arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.09575eess.SP
收藏

用于Jetson Nano的JNEEG屏蔽板:实现基于深度学习的实时EEG信号处理

JNEEG shield for Jetson Nano for real-time EEG signal processing with deep learning

Ildar Rakhmatulin

AI总结:

本研究推出可将Jetson Nano转为8通道脑机接口的JNEEG设备,支持无需数据传输的深度学习实时EEG等信号处理,经测试其噪声与精度满足机器学习应用需求,为低成本神经科学研究及应用提供了便捷方案。

摘要:

本文介绍了一种通过JNEEG设备进入神经科学领域的便捷途径。该设备可将Jetson Nano开发板转换为脑机接口,能够轻松测量8通道的EEG(脑电图)、EMG(肌电图)和ECG(心电图)信号。借助Jetson Nano,无需任何数据传输即可利用深度学习进行实时信号处理和EEG特征实时提取。过去十年间,人工智能的普及对包括神经生物学在内的多个行业产生了显著影响。机器学习技术的整合为EEG信号在各科技领域的实际应用开辟了道路。这种研究兴趣的激增使得能够通过非侵入性电极记录EEG信号的低成本脑机接口设备广泛普及。JNEEG设备在噪声水平和准确性方面表现令人满意,可用于结合机器学习的应用任务。

英文摘要:

The article presents an accessible route into the field of neuroscience through the JNEEG device. This device allows converting the Jetson Nano board into a brain-computer interface, making it easy to measure EEG, EMG, and ECG signals with 8 channels. With Jetson Nano is possible use deep learning for real-time signal processing and feature extraction from EEG in real-time without any data transmission. Over the past decade, the proliferation of artificial intelligence has significantly impacted various industries, including neurobiology. The integration of machine learning techniques has opened avenues for practical applications of EEG signals across technology sectors. This surge in interest has led to the widespread popularity of low-cost brain-computer interface devices capable of recording EEG signals using non-invasive electrodes. JNEEG device demonstrates satisfactory noise levels and accuracy for use in applied tasks with machine learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