检索结果-内蒙古大学图书馆

Guest Editorial: Special Issue on Selected Articles From ieee BioCAS 2023

ieee Transactions on biomedical circuits and systems 2024年第4期18卷 718-719页

作者： Chung-Chih Hung Mohamed Atef Vanessa Chen Department of Electronics and Electrical Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Department of Electrical and Communication Engineering United Arab Emirates University Al Ain Abu Dhabi UAE Department of Electrical and Computer Engineering Carnegie Mellon University Pittsburgh PA USA

The 12 articles in this special issue were presented at the 2023 ieee biomedical circuits and systems conference (BioCAS) in Toronto, Canada, from October 19–21, 2023. BioCAS 2023 was jointly sponsored by the ieee circuits and systems (CAS) Society, ieee Solid-State circuits (SSC) Society, and the ieee Engineering in Medicine and Biology (EMB) Society.

关键词： Special issues and sections Meetings biomedical engineering circuits and systems

来源：评论

学校读者我要写书评

暂无评论

EpiDeNet: An Energy-Efficient Approach to Seizure Detection for Embedded systems

EpiDeNet: An Energy-Efficient Approach to Seizure Detection ...

引用

2023 ieee biomedical circuits and systems conference, BioCAS 2023

作者： Ingolfsson, Thorir Mar Chakraborty, Upasana Wang, Xiaying Beniczky, Sandor Ducouret, Pauline Benatti, Simone Ryvlin, Philippe Cossettini, Andrea Benini, Luca Eth Zürich Zürich Switzerland Aarhus University Hospital Aarhus Denmark Dianalund Denmark Switzerland Università di Modena e Reggio Emilia Reggio Emilia Italy University of Bologna Bologna Italy

ISBN: (纸本)9798350300260

Epilepsy is a prevalent neurological disorder that affects millions of individuals globally, and continuous monitoring coupled with automated seizure detection appears as a necessity for effective patient treatment. To enable long-term care in daily-life conditions, comfortable and smart wearable devices with long battery life are required, which in turn set the demand for resource-constrained and energy-efficient computing solutions. In this context, the development of machine learning algorithms for seizure detection faces the challenge of heavily imbalanced datasets. This paper introduces EpiDeNet, a new lightweight seizure detection network, and Sensitivity-Specificity Weighted Cross-Entropy (SSWCE), a new loss function that incorporates sensitivity and specificity, to address the challenge of heavily unbalanced datasets. The proposed EpiDeNet-SSWCE approach demonstrates the successful detection of 91.16% and 92.00% seizure events on two different datasets (CHB-MIT and PEDESITE, respectively), with only four EEG channels. A three-window majority voting-based smoothing scheme combined with the SSWCE loss achieves 3× reduction of false positives to 1.18 FP/h. EpiDeNet is well suited for implementation on low-power embedded platforms, and we evaluate its performance on two ARM Cortex-based platforms (M4F/M7) and two parallel ultra-low power (PULP) systems (GAP8, GAP9). The most efficient implementation (GAP9) achieves an energy efficiency of 40 GMAC/s/W, with an energy consumption per inference of only 0.051 mJ at high performance (726.46 MMAC/s), outperforming the best ARM Cortex-based solutions by approximately 160× in energy efficiency. The EpiDeNet-SSWCE method demonstrates effective and accurate seizure detection performance on heavily imbalanced datasets, while being suited for implementation on energy-constrained platforms. © 2023 ieee.

关键词： Embedded Deployment Epilepsy Seizure Detection Wearable devices

来源：评论

学校读者我要写书评

暂无评论

Discrete-Analog Filters on Switchable Capacitors with a Summator of Input and Output Signals on a Differential Difference Operational Amplifier

Discrete-Analog Filters on Switchable Capacitors with a Summ...

