Real-time drowsiness detection using wearable, lightweight brain sensing headbands

被引:41
作者
Rohit, Fnu [1 ]
Kulathumani, Vinod [1 ]
Kavi, Rahul [1 ]
Elwarfalli, Ibrahim [1 ]
Kecojevic, Vlad [2 ]
Nimbarte, Ashish [3 ]
机构
[1] West Virginia Univ, Dept Comp Sci & Elect Engn, Morgantown, WV 26506 USA
[2] West Virginia Univ, Dept Min Engn, Morgantown, WV 26506 USA
[3] West Virginia Univ, Dept Ind Engn, Morgantown, WV 26506 USA
关键词
electroencephalography; signal classification; signal detection; spectral analysis; support vector machines; real-time drowsiness detection; wearable brain sensing headbands; wearable electroencephalogram sensors; wearable EEG sensors; EEG signals; SVM; drowsy state classification; cross-subject validation; radial basis kernel; temporal aggregation strategy; blink duration; blink analysis; DAYTIME SLEEPINESS; EEG; WAKEFULNESS; SIGNALS;
D O I
10.1049/iet-its.2016.0183
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The feasibility of real-time drowsiness detection using commercially available, off-the-shelf, lightweight, wearable electroencephalogram (EEG) sensors is explored. While EEG signals are known to be reliable indicators of fatigue and drowsiness, they have not been used widely due to their size and form factor. However, the use of lightweight wearable EEGs alleviates this concern. Spectral analysis of EEG signals from these sensors using support vector machines (SVMs) is shown to classify drowsy states with high accuracy. The system is validated using data collected on 23 subjects in fresh and drowsy states. An accuracy of 81% is obtained at a per-subject level and 74% in cross-subject validation using SVM with radial basis kernel. Using a temporal aggregation strategy, the cross-subject validation accuracy is shown to improve to 87%. The EEG signals are also used to characterise the blink duration and frequency of subjects. However, classification of drowsy states using blink analysis is shown to have lower accuracy than that using spectral analysis.
引用
收藏
页码:255 / 263
页数:9
相关论文
共 31 条
  • [1] Detecting deteriorated vigilance using percentage of eyelid closure time during behavioral maintenance of wakefulness tests
    Abe, Takashi
    Nonomura, Tomohide
    Komada, Yoko
    Asaoka, Shoichi
    Sasai, Taeko
    Ueno, Akinori
    Inoue, Yuichi
    [J]. INTERNATIONAL JOURNAL OF PSYCHOPHYSIOLOGY, 2011, 82 (03) : 269 - 274
  • [2] Aizerman A., 1964, AUTOMAT REM CONTR, V25, P821
  • [3] Real-time system for monitoring driver vigilance
    Bergasa, LM
    Nuevo, J
    Sotelo, MA
    Barea, R
    Lopez, ME
    [J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2006, 7 (01) : 63 - 77
  • [4] Automatic detection of alertness/drowsiness from physiological signals using wavelet-based nonlinear features and machine learning
    Chen, Lan-lan
    Zhao, Yu
    Zhang, Jian
    Zou, Jun-zhong
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2015, 42 (21) : 7344 - 7355
  • [5] CTC and Associates, 2015, TRS1501 MINN DEP TRA
  • [6] A visual approach for driver inattention detection
    D'Orazio, T.
    Leo, M.
    Guaragnella, C.
    Distante, A.
    [J]. PATTERN RECOGNITION, 2007, 40 (08) : 2341 - 2355
  • [7] The boundary between wakefulness and steep: Quantitative electroencephalographic changes during the sleep onset period
    De Gennaro, L
    Ferrara, M
    Bertini, M
    [J]. NEUROSCIENCE, 2001, 107 (01) : 1 - 11
  • [8] Automatic detection of drowsiness in EEG records based on multimodal analysis
    Garces Correa, Agustina
    Orosco, Lorena
    Laciar, Eric
    [J]. MEDICAL ENGINEERING & PHYSICS, 2014, 36 (02) : 244 - 249
  • [9] García I, 2012, 2012 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV), P618, DOI 10.1109/IVS.2012.6232222
  • [10] Goodbody A., 2013, MIN MAG, V7, P38