A method for terrain classification based on vibration response resulted from wheel-terrain interaction is presented. Four types of terrains including sine,gravel,cement and pebble were tested.The vibration data were ...A method for terrain classification based on vibration response resulted from wheel-terrain interaction is presented. Four types of terrains including sine,gravel,cement and pebble were tested.The vibration data were collected by two single axis accelerometers and a triaxial seat pad accelerometer,and five data sources were utilized. The feature vectors were obtained by combining features extracted from amplitude domain,frequency domain,and time-frequency domain. The ReliefF algorithm was used to evaluate the importance of attributes; accordingly,the optimal feature subsets were selected. Further,the predicted class was determined by fusion of outputs provided by five data sources. Finally,a voting algorithm,wherein a class with the most frequent occurrence is the predicted class,was employed. In addition,four different classifiers,namely support vector machine,k-nearest neighbors,Nave Bayes,and decision tree,were used to perform the classification and to test the proposed method. The results have shown that performances of all classifiers are improved.Therefore,the proposed method is proved to be effective.展开更多
基金Supported by the National Natural Science Foundation of China(51005018)
文摘A method for terrain classification based on vibration response resulted from wheel-terrain interaction is presented. Four types of terrains including sine,gravel,cement and pebble were tested.The vibration data were collected by two single axis accelerometers and a triaxial seat pad accelerometer,and five data sources were utilized. The feature vectors were obtained by combining features extracted from amplitude domain,frequency domain,and time-frequency domain. The ReliefF algorithm was used to evaluate the importance of attributes; accordingly,the optimal feature subsets were selected. Further,the predicted class was determined by fusion of outputs provided by five data sources. Finally,a voting algorithm,wherein a class with the most frequent occurrence is the predicted class,was employed. In addition,four different classifiers,namely support vector machine,k-nearest neighbors,Nave Bayes,and decision tree,were used to perform the classification and to test the proposed method. The results have shown that performances of all classifiers are improved.Therefore,the proposed method is proved to be effective.
