Saddam Putra Kunsina, Iswanto, Alfian Maarif, Gilang Nugraha Putu Pratama
Accurate sensor readings have an important role in ensuring the reliability of data for IoT devices. However, sensor measurements are susceptible to noise, leading to unreliable data. This research paper addresses the issue of sensor reading errors and proposes a solution using Kalman Filter to mitigate the impact of noise. The study focuses on implementing the widely known Kalman Filter, a filtering method, that can be used to reduce the influence of noise on sensor readings. Moreover, for optimizing the parameters of Kalman Filter, Genetic Algorithm is employed. The optimized parameters, denoted as Q = 9.9 and R = 0.1, represent the covariance matrices for process and measurement noise, respectively. In order to demonstrate practicality, this research utilizes the ESP32 and Analog-to-Digital Converter for collecting sensor data. Experimental results validate the effectiveness of the proposed approach. The optimized Kalman Filter can reduce the MSE caused by noise to 74.102. It indicates a noteworthy enhancement in sensor reading accuracy. This achievement holds potential for IoT applications where reliable and precise sensor data is of utmost importance. It can be concluded that by combining the Kalman Filter, Genetic Algorithm, this study contributes to the development of robust noise reduction mechanisms in IoT systems. The findings of this research offer promising prospects for enhancing the overall quality of sensor data in many IoT applications. © 2023 IEEE.
Universitas Negeri Yogyakarta, Yogyakarta, Indonesia; Universitas Muhammadiyah Yogyakarta, Yogyakarta, Indonesia; Universitas Ahmad Dahlan, Yogyakarta, Indonesia
