Paola Busia, Gianluca Leone, Andrea Matticola, Luigi Raffo, Paolo Meloni
{"title":"Wearable Epilepsy Seizure Detection on FPGA with Spiking Neural Networks.","authors":"Paola Busia, Gianluca Leone, Andrea Matticola, Luigi Raffo, Paolo Meloni","doi":"10.1109/TBCAS.2025.3575327","DOIUrl":"https://doi.org/10.1109/TBCAS.2025.3575327","url":null,"abstract":"<p><p>The development of epilepsy monitoring solutions suitable for everyday use is a very challenging task, where different constraints should be combined, resulting from the required accuracy standards, the unobtrusiveness of the monitoring device, and the efficiency of real-time operation. Considering the time-varying nature of the electroencephalography signal (EEG), Spiking Neural Networks (SNNs) represent a promising solution to model the evolution of the brain state based on the history of the previously processed signal. This work proposes an extremely lightweight SNN-based seizure detection solution, utilizing a simple encoding scheme to ensure high levels of sparsity. Despite the reduced complexity, the model provides a detection performance comparable with the state-of-the-art SNN-based approaches on the evaluated data from the CHB-MIT dataset, reaching a 96% area under the curve (AUC) and allowing 99.3% average accuracy, with the detection of 100% of the examined seizure events and a false alarm rate of 0.3 false positives per hour. The suitability for real-time inference execution on wearable monitoring devices was assessed on SYNtzulu, demonstrating 0.5 μs inference time with 4.55 nJ energy consumption.</p>","PeriodicalId":94031,"journal":{"name":"IEEE transactions on biomedical circuits and systems","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144188720","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}
{"title":"A 96 dB Input Dynamic Range Galvanic Skin Response Readout IC with 3.5 pArms Input-Referred Noise for Mental Stress Monitoring.","authors":"Yi-Jie Lin, Lin Chou, Kun-Ju Tsai, Yu-Te Liao","doi":"10.1109/TBCAS.2025.3573614","DOIUrl":"https://doi.org/10.1109/TBCAS.2025.3573614","url":null,"abstract":"<p><p>This paper presents a low-noise, low-power galvanic skin response (GSR) sensing circuit capable of simultaneously measuring skin conductance level (SCL) and skin conductance response (SCR) for psychological stress monitoring. The circuit incorporates second-order sub-ten-hertz filters that suppresses out-of-band interference and a programmable gain amplifier (PGA) to accommodate signals of varying magnitudes. Additionally, a dynamic range adjustment mechanism optimizes the primary amplifier's operating range based on real-time SCL readings. The design achieves a 96.4 dB dynamic range with an input-referred noise of only 3.47 pArms within 0.5-5 Hz under optimal conditions. These advancements significantly enhance measurement accuracy and robustness for wearable stress monitoring and real-time biofeedback applications.</p>","PeriodicalId":94031,"journal":{"name":"IEEE transactions on biomedical circuits and systems","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144153009","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}
Thorir Mar Ingolfsson, Victor Kartsch, Luca Benini, Andrea Cossettini
{"title":"A Wearable Ultra-Low-Power System for EEG-based Speech-Imagery Interfaces.","authors":"Thorir Mar Ingolfsson, Victor Kartsch, Luca Benini, Andrea Cossettini","doi":"10.1109/TBCAS.2025.3573027","DOIUrl":"https://doi.org/10.1109/TBCAS.2025.3573027","url":null,"abstract":"<p><p>Speech imagery-the process of mentally simulating speech without vocalization-is a promising approach for brain-computer interfaces (BCIs), enabling assistive communication for individuals with speech impairments or to enhance privacy. However, existing EEG-based speech imagery systems remain impractical for use outside specialized laboratories due to their reliance on high-channel-count and resource-intensive machine learning models running on external computing platforms. In this work, we present the first end-to-end demonstration of EEG-based speech imagery decoding on a low-channel, ultra-low-power wearable device. Building on our previous work on vowel imagery, we introduce an extended framework leveraging the BioGAP platform and VOWELNET, a lightweight neural network optimized for embedded speech imagery classification. In particular, we demonstrate state-of- the-art accuracy in the classification of an expanded vocabulary comprising vowels, commands, and rest states (13 classes) with a subject-specific training approach, achieving up to 50.0% for one subject (42.8% average) in multi-class classification. We deploy our model on an embedded