This content is not included in your SAE MOBILUS subscription, or you are not logged in.
“Fitting Data”: A Case Study on Effective Driver Distraction State Classification
ISSN: 0148-7191, e-ISSN: 2688-3627
Published April 2, 2019 by SAE International in United States
This content contains downloadable datasetsAnnotation ability available
The goal of this project was to investigate how to make driver distraction state classification more efficient by applying selected machine learning techniques to existing datasets. The data set used in this project included both overt driver behavior measures (e.g., lane keeping and headway measures) and indices of internal cognitive processes (e.g., driver situation awareness responses) collected under four distraction conditions, including no-distraction, visual-manual distraction only, cognitive distraction only, and dual distraction conditions. The baseline classification method that we employed was a support vector machine (SVM) to first identify driver states of visual-manual distraction and then to identify any cognitive-related distraction among the visual-manual distraction cases and other non-visual manual distraction cases. The new aspect of this research is optimization of the classification effort, which involved cardinality constraints on 16 overt driver behavior measures. A spline transformation was also implemented to achieve better classification performance. In addition to testing our optimization approach with the SVM, we also explored logistic regression. Results revealed the spline-transformed variables to produce a good “out-of-sample” performance for both the SVM and logistic regression. Beyond this, the cardinality constraints were important for selection of the most influential variables in driver state classification accuracy and preventing data overfitting. Regarding the objective of efficiency in distraction classification, with only two input variables our optimized approach achieved state classification accuracies similar to accuracies achieved with “brute-force” application of SVM with all 16 overt driver behavior measures as inputs. Interestingly, with splined- transformed variables, reducing the number of input variables to 2 only led to a marginal decrease in classification accuracy (75.38% to 74.16%). The optimization methods explored in this paper could be applied to other in-vehicle real-time data to reduce computational demands in using machine learning methods for driver state classification.
CitationZhang, Y., Kaber, D., Uryasev, S., and Zrazhevsky, A., "“Fitting Data”: A Case Study on Effective Driver Distraction State Classification," SAE Technical Paper 2019-01-0875, 2019, https://doi.org/10.4271/2019-01-0875.
Data Sets - Support Documents
|[Unnamed Dataset 1]|
|[Unnamed Dataset 2]|
|[Unnamed Dataset 3]|
|[Unnamed Dataset 4]|
|[Unnamed Dataset 5]|
|[Unnamed Dataset 6]|
|[Unnamed Dataset 7]|
|[Unnamed Dataset 8]|
- Chen, L.L., Zhao, Y., Zhang, J., and Zou, J.Z., “Automatic Detection of Alertness/Drowsiness from Physiological Signals Using Wavelet-based Nonlinear Features and Machine Learning,” Expert Systems with Applications 42(21):7344-7355, 2015.
- Nasoz, F., Lisetti, C.L., and Vasilakos, A.V., “Affectively Intelligent and Adaptive Car Interfaces,” Information Sciences 180(20):3817-3836, 2010.
- Zhang, Y. and Kaber, D.B., “Evaluation of Strategies for Integrated Classification of Visual-Manual and Cognitive Distractions in Driving,” Human factors 58(6):944-958, 2016, doi:10.1177/0018720816647607.
- Liang, Y. “Detecting Driver Distraction, ” Ph.D. thesis, Industrial Engineering Department, Iowa University, Iowa City, 2009. Retrieved from http://ir.uiowa.edu/etd/248.
- Tran, C., Doshi, A., and Trivedi, M.M., “Modeling and Prediction of Driver Behavior by Foot Gesture Analysis,” Computer Vision and Image Understanding 116(3):435-445, 2012, doi:10.1016/j.cviu.2011.09.008.
- Jain, A., Koppula, H. S., Raghavan, B., Soh, S., et al. “Car that Knows Before You Do: Anticipating Maneuvers via Learning Temporal Driving Models,” in Proceedings of the IEEE International Conference on Computer Vision, 2015, 3182-3190.
- Birek, L., Grzywaczewski, A., Iqbal, R., Doctor, F. et al., “A Novel Big Data Analytics and Intelligent Technique to Predict Driver's Intent,” Computers in Industry 99:226-240, 2018, doi:10.1016/j.compind.2018.03.025.
- Kaisler, S., Armour, F., Espinosa, J. A., and Money, W., “Big Data: Issues and Challenges Moving Forward,” in System sciences (HICSS), 46th Hawaii international conference on System Sciences, 2013, 995-1004.
- Triguero, I., Peralta, D., Bacardit, J., García, S. et al., “MRPR: A MapReduce Solution for Prototype Reduction in Big Data Classification,” Neurocomputing 150(A):331-345, 2015.
- Konno, H. and Yamamoto, R., “Choosing the Best Set of Variables in Regression Analysis Using Integer Programming,” Journal of Global Optimization 44(2):273-282.
- Rogers, M.L., Zhang, Y., Kaber, D.B., and Liang, Y., “The Effects of Visual and Cognitive Distraction on Driver Situation Awareness,” in Harris D. (Ed.), in Proceedings of HCII Engineering Psychology and Cognitive Ergonomics, 2011, 186-195, doi:10.1007/978-3-642-21741-8_21
- Kaber, D.B., Liang, Y., Zhang, Y., Rogers, M.L. et al., “Driver Performance Effects of Simultaneous Visual and Cognitive Distraction and Adaptation Behavior,” Transportation Research Part F: Traffic Psychology and Behaviour 15(5):491-5 501, 2012, doi:10.1016/j.trf.2012.05.004.
- Zhang, Y., Kaber, D.B., Rogers, M., Liang, Y. et al., “The Effects of Visual and Cognitive Distractions on Operational and Tactical Driving Behaviors,” Human Factors: The Journal of the Human Factors and Ergonomics Society 56(3):592-604, 2014, doi:10.1177/0018720813495279.
- Zhang, Y. and Kaber, D.B., “The Role of Situation Awareness in Classifying Driver Cognitive Distraction States,” . In: Stanton N.a., editor. Advances in Human Aspects of Road and Rail Transportation. (CRC Press, 2012), 219-228.
- Karatzoglou, A., Meyer, D., and Hornik, K. “Support Vector Machine in R,” Research Report Series/Department of Statistics and Mathematics, 21, WU Vienna University of Economics and Business, Vienna, 2005. Retrieved from http://epub.wu.ac.at/1500/1/document.pdf, accessed on Oct. 2018.
- Hsu, C., Chang, C., and Lin, C., “A Practical Guide to Support Vector Classification (Vol. 1),” 2003, retrieved from http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf, accessed on April, 2018.
- AORDA (American Optical Decisions, Inc.), “Portfolio Safeguard (PSG) help,” Retrieved from http://www.aorda.com/html/PSG_Help_HTML/index.html?why_psg.htm, accessed on Aug. 2018.
- Chen, C.-L., Kaber, D.B., and Dempsey, P.G., “A New Approach to Applying Feedforward Neural Networks to the Prediction of Musculoskeletal Disorder Risk,” Applied Ergonomics 31:269-282, 2000.
- AORDA (American Optical Decisions, Inc.), “Logistic Regression with Factors Transformed by Splines and Approaches for Dimension Reduction,” Retrieved from http://www.aorda.com/html/PSG_CS_HTML/index.html?approaches_for_dimension_reduction_logistic.htm, assessed on Aug. 2018.