A Multi-Clustering Algorithm to Solve Driving Cycle Prediction Problems Based on Unbalanced Data Sets: A Chinese Case Study
Vehicle evaluation parameters, which are increasingly of concern for governments and consumers, quantify performance indicators, such as vehicle performance, emissions, and driving experience to help guide consumers in purchasing cars. While past approaches for driving cycle prediction have been pro...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/9/2448 |
| _version_ | 1797569614363754496 |
|---|---|
| author | Yuewei Wu Wutong Zhang Long Zhang Yuanyuan Qiao Jie Yang Cheng Cheng |
| author_facet | Yuewei Wu Wutong Zhang Long Zhang Yuanyuan Qiao Jie Yang Cheng Cheng |
| author_sort | Yuewei Wu |
| collection | DOAJ |
| description | Vehicle evaluation parameters, which are increasingly of concern for governments and consumers, quantify performance indicators, such as vehicle performance, emissions, and driving experience to help guide consumers in purchasing cars. While past approaches for driving cycle prediction have been proven effective and used in many countries, these algorithms are difficult to use in China with its complex traffic environment and increasingly high frequency of traffic jams. Meanwhile, we found that the vehicle dataset used by the driving cycle prediction problem is usually unbalanced in real cases, which means that there are more medium and high speed samples and very few samples at low and ultra-high speeds. If the ordinary clustering algorithm is directly applied to the unbalanced data, it will have a huge impact on the performance to build driving cycle maps, and the parameters of the map will deviate considerable from actual ones. In order to address these issues, this paper propose a novel driving cycle map algorithm framework based on an ensemble learning method named multi-clustering algorithm, to improve the performance of traditional clustering algorithms on unbalanced data sets. It is noteworthy that our model framework can be easily extended to other complicated structure areas due to its flexible modular design and parameter configuration. Finally, we tested our method based on actual traffic data generated in Fujian Province in China. The results prove the multi-clustering algorithm has excellent performance on our dataset. |
| first_indexed | 2024-03-10T20:14:06Z |
| format | Article |
| id | doaj.art-0b0c6b81c81b40e5aae0db8342555254 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T20:14:06Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0b0c6b81c81b40e5aae0db83425552542023-11-19T22:41:52ZengMDPI AGSensors1424-82202020-04-01209244810.3390/s20092448A Multi-Clustering Algorithm to Solve Driving Cycle Prediction Problems Based on Unbalanced Data Sets: A Chinese Case StudyYuewei Wu0Wutong Zhang1Long Zhang2Yuanyuan Qiao3Jie Yang4Cheng Cheng5School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaVehicle evaluation parameters, which are increasingly of concern for governments and consumers, quantify performance indicators, such as vehicle performance, emissions, and driving experience to help guide consumers in purchasing cars. While past approaches for driving cycle prediction have been proven effective and used in many countries, these algorithms are difficult to use in China with its complex traffic environment and increasingly high frequency of traffic jams. Meanwhile, we found that the vehicle dataset used by the driving cycle prediction problem is usually unbalanced in real cases, which means that there are more medium and high speed samples and very few samples at low and ultra-high speeds. If the ordinary clustering algorithm is directly applied to the unbalanced data, it will have a huge impact on the performance to build driving cycle maps, and the parameters of the map will deviate considerable from actual ones. In order to address these issues, this paper propose a novel driving cycle map algorithm framework based on an ensemble learning method named multi-clustering algorithm, to improve the performance of traditional clustering algorithms on unbalanced data sets. It is noteworthy that our model framework can be easily extended to other complicated structure areas due to its flexible modular design and parameter configuration. Finally, we tested our method based on actual traffic data generated in Fujian Province in China. The results prove the multi-clustering algorithm has excellent performance on our dataset.https://www.mdpi.com/1424-8220/20/9/2448unbalanced datadriving cyclemulti-clustering algorithmstacking algorithm |
| spellingShingle | Yuewei Wu Wutong Zhang Long Zhang Yuanyuan Qiao Jie Yang Cheng Cheng A Multi-Clustering Algorithm to Solve Driving Cycle Prediction Problems Based on Unbalanced Data Sets: A Chinese Case Study Sensors unbalanced data driving cycle multi-clustering algorithm stacking algorithm |
| title | A Multi-Clustering Algorithm to Solve Driving Cycle Prediction Problems Based on Unbalanced Data Sets: A Chinese Case Study |
| title_full | A Multi-Clustering Algorithm to Solve Driving Cycle Prediction Problems Based on Unbalanced Data Sets: A Chinese Case Study |
| title_fullStr | A Multi-Clustering Algorithm to Solve Driving Cycle Prediction Problems Based on Unbalanced Data Sets: A Chinese Case Study |
| title_full_unstemmed | A Multi-Clustering Algorithm to Solve Driving Cycle Prediction Problems Based on Unbalanced Data Sets: A Chinese Case Study |
| title_short | A Multi-Clustering Algorithm to Solve Driving Cycle Prediction Problems Based on Unbalanced Data Sets: A Chinese Case Study |
| title_sort | multi clustering algorithm to solve driving cycle prediction problems based on unbalanced data sets a chinese case study |
| topic | unbalanced data driving cycle multi-clustering algorithm stacking algorithm |
| url | https://www.mdpi.com/1424-8220/20/9/2448 |
| work_keys_str_mv | AT yueweiwu amulticlusteringalgorithmtosolvedrivingcyclepredictionproblemsbasedonunbalanceddatasetsachinesecasestudy AT wutongzhang amulticlusteringalgorithmtosolvedrivingcyclepredictionproblemsbasedonunbalanceddatasetsachinesecasestudy AT longzhang amulticlusteringalgorithmtosolvedrivingcyclepredictionproblemsbasedonunbalanceddatasetsachinesecasestudy AT yuanyuanqiao amulticlusteringalgorithmtosolvedrivingcyclepredictionproblemsbasedonunbalanceddatasetsachinesecasestudy AT jieyang amulticlusteringalgorithmtosolvedrivingcyclepredictionproblemsbasedonunbalanceddatasetsachinesecasestudy AT chengcheng amulticlusteringalgorithmtosolvedrivingcyclepredictionproblemsbasedonunbalanceddatasetsachinesecasestudy AT yueweiwu multiclusteringalgorithmtosolvedrivingcyclepredictionproblemsbasedonunbalanceddatasetsachinesecasestudy AT wutongzhang multiclusteringalgorithmtosolvedrivingcyclepredictionproblemsbasedonunbalanceddatasetsachinesecasestudy AT longzhang multiclusteringalgorithmtosolvedrivingcyclepredictionproblemsbasedonunbalanceddatasetsachinesecasestudy AT yuanyuanqiao multiclusteringalgorithmtosolvedrivingcyclepredictionproblemsbasedonunbalanceddatasetsachinesecasestudy AT jieyang multiclusteringalgorithmtosolvedrivingcyclepredictionproblemsbasedonunbalanceddatasetsachinesecasestudy AT chengcheng multiclusteringalgorithmtosolvedrivingcyclepredictionproblemsbasedonunbalanceddatasetsachinesecasestudy |