引用

2024 ieee Ural-Siberian conference on biomedical Engineering, Radioelectronics and Information Technology, USBEREIT 2024

作者： Denisenko, Darya Titov, Alexey Prokopenko, Nikolay Butyrlagin, Nikolay Don State Technical University Department Of Scientific Research Rostov-on-Don Russia Southern Federal University Department Of Automatic Control Systems Rostov-on-Don Russia Don State Technical University Department Of Information Systems And Radio Engineering Rostov-on-Don Russia

ISBN: (纸本)9798350362893

Four new modifications of discrete analog filters (DAF) of second order low frequencies (LPF) on switched capacitors, which are protected by the authors of the article as objects of intellectual property, have been developed and studied. In the considered DAF family, unlike other known circuit solutions, summation of input and output signals is provided using a differential difference operational amplifier. As a result, the low-pass filter transmission coefficient in the passband does not depend on the passive elements of the circuit and is always equal to minus one. Buffer amplifiers in two DAF circuits are necessary to reduce the influence of switching circuits on transient processes. In the Micro-Cap environment, computer simulations of four modifications of DAFs were performed, showing that the proposed DAFs have the amplitude-frequency response of a low-pass filter. Sequences of pulses are given that should control four electronic keys, made, for example, on CMOS transistors. Graphs of transient processes of the DAF are shown for an input sinusoidal signal with an amplitude of 1V and a frequency of 1591 Hz, equal to the pole frequency at a switching frequency of electronic keys of 1 MHz. The DAF transmission coefficients for the input sinusoidal signal in different frequency ranges are determined. It has been established that with the selected parameters of the elements in the considered DAFs, which are low-pass filters, the input signal at a frequency of 159.10 kHz is attenuated by more than 60 dB. © 2024 ieee.

关键词： Low pass filters

来源：评论

学校读者我要写书评

暂无评论

A 10-Bit Power Efficient SAR ADC Designed with Enhanced Signal Integrity for biomedical Applications

A 10-Bit Power Efficient SAR ADC Designed with Enhanced Sign...

引用

2024 International conference on Smart Electronics and Communication systems, ISENSE 2024

作者： Soundharya, A.A. Santhosh Kumar, A. Gracia Nirmala Rani, D. Thiagarajar College of Engineering Department of electronics and communication engineering Tamil Nadu Madurai India

ISBN: (数字)9798331528126

ISBN: (纸本)9798331528126

biomedical devices require high resolution, fast conversion speeds, low power consumption, and compact designs to ensure accurate monitoring, diagnosis, and longer battery life. Traditional SAR ADCs often struggle with limitations in resolution, noise, power efficiency, and speed, which hinders their applicability in healthcare. This research introduces a 10-bit low-noise SAR ADC designed with 90 nm CMOS technology operating at a 1V supply, achieving a power consumption of 11.887 microwatts for a 1-megahertz sinusoidal input signal. The design incorporates a double-tail dynamic latch comparator, known for its optimal power usage and minimal propagation delay, and explores split capacitive DAC structures for enhanced low-power efficiency. These improvements make the ADC suitable for reliable and energy-efficient biomedical applications, advancing healthcare technology. © 2024 ieee.

关键词： CMOS integrated circuits

来源：评论

学校读者我要写书评

暂无评论

Signal Reconstruction from Level Crossing ADC 34

Signal Reconstruction from Level Crossing ADC

引用

34th Irish Signals and systems conference (ISSC)

作者： Harbison, Thomas Saeed, Maryam Cardiff, Barry Univ Coll Dublin Sch Elect & Elect Engn Dublin Ireland

ISBN: (纸本)9798350340570

The processing of electrocardiogram (ECG) signals enables the diagnoses of many different heart conditions. Finding signal processing methods that reduce the computational intensity of ECG processing algorithms can facilitate faster and cheaper identification of often life threatening cardiovascular diseases. This conference paper seeks to analyse different methods of reconstructing ECG signals that have been sampled by a Level Crossing Analog to Digital Converter (LC-ADC). Traditionally, ECG signals are sampled uniformly in time. However energy savings can be achieved by using an LC-ADC at the cost of the ECG signal being non-uniformly sampled in time, making downstream signal processing more difficult. Classification of these signals often requires post-processing techniques to derive a fixed length vector of features as an input to a conventional classifier. One way to achieve this is through the use of time-domain interpolation. We will compare the results of several different interpolation algorithms with the goal of finding the most accurate method of reconstructing the signal sampled by the LC-ADC.

