Preventing Road Accidents Through Early Detection of Driver Behavior Using Smartphone Motion Sensor Data: An Ensemble Feature Engineering Approach
Driver behavior refers to the actions and attitudes of individuals behind the wheel of a vehicle. Poor driving behavior can have serious consequences, including accidents, injuries, and fatalities. One of the main disadvantages of poor driving behavior is the increased risk of road accidents, higher...
| Päätekijät: | , , , , , , |
|---|---|
| Aineistotyyppi: | Artikkeli |
| Kieli: | English |
| Julkaistu: |
IEEE
2023-01-01
|
| Sarja: | IEEE Access |
| Aiheet: | |
| Linkit: | https://ieeexplore.ieee.org/document/10347206/ |
| _version_ | 1827398897107992576 |
|---|---|
| author | Ali Raza Iqra Akhtar Laith Abualigah Raed Abu Zitar Mohamed Sharaf Mohammad SH. Daoud Heming Jia |
| author_facet | Ali Raza Iqra Akhtar Laith Abualigah Raed Abu Zitar Mohamed Sharaf Mohammad SH. Daoud Heming Jia |
| author_sort | Ali Raza |
| collection | DOAJ |
| description | Driver behavior refers to the actions and attitudes of individuals behind the wheel of a vehicle. Poor driving behavior can have serious consequences, including accidents, injuries, and fatalities. One of the main disadvantages of poor driving behavior is the increased risk of road accidents, higher insurance premiums, fines, and even criminal charges. The primary aim of our study is to detect driver behavior early with high-performance scores. The publicly available smartphone motion sensor data is utilized to conduct our study experiments. A novel LR-RFC (Logistic Regression Random Forest Classifier) method is proposed for feature engineering. The proposed LR-RFC method combines the logistic regression and random forest classifier for feature engineering from the motion sensor data. The original smartphone motion sensor data is input into the LR-RFC method, generating new probabilistic features. The newly extracted probabilistic features are then input to the applied machine learning methods for predicting driver behavior. The study results show that the proposed LR-RFC approach achieves the highest performance score. Extensive study experiments demonstrate that the random forest achieved the highest performance score of 99% using the proposed LR-RFC method. The performance is validated using k-fold cross-validation and hyperparameter optimization. Our novel proposed study has the potential to revolutionize the early detection of driver behavior to avoid road accidents. |
| first_indexed | 2024-03-08T19:36:31Z |
| format | Article |
| id | doaj.art-94ba42cc091147bdaa169874e1531dad |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T19:36:31Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-94ba42cc091147bdaa169874e1531dad2023-12-26T00:09:36ZengIEEEIEEE Access2169-35362023-01-011113845713847110.1109/ACCESS.2023.334030410347206Preventing Road Accidents Through Early Detection of Driver Behavior Using Smartphone Motion Sensor Data: An Ensemble Feature Engineering ApproachAli Raza0https://orcid.org/0000-0001-5429-9835Iqra Akhtar1Laith Abualigah2https://orcid.org/0000-0002-2203-4549Raed Abu Zitar3https://orcid.org/0000-0003-2693-2132Mohamed Sharaf4https://orcid.org/0000-0001-6722-8366Mohammad SH. Daoud5https://orcid.org/0000-0003-2682-9231Heming Jia6Institute of Computer Science, Khwaja Fareed University of Engineering and Information Technology, Rahim Yar Khan, PakistanDepartment of Electrical and Biomedical Engineering, Khwaja Fareed University of Engineering and Information Technology, Rahim Yar Khan, PakistanComputer Science Department, Prince Hussein Bin Abdullah Faculty for Information Technology, Al-Albayt University, Mafraq, JordanSorbonne Center of Artificial Intelligence, Sorbonne University Abu Dhabi, Abu Dhabi, United Arab EmiratesIndustrial Engineering Department, College of Engineering, King Saud University, Riyadh, Saudi ArabiaCollege of Engineering, Al Ain University, Abu Dhabi, United Arab EmiratesSchool of Information Engineering, Sanming University, Sanming, ChinaDriver behavior refers to the actions and attitudes