biosignal acquisition and processing platform (BioGAP), based on the GAP9 processor, for real-time inference with minimal power consumption (25.93 mW). Our system achieves continuous execution for more than 21 hours on a small LiPo battery while maintaining classification latencies of 40.9 ms. Finally, we also explore the benefits of applying Continual Learning techniques to progressively improve the system's performance throughout its operational lifetime, and we demonstrate that electrodes located on the temporal area contribute the most to the overall accuracy. This work marks a significant step toward practical, real-time, and unobtrusive speech imagery BCIs, unlocking new opportunities for covert communication and assistive technologies.</p>","PeriodicalId":94031,"journal":{"name":"IEEE transactions on biomedical circuits and systems","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144133226","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}
{"title":"A 0.48° Phase Error 91.1dB SNR Bioimpedance Measurement IC for Monitoring Cardiopulmonary Diseases.","authors":"Jiarun Yuan, Yanxing Suo, Qiao Cai, Hui Wang, Yongfu Li, Yong Lian, Yang Zhao","doi":"10.1109/TBCAS.2025.3572374","DOIUrl":"https://doi.org/10.1109/TBCAS.2025.3572374","url":null,"abstract":"<p><p>This article presents a low-power and low phase error bioimpedance (BioZ) measurement IC designed for monitoring cardiopulmonary diseases. To compensate for the phase shift introduced along the signal path by current generator (CG), electrodes and sensor analog front-end (AFE), a novel phase shift calibration logic is proposed. Utilizing this calibration logic, a single-channel in-phase demodulation-based impedance measurement scheme is developed. A noise shaping pseudo-sine wave CG with data-weighted averaging (DWA) is used to minimize modulation harmonics. Fabricated in a 0.18μm CMOS process, the chip occupies 0.73mm<sup>2</sup> and consumes between 52.7 to 97.5μA current from a 1.8V supply. The CG achieves 74.1dB SFDR and -70dB THD at 15.5kHz with a 50μApk stimulation current. The chip achieves $2 text{m} Omega / sqrt{} Hz$ input-referred impedance noise at 1Hz, 91.1dB SNR (BW=4Hz), $36 text{k} Omega$ input range and less than 0.48° phase error (0-90°, 1-20kHz). On-body BioZ experiments using a 4-electrode configuration demonstrate clear recordings of Impedance Cardiography (ICG) and respiration signals.</p>","PeriodicalId":94031,"journal":{"name":"IEEE transactions on biomedical circuits and systems","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144121784","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}
Sudip Nag, Aryasree Remadevi, Jin Che, Matvii Prytula, Hanzhang Xing, Hanrui Xing, Xiaoxuan Xiao, Andreas Constas-Malvanets, Hengjia Zhang, Yinghe Sun, Joshua Olorocisimo, Jose Zariffa, Roman Genov
{"title":"Energy-Efficient Adaptive Neural Stimulator with Waveform Prediction by Sub-Threshold Interrogation of the Electrode-Tissue Interface.","authors":"Sudip Nag, Aryasree Remadevi, Jin Che, Matvii Prytula, Hanzhang Xing, Hanrui Xing, Xiaoxuan Xiao, Andreas Constas-Malvanets, Hengjia Zhang, Yinghe Sun, Joshua Olorocisimo, Jose Zariffa, Roman Genov","doi":"10.1109/TBCAS.2025.3570264","DOIUrl":"https://doi.org/10.1109/TBCAS.2025.3570264","url":null,"abstract":"<p><p>This paper presents an implantable low-power neural stimulator that generates electrical stimulation pulses based on subject-specific edge-learning of electrode-tissue voltage profiles. The system deploys a low-magnitude constant-current stimulation pulse to create a training dataset, which is subsequently utilized to predict the desired electrode voltage waveforms for higher magnitudes of constant-current stimulation. The predicted waveform dataset has been used to control a custom switched-capacitor output stage, thereby avoiding V<sub>driver_transistor</sub> · I<sub>stimulation</sub> power loss as in the conventional neural stimulator drivers. The proposed system incorporates on-chip learning and prediction implemented within an ultra-low-power microcontroller, which has been optimized for memory- and power-constrained implantable environments. The stimulator output stage reduces power loss by up to 20% as compared to dynamic power supply scaling method, and consumes up to 3.63× lower as compared to conventional constant-current output stages. The intelligent neural interface system has been powered by a wireless inductive energy transfer link and is remotely controlled through a WiFi-based internet network. A custom-developed application interface, compatible with both mobile devices and personal computers, facilitates secure remote adjustments of stimulation parameters. The proposed system has been validated through a combination of in vivo rat peripheral nerve stimulation, in vitro saline tests, and benchtop experiments. These results collectively demonstrate the potential to advance future neural implant technologies by enabling intelligence, safety, energy efficiency, and remotely controllable neural organ modulation.</p>","PeriodicalId":94031,"journal":{"name":"IEEE transactions on biomedical circuits and systems","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144121873","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}
