AnomalyNet Leraging Neural Networks for unsupervised detection of fish net damages in aquaculture
Description
Full text not available
Abstract
This thesis explores the application of unsupervised neural network models, specifically autoencoders and transformers, for detecting anomalies in fish nets using acceleration vibration signals. The study evaluates the comparative performance of these models in terms ofaccuracy, precision, recall, and F1-score, and investigates their robustness to environmental noise and sensitivity to low wave height and length configurations. The transformermodel consistently outperformed the autoencoder, achieving an F1-score of 0.95 comparedto the autoencoder’s 0.90. This superior performance is attributed to the transformer’s advanced architecture, which effectively captures complex patterns in the data. Additionally,the transformer model demonstrated greater robustness to environmental noise, maintaininghigh performance levels even with noisy or incomplete data. Contrary to initial expectations,both models performed well in low wave height and length configurations, highlighting theiradaptability to varying environmental conditions. The findings underscore the potentialof transformers in advancing structural health monitoring for aquaculture, while also acknowledging the autoencoder’s viability in resource-constrained scenarios due to its lowercomputational requirements. Future research should focus on optimizing these models forreal-time deployment, exploring hybrid solutions, and ensuring their long-term viability indiverse environmental conditions.