Adaptive Fuzzy Prediction for Automotive Applications Usage

IEEE Trans. Intell. Transport. Syst.

et al. 2019

In addition to vehicle control, drivers often perform secondary tasks that impede driving. Reduction of driver distraction is an important challenge for the safety of intelligent transportation systems. In this paper, a methodology for detection and evaluation of driver distraction while performing secondary tasks is described and an appropriate hardware and software environment is offered and studied. The system includes a model of normal driving, a subsystem for measuring the errors from the secondary tasks, and a module for total distraction evaluation. A new machine learning algorithm defines driver performance in lane keeping and speed maintenance on a specific road segment. To recognize the errors, a method is proposed, which compares normal driving parameters with ones obtained while conducting a secondary task. To evaluate distraction, an effective fuzzy logic algorithm is used. To verify the proposed approach, a case study with driver-in-the-loop experiments was carried out, in which participants performed the secondary task, namely chatting on a cell phone. The results presented in this research confirm its capability to detect and to precisely measure a level of abnormal driver performance.

Section: Discussionmentioning

confidence: 99%

“…An example of the DD detection usage in ADAS is described in [20]. The scholars presented fuzzy system, which personalizes the fuzzy membership functions based on individual driving habits.…”

Section: Related Work and Problem Statementmentioning

confidence: 99%

Detection and Evaluation of Driver Distraction Using Machine Learning and Fuzzy Logic

IEEE Trans. Intell. Transport. Syst.

et al. 2019

“…In [12], [13], the same algorithm was combined with ANN. Other computational intelligence and statistical learning theory approaches, like SVM [14], fuzzy logic [15], ANN with SVM [16], [17] were also applied for induced by secondary activity DD classification.…”

Section: Introductionmentioning

confidence: 99%

A Method for Detection and Evaluation of Driver Distraction Induced by In-Vehicle Information Systems

IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society

et al. 2018

“…In addition, these methods do not require supplementary hardware, and turn out to be more applicable in practice, because the data can be gathered using only the sensors available in passenger vehicles, such as steering wheel angle gauges, vehicle velocity transducers, etc. Using these signals, researchers designed different DD detection algorithms based on artificial and computational intelligence: FL [11], SVM [12], Gaussian mixture model (GMM) [13], and their combinations, such as hidden Markov model with GMM [14], ANN with GMM [15], and ANN with SVM [16].…”

Section: Introductionmentioning

confidence: 99%

An Enhancement of the Driver Distraction Detection and Evaluation Method Based on Computational Intelligence Algorithms

2018 IEEE 16th International Conference on Industrial Informatics (INDIN)

et al. 2018

Driver distraction is a fundamental problem for human safety, because the number of traffic accidents due to distracted driving does not decrease. In this paper, an enhancement of previously proposed driver distraction detection and evaluation methodology is introduced. The method is composed of computational intelligence algorithms: a driver performance prediction algorithm with nearest neighbor regression and an intelligent fuzzy logic evaluation algorithm. Thanks to the improvement, an additional variable for driver performance prediction and an additional performance-based indicator were introduced. To verify the novelty, the series of thirty driver-in-the-loop experiments has been delivered on an industrial vehicle simulator. At this, an interaction with a vehicle on-board computer was exploited as a distractive activity. Finally, the enhanced method is compared to the previously described one.