2026-10-13T04:35:42Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33814435 2026-09-15T17:58:17Z category_146 category_15 category_39 category_734 category_931 portal_5 item_type_3 month_year_09_2026

<p>YOLO-CBNet model hyperparameters.</p> Mahdi Hamzaoui (24950158) Leila Bousbia (24950161) Mohamed Ould-Elhassen Aoueileyine (19743433) Imen Filali (23739873) Ridha Bouallegue (19769292) Space Science Neuroscience Ecology Biological Sciences not elsewhere classified Information Systems not elsewhere classified traditional recognition approaches partially occluded fish overall production efficiency fish species remains experimental results indicate enhanced architecture designed counter low contrast underwater fish recognition baseline yolov11 model world aquaculture systems clear performance boost improvements highlight yolo cbnet &# 8217 enhanced detection framework yolov11 framework underwater detection xlink "> uneven lighting suspended particles stage strategy significantly limit robust attention reliable solution reduced visibility pivotal challenge method adopts health monitoring dependable monitoring combination intended color distortion bifpn ), achieved 0 accurate identification <div><p>The accurate identification of fish species remains a pivotal challenge in aquaculture, as it directly influences population management, health monitoring, and overall production efficiency. Yet, underwater environments often present difficult conditions such as reduced visibility, suspended particles, and uneven lighting that significantly limit the performance of traditional recognition approaches. In this study, we introduce YOLO-CBNet, an enhanced architecture designed to overcome these constraints and provide more dependable monitoring in real-world aquaculture systems. The method adopts a two-stage strategy. First, a Contrast Limited Adaptive Histogram Equalization (CLAHE) module is employed to counter low contrast, turbidity, and color distortion, restoring essential visual information. Second, the YOLOv11 framework is refined through the integration of the Convolutional Block Attention Module (CBAM) and a Bidirectional Feature Pyramid Network (BiFPN), a combination intended to improve multiscale feature fusion and reinforce the detection of small or partially occluded fish. Experimental results indicate that YOLO-CBNet delivers a clear performance boost, the precision score reaches 0.951, surpassing the baseline YOLOv11 model, which achieved 0.911 under the same conditions. These improvements highlight YOLO-CBNet’s potential as a reliable solution for underwater detection and recognition tasks within modern aquaculture environments.</p></div> 2026-09-15T17:57:59Z Dataset Dataset 10.1371/journal.pone.0341525.t002 https://figshare.com/articles/dataset/_p_YOLO-CBNet_model_hyperparameters_p_/33814435 CC BY 4.0