Classifying Shark Behavior in Time and Frequency Domain using CNN and RNN

Abstract

This paper uses accelerometer data from California horn sharks obtained from the Shark Lab at California State University, Long Beach, (CSULB) to build a behavior classifier using deep convolutional neural networks (CNN) and recurrent neural networks (RNN). By transforming time series data into frequency domain using Fast Fourier Transform (FFT), we aim to improve the accuracy of classification for our four different behaviors: feeding, swimming, resting, and nondeterministic motion (NDM). We process 2, 5, and 10 seconds snapshots of the data in the time and frequency domains, which are fed into the neural networks toolbox to train the classifiers. It is observed that the performance of both models is drastically improved when the frequency domain data is applied in the deep neural network.