|
Title: DESIGN OF A FATIGUE RELIEF SYSTEM FOR LOCOMOTIVE DRIVERS BASED ON VIGILANCE DETECTION
Accession Number: 01594432
Record Type: Component
Abstract: In this paper, a type of fatigue relief system based on vigilance detection is proposed to relieve the fatigue of the locomotive driver when driver fatigue is detected using EEG and SVM. This system is designed to replace the traditional driver alarm device, where a pedal must be stepped on every 30 seconds, to detect whether the driver is alert. This new system contains three parts: 1) EEG collection, 2) driver’s vigilance detection, and 3) driver’s fatigue relief. In the first part, an 8-channel wearable brain-computer interface (BCI) device is designed to acquire the driver’s electroencephalogram (EEG) signal and transmit its recorded data to a personal computer (PC) via Bluetooth. In the second step, the SVM classification algorithm with the Fast Fourier transform (FFT) feature extraction method is implemented in the driver’s EEG to determine the vigilance level of the driver. Finally, a fatigue relief device is designed based on the traditional massage chair to relieve the locomotive driver’s fatigue by massaging the back of the driver when fatigue is detected. The experimental result demonstrates the feasibility of the proposed fatigue-relieving system.
Supplemental Notes: This paper was sponsored by TRB committee AR070 Standing Committee on Railroad Operational Safety.
Monograph Title: Monograph Accession #: 01584066
Report/Paper Numbers: 16-1954
Language: English
Corporate Authors: Transportation Research Board 500 Fifth Street, NW Authors: Zhang, ZutaoLuo, DianyuanLiu, YugangMeng, GuanjunPagination: 12p
Publication Date: 2016
Conference:
Transportation Research Board 95th Annual Meeting
Location:
Washington DC, United States Media Type: Digital/other
Features: Figures; Photos; References; Tables
TRT Terms: Subject Areas: Railroads; Safety and Human Factors
Source Data: Transportation Research Board Annual Meeting 2016 Paper #16-1954
Files: TRIS, TRB, ATRI
Created Date: Jan 12 2016 4:51PM
|