TY - JOUR
T1 - Driving maneuver classification from time series data
T2 - a rule based machine learning approach
AU - Haque, Md Mokammel
AU - Sarker, Supriya
AU - Dewan, M. Ali Akber
N1 - Publisher Copyright:
© 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
PY - 2022/11
Y1 - 2022/11
N2 - Drivers’ improper driving behavior plays a vital role in road accidents. Different approaches have been proposed to classify and evaluate driving performance to ensure road safety. However, most of the techniques are based on neural networks which work like a black box and make the logical reasoning behind the classification decision unclear. In this paper, we propose a rule-based machine learning technique using a sequential covering algorithm to classify the driving maneuvers from time-series data. In the sequential covering algorithm, the impact of each rule is measured as the metrics of coverage and accuracy, where the coverage and accuracy indicate the amount of covered and correctly identified instances in a maneuver class, respectively. The final ruleset for each maneuver class is formed with only the significant rules. In this way, the rules are learned in an unsupervised manner and only the best performance of the rules are included in the ruleset. The set of rules is also optimized by pruning based on the performance of the test data. Application of the proposed system is beneficial compared to the traditional machine learning and deep learning approaches which typically require a larger dataset and higher computational time and complexity.
AB - Drivers’ improper driving behavior plays a vital role in road accidents. Different approaches have been proposed to classify and evaluate driving performance to ensure road safety. However, most of the techniques are based on neural networks which work like a black box and make the logical reasoning behind the classification decision unclear. In this paper, we propose a rule-based machine learning technique using a sequential covering algorithm to classify the driving maneuvers from time-series data. In the sequential covering algorithm, the impact of each rule is measured as the metrics of coverage and accuracy, where the coverage and accuracy indicate the amount of covered and correctly identified instances in a maneuver class, respectively. The final ruleset for each maneuver class is formed with only the significant rules. In this way, the rules are learned in an unsupervised manner and only the best performance of the rules are included in the ruleset. The set of rules is also optimized by pruning based on the performance of the test data. Application of the proposed system is beneficial compared to the traditional machine learning and deep learning approaches which typically require a larger dataset and higher computational time and complexity.
KW - Driving behavior classification
KW - Driving maneuver
KW - Explainable AI
KW - Interpretable machine learning
KW - Rule learning
KW - Rule-based machine learning
KW - Sequential covering
UR - http://www.scopus.com/inward/record.url?scp=85127299527&partnerID=8YFLogxK
U2 - 10.1007/s10489-022-03328-3
DO - 10.1007/s10489-022-03328-3
M3 - Journal Article
AN - SCOPUS:85127299527
SN - 0924-669X
VL - 52
SP - 16900
EP - 16915
JO - Applied Intelligence
JF - Applied Intelligence
IS - 14
ER -