IEEE transactions on biomedical circuits and systems最新文献_第8页

An Ultra-Low Power Wearable BMI System With Continual Learning Capabilities 具有持续学习功能的超低功耗可穿戴式 BMI 系统

IEEE transactions on biomedical circuits and systems Pub Date : 2024-09-10 DOI: 10.1109/TBCAS.2024.3457522

Lan Mei;Thorir Mar Ingolfsson;Cristian Cioflan;Victor Kartsch;Andrea Cossettini;Xiaying Wang;Luca Benini

{"title":"An Ultra-Low Power Wearable BMI System With Continual Learning Capabilities","authors":"Lan Mei;Thorir Mar Ingolfsson;Cristian Cioflan;Victor Kartsch;Andrea Cossettini;Xiaying Wang;Luca Benini","doi":"10.1109/TBCAS.2024.3457522","DOIUrl":"10.1109/TBCAS.2024.3457522","url":null,"abstract":"Driven by the progress in efficient embedded processing, there is an accelerating trend toward running machine learning models directly on wearable Brain-Machine Interfaces (BMIs) to improve portability and privacy and maximize battery life. However, achieving low latency and high classification performance remains challenging due to the inherent variability of electroencephalographic (EEG) signals across sessions and the limited onboard resources. This work proposes a comprehensive BMI workflow based on a CNN-based Continual Learning (CL) framework, allowing the system to adapt to inter-session changes. The workflow is deployed on a wearable, parallel ultra-low power BMI platform (BioGAP). Our results based on two in-house datasets, Dataset A and Dataset B, show that the CL workflow improves average accuracy by up to 30.36% and 10.17%, respectively. Furthermore, when implementing the continual learning on a Parallel Ultra-Low Power (PULP) microcontroller (GAP9), it achieves an energy consumption as low as 0.45 mJ per inference and an adaptation time of only 21.5 ms, yielding around 25 h of battery life with a small 100 mAh, 3.7 V battery on BioGAP. Our setup, coupled with the compact CNN model and on-device CL capabilities, meets users’ needs for improved privacy, reduced latency, and enhanced inter-session performance, offering good promise for smart embedded real-world BMIs.","PeriodicalId":94031,"journal":{"name":"IEEE transactions on biomedical circuits and systems","volume":"19 3","pages":"511-522"},"PeriodicalIF":0.0,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142195023","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}

引用次数: 0

Real-Time sEMG Processing With Spiking Neural Networks on a Low-Power 5K-LUT FPGA 在低功耗 5K-LUT FPGA 上利用尖峰神经网络进行实时 sEMG 处理

IEEE transactions on biomedical circuits and systems Pub Date : 2024-09-09 DOI: 10.1109/TBCAS.2024.3456552

Matteo Antonio Scrugli;Gianluca Leone;Paola Busia;Luigi Raffo;Paolo Meloni

{"title":"Real-Time sEMG Processing With Spiking Neural Networks on a Low-Power 5K-LUT FPGA","authors":"Matteo Antonio Scrugli;Gianluca Leone;Paola Busia;Luigi Raffo;Paolo Meloni","doi":"10.1109/TBCAS.2024.3456552","DOIUrl":"10.1109/TBCAS.2024.3456552","url":null,"abstract":"The accurate modeling of hand movement based on the analysis of surface electromyographic (sEMG) signals offers exciting opportunities for the development of complex prosthetic devices and human-machine interfaces, moving from discrete gesture recognition, towards continuous movement tracking. In this study, we present two solutions for real-time sEMG processing, based on lightweight Spiking Neural Networks (SNNs) and efficiently implemented on a Lattice iCE40-UltraPlus FPGA, especially suitable for low-power applications. We first assess the performance in the discrete finger gesture recognition task, considering as a reference the NinaPro DB5 dataset, and demonstrating an accuracy of 83.17% in the classification of twelve different finger gestures. We also consider the more challenging problem of continuous finger force modeling, referencing the Hyser dataset for finger tracking during independent extension and contraction exercises. The assessment reveals a correlation of up to 0.875 with the ground-truth forces. Our systems take advantage of SNNs’ inherent efficiency and, dissipating 11.31 mW in active mode, consume 44.6 µJ for a gesture recognition classification and 1.19 µJ for a force modeling inference. Considering dynamic power-consumption management and the introduction of idle periods, average power drops to 1.84 mW and 3.69 mW for these respective tasks.","PeriodicalId":94031,"journal":{"name":"IEEE transactions on biomedical circuits and systems","volume":"19 1","pages":"68-81"},"PeriodicalIF":0.0,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10669772","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142195025","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}

