Skip to main content

ORIGINAL RESEARCH article

Front. Mar. Sci.
Sec. Ocean Observation
Volume 11 - 2024 | doi: 10.3389/fmars.2024.1437173
This article is part of the Research Topic Personalized and Intelligent Feeding in Aquaculture View all 4 articles

Recognition of Feeding Sounds of Large-mouth Black Bass Based on Low-dimensional Acoustic Features

Provisionally accepted
Shijing Liu Shijing Liu 1*Shengnan Liu Shengnan Liu 2Renyu Qi Renyu Qi 1Haojun Zheng Haojun Zheng 2Jiapeng Zhang Jiapeng Zhang 1Cheng Qian Cheng Qian 1Huang Liu Huang Liu 1*
  • 1 Fishery Machinery and Instrument Research Institute, Chinese Academy of Fishery Sciences (CAFS), Beijing, China
  • 2 Dalian Ocean University, Dalian, Liaoning, China

The final, formatted version of the article will be published soon.

    The eating sounds of largemouth black bass (Micropterus salmoides) are primarily categorized into swallowing and chewing sounds, both intensities of which are closely correlated with fish density and feeding desire. Therefore, accurate recognition of these two sounds is of significant importance for studying fish feeding behavior. In this study, we propose a method based on low-dimensional acoustic features (LDAF) for the recognition of swallowing and chewing sounds in fish. Initially, utilizing synchronous audio-visual means, we collect feeding sound signals and image signals of largemouth black bass. By analyzing the time-frequency domain features of the sound signals, we identify 15 key acoustic features across four categories including short-time average energy, average Mel-frequency cepstral coefficients, power spectral peak, and center frequency. Subsequently, employing nine dimensionality reduction algorithms, we select the top Top-6 features from the 15-dimensional acoustic features and compare their precision in recognizing swallowing and chewing sounds using four machine learning models. Results indicate that supervised feature pre-screening positively enhances the accuracy of largemouth black bass feeding feature recognition. Extracted acoustic features demonstrate global correlation and linear characteristics. When considering feature dimensionality and classification performance, the combination of feature dimensionality reduction and recognition model based on the random forest model exhibits the best performance, achieving an identification accuracy of 98.63%. The proposed method offers higher assessment accuracy of swallowing and chewing sounds with lower computational complexity, thus providing effective technical support for the research on precise feeding technology in fish farming.

    Keywords: largemouth black bass, Feature Selection, Feature dimensionality reduction, recognition, machine learning models

    Received: 23 May 2024; Accepted: 13 Aug 2024.

    Copyright: © 2024 Liu, Liu, Qi, Zheng, Zhang, Qian and Liu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence:
    Shijing Liu, Fishery Machinery and Instrument Research Institute, Chinese Academy of Fishery Sciences (CAFS), Beijing, China
    Huang Liu, Fishery Machinery and Instrument Research Institute, Chinese Academy of Fishery Sciences (CAFS), Beijing, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.