Enhanced Livestock Monitoring with Modified Kalman Filter and Decision Tree Algorithm for Noise-Reduction in Sensor Data

Kalman filtering, a robust statistical estimation method, has emerged as a pivotal tool across disciplines, excelling in noise reduction and state estimation with minimal computational demands. Its adaptability has fostered diverse implementations, notably in complex sensory and robotic systems. This technique significantly enhances system reliability and efficiency by effectively filtering signals from noise, thereby catalyzing technological progress across numerous sectors. The method is precious in modern systems that rely on high-sensitivity sensors like accelerometers and gyroscopes, which are crucial for improved performance but vulnerable to noise. By addressing the challenge of noisy data readings, which can significantly impact system performance. By strategically deploying sensors on cattle, real-time data on animal movements are collected, and with this, we can predict valuable insights into their daily activities are possible. This innovative research on animal welfare management has been adopted to optimize farm operations. The suggested revised algorithm of the standard Kalman filter can effectively minimize noise in the livestock management system. Different combinations of values for the Q and R variables are tested and tabulated at Q = 0.01 and R = 100, also Q = 0.01, and R = 1000 we got maximum results. Also, we get better results on the proposed modified Kalman filter with the decision tree algorithm, which effectively predicts the actual data with an accuracy of 88.67%, precision of 87.53%, recall of 87.5%, and F1 score of 87.47%, indicating its strong ability to capture the underlying patterns in the dataset. In contrast, the Linear Regression model may be underfitting due to its inability to model such non-linearity effectively. When comparing the results, the decision tree regression method outperformed linear regression and polynomial regression methods. Also, it is well-suited for capturing sudden shifts and plateaus in the cattle's behavior. This innovative project adopted an advanced system that enhances animal welfare management and optimizes farm operations.