Page 217 - 《水产学报》2025年第7期

曹正良，等 水产学报, 2025, 49(7): 079616

Acoustic signal classification methods of Macrobrachium rosenbergii
based on improved residual network

1
1
1
2
CAO Zhengliang , JIANG Qianqing , JIANG Shan , WANG Zixian ,
3
3
LI Zhaocheng , JIN Yuxue , HU Qingsong 2*
1. College of Oceanography and Ecological Science, Shanghai Ocean University, Shanghai 201306, China;
2. College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, China;
3. College of Marine Living Resource Sciences and Management, Shanghai Ocean University, Shanghai 201306, China
Abstract: The precise identification of shrimp behavior in aquaculture is of great significance for optimizing feeding and dis-
ease prevention. In view of the limitations of traditional optical monitoring methods in complex aquaculture environments, with
integrated passive acoustic technology, this research acquires the acoustic information associated with different behaviors of the
Macrobrachium rosenbergii and proposes a deep learning-based method for behavior recognition in M. rosenbergii. The acous-
tic signals of three behaviors (i.e., feeding, moving, and fighting) were collected and converted into Mel spectrograms as the
dataset. Then the classification effects of CNN, ResNet18, and VGG16 neural network models were compared. The results
showed that ResNet18 in terms of recognition accuracy (97.67%) outperforms VGG16 and CNN. After introducing the Batch
Normalization (BN) algorithm, the recognition accuracy of BN-ResNet18 increased to 99.00%, representing a 1.33% enhance-
ment relative to the baseline ResNet18 model. In addition, BN-ResNet18 showed the best classification performance in the 14.0-
44.1 kHz frequency band, which further proved that the synergistic optimization of residual connection and BN module could
effectively enhance model performance. BN-ResNet18 demonstrates high accuracy and robustness in feature classification of
complex behavioral acoustic signals. This study provides technical support for intelligent recognition based on the acoustic sig-
nals of shrimp behaviors and has potential application value in the refined management of aquaculture.
Key words: Macrobrachium rosenbergii; Mel spectrogram; neural network; Batch Normalization; acoustic signal
Corresponding author: HU Qingsong. E-mail: qshu@shou.edu.cn
Funding projects: Shanghai Agricultural Science and Technology Innovation Project (T2023108); Shanghai Aquatic Animal
Breeding and Green Breeding Collaborative Innovation Center Project (2021 S-T 02-12)

中国水产学会主办 sponsored by China Society of Fisheries https://www.china-fishery.cn
11