Variational Mode Decomposition of Seismic Signals for Detection of Moving Elephants
D. S. Parihar, Ripul Ghosh, Aparna Akula, Satish Kumar, H. K. Sardana
Abstract
Elephant monitoring in the vicinity of railway tracks is an important area of research for the reduction of rail-induced elephant accidents. Due to the lack of an autonomous system, effective detection and classification of pachyderms’ movement remain a challenge for early warning applications. This paper presents a hybrid approach of using Variational Mode Decomposition coupled with feature extraction, to classify elephants’ movement in a forest environment. Further, temporal, spectral, and cepstral domain features are extracted from the principal modes of Variational Mode Decomposition and are used to classify the seismic signatures of other movements such as deer, humans’ movement, trains, and electrical noise using Support Vector Machines. The proposed method is compared with the traditional signal decomposition approaches such as Empirical Mode Decomposition, Empirical Wavelet Transform. The classification results for the Elephants class show an average improvement of ~23% and ~16% in F1 score and false-negative rate respectively in comparison with the Empirical Mode Decomposition and Empirical Wavelet Transform. The Variational Mode Decomposition of the seismic signals have an average accuracy of ~73±5% for the classifier Support Vector Machines with quadratic kernel.