Development of Deep Learning-Based Algorithm for Extracting Abnormal Deceleration Patterns
A smart regenerative braking system for EVs can reduce unnecessary brake operations by assisting in the braking of a vehicle according to the driving situation, road slope, and driver’s preference. Since the strength of regenerative braking is generally determined based on calibration data determine...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | World Electric Vehicle Journal |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2032-6653/16/1/37 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587268541382656 |
|---|---|
| author | Youngho Jun Minha Kim Kangjun Lee Simon S. Woo |
| author_facet | Youngho Jun Minha Kim Kangjun Lee Simon S. Woo |
| author_sort | Youngho Jun |
| collection | DOAJ |
| description | A smart regenerative braking system for EVs can reduce unnecessary brake operations by assisting in the braking of a vehicle according to the driving situation, road slope, and driver’s preference. Since the strength of regenerative braking is generally determined based on calibration data determined during the vehicle development process, some drivers could encounter inconveniences when the regenerative braking is activated differently from their driving habits. In order to solve this problem, various deep learning-based algorithms have been developed to provide driving stability by learning the driving data. Among those artificial intelligence algorithms, anomaly detection algorithms can successfully separate the deceleration data in abnormal driving situations, and the resulting refined deceleration data can be used to train the regression model to achieve better driving stability. This study evaluates the performance of a personalized driving assistance system by applying driver characteristic data, obtained through an anomaly detection algorithm, to vehicle control. |
| format | Article |
| id | doaj-art-2275609195194d6db5c4cdd1e8ed591b |
| institution | Kabale University |
| issn | 2032-6653 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | World Electric Vehicle Journal |
| spelling | doaj-art-2275609195194d6db5c4cdd1e8ed591b2025-01-24T13:52:51ZengMDPI AGWorld Electric Vehicle Journal2032-66532025-01-011613710.3390/wevj16010037Development of Deep Learning-Based Algorithm for Extracting Abnormal Deceleration PatternsYoungho Jun0Minha Kim1Kangjun Lee2Simon S. Woo3Vehicle Control Solutions Center, Hyundai-KEFICO, Gunpo 15849, Republic of KoreaDepartment of Artificial Intelligence, Sungkyunkwan University, Seoul 03063, Republic of KoreaDepartment of Computer Science & Engineering, Sungkyunkwan University, Seoul 03063, Republic of KoreaDepartment of Computer Science & Engineering, Sungkyunkwan University, Seoul 03063, Republic of KoreaA smart regenerative braking system for EVs can reduce unnecessary brake operations by assisting in the braking of a vehicle according to the driving situation, road slope, and driver’s preference. Since the strength of regenerative braking is generally determined based on calibration data determined during the vehicle development process, some drivers could encounter inconveniences when the regenerative braking is activated differently from their driving habits. In order to solve this problem, various deep learning-based algorithms have been developed to provide driving stability by learning the driving data. Among those artificial intelligence algorithms, anomaly detection algorithms can successfully separate the deceleration data in abnormal driving situations, and the resulting refined deceleration data can be used to train the regression model to achieve better driving stability. This study evaluates the performance of a personalized driving assistance system by applying driver characteristic data, obtained through an anomaly detection algorithm, to vehicle control.https://www.mdpi.com/2032-6653/16/1/37time seriesanomaly detectionelectric vehiclepersonalized data |
| spellingShingle | Youngho Jun Minha Kim Kangjun Lee Simon S. Woo Development of Deep Learning-Based Algorithm for Extracting Abnormal Deceleration Patterns World Electric Vehicle Journal time series anomaly detection electric vehicle personalized data |
| title | Development of Deep Learning-Based Algorithm for Extracting Abnormal Deceleration Patterns |
| title_full | Development of Deep Learning-Based Algorithm for Extracting Abnormal Deceleration Patterns |
| title_fullStr | Development of Deep Learning-Based Algorithm for Extracting Abnormal Deceleration Patterns |
| title_full_unstemmed | Development of Deep Learning-Based Algorithm for Extracting Abnormal Deceleration Patterns |
| title_short | Development of Deep Learning-Based Algorithm for Extracting Abnormal Deceleration Patterns |
| title_sort | development of deep learning based algorithm for extracting abnormal deceleration patterns |
| topic | time series anomaly detection electric vehicle personalized data |
| url | https://www.mdpi.com/2032-6653/16/1/37 |
| work_keys_str_mv | AT younghojun developmentofdeeplearningbasedalgorithmforextractingabnormaldecelerationpatterns AT minhakim developmentofdeeplearningbasedalgorithmforextractingabnormaldecelerationpatterns AT kangjunlee developmentofdeeplearningbasedalgorithmforextractingabnormaldecelerationpatterns AT simonswoo developmentofdeeplearningbasedalgorithmforextractingabnormaldecelerationpatterns |