Asish Koruprolu, Tyler Hack, Omid Ghadami, Aditi Jain, Drew A Hall
{"title":"From Wearables to Implantables: Harnessing sensor technologies for continuous health monitoring.","authors":"Asish Koruprolu, Tyler Hack, Omid Ghadami, Aditi Jain, Drew A Hall","doi":"10.1109/TBCAS.2025.3568754","DOIUrl":"https://doi.org/10.1109/TBCAS.2025.3568754","url":null,"abstract":"<p><p>Continuous health monitoring by placing sensors onto and into the human body has emerged as a pivotal approach in healthcare. This paper delves into the vast array of opportunities presented by instrumenting the body using wearable, ingestible, injectable, and implantable sensors. These sensors enable the continuous monitoring of vital signs, biomarkers, and other crucial health metrics, thus assessing an individual's physiological state. This comprehensive health data empowers healthcare providers and individuals alike to make informed decisions and take timely action. Moreover, integrating sensors into the human body enables personalized medicine, enhances disease detection and management, and offers possibilities for proactive health interventions and preventive care to improve overall well-being.</p>","PeriodicalId":94031,"journal":{"name":"IEEE transactions on biomedical circuits and systems","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144029207","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}
{"title":"Artifact-Tolerant Electrophysiological Sensor Interface with 3.6V/1.8V DM/CM Input Range and 52.3mV<sub>pp</sub>/μs Recovery Using Asynchronous Signal Folding.","authors":"Qiao Cai, Xinzi Xu, Yanxing Suo, Guanghua Qian, Yongfu Li, Guoxing Wang, Yong Lian, Yang Zhao","doi":"10.1109/TBCAS.2025.3567524","DOIUrl":"https://doi.org/10.1109/TBCAS.2025.3567524","url":null,"abstract":"<p><p>In the practical implementations of wearable sensors, motion artifacts with large amplitudes often cause signal chain saturation, significantly degrading biopotential signal integrity. Similarly, rapid stimulation artifacts are inevitable during closed-loop brain stimulation therapy, posing additional challenges for real-time signal acquisition. To address motion and stimulation artifacts with amplitudes reaching hundreds of mV while minimizing information loss, a sensor interface with high input range and fast artifacts recovery capability is essential. This paper presents a continuous-time track-and-zoom (CT-TAZ) technique designed to handle large artifacts events without saturation. The proposed system achieves a 3.6V/1.8V differential-mode/common-mode full-scale input range. Fabricated in a 180nm CMOS process, the prototype chip occupies an area of 0.694mm<sup>2</sup> and consumes 12/32.6/51.6μW for recordings without/with single-end/ with differential rail-to-rail artifacts. The system demonstrates an average artifacts recovery time of 65.3 μs under 3.6V stimulation artifacts, achieving an average artifacts recovery speed of 52.3mV<sub>pp</sub>/μs, which is 2.25× larger input range and 3× faster recovery compared to the state-of-the-art.</p>","PeriodicalId":94031,"journal":{"name":"IEEE transactions on biomedical circuits and systems","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143995414","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}
Gayas Mohiuddin Sayed, Armin Bartels, Daniel De Dorigo, Tim Fleiner, Nicole Rosskothen-Kuhl, Matthias Kuhl
{"title":"Stochastic Signal Processing Based Stimulation Artifact Cancellation in ΔΣ Neural Frontend.","authors":"Gayas Mohiuddin Sayed, Armin Bartels, Daniel De Dorigo, Tim Fleiner, Nicole Rosskothen-Kuhl, Matthias Kuhl","doi":"10.1109/TBCAS.2025.3563684","DOIUrl":"https://doi.org/10.1109/TBCAS.2025.3563684","url":null,"abstract":"<p><p>This paper presents a neural recorder frontend featuring electrical stimulation artifact cancellation by employing an adaptive LMS filter in the stochastic domain. The recording system comprises of a low-noise analog frontend and a 1st-order ΔΣ modulator. A power-efficient stochastic signal processor, occupying an area of 0.12 mm2, processes the ΔΣ modulator output bitstream