MEAT QUALITY PREDICTION USING MACHINE LEARNING

Meat quality is an essential aspect of the food industry. However, traditional methods of meat quality prediction have limitations in terms of accuracy, cost, and time efficiency. This project focused on utilizing advanced Deep learning and Machine learning algorithms to develop- machine learning models that could predict the freshness (or spoilage) of meat with a 100% accuracy, based on image data. In addition to accuracy, this study emphasizes the significance of speed and time in selecting the optimal machine learning model. The research questions are: Q1. What hybrid neural networks should be used to predict freshness? Q2. How do hybrid neural networks determine the freshness of the meat based on the image? Q3. How can accuracy and performance speed be improved? A dataset from the Kaggle repository was used to explore various machine learning algorithms such as Support Vector Machines, Decision Trees, and Random Forests with a combination of Convolutional Neural Network, a deep learning network. The findings are: Q1. A combination of Support Vector Machines-Convolutional Neural Network, Decision Trees-Convolutional Neural Network, and Random Forests-Convolutional Neural Network were used to predict freshness. 2) The hybrid neural networks were trained using the tensorflow.keras.models, a high-level neural networks API of the TensorFlow library, which allowed the creation and training of complex machine learning models in a simple and straightforward manner. 3) The accuracy and performance speed of the model can be improved by utilizing a distributed computing environment for training, which involves the collaboration of multiple machines to carry out computations. The conclusion from our project is that Utilizing the hybrid neural networks developed, it is possible to classify meat products as either fresh or spoiled using image analysis. This approach not only reduces the reliance on human input for meat classification but also decreases the time taken to complete the classification process. Furthermore, emerging areas for future research that emerged from this study is to develop machine learning models that can integrate and fuse multi-modal data such as genetics, feeding and processing techniques to make more accurate predictions of meat quality