引用次数: 0

NEXUS: A 28nm 3.3pJ/SOP 16-Core Spiking Neural Network With a Diamond Topology for Real-Time Data Processing NEXUS：用于实时数据处理的 28 纳米 3.3pJ/SOP 16 核钻石拓扑尖峰神经网络。

IEEE transactions on biomedical circuits and systems Pub Date : 2024-08-30 DOI: 10.1109/TBCAS.2024.3452635

Maryam Sadeghi;Yasser Rezaeiyan;Dario Fernandez Khatiboun;Sherif Eissa;Federico Corradi;Charles Augustine;Farshad Moradi

{"title":"NEXUS: A 28nm 3.3pJ/SOP 16-Core Spiking Neural Network With a Diamond Topology for Real-Time Data Processing","authors":"Maryam Sadeghi;Yasser Rezaeiyan;Dario Fernandez Khatiboun;Sherif Eissa;Federico Corradi;Charles Augustine;Farshad Moradi","doi":"10.1109/TBCAS.2024.3452635","DOIUrl":"10.1109/TBCAS.2024.3452635","url":null,"abstract":"The realization of brain-scale spiking neural networks (SNNs) is impeded by power constraints and low integration density. To address these challenges, multi-core SNNs are utilized to emulate numerous neurons with high energy efficiency, where spike packets are routed through a network-on-chip (NoC). However, the information can be lost in the NoC under high spike traffic conditions, leading to performance degradation. This work presents NEXUS, a 16-core SNN with a diamond-shaped NoC topology fabricated in 28-nm CMOS technology. It integrates 4096 leaky integrate-and-fire (LIF) neurons with 1M 4-bit synaptic weights, occupying an area of 2.16 mm2. The proposed NoC architecture is scalable to any network size, ensuring no data loss due to contending packets with a maximum routing latency of 5.1<inline-formula><tex-math>$mu$</tex-math></inline-formula>s for 16 cores. The proposed congestion management method eliminates the need for FIFO in routers, resulting in a compact router footprint of 0.001 mm2. The proposed neurosynaptic core allows for increasing the processing speed by up to 8.5<inline-formula><tex-math>$times$</tex-math></inline-formula> depending on input sparsity. The SNN achieves a peak throughput of 4.7 GSOP/s at 0.9 V, consuming a minimum energy per synaptic operation (SOP) of 3.3 pJ at 0.55 V. A 4-layer feed-forward network is mapped onto the chip, classifying MNIST digits with 92.3% accuracy at 8.4K-classification/s and consuming 2.7-<inline-formula><tex-math>$mu$</tex-math></inline-formula>J/classification. Additionally, an audio recognition task mapped onto the chip achieves 87.4% accuracy at 215-<inline-formula><tex-math>$mu$</tex-math></inline-formula>J/classification.","PeriodicalId":94031,"journal":{"name":"IEEE transactions on biomedical circuits and systems","volume":"19 3","pages":"523-535"},"PeriodicalIF":0.0,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142116468","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}

引用次数: 0

GCOC: A Genome Classifier-On-Chip Based on Similarity Search Content Addressable Memory GCOC：基于相似性搜索内容可寻址内存的片上基因组分类器。

IEEE transactions on biomedical circuits and systems Pub Date : 2024-08-28 DOI: 10.1109/TBCAS.2024.3449788

Yuval Harary;Paz Snapir;Shir Siman Tov;Chen Kruphman;Eyal Rechef;Zuher Jahshan;Esteban Garzón;Leonid Yavits

{"title":"GCOC: A Genome Classifier-On-Chip Based on Similarity Search Content Addressable Memory","authors":"Yuval Harary;Paz Snapir;Shir Siman Tov;Chen Kruphman;Eyal Rechef;Zuher Jahshan;Esteban Garzón;Leonid Yavits","doi":"10.1109/TBCAS.2024.3449788","DOIUrl":"10.1109/TBCAS.2024.3449788","url":null,"abstract":"GCOC is a genome classification system-on-chip (SoC) that classifies genomes by <inline-formula><tex-math>$k$</tex-math></inline-formula>-mer matching, an approach that divides a DNA query sequence into a set of short DNA fragments of size <italic>k, which are searched in a reference genome database, with the underlying assumption that sequenced DNA reads of the same organism (or its close variants) share most of such <inline-formula><tex-math>$k$</tex-math></inline-formula>-mers. At the core of GCOC is a similarity, or approximate search-capable Content Addressable Memory (SAS-CAM), which in addition to exact match, also supports approximate, or Hamming distance tolerant search. Classification operation is controlled by an embedded RISC-V processor. GCOC classification platform was designed and manufactured in a commercial 65nm process. We conduct a thorough analysis of GCOC classification efficiency as well as its performance, silicon area, and power consumption using silicon measurements. GCOC classifies 769.2K short DNA reads/sec. The silicon area of GCOC SoC is 3.12 <inline-formula><tex-math>$mathrm{mm}^{2}$</tex-math></inline-formula> and its power consumption is 1.27 <inline-formula><tex-math>$mathrm{mW}$</tex-math></inline-formula>. We envision GCOC deployed as a field (for example at points of care) portable classifier where the classification is required to be real-time, easy to operate and energy efficient.","PeriodicalId":94031,"journal":{"name":"IEEE transactions on biomedical circuits and systems","volume":"19 3","pages":"484-495"},"PeriodicalIF":0.0,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142086424","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}

