Driving-Pattern Identification and Event Detection Based on an Unsupervised Learning Framework: Case of a Motorcycle-Riding Simulator
Analysis of human driving behavior aims to inspect drivers’ behavior in the real-world and in a virtual environment. The study of driving behaviors can be conducted in naturalistic situations or controlled experiments. Analyzing driving behaviors based on the data collected in naturalisti...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9625971/ |
| _version_ | 1818573702843858944 |
|---|---|
| author | Mohamed Yacine Bouaouni Rayane Ait Ali Yahia Abderrahmane Boubezoul |
| author_facet | Mohamed Yacine Bouaouni Rayane Ait Ali Yahia Abderrahmane Boubezoul |
| author_sort | Mohamed Yacine Bouaouni |
| collection | DOAJ |
| description | Analysis of human driving behavior aims to inspect drivers’ behavior in the real-world and in a virtual environment. The study of driving behaviors can be conducted in naturalistic situations or controlled experiments. Analyzing driving behaviors based on the data collected in naturalistic driving experiments or controlled experiments in the real-world or in a virtual environment is beneficial to fill in many of the knowledge gaps about driving behaviors and risk factors. The amount of data collected during complex experiments with many laps and many drivers tested under different experimental conditions and with different instructions can be huge. Analyzing such data can thus be considered challenging and time-consuming if done manually because it requires calling on experts in traffic psychology to inspect and understand various specific situations at a macroscopic scale involving different riders and at a microscopic scale for a particular rider on a specific lap. Also, it can be challenging in an unsupervised context to detect and match the same patterns in different laps to study similar patterns and spot important and risky events. This paper proposes a multi-step framework for analyzing driving behavior on both the macroscopic and microscopic scales. The core step of this framework is based on unsupervised machine learning algorithms applied to driving-pattern identification and the detection of critical driving events using anomaly-detection algorithms. The detected events are interpreted and described by computing their feature importance using graphs centrality measures. This provides new insight into driving behavior by identifying the motives behind the driver’s actions. The present experimental study, based on a dataset collected from the Honda Riding Trainer (HRT) simulator was conducted in the context of the European project SimuSafe and demonstrates the effectiveness of the proposed methodology. These results argue in favor of the development of such methodologies in driving-behavior studies. |
| first_indexed | 2024-12-15T00:15:42Z |
| format | Article |
| id | doaj.art-0ca54f80f03342a6aaf3f7ac906823da |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-15T00:15:42Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-0ca54f80f03342a6aaf3f7ac906823da2022-12-21T22:42:27ZengIEEEIEEE Access2169-35362021-01-01915845615846910.1109/ACCESS.2021.31304009625971Driving-Pattern Identification and Event Detection Based on an Unsupervised Learning Framework: Case of a Motorcycle-Riding SimulatorMohamed Yacine Bouaouni0https://orcid.org/0000-0001-6674-5329Rayane Ait Ali Yahia1Abderrahmane Boubezoul2https://orcid.org/0000-0003-3967-1242Department of Electronics, Ecole Nationale Polytechnique, Algiers, AlgeriaDepartment of Electronics, Ecole Nationale Polytechnique, Algiers, AlgeriaTS2-SATIE-MOSS, Gustave Eiffel University, Marne la Vallée, FranceAnalysis of human driving behavior aims to inspect drivers’ behavior in the real-world and in a virtual environment. The study of driving behaviors can be conducted in naturalistic situations or controlled experiments. Analyzing driving behaviors based on the data collected in naturalistic driving experiments or controlled experiments in the real-world or in a virtual environment is beneficial to fill in many of the knowledge gaps about driving behaviors and risk factors. The amount of data collected during complex experiments with many laps and many drivers tested under different experimental conditions and with different instructions can be huge. Analyzing such data can thus be considered challenging and time-consuming if done manually because it requires calling on experts in traffic psychology to inspect and understand various specific situations at a macroscopic scale involving different riders and at a microscopic scale for a particular rider on a specific lap. Also, it can be challenging in an unsupervised context to detect and match the same patterns in different laps to study similar patterns and spot important and risky events. This paper proposes a multi-step framework for analyzing driving behavior on both the macroscopic and microscopic scales. The core step of this framework is based on unsupervised machine learning algorithms applied to driving-pattern identification and the detection of critical driving events using anomaly-detection algorithms. The detected events are interpreted and described by computing their feature importance using graphs centrality measures. This provides new insight into driving behavior by identifying the motives behind the driver’s actions. The present experimental study, based on a dataset collected from the Honda Riding Trainer (HRT) simulator was conducted in the context of the European project SimuSafe and demonstrates the effectiveness of the proposed methodology. These results argue in favor of the development of such methodologies in driving-behavior studies.https://ieeexplore.ieee.org/document/9625971/Time series analysistime series segmentationdriving-pattern identificationmotorcycle simulatorunsupervised learninganomaly detection |
| spellingShingle | Mohamed Yacine Bouaouni Rayane Ait Ali Yahia Abderrahmane Boubezoul Driving-Pattern Identification and Event Detection Based on an Unsupervised Learning Framework: Case of a Motorcycle-Riding Simulator IEEE Access Time series analysis time series segmentation driving-pattern identification motorcycle simulator unsupervised learning anomaly detection |
| title | Driving-Pattern Identification and Event Detection Based on an Unsupervised Learning Framework: Case of a Motorcycle-Riding Simulator |
| title_full | Driving-Pattern Identification and Event Detection Based on an Unsupervised Learning Framework: Case of a Motorcycle-Riding Simulator |
| title_fullStr | Driving-Pattern Identification and Event Detection Based on an Unsupervised Learning Framework: Case of a Motorcycle-Riding Simulator |
| title_full_unstemmed | Driving-Pattern Identification and Event Detection Based on an Unsupervised Learning Framework: Case of a Motorcycle-Riding Simulator |
| title_short | Driving-Pattern Identification and Event Detection Based on an Unsupervised Learning Framework: Case of a Motorcycle-Riding Simulator |
| title_sort | driving pattern identification and event detection based on an unsupervised learning framework case of a motorcycle riding simulator |
| topic | Time series analysis time series segmentation driving-pattern identification motorcycle simulator unsupervised learning anomaly detection |
| url | https://ieeexplore.ieee.org/document/9625971/ |
| work_keys_str_mv | AT mohamedyacinebouaouni drivingpatternidentificationandeventdetectionbasedonanunsupervisedlearningframeworkcaseofamotorcycleridingsimulator AT rayaneaitaliyahia drivingpatternidentificationandeventdetectionbasedonanunsupervisedlearningframeworkcaseofamotorcycleridingsimulator AT abderrahmaneboubezoul drivingpatternidentificationandeventdetectionbasedonanunsupervisedlearningframeworkcaseofamotorcycleridingsimulator |