Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Driver state estimation by convolutional neural network using multimodal sensor data

© The Institution of Engineering and Technology
Received 24/04/2016, Published 25/07/2016

A driver state estimation algorithm that uses multimodal vehicular and physiological sensor data is proposed. Deep learning is applied to the fused multimodal data rather than each modality being treated as a different feature. A convolutional neural network model is developed and the driver state estimation algorithm is implemented using Google TensorFlow. The results show that deep learning is a very promising approach for driver state estimation compared with previously studied algorithms, such as dynamic Bayesian networks.

Inspec keywords: neural nets; driver information systems; sensor fusion; learning (artificial intelligence); state estimation

Other keywords: multimodal sensor data; multimodal vehicular data; deep learning; Google TensorFlow; driver state estimation algorithm; physiological sensor data; convolutional neural network model

Subjects: Data handling techniques; Sensor fusion; Traffic engineering computing; Neural computing techniques

References

    1. 1)
      • 3. Martínez, H.P., Yannakakis, G.N.: ‘Deep multimodal fusion: combining discrete events and continuous signals’. ACM Int. Conf. on Multimodal Interaction, Istanbul, Turkey, November 12–16, 2014.
    2. 2)
      • 4. Yang, J.H., Jeong, H.B.: ‘Improvement of driver- state estimation algorithm using multi-modal information’. Int. Conf. on Control, Automation and Systems, Busan, Korea, October 13–16, 2015.
    3. 3)
      • 2. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ‘ImageNet classification with deep convolutional neural networks’, Adv. Neural Inf. Process. Syst., 2012, 25, pp. 1097–1105.
    4. 4)
      • 1. Singh, S.: ‘Critical reasons for crashes investigated in the National Motor Vehicle Crash Causation Survey’. Traffic safety facts crash stats, Report No. DOT HS 812 115, National Highway Traffic Safety Administration, Washington, DC, February 2015.
    5. 5)
      • 6. Google TensorFlow API, https://www.tensorflow.org/.
    6. 6)
      • 5. Yang, J.H., Jeong, H.B.: ‘Validity analysis of vehicle and physiological data for detecting driver drowsiness, distraction, and workload’. IEEE Int. Conf. on Systems, Man, and Cybernetics, October 2015, pp. 1238–1243.
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2016.1393
Loading

Related content

content/journals/10.1049/el.2016.1393
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address