Skip to Content
  • Proceeding Paper
  • Open Access

20 October 2026

7 Pages

Machine Learning-Based Optimization with IoT of an Automated Composting System for Coffee Grounds †

,
and
School of Electrical, Electronics, and Computer Engineering, Mapua University, 658 Muralla St., Intramuros, Manila 1002, Philippines
*
Author to whom correspondence should be addressed.
†
Presented at the 6th International Conference on Electronic Communications, Internet of Things and Big Data (ICEIB 2026), New Taipei, Taiwan, 24–26 April 2026.

Abstract

Traditional composting requires months to mature and is often disrupted by uncontrolled environmental factors, such as insufficient heat generation during colder seasons. Therefore, we developed a smart, automated composting system that maintains a controlled environment with regulated heating, watering, mixing, and ventilation. Sensor feedback continuously drives the system toward optimal parameters. Coffee grounds were selected as feedstock because of the growing waste generated by increasing coffee consumption. The bin integrates IoT devices for real-time monitoring, and the collected data were analyzed using machine learning techniques, including principal component analysis, random forest, and decision tree algorithms, to predict compost maturity. The developed system reduced the maturation period to 12 days and produced compost of higher quality and safety compared with traditional methods. Optimal parameters were achieved, including soil temperature of 55–60 °C, moisture levels of 40–65%, and pH between 5.5 and 9.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.