Treffer: 基于Android平台的精神疲劳检测系统的设计与应用.

Objective To design a mental fatigue detection system to execute real-time detection and monitoring of meutal fatigue. Methods A mental fatigue detection system composed of a mobile terminal and a server terminal was designed and implemented with the principles of accuracy, usability and portability, EEG signal multi-scale entropy combined with longshort term memory(LSTM) artificial neural network model as well as MindWave series single-channel EEG acquisition device. The mobile terminal was developed with Android Studio and Java programming language, and the server terminal was realized with Eclipse and Tomcat operation environment. Results The system displayed EEG waveform, concentration and meditation curve, α wave, β wave and θ wave waveform extracted from the original EEG data, quantified the level of mental fatigue, stored user data and constantly improved the LSTM artificial neural network model, so that the quantitative results could be more and more accurate. Conclusion The mental fatigue detection system based on Android platform is small and convenient, which can detect and monitor users’ mental fatigue state in a simple, fast and real-time way, and can prevent safety accidents caused by fatigue. [ABSTRACT FROM AUTHOR]

目的:设计一套基于Android平台的精神疲劳检测系统,实时检测、监测被测对象的精神疲劳状态。方法:遵循准确性、易用性、便携性原则利用脑电信号多尺度熵结合长短期记忆(long-short term memory,LSTM)人工神经网络模型,通过MindWave系列单通道脑电信号采集设备,设计并实现包括移动端和服务器端两大部分的精神疲劳检测系统。其中移动端采用Android Studio作为开发工具通过Java编程语言进行设计;服务器端采用Eclipse作为开发工具在Tomcat运行环境下进行设计。结果:该系统不仅可以显示脑电信号波形图,专注度、冥想度曲线图,以及从原始脑电信号数据提取出来的α波、β波和θ波波形图,对精神疲劳等级进行量化还可以存储用户数据不断完善LSTM人工神经网络模型,从而使量化结果越来越准确。结论:基于Android平台的精神疲劳检测系统小型、便捷,能够简便、快速、实时地对用户精神疲劳状态进行检测与监测,可防止疲劳作业引发的安全事故。 [ABSTRACT FROM AUTHOR]

Copyright of Chinese Medical Equipment Journal is the property of Chinese Medical Equipment Journal Editorial Office and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)