Hybrid Approach of CNN and SVM for Shrimp Freshness Diagnosis in Aquaculture Monitoring System using IoT based Learning Support System

Hybrid Approach of CNN and SVM for Shrimp Freshness Diagnosis in Aquaculture Monitoring System using IoT based Learning Support System

Intelligent monitoring and spoilage detection of meat products is one of the most efficient approach which ensures that the food is consumed when it is fresh and avoids health hazards. Shrimp is most popular in terms of nutrition and exquisite nature. Shrimp has its own biochemical components like protein, carbohydrate, lipid and amino acids. However, the quality and freshness of shrimp is hindered in the post-harvested phase due to storage, handling and processing. The objective of this work is to propose an IoT- enabled real time vision-based support system for diagnosis of shrimp freshness, which is capable of performing assessment of quality and freshness using effective deep learning framework based on convolutional neural networks (CNN) and Support Vector Machine (SVM). The proposed model was measured with metrics such as precision, accuracy, F1 score which is respectively compared with the classical model (CNN with SoftMax) respectively. The comparisons shows that the hybrid model achieves 96.2% which is better than the classic model 94.7%. Based on this, it is observed that hybrid model using CNN and SVM found to be a better approach, which makes a difference to decrease the quality misfortune and help in advancement of criticism framework in industry 4.0.