Abstract
A novel multi-class classification method named the voting-cross support vector machine (SVM) method was proposed in this study, for classifying vehicle targets in wireless sensor networks. The advantages and disadvantages of available methods were summarized, after a comparative analysis of commonly used multi-objective classification algorithms. To improve the classification accuracy of multi-class classification and ensure the low complexity of the algorithm for engineering implementation on wireless sensor network (WSN) nodes, a framework was proposed for cross-matching and voting on the category to which the vehicle belongs after combining the advantages of the directed acyclic graph SVM (DAGSVM) method and binary-tree SVM method. The SVM classifier was selected as the basis two-class classifier in the framework, after comparing the classification performance of several commonly used methods. We utilized datasets acquired from a real-world experiment to validate the proposed method. The calculated results demonstrated that the cross-voting SVM method could effectively increase the classification accuracy for the classification of multiple vehicle targets, with a limited increase in the algorithm complexity. The application of the cross-voting SVM method effectively improved the target classification accuracy (by approximately 7%), compared with the DAGSVM method and the binary-tree SVM method, whereas time consumption decreased by approximately 70% compared to the DAGSVM method.
Highlights
Wireless sensor networks (WSNs) consist of nodes capable of sensing, signal processing, and communicating
Determined by the classification accuracy of three two-class classifiers (PAD (A), PAC (A), and PAB (A)), The classification accuracy calculation Formulas (9)–(12), reveal that the target classification accuracy and the classification error of each two-class classifiers will reduce the final classification accuracy of the directed acyclic graph SVM (DAGSVM) algorithm depends on the category number N, and the classification accuracy of the PABCD (A)
The results demonstrated that the cross-voting method using the decision tree (DT) two-class classifier, adaboosting two-class classifier, or support vector machine (SVM) classifier could effectively classify the targets in the WSN system
Summary
Wireless sensor networks (WSNs) consist of nodes capable of sensing, signal processing, and communicating. The available multi-class classification algorithms for classifying multiple types of vehicles detected in the WSN system can be divided into two categories. The first category of multi-class classification method improves on the principle of two-class classification algorithm. Of the algorithms mentioned above, a few can classify vehicle type in WSNs by using the acoustic signal, seismic signal, or magnetic signal of the target acquired by a single sensor node in WSNs. The first category of multi-class classification methods is based on the improvement of the two-class classifier, and substantially increases the computational complexity of the algorithm.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call