What is it about?
This study aimed to find out what factors have the biggest impact on milk quality. We looked at 9 different variables including pH, temperature, taste, odor, fat, turbidity, color, and grade to see which ones were the most important. We used the method called Principal Component Analysis (PCA) and found that temperature and color were the top factors affecting milk quality, with over 95% contribution to PCA-1 and PCA-2. We also divided the milk samples into three grades - low, medium, and high - and used a machine learning algorithm called Artificial Neural Network (ANN) to classify the milk samples. We found that the ANN model was able to classify the milk samples with high accuracy (0.9988) and was more accurate and stable compared to other methods
Featured Image
Why is it important?
This study identifies temperature and color as the primary factors influencing milk quality through Principal Component Analysis (PCA), and successfully classifies milk into quality grades with high precision using an Artificial Neural Network (ANN), demonstrating the potential of machine learning in enhancing dairy industry standards. It represents a significant step towards the application of advanced analytical and predictive technologies in the dairy sector, promising improved product quality and consumer satisfaction.
Perspectives
This research highlights the synergy between data-driven approaches and dairy quality control, showcasing how advanced computational methods like PCA and ANN can revolutionize the assessment and classification of milk quality. It paves the way for integrating technology with traditional industries to achieve higher accuracy and efficiency in product evaluation.
Dr. Debajyoty Banik
Read the Original
This page is a summary of: Deep Learning Based Approach for Milk Quality Prediction, April 2023, Institute of Electrical & Electronics Engineers (IEEE),
DOI: 10.1109/icetet-sip58143.2023.10151626.
You can read the full text:
Contributors
The following have contributed to this page
