基于FPGA的便攜心電智能診斷加速器及優(yōu)化選芯方案
電子技術(shù)應(yīng)用
郭千禧,劉文涵,羅德宇,黃啟俊
武漢大學(xué) 物理科學(xué)與技術(shù)學(xué)院
摘要: 心電圖(electrocardiogram, ECG)是診斷與心臟相關(guān)疾病的關(guān)鍵工具,可穿戴心電監(jiān)護(hù)儀Holter是院外檢測(cè)的重要手段,小型化、便攜性、實(shí)時(shí)檢測(cè)是優(yōu)化方向。人工智能技術(shù)應(yīng)用于包括心電診斷的各個(gè)領(lǐng)域,但存在參數(shù)量大、難于小型化、計(jì)算速度慢的問(wèn)題,不滿足便攜心電監(jiān)護(hù)儀的要求,而可編程邏輯門器件(Field-Programmable Gate Array, FPGA)有并行加速的特性。在AI智能算法硬件化的工程應(yīng)用上,存在成本、速度、資源利用率的權(quán)衡,需要進(jìn)行科學(xué)的芯片選型。開發(fā)了一種基于1D-CNN的、用于心電診斷的BeatNet ,對(duì)于4分類的檢測(cè)任務(wù),該模型具有98.5% 的分類準(zhǔn)確率。
中圖分類號(hào):TN911.72 文獻(xiàn)標(biāo)志碼:A DOI: 10.16157/j.issn.0258-7998.234802
中文引用格式: 郭千禧,劉文涵,羅德宇,等. 基于FPGA的便攜心電智能診斷加速器及優(yōu)化選芯方案[J]. 電子技術(shù)應(yīng)用,2024,50(6):89-95.
英文引用格式: Guo Qianxi,Liu Wenhan,Luo Deyu,et al. FPGA-based portable ECG smart diagnostic gas pedal and optimized core selection scheme[J]. Application of Electronic Technique,2024,50(6):89-95.
中文引用格式: 郭千禧,劉文涵,羅德宇,等. 基于FPGA的便攜心電智能診斷加速器及優(yōu)化選芯方案[J]. 電子技術(shù)應(yīng)用,2024,50(6):89-95.
英文引用格式: Guo Qianxi,Liu Wenhan,Luo Deyu,et al. FPGA-based portable ECG smart diagnostic gas pedal and optimized core selection scheme[J]. Application of Electronic Technique,2024,50(6):89-95.
FPGA-based portable ECG smart diagnostic gas pedal and optimized core selection scheme
Guo Qianxi,Liu Wenhan,Luo Deyu,Huang Qijun
Department of Physical Science and Technology, Wuhan University
Abstract: Electrocardiogram (ECG) is a key tool for diagnosing heart-related diseases. The wearable ECG monitor Holter is an important means of out-of-hospital detection. Miniaturization, portability, and real-time detection are the optimization directions. Artificial intelligence technology is used in various fields including electrocardiogram diagnosis, but there are problems such as large number of parameters, difficulty in miniaturization, and slow calculation speed. It does not meet the requirements of portable electrocardiogram monitors, and programmable logic gate devices (Field-Programmable Gate Array, FPGA) has parallel acceleration characteristics. This article developed a BeatNet based on 1D-CNN for ECG diagnosis.
Key words : electrocardiogram detection;deep learning;FPGA;RTL-level;portable medical device
引言
根據(jù)世界衛(wèi)生組織的數(shù) NC據(jù)[1],心血管疾?。–ardiovascular disease, CVD)仍然是全球健康面臨的重大挑戰(zhàn)。CVD是全球死亡的主要原因(占全部死亡原因的35%),每年約有1790萬(wàn)人死于此因。在心血管疾病的預(yù)防和治療中,心電圖(electrocardiogram, ECG)在檢測(cè)和診斷各種心臟狀況方面起著關(guān)鍵作用[2]。解讀心電圖需要一套特定的技能和知識(shí),深度學(xué)習(xí)的最新進(jìn)展[3]使得高準(zhǔn)確性的人工智能算法用于心電信號(hào)診斷,一方面可以大幅度減少醫(yī)生診斷工作量,另一方面配合邊緣硬件部署可以實(shí)時(shí)自動(dòng)監(jiān)測(cè)心臟狀態(tài)。
本文詳細(xì)內(nèi)容請(qǐng)下載:
http://theprogrammingfactory.com/resource/share/2000006037
作者信息:
郭千禧,劉文涵,羅德宇,黃啟俊
(武漢大學(xué) 物理科學(xué)與技術(shù)學(xué)院,湖北 武漢430072)
此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。