Research and Application of Efficient Detection Algorithm for Harmful Substances in Food

With food safety becoming the focus of global attention, rapid and accurate detection of harmful substances in food has become the key to protect public health. In this study, the efficient detection algorithm of harmful substances in food is deeply studied, aiming at developing a hybrid model combining advanced machine learning technology and big data analysis to realize rapid and accurate identification of harmful substances in food. By constructing a hybrid model (CNN-LSTM) based on Convolutional Neural Network (CNN) and Long Short Term Memory Network (LSTM), this study fully utilizes the complementary information in food image and spectral data to improve detection accuracy and efficiency. The experimental results show that the proposed CNN-LSTM hybrid model shows excellent performance in the detection of harmful substances in food, with high accuracy and strong generalization ability, and can be applied to various types of food samples and harmful substances. This study not only provides an efficient and convenient detection method for food safety supervision, but also provides a new idea and method for the research of harmful substances detection algorithm in food.