Comparative Analysis of Ultrasonic Sensor Accuracy for Smart Trash ATM Application

Abstract

Waste level monitoring is still often done manually, making it inefficient in preventing accumulation. Ultrasonic sensors are widely used because they are practical and affordable, but their accuracy is often affected by environmental and hardware conditions. This study aims to compare the Kalman Filter and Exponential Moving Average methods to improve the accuracy of ultrasonic sensor readings in an automated waste monitoring system. The type of research used is an experiment with a microcontroller-based system that is tested on various waste height variations. The Kalman Filter combines previous estimates with new data, while the Exponential Moving Average gives more weight to the most recent value. The performance of both methods is assessed based on measurement consistency and error rate.The data was then analyzed quantitatively using Root Mean Square Error (RMSE).The results show that the Kalman Filter produces lower errors and more stable data compared to the Exponential Moving Average or raw data. In conclusion, the Kalman Filter is more effective in improving the reliability and accuracy of the automated waste monitoring system. The implications of this research suggest that selecting the right sensor type can significantly improve system performance in detecting waste capacity in real time.Pemantauan ketinggian sampah di tempat sampah masih banyak dilakukan secara manual, sehingga kurang efisien dalam mencegah terjadinya penumpukan sebelum ditangani. Sensor ultrasonik menjadi solusi umum karena praktis dan terjangkau, tetapi pembacaannya rentan terhadap gangguan lingkungan dan perangkat keras yang menyebabkan ketidakstabilan data. Penelitian ini bertujuan membandingkan dua metode pemrosesan data, yaitu Kalman Filter dan Exponential Moving Average, dalam meningkatkan keakuratan pembacaan sensor ultrasonik pada sistem pemantauan sampah otomatis. Sistem dirancang menggunakan mikrokontroler dan diuji dalam kondisi variasi ketinggian sampah. Hasil pengujian menunjukkan bahwa metode Kalman Filter menghasilkan nilai kesalahan lebih rendah dibandingkan metode Exponential Moving Average dan data mentah sensor. Kalman Filter mampu meningkatkan keandalan pengukuran ketinggian sampah secara lebih optimal. Kesimpulannya, metode Kalman Filter lebih efektif dalam mengurangi ketidakstabilan data dan meningkatkan akurasi sistem pemantauan sampah otomatis.