Abstract
The long term accumulated driving information can effectively summarize the specific driver behavior by statistical analysis. In order to widely and chronically collect driving information of drivers, the cloud computing platform is the most suitable mechanism to log the dynamic vehicle information stream from OBD port to build up Big Data for data mining about driver behavior, currently. The research of this paper has focused on the application layer in the cloud computing platform, Python has been adopted to as the main development tool accompanying with the packages of numpy, pandas, and scipy to calculate the kurtosis and skewness in statistics of each driving route, then decision tree classification technique was applied to generate the analyzing knowledge for driver behavior analysis. Finally the driver behavior are summarized from the completed decision tree classifier to defensive, weak defensive, weak aggressive, and aggressive to complete the overall operations.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 32nd IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2018 |
| Editors | Lidia Ogiela, Tomoya Enokido, Marek R. Ogiela, Nadeem Javaid, Leonard Barolli, Makoto Takizawa |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 636-639 |
| Number of pages | 4 |
| ISBN (Electronic) | 9781538653944 |
| DOIs | |
| Publication status | Published - 2018 Jul 20 |
| Event | 32nd IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2018 - Krakow, Poland Duration: 2018 May 16 → 2018 May 18 |
Publication series
| Name | Proceedings - 32nd IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2018 |
|---|---|
| Volume | 2018-January |
Other
| Other | 32nd IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2018 |
|---|---|
| Country | Poland |
| City | Krakow |
| Period | 18-05-16 → 18-05-18 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
- Computer Networks and Communications
- Computer Science Applications
- Hardware and Architecture
- Information Systems and Management
Cite this
}
Apply Scikit-learn in python to analyze driver behavior based on OBD data. / Hwang, Chipan; Chen, Mu Song; Shih, Chih Min; Chen, Hsing Yu; Liu, Wen Kai.
Proceedings - 32nd IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2018. ed. / Lidia Ogiela; Tomoya Enokido; Marek R. Ogiela; Nadeem Javaid; Leonard Barolli; Makoto Takizawa. Institute of Electrical and Electronics Engineers Inc., 2018. p. 636-639 8418144 (Proceedings - 32nd IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2018; Vol. 2018-January).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Apply Scikit-learn in python to analyze driver behavior based on OBD data
AU - Hwang, Chipan
AU - Chen, Mu Song
AU - Shih, Chih Min
AU - Chen, Hsing Yu
AU - Liu, Wen Kai
PY - 2018/7/20
Y1 - 2018/7/20
N2 - The long term accumulated driving information can effectively summarize the specific driver behavior by statistical analysis. In order to widely and chronically collect driving information of drivers, the cloud computing platform is the most suitable mechanism to log the dynamic vehicle information stream from OBD port to build up Big Data for data mining about driver behavior, currently. The research of this paper has focused on the application layer in the cloud computing platform, Python has been adopted to as the main development tool accompanying with the packages of numpy, pandas, and scipy to calculate the kurtosis and skewness in statistics of each driving route, then decision tree classification technique was applied to generate the analyzing knowledge for driver behavior analysis. Finally the driver behavior are summarized from the completed decision tree classifier to defensive, weak defensive, weak aggressive, and aggressive to complete the overall operations.
AB - The long term accumulated driving information can effectively summarize the specific driver behavior by statistical analysis. In order to widely and chronically collect driving information of drivers, the cloud computing platform is the most suitable mechanism to log the dynamic vehicle information stream from OBD port to build up Big Data for data mining about driver behavior, currently. The research of this paper has focused on the application layer in the cloud computing platform, Python has been adopted to as the main development tool accompanying with the packages of numpy, pandas, and scipy to calculate the kurtosis and skewness in statistics of each driving route, then decision tree classification technique was applied to generate the analyzing knowledge for driver behavior analysis. Finally the driver behavior are summarized from the completed decision tree classifier to defensive, weak defensive, weak aggressive, and aggressive to complete the overall operations.
UR - http://www.scopus.com/inward/record.url?scp=85056264982&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85056264982&partnerID=8YFLogxK
U2 - 10.1109/WAINA.2018.00159
DO - 10.1109/WAINA.2018.00159
M3 - Conference contribution
AN - SCOPUS:85056264982
T3 - Proceedings - 32nd IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2018
SP - 636
EP - 639
BT - Proceedings - 32nd IEEE International Conference on Advanced Information Networking and Applications Workshops, WAINA 2018
A2 - Ogiela, Lidia
A2 - Enokido, Tomoya
A2 - Ogiela, Marek R.
A2 - Javaid, Nadeem
A2 - Barolli, Leonard
A2 - Takizawa, Makoto
PB - Institute of Electrical and Electronics Engineers Inc.
ER -