Acoustic Signal Processing using Deep Learning for Intelligent Feed Monitoring of Dicentrarchus Labrax

Acoustic signal processing holds significant promise for real-time fish feeding intensity estimation in aquaculture. Unlike traditional methods reliant on visual cues or sensor data, acoustic analysis provides valuable insights into feeding behavior and demand. By capturing indicators such as water splashing, acoustic techniques can estimate the current feeding demand of fish. Acoustic techniques in aquaculture remain under explored, especially those delving into temporal information within acoustic spectrograms. This paper presents an intelligent monitoring approach using deep learning and acoustic signals. It investigates the perceptual domain of fish feeding acoustic spectrum recognition, extracting insights from Mel Spectrogram feature maps. Employing a supervised machine learning method with a multi-instance multi-label technique, the study classifies audio events during operational scenarios. Furthermore, the research assesses the effectiveness of the proposed neural network (NN) models for multi-label classification by comparing it with established NN architectures like AlexNet, ResNet18, and VGG11, showcasing its superior performance.