Tracking the Nodal Point of Weakly Electric Fish Using Artificial Neural Networks

Abstract

In living beings, there is a closed-loop system called sensorimotor transformation, in which the signals received by the sensory organs from the environment are processed in the nervous system, and the necessary motor signals are transmitted to the muscular system. Unfortunately, the closed-loop nature of the structure makes it difficult to decipher the relationship between inputs and outputs. Since the nodal point on the anal fin of the weakly electric fish (Eigenmannia virescens) may be an output of the sensorimotor control system, precisely monitoring its position is important. The method used in the literature to find the nodal point so far is to mark each video frame manually. However, manual marking creates a significant workload and causes a waste of time. This study aims to determine the position of the node that has been manually marked so far by using artificial neural networks more easily and effectively.