to learn and compensate for artifacts induced by concurrent electrical stimulation. The proposed approach, validated on a prototype ASIC fabricated in 180 nm CMOS technology, has a total power consumption of 6.83 μW, with the stochastic signal processor consuming only 0.51 μW. Experimental results demonstrate that the system effectively suppresses peak-to-peak stimulation artifacts of 200 mV by approximately 33 dB over a 10 kHz bandwidth, establishing it as a novel state-of-the-art real-time artifact cancellation system. Furthermore, in-vitro validation for both biphasic and monophasic stimulation confirms its efficacy, with 74.3 mVpp artifacts from biphasic stimulation being attenuated by 25 dB.</p>","PeriodicalId":94031,"journal":{"name":"IEEE transactions on biomedical circuits and systems","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144056116","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}
{"title":"A 101-dB DR 2.2GΩ-Input-Impedance Direct Digitization ExG Front-End With Δ-Modulation.","authors":"Yuying Li, Hao Li, Tianxiang Qu, Qi Liu, Zhiliang Hong, Jiawei Xu","doi":"10.1109/TBCAS.2025.3563304","DOIUrl":"https://doi.org/10.1109/TBCAS.2025.3563304","url":null,"abstract":"<p><p>Long-term, continuous health monitoring imposes stringent demands on bio-recording analog front-end (AFE) circuits, specifically in terms of dynamic range (DR), noise, input impedance, and power consumption. This work introduces a DR-enhanced direct-digitization AFE based on a Δ-modulated transconductor (TC) stage, followed by a second-order ΔΣ ADC. In this architecture, the accumulated DAC is subtracted exclusively at the TC input stage, allowing the integrators to process only the low-amplitude Δ-modulated signal and thus relaxing the dynamic range constraints of conventional G<sub>m</sub>-C ΔΣ ADCs. The TC input stage achieves high input impedance and high linearity through a current-balancing transconductor and a flipped-voltage-follower (FVF) loop. Fabricated with a standard 180nm CMOS process, the proposed Δ-ΔΣ AFE exhibits an SNDR of 91 dB, a dynamic range of 101 dB, input referred noise of 58 nV/√Hz, and a power consumption of 63 μW. These results correspond to a FoMSNDR of 160.1 dB and a FoMDR of 170 dB. The AFE prototype has been validated through scalp EEG, leg EMG, and chest ECG with significant body movements, demonstrating its effectiveness as a motion-artifact-tolerant direct-ADC front end.</p>","PeriodicalId":94031,"journal":{"name":"IEEE transactions on biomedical circuits and systems","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144052464","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}
{"title":"A 6.4GΩ-Input-Impedance 104.5dB-CMRR 96dB-DR DD-AFE with Tri-Level IDAC for Small-Diameter Dry-Electrode Interface.","authors":"Yijie Li, Yuxiang Tang, Jianhong Zhou, Tianxiang Qu, Zhiliang Hong, Jiawei Xu","doi":"10.1109/TBCAS.2025.3558094","DOIUrl":"10.1109/TBCAS.2025.3558094","url":null,"abstract":"<p><p>This article presents a direct-digitization analog front end (DD-AFE) with enhanced input-impedance, common-mode rejection ratio (CMRR), and dynamic range (DR) for wearable biopotential (ExG) signal acquisition, especially for small-diameter dry electrodes. The DD-AFE employs a second-order continuous-time delta-sigma modulator (CT-ΔSM) and multiple circuit techniques to support direct-digitization readouts. These include 1) A high input-impedance input feedforward (FF), embedded in a 4-input 4-bit successive approximation register (SAR) quantizer. This allows two integrators to adopt a compact and energy-efficient G<sub>m</sub>-C structure, and improves stability and linearity, resulting in a 6.6dB increase in DR, 42dB increase in SQNR at peak input and a unity-gain signal transfer function (STF) with a gain flatness of 0.04%. 2) A fixed-voltage dead-band assisted tri-level current-steering DAC (IDAC). It not only increases the DR and CMRR of the DD-AFE but also eliminates the harmonic distortion induced by tri-level dynamic element matching (DEM). 3) A high-gain two-stage G<sub>m</sub>-boosting inverter-based OTA with embedded low-frequency chopping. The former largely improves linearity and CMRR, while the latter mitigates 1/f noise without compromising the input impedance. Fabricated in a 0.18-μm CMOS process, this DD-AFE achieves 6.4GΩ input impedance and 104.5dB CMRR at 50Hz, as well as 90.4dB peak SNDR, 96dB DR, and up to 425mV<sub>PP</sub> linear input range.</p>","PeriodicalId":94031,"journal":{"name":"IEEE transactions on biomedical circuits and systems","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143784659","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}