of individuals behind the wheel of a vehicle. Poor driving behavior can have serious consequences, including accidents, injuries, and fatalities. One of the main disadvantages of poor driving behavior is the increased risk of road accidents, higher insurance premiums, fines, and even criminal charges. The primary aim of our study is to detect driver behavior early with high-performance scores. The publicly available smartphone motion sensor data is utilized to conduct our study experiments. A novel LR-RFC (Logistic Regression Random Forest Classifier) method is proposed for feature engineering. The proposed LR-RFC method combines the logistic regression and random forest classifier for feature engineering from the motion sensor data. The original smartphone motion sensor data is input into the LR-RFC method, generating new probabilistic features. The newly extracted probabilistic features are then input to the applied machine learning methods for predicting driver behavior. The study results show that the proposed LR-RFC approach achieves the highest performance score. Extensive study experiments demonstrate that the random forest achieved the highest performance score of 99% using the proposed LR-RFC method. The performance is validated using k-fold cross-validation and hyperparameter optimization. Our novel proposed study has the potential to revolutionize the early detection of driver behavior to avoid road accidents.https://ieeexplore.ieee.org/document/10347206/Machine learningdriver behaviorsensor datafeature engineeringensemble learning |
| spellingShingle | Ali Raza Iqra Akhtar Laith Abualigah Raed Abu Zitar Mohamed Sharaf Mohammad SH. Daoud Heming Jia Preventing Road Accidents Through Early Detection of Driver Behavior Using Smartphone Motion Sensor Data: An Ensemble Feature Engineering Approach IEEE Access Machine learning driver behavior sensor data feature engineering ensemble learning |
| title | Preventing Road Accidents Through Early Detection of Driver Behavior Using Smartphone Motion Sensor Data: An Ensemble Feature Engineering Approach |
| title_full | Preventing Road Accidents Through Early Detection of Driver Behavior Using Smartphone Motion Sensor Data: An Ensemble Feature Engineering Approach |
| title_fullStr | Preventing Road Accidents Through Early Detection of Driver Behavior Using Smartphone Motion Sensor Data: An Ensemble Feature Engineering Approach |
| title_full_unstemmed | Preventing Road Accidents Through Early Detection of Driver Behavior Using Smartphone Motion Sensor Data: An Ensemble Feature Engineering Approach |
| title_short | Preventing Road Accidents Through Early Detection of Driver Behavior Using Smartphone Motion Sensor Data: An Ensemble Feature Engineering Approach |
| title_sort | preventing road accidents through early detection of driver behavior using smartphone motion sensor data an ensemble feature engineering approach |
| topic | Machine learning driver behavior sensor data feature engineering ensemble learning |
| url | https://ieeexplore.ieee.org/document/10347206/ |
| work_keys_str_mv | AT aliraza preventingroadaccidentsthroughearlydetectionofdriverbehaviorusingsmartphonemotionsensordataanensemblefeatureengineeringapproach AT iqraakhtar preventingroadaccidentsthroughearlydetectionofdriverbehaviorusingsmartphonemotionsensordataanensemblefeatureengineeringapproach AT laithabualigah preventingroadaccidentsthroughearlydetectionofdriverbehaviorusingsmartphonemotionsensordataanensemblefeatureengineeringapproach AT raedabuzitar preventingroadaccidentsthroughearlydetectionofdriverbehaviorusingsmartphonemotionsensordataanensemblefeatureengineeringapproach AT mohamedsharaf preventingroadaccidentsthroughearlydetectionofdriverbehaviorusingsmartphonemotionsensordataanensemblefeatureengineeringapproach AT mohammadshdaoud preventingroadaccidentsthroughearlydetectionofdriverbehaviorusingsmartphonemotionsensordataanensemblefeatureengineeringapproach AT hemingjia preventingroadaccidentsthroughearlydetectionofdriverbehaviorusingsmartphonemotionsensordataanensemblefeatureengineeringapproach |