Utilization of the Decision Tree Method for pH Monitoring in IoT-Based Black Soldier Fly (Hermetia Illucens) Cultivation
DOI:
https://doi.org/10.33795/jartel.v16i2.9077Keywords:
Bioconversion, Black Soldier Fly (BSF), Decision Tree, Internet of Things (IoT), Multiparameter SensorAbstract
Organic waste management is a significant challenge in urban areas, and bioconversion using Black Soldier Fly (BSF) larvae has emerged as a promising solution. However, the optimal cultivation process for BSF requires intensive and precise