics. EEGNet, with all electrodes, achieved an average accuracy of 69.30% and an average F1-score of 0.6910. As the number of electrodes was progressively reduced, performance declined gradually, with a noticeable drop observed after a 50% reduction. Notably, even with 50% fewer electrodes, accuracy remained within 8.59% of the full-electrode configuration. Topographic analysis showed that electrodes near the motor cortex, exhibiting higher signal power, were most critical for classification. In contrast, peripheral electrodes with lower signal power were less informative and could be removed, demonstrating the effectiveness of the proposed method. Similar trends were observed for ShallowConvNet and DeepConvNet, further confirming the method’s generalizability. This approach provides a promising direction for developing more practical, faster, cost-effective, and resource-efficient BCI systems.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 12","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145449314","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}
Given the rising mortality rates from cardiovascular diseases and the high incidence of neurological disorders, this letter presents a device that integrates a seven-channel functional near-infrared spectroscopy (NIRS) pathway and a single-channel electrocardiogram (ECG) signal pathway for accurate detection, transmission, and display of multimodal signals. Using a Teensy 3.1 processor as the control core, and simultaneously controls the opening and closing of multiple signal acquisition channels. The host computer software developed on the Python Qt 5 framework displays and saves real-time data. Experimental results demonstrate that in ECG testing, the relative error between the heart rate data collected by the device and that measured by the Apple Watch S6 is within 5%, indicating high precision in ECG signal acquisition. A passive leg-raising experiment was further designed to validate that the integrated NIRS-ECG system can effectively reflect neurovascular coupling in the human body. This approach overcomes the limitations of single-modality detection methods.
{"title":"Design and Implementation of a Multimodal Neurovascular Coupling Detection System Based on ECG and NIRS","authors":"Yunfei Ma;Guangmao Zhang;Pengbo Sun;Zewen Qi;Jiabei Chen;Zhanyi Li;Jing Yuan;Xiaohong Huang","doi":"10.1109/LSENS.2025.3622256","DOIUrl":"https://doi.org/10.1109/LSENS.2025.3622256","url":null,"abstract":"Given the rising mortality rates from cardiovascular diseases and the high incidence of neurological disorders, this letter presents a device that integrates a seven-channel functional near-infrared spectroscopy (NIRS) pathway and a single-channel electrocardiogram (ECG) signal pathway for accurate detection, transmission, and display of multimodal signals. Using a Teensy 3.1 processor as the control core, and simultaneously controls the opening and closing of multiple signal acquisition channels. The host computer software developed on the Python Qt 5 framework displays and saves real-time data. Experimental results demonstrate that in ECG testing, the relative error between the heart rate data collected by the device and that measured by the Apple Watch S6 is within 5%, indicating high precision in ECG signal acquisition. A passive leg-raising experiment was further designed to validate that the integrated NIRS-ECG system can effectively reflect neurovascular coupling in the human body. This approach overcomes the limitations of single-modality detection methods.","PeriodicalId":13014,"journal":{"name":"IEEE Sensors Letters","volume":"9 12","pages":"1-4"},"PeriodicalIF":2.2,"publicationDate":"2025-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145510182","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：