FinSecure: Utilizing IoT Sensors for Formaldehyde Detection and Fish Freshness Detection for Enhancing Safety in Fish Consumption Using Machine Learning and Deep Learning

The global food supply heavily relies on fisheries, highlighting the crucial importance of ensuring the safety of fish products. However, the widespread application of antibiotics and the existence of compounds such as formaldehyde present significant hazards to both human consumers and the underwater ecosystem. These risks are compounded by processes like bio-magnification, further emphasizing the need for vigilant monitoring and regulation. This project presents a comprehensive approach to fisheries management and food safety monitoring through the integration of advanced machine learning, deep learning techniques and IoT sensor technology. The overall objective is to develop a model that can determine whether the given sample Fish Species is safe or unsafe for human consumption, by considering parameters: Fish Freshness Detection, using a HCHO Sensor to determine the Formaldehyde levels in the given Fish and finally using these parameters to determine whether the fish can be consumed or not. For the Fish Freshness Detection, utilizing Transfer Learning (pre-trained MobileNetV2 model), the system achieves an impressive accuracy of 99.02%. Thus, integrating all these models, determine whether the supplied fish is safe for consumption or not. By integrating these functionalities, the system contributes to proactive fisheries and food safety monitoring and protection. The holistic approach of this project, combining accurate positions the developed model and IoT application as valuable assets for sustainable aquaculture practices and the preservation of aquatic ecosystems. The project's outcomes contribute to the advancement of several interdisciplinary domains such as machine learning, and fisheries management, laying the groundwork for continued innovation in this interdisciplinary domain.