Optimization of Wi-Fi Throughput for IoT Livestock Monitoring Using Machine Learning

Abstract

The Internet of Things (IoT) has revolutionized agricultural
activities, especially in the area of remote monitoring. Although, it
has some limitations in terms of network instability and data
security. The issue of Wi-Fi network instability and data security
have impacted negatively on the IoT technology for monitoring
livestock. In this study, a Logistic Regression (LR) algorithm of the
Machine Learning (ML) technique was deployed for the
optimization of the Wi-Fi network throughput function. Data
security and privacy for a secured network were implemented using
cryptography and steganography encryption methods. A graphical
user interface and a database in form of a web application were
created for viewing real-time livestock activities. The significant
results of the study showed a positive impact of both machine
learning and encryption on IoT technology. The paper, results were
tested with MATLAB software application.