ABSTRACT Livestock monitoring systems have been significantly transformed by the implementation of Internet of Things (IoT) technology in agriculture. This integration enables the collection and analysis of data in real time, which contributes to improved animal welfare and productivity. This paper showcases the integration of various microcontrollers, sensors and sophisticated algorithms to give an extensive assessment of the most recent IoT‐based livestock health monitoring systems. A wide array of sensors, including accelerometers, temperature sensors, heart rate sensors and more, coupled with various microcontrollers, such as Raspberry Pi, ESP8266, Arduino and ESP32, are primarily used in monitoring systems. Internet of Things (IoT) platforms such as ThingSpeak and Blynk, as well as the development of online interfaces and mobile applications, provide extensive user input. The integration of state‐of‐the‐art algorithms is explored in detail, including support vector machines (SVM), decision trees, artificial neural networks (ANN), YOLOv5 object detection, different machine learning algorithms, random forest classifiers and ThingSpeak IoT analytics platform. Particular attention is given to algorithms that detect various parameters, including acetone levels, cow location, hormone release, body temperature, activity level, bellowing, jaw movement, heart rate, temperature, oestrous cycle, detection and tracking, action recognition, size variations, motion deformation, heat stress, ambient temperature, sleep tracking and more. The purpose of this review article is to facilitate the adoption of Internet of Things (IoT) solutions for sustainable and effective livestock management practices by offering a thorough analysis of existing IoT technologies used in livestock monitoring.
Modak et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: