IOT Based Livestock Monitoring with Location Tracking and Smart Feeding System Using ML Algorithms

Effective management of livestock is crucial for increasing agricultural productivity, safeguarding animal health, and minimizing financial losses for farmers. Early identification of health abnormalities, along with efficient feeding strategies, plays a significant role in preventing disease transmission and improving animal welfare. This study proposes an Internet of Things (IoT)–enabled livestock monitoring system that incorporates real-time location tracking and an intelligent feeding approach powered by machine learning algorithms. The system continuously acquires physiological, behavioural, and environmental parameters using various sensors, including a MEMS sensor to assess animal motion and posture, a DS18B20 sensor for measuring body temperature, and a pulse sensor to monitor heart rate. Data collection, processing, and control operations are performed using an Arduino Mega and an STM32F103C8T6 microcontroller. The acquired sensor data is forwarded to a Python-based machine learning framework to identify unusual health patterns and to adjust feeding schedules based on the animal’s condition and activity levels. A GPS module enables continuous tracking of livestock location. When abnormal health conditions are detected, the system activates a buzzer and sends alert messages containing health information and location details to the farmer through a GSM communication module. This integrated solution supports continuous monitoring, data-driven decision-making, and remote livestock supervision, leading to improved animal health, optimized feeding practices, and sustainable farm management.