• E/18/154, Jayasumana C.H. email
• E/18/327, Senevirathna M.D.C.D. email
• E/18/349, Thalisha W.G.A.P. email

1. Introduction
2. Key Features
3. Links

Welcome to the Disease Monitoring in the Dairy Industry web page! Our project focuses on addressing the issue of Subclinical Mastitis (SCM) in dairy cows using advanced technology and machine learning.

Subclinical Mastitis is a common and costly disease that affects dairy cows. It is challenging to detect because there are no visible signs of inflammation or abnormalities in the udder. However, it can have a significant impact on milk quality and production.

Our solution utilizes a machine learning model trained on milk data to identify cases of Subclinical Mastitis. By analyzing various milk quality parameters such as lactation number, pH, conductivity, fat content, and salt levels, our model can predict the likelihood of SCM positivity.

The web application is the central component of our solution. It provides an intuitive and user-friendly interface where dairy farmers and industry professionals can input milk data from individual cows or bulk tank samples. The application then processes the data through the machine learning model to generate predictions on the presence of SCM.

1. Data Input: Users can easily enter milk data for individual cows or bulk tank samples, including relevant parameters.
2. Prediction Results: Once the data is submitted, the machine learning model analyzes the input and provides predictions on the likelihood of Subclinical Mastitis positivity. The results are presented in a clear and understandable format.
3. Data Visualization: The web application offers interactive charts and graphs to visualize the data and trends associated with Subclinical Mastitis. This visual representation assists users in comprehending and interpreting the information effectively.

Our Disease Monitoring web application empowers dairy farmers and industry professionals with an efficient and accurate tool for early detection and prevention of Subclinical Mastitis in their herds. By utilizing machine learning and milk quality data, we aim to improve the overall health and productivity of dairy cows, ultimately benefiting the dairy industry as a whole.

• Project Repository
• Project Page
• Department of Computer Engineering
• University of Peradeniya