引用次数: 0

An Electrochemical CMOS Biosensor Array Using Phase-Only Modulation With 0.035% Phase Error and In-Pixel Averaging 使用相位误差为 0.035% 的纯相位调制和像素内平均的电化学 CMOS 生物传感器阵列

IEEE transactions on biomedical circuits and systems Pub Date : 2024-08-28 DOI: 10.1109/TBCAS.2024.3450843

Aditi Jain;Saeromi Chung;Eliah Aronoff Spencer;Drew A. Hall

引用次数: 0

Parallel Resonant Magnetic Field Generator for Biomedical Applications 用于生物医学应用的并联谐振磁场发生器。

IEEE transactions on biomedical circuits and systems Pub Date : 2024-08-28 DOI: 10.1109/TBCAS.2024.3450881

Yuan Lei;Shoulong Dong;Runze Liang;Sizhe Xiang;Qinyu Huang;Junhao Ma;Hongyu Kou;Liang Yu;Chenguo Yao

{"title":"Parallel Resonant Magnetic Field Generator for Biomedical Applications","authors":"Yuan Lei;Shoulong Dong;Runze Liang;Sizhe Xiang;Qinyu Huang;Junhao Ma;Hongyu Kou;Liang Yu;Chenguo Yao","doi":"10.1109/TBCAS.2024.3450881","DOIUrl":"10.1109/TBCAS.2024.3450881","url":null,"abstract":"In recent years, pulsed magnetic field (PMF) have attracted significant attention as a non-invasive electroporation method in the biomedical field. To further explore the biomedical effects generated by oscillating PMF, we designed a novel PMF generator for biomedical research. Based on resonance principles, the designed generator outputs sinusoidal oscillating PMF. To validate the feasibility and application value of the designed topology, a miniaturized platform was constructed using a selected multi-turn solenoid coil. The output performance of the generator was tested under different discharge voltage levels. The results revealed that the current multiplication factor remained consistently around 2 times, with the energy efficiency and circuit quality factor maintained at 82% and above 4.5, respectively. In addition, the generator's ability to flexibly modulate the number of pulse oscillations was demonstrated. The compatibility of the designed coil parameters and generator circuit parameters was analyzed, with tests on the effects of coil resistance and switch action time on the generator's output performance. Based on the magnetic field action platform, a simulation model of the actual scale coil was established. The spatial and temporal distribution of the magnetic field, induced electric field, and power transmission in the target area were described from multiple angles. Finally, biological experiments conducted using the constructed generator revealed the synergistic effect of sinusoidal oscillating PMF combined with drugs in tumor cell killing.","PeriodicalId":94031,"journal":{"name":"IEEE transactions on biomedical circuits and systems","volume":"19 3","pages":"496-510"},"PeriodicalIF":0.0,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142086426","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}

引用次数: 0

IEEE Transactions on Biomedical Circuits and Systems Publication Information IEEE 生物医学电路与系统论文集》出版信息

IEEE transactions on biomedical circuits and systems Pub Date : 2024-08-21 DOI: 10.1109/TBCAS.2024.3437552

引用次数: 0

Guest Editorial: Special Issue on Selected Articles From IEEE BioCAS 2023 特邀编辑：IEEE BioCAS 2023 文章选编特刊

IEEE transactions on biomedical circuits and systems Pub Date : 2024-08-21 DOI: 10.1109/TBCAS.2024.3434009

Chung-Chih Hung;Mohamed Atef;Vanessa Chen

引用次数: 0

IEEE Circuits and Systems Society Information 电气和电子工程师学会电路与系统协会信息

IEEE transactions on biomedical circuits and systems Pub Date : 2024-08-21 DOI: 10.1109/TBCAS.2024.3437554

引用次数: 0

TechRxiv: Share Your Preprint Research with the World! TechRxiv：与世界分享您的预印本研究成果！

IEEE transactions on biomedical circuits and systems Pub Date : 2024-08-21 DOI: 10.1109/TBCAS.2024.3439815

引用次数: 0