Detection of Epizootic Ulcerative Syndrome in Freshwater Edible Fish Using AI Techniques #981747

Detection of Epizootic Ulcerative Syndrome in Freshwater Edible Fish Using AI Techniques explores innovative methods for identifying and managing a serious fish disease affecting aquaculture worldwide. Epizootic Ulcerative Syndrome (EUS), caused by the oomycete Aphanomyces invadans, leads to hemorrhagic ulcers, tissue necrosis, and high mortality in freshwater and estuarine fish, threatening food security and livelihoods. Traditional detection relies on visual inspection or laboratory tests like PCR, which are accurate but slow and require skilled personnel. This book highlights how artificial intelligence (AI) and image-based machine learning can overcome these challenges. Techniques such as Principal Component Analysis (PCA) with feature detectors, neural networks, and deep learning architectures like MobileNetV2 are applied to automatically detect and classify EUS from fish images with high accuracy (≈84 %). Colour thresholding and object segmentation further improve the detection of affected regions. By enabling rapid, scalable, and objective disease identification, these AI-driven approaches support early intervention, reduce economic losses, and empower farmers without specialised expertise. The book also discusses future improvements, including training models on diverse datasets to enhance field reliability and applicability. Key Features: -Focus on Epizootic Ulcerative Syndrome (EUS) in freshwater edible fish -Use of AI and machine learning for automated, rapid disease detection -Techniques include PCA, feature detectors, neural networks, and deep learning (MobileNetV2) -Practical applications for real-time monitoring in aquaculture -Strategies to reduce economic losses and improve fish health