关键词： biomedical Signal Processing Interpolation Level Crossing ADC Fourier ECG

来源：评论

学校读者我要写书评

暂无评论

Multipolar Stimulator for DBS Application with Concurrent Imbalance Compensation 30

Multipolar Stimulator for DBS Application with Concurrent Im...

引用

30th ieee International conference on Electronics, circuits and systems, ICECS 2023

作者： Shokri, Reza Koolivand, Yarallah Shoaei, Omid Aiello, Orazio Caviglia, Daniele D. University of Genoa DITEN Genoa Italy University of Tehran Biomedical Integrated System Lab Tehran Iran Khajeh Nasir Toosi University of Technology Tehran Iran

ISBN: (纸本)9798350326499

Deep brain stimulation systems which consist of recording, stimulation, and detection functions play a key role in the treatment of neurological disorders such as Parkinson's, Epilepsy, etc. In this paper, a multipolar biphasic current stimulation system is presented. The system includes 5 stimulators on each side of the brain, four of which are connected locally in the brain, and the fifth is connected to the body of the implantable pulse generator for monopolar stimulation. This stimulator can also be used as a voltage stimulator. The maximum current that can be supplied by the stimulator is 12.75 mA, with 8-bit resolution. Passive charge balancing is used, and due to safety concerns, a DC blocking capacitor is used for electrical isolation and negligible DC current flow even at system failure. In the proposed architecture, the mismatch among the total stimulation current sinks can be compensated up to ±45% by current sources, and the current errors are distributed with the ideal ratio of the adjusted currents. The stimulator voltage can be varied up to 30V. The efficiency of this stimulator at the mid-high load is 55% without considering the digital control core. © 2023 ieee.

关键词： Electric loads

来源：评论

学校读者我要写书评

暂无评论

Skilog: A Smart Sensor System for Performance Analysis and Biofeedback in Ski Jumping

Skilog: A Smart Sensor System for Performance Analysis and B...

引用

2023 ieee biomedical circuits and systems conference, BioCAS 2023

作者： Schulthess, Lukas Ingolfsson, Thorir Mar Nolke, Marc Magno, Michele Benini, Luca Leitner, Christoph Eth Zürich Center for Project Based Learning Zürich Switzerland Pzn Krakow Poland Eth Zürich Integrated Systems Laboratory Zürich Switzerland University of Bologna Dei Bologna Italy

ISBN: (纸本)9798350300260

In ski jumping, low repetition rates of jumps limit the effectiveness of training. Thus, increasing learning rate within every single jump is key to success. A critical element of athlete training is motor learning, which has been shown to be accelerated by feedback methods. In particular, a fine-grained control of the center of gravity in the in-run is essential. This is because the actual takeoff occurs within a blink of an eye (∼ 300 ms), thus any unbalanced body posture during the in-run will affect *** paper presents a smart, compact, and energy-efficient wireless sensor system for real-time performance analysis and biofeedback during ski jumping. The system operates by gauging foot pressures at three distinct points on the insoles of the ski boot at 100 Hz. Foot pressure data can either be directly sent to coaches to improve their feedback, or fed into a Machine Learning (ML) model to give athletes instantaneous in-action feedback using a vibration motor in the ski boot. In the biofeedback scenario, foot pressures act as input variables for an optimized XGBoost model. We achieve a high predictive accuracy of 92.7 % for center of mass predictions (dorsal shift, neutral stand, ventral shift). Subsequently, we parallelized and fine-tuned our XGBoost model for a RISC-V based low power parallel processor (GAP9), based on the Parallel Ultra-Low Power (PULP) architecture. We demonstrate real-time detection and feedback (0.0109 ms/inference) using our on-chip deployment. The proposed smart system is unobtrusive with a slim form factor (13 mm baseboard, 3.2 mm antenna) and a lightweight build (26 g). Power consumption analysis reveals that the system's energy-efficient design enables sustained operation over multiple days (up to 300 hours) without requiring recharge. © 2023 ieee.

关键词： Biomechanics Data logger Sensor Sport tinyML Wearable Wireless

来源：评论

学校读者我要写书评

暂无评论

Low-cost PVDF High-Frequency Ultrasound Sensor Design and Manufacturing for Thermoacoustic Imaging Applications 29

Low-cost PVDF High-Frequency Ultrasound Sensor Design and Ma...

引用

29th ieee International conference on Electronics, circuits and systems (ieee ICECS)

作者： Vallicelli, Elia A. Baig, Mirza Hassan La Gala, Andrea Chirico, Giuseppe Baschirotto, Andrea De Matteis, Marcello Univ Milano Bicocca Milan Italy

ISBN: (数字)9781665488235

ISBN: (纸本)9781665488235

This work presents the development and experimental validation of an ultrasound piezoelectric sensor for thermoacoustic imaging that exploits printed circuit boards technology to define with high precision the sensor active area while minimizing manufacturing complexity and cost. A prototype single-channel sensor with 4x4 mm active area has been manufactured and experimentally validated in electrical and acoustic testbenches.

关键词： circuits and systems for biomedical Applications Radiation Therapy Ultrasound Sensors

来源：评论

学校读者我要写书评

暂无评论

A 0.46 nV/√Hz JFET Low-Noise Amplifier for Characterization of Nanoelectrode Coating Materials 29

A 0.46 nV/√Hz JFET Low-Noise Amplifier for Characterization...

引用

29th ieee International conference on Electronics, circuits and systems (ieee ICECS)

作者： Vallicelli, Elia A. Di Palma, Valerio De Matteis, Marcello Baschirotto, Andrea Fanciulli, Marco Univ Milano Bicocca Dept Phys Milan Italy Univ Milano Bicocca Dept Mat Sci Milan Italy

ISBN: (数字)9781665488235

ISBN: (纸本)9781665488235

This work presents the design and experimental validation of a low-noise amplifier based on a ultra-low-noise JFET for noise characterization of materials samples for neural interfaces. The JFET LNA amplifies the sample noise power by 46 dB well above a lock-in amplifier noise floor, used as spectrum analyzer for noise characterization. The LNA exploits the high gm and low flicker corner frequency of JFETs to achieve 0.15 dB noise figure. The JFET LNA has been characterized in terms of frequency response and noise power spectrum and experimentally validated by characterizing the noise spectrum of a platinum silicide (PtSi) sample.

关键词： JFET circuits and systems for biomedical Applications

来源：评论

学校读者我要写书评

暂无评论

Pathological Diagnosis of Gastric Cancer Using Advanced MIFNET Algorithm 2

Pathological Diagnosis of Gastric Cancer Using Advanced MIFN...

引用

2nd ieee International conference on Integrated circuits and Communication systems, ICICACS 2024

作者： Rajeswari, S. Divya, G. Indumathi, R. Vasuki, R. Bharath Institute of Higher Education and Research Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350317558

By employing MIFNET, an advanced Deep Learning (DL) algorithm, this study developed an innovative method for detecting gastric cancer (GC). Incorporating the Multi-task Net, Fusion Net, and Global Net techniques, MIFNET substantially improves the precision of GC detection, according to the study. By employing histological features, genotypes, and genetic phenotypes, this study presents an innovative methodology for classifying GC, which has the potential to facilitate early detection, prevention, and treatment. AI (Artificial Intelligence) may be a useful instrument in pathology, particularly for GC, which has an extremely dismal prognosis, according to the findings. The algorithm's capacity to make precise predictions regarding the presence of GC without requiring additional diagnostic procedures is encouraging considering the worldwide scarcity of pathologists. This augur well for the precision and efficacy of the diagnostic process. As the paper demonstrates, additional research is required to validate and implement these developments. The ultimate objective is to develop GC diagnostic models that are more precise and efficient than those currently in use. © 2024 ieee.

关键词： Accuracy Deep Learning Fusion Net Gastric Cancer Global Net Multi-Task Net Prediction

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：