Vehicle Classification Using an Imbalanced Dataset Based on a Single Magnetic Sensor
This paper aims to improve the accuracy of automatic vehicle classifiers for imbalanced datasets. Classification is made through utilizing a single anisotropic magnetoresistive sensor, with the models of vehicles involved being classified into hatchbacks, sedans, buses, and multi-purpose vehicles (M...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/18/6/1690 |
| _version_ | 1811305024786006016 |
|---|---|
| author | Chang Xu Yingguan Wang Xinghe Bao Fengrong Li |
| author_facet | Chang Xu Yingguan Wang Xinghe Bao Fengrong Li |
| author_sort | Chang Xu |
| collection | DOAJ |
| description | This paper aims to improve the accuracy of automatic vehicle classifiers for imbalanced datasets. Classification is made through utilizing a single anisotropic magnetoresistive sensor, with the models of vehicles involved being classified into hatchbacks, sedans, buses, and multi-purpose vehicles (MPVs). Using time domain and frequency domain features in combination with three common classification algorithms in pattern recognition, we develop a novel feature extraction method for vehicle classification. These three common classification algorithms are the k-nearest neighbor, the support vector machine, and the back-propagation neural network. Nevertheless, a problem remains with the original vehicle magnetic dataset collected being imbalanced, and may lead to inaccurate classification results. With this in mind, we propose an approach called SMOTE, which can further boost the performance of classifiers. Experimental results show that the k-nearest neighbor (KNN) classifier with the SMOTE algorithm can reach a classification accuracy of 95.46%, thus minimizing the effect of the imbalance. |
| first_indexed | 2024-04-13T08:18:10Z |
| format | Article |
| id | doaj.art-92c7f66511dd4bf7aa3947d3b12f9072 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T08:18:10Z |
| publishDate | 2018-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-92c7f66511dd4bf7aa3947d3b12f90722022-12-22T02:54:43ZengMDPI AGSensors1424-82202018-05-01186169010.3390/s18061690s18061690Vehicle Classification Using an Imbalanced Dataset Based on a Single Magnetic SensorChang Xu0Yingguan Wang1Xinghe Bao2Fengrong Li3Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai 200050, ChinaShanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai 200050, ChinaShanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai 200050, ChinaShanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai 200050, ChinaThis paper aims to improve the accuracy of automatic vehicle classifiers for imbalanced datasets. Classification is made through utilizing a single anisotropic magnetoresistive sensor, with the models of vehicles involved being classified into hatchbacks, sedans, buses, and multi-purpose vehicles (MPVs). Using time domain and frequency domain features in combination with three common classification algorithms in pattern recognition, we develop a novel feature extraction method for vehicle classification. These three common classification algorithms are the k-nearest neighbor, the support vector machine, and the back-propagation neural network. Nevertheless, a problem remains with the original vehicle magnetic dataset collected being imbalanced, and may lead to inaccurate classification results. With this in mind, we propose an approach called SMOTE, which can further boost the performance of classifiers. Experimental results show that the k-nearest neighbor (KNN) classifier with the SMOTE algorithm can reach a classification accuracy of 95.46%, thus minimizing the effect of the imbalance.http://www.mdpi.com/1424-8220/18/6/1690intelligent transport systemvehicle classificationimbalanced datasetanisotropic magnetoresistive sensor |
| spellingShingle | Chang Xu Yingguan Wang Xinghe Bao Fengrong Li Vehicle Classification Using an Imbalanced Dataset Based on a Single Magnetic Sensor Sensors intelligent transport system vehicle classification imbalanced dataset anisotropic magnetoresistive sensor |
| title | Vehicle Classification Using an Imbalanced Dataset Based on a Single Magnetic Sensor |
| title_full | Vehicle Classification Using an Imbalanced Dataset Based on a Single Magnetic Sensor |
| title_fullStr | Vehicle Classification Using an Imbalanced Dataset Based on a Single Magnetic Sensor |
| title_full_unstemmed | Vehicle Classification Using an Imbalanced Dataset Based on a Single Magnetic Sensor |
| title_short | Vehicle Classification Using an Imbalanced Dataset Based on a Single Magnetic Sensor |
| title_sort | vehicle classification using an imbalanced dataset based on a single magnetic sensor |
| topic | intelligent transport system vehicle classification imbalanced dataset anisotropic magnetoresistive sensor |
| url | http://www.mdpi.com/1424-8220/18/6/1690 |
| work_keys_str_mv | AT changxu vehicleclassificationusinganimbalanceddatasetbasedonasinglemagneticsensor AT yingguanwang vehicleclassificationusinganimbalanceddatasetbasedonasinglemagneticsensor AT xinghebao vehicleclassificationusinganimbalanceddatasetbasedonasinglemagneticsensor AT fengrongli vehicleclassificationusinganimbalanceddatasetbasedonasinglemagneticsensor |