ABSTRACT
Vehicular accidents are increasingly contributing towards loss of lives across the world. Timely detection of physiological and psychological parameters of the vehicular driver, which could cause various levels of physical and mental fatigue that lead to slower reflexes is therefore extremely important. As part of an ambitious research initiative, India is developing a pervasive computing solution for eliminating / reducing such accidents. As one of the component of such solution, a wearable computing system has been envisioned to be worn by the driver. A complex set of noninvasive and nonintrusive sensor-compute element integrated with appropriate e-textile would form the primary part of this wearable computer.
Out of the initial set of physiological parameters such as Skin Conductance, Oximetry Pulse, Respiration, SPO2, the current work focuses on the first two parameters to detect and monitor the mental fatigue / drowsiness of a driver. Using Neural Network approach, Multilayer Perceptron Neural Networks (MLP NN) have been designed to classify Pre and Posting driving fatigue levels. The performance of single hidden layer and two hidden layers based MLP NN have been discussed using the performance measures such as, Percentage Classification Accuracy (PCLA), Mean Square Error (MSE), Normalized Mean Square Error (NMSE), Area under Receiver Operating Characteristic Curve (AROC), Area under Convex Hull of ROC (AHROC). It was discovered that the performance of one hidden layer based MLP NN is comparable to the two hidden layers based MLP NN and there is slight rise in PCLA from One hidden layer to two hidden layer.
- Abdulhamit, Subasi, Automatic recognition of alertness level from EEG by using neural network and wavelet coefficients. Expert Systems with Applications 28 (2005), 701--711, Elsevier Google ScholarDigital Library
- Banerjee, Rahul, 2005 From Research To Classroom: A Course in Pervasive Computing. Journal of IEEE Pervasive Computing, July-September 2005, Vol. 4, No. 3, pp. 83--86. Google ScholarDigital Library
- Baum, E. B., 1988 On the capabilities of multilayer perceptrons. Journal of Complexity-4, 193--215.-11Google Scholar
- Bundele, Mahesh M., 2008 Identification of Body Parameters for changes in Reflexes of a vehicular driver under Drowsiness / Fatigue / Stress Conditions. In Proceeding of the National Conference FRONTIER-2008, organized by, Babasaheb Naik College of Engineering Pusad MS India, December 16--18, 2008.Google Scholar
- Bundele, Mahesh M., Banerjee, Rahul 2009 An SVM Classifier for Fatigue-Detection using Skin Conductance for Use in BITS Life Guard Wearable Computing System. Accepted for presentation in International Conference ICETET-09 on Emerging Trends in Engineering and Technology. Technically Co-sponsored by IEEE Systems, Man & Cybernetics Society Bombay Section being organized at G H Raisoni College of Engineering Nagpur scheduled on December 16--18, 2009.Google Scholar
- Charniya, Nadir N., Dudul, S. V., Neural Network based Sensor for Classification of Material Type and its Surface Properties. Proceeding of International Joint Conference on Neural Networks, (August 2007), 424--429.Google Scholar
- Eun-Jung Sung, Byung-Chan Min, Seung-Chul Kim, Chul-Jung Kimd, 2005 Effects of oxygen concentrations on driver fatigue during simulated driving. Journal of Applied Ergonomics Elsevier Publication-36, 25--31.Google Scholar
- Hu Shuyan, Zheng Gangtie, 2009 Driver drowsiness detection with eyelid related parameters by Support VectorMachine. Expert Systems with Applications, Elsevier 36(2009), 7651--7658. Google ScholarDigital Library
- Mervyn, V. M. Yeo a, Xiaoping, Li, Kaiquan, Shen, Einar, P. V., Wilder-Smith, Can SVM be used for automatic EEG detection of drowsiness during car driving?. Journal of Safety Science, Elsevier 47 (2009), 115--124.Google Scholar
- Muhammed, B. Kurt a, Necmettin Sezgin a, Mehmet Akin a, Gokhan Kirbas b, Muhittin Bayram a, 2009 The ANNbased computing of drowsy level. Journal of Elsevier Expert Systems and Applications, 2009, 2534--2552. Google ScholarDigital Library
- Nuria Oliver, Fernando Flores-Mangas, HealthGear: Automatic Sleep Apnea Detection and Monitoring with a Mobile Phone. Journal of Communications-2(March 2007)Google Scholar
- Pal, Nikhil R., Chuang, Chien-Yao, Ko, Li-Wei, Chao, Chih-Feng, Jung, Tzyy-Ping, Liang, Sheng-Fu, Lin, Chin-Teng, 2008 EEG-based subject- and session-independent drowsiness detection: an unsupervised approach. EURASIP Journal on Advances in Signal Processing Google ScholarDigital Library
- Principe, J., Euliano, N., Lefebvre C., 1999 Neural and adaptive systems: fundamentals through simulations. John Wiley and Sons, 1999. Google ScholarDigital Library
- Stephen Paul Linder, Suzanne Wendelken, 2006 Detecting Exercise Induced Stress using the Photoplethysmogram. EMBS'06' 28th International Conference of IEEE on Engineering in Medicine and Biology Society, pp. 5109--5112.Google Scholar
- Stephen Paul Linder, Suzanne Wendelken, Jeffrey Clayman, and Paul R. Steiner, Noninvasive detection of the Hemodynamic Stress of Exercise using the Photoplethysmogram. Journal of clinical monitoring and computing (2008) Springer 22, 269--278.Google Scholar
- Woods, Kevin S., Bowyer, Kevin W., Generating ROC Curves for Artificial Neural Networks. 1063--7125/94 1994 IEEE.Google Scholar
- Assessment of a Drowsy Driver Warning System for Heavy-Vehicle Drivers, Report by US department of Transport NHTSA, April 2009.Google Scholar
Index Terms
- Detection of fatigue of vehicular driver using skin conductance and oximetry pulse: a neural network approach
Recommendations
Driver Fatigue Detection using Recurrent Neural Networks
NISS '19: Proceedings of the 2nd International Conference on Networking, Information Systems & SecurityRoad accidents are becoming a real global scourge because of the high number of victims involved and the severe consequences that affect road users as well as their families.
Despite the awareness campaigns on the vigilance and caution that must be ...
Classification error of multilayer perceptron neural networks
In subject classification, artificial neural networks (ANNS) are efficient and objective classification methods. Thus, they have been successfully applied to the numerous classification fields. Sometimes, however, classifications do not match the real ...
Application Heart Rate Variability to Driver Fatigue Detection of Dangerous Chemicals Vehicles
ISDEA '14: Proceedings of the 2014 Fifth International Conference on Intelligent Systems Design and Engineering ApplicationsFor fatigue monitoring issues, this paper proposes the idea that detects the heart rate volatility to determine whether the driver is in a state of fatigue, and the method is to comprehensively analyze the standard deviation which obtains by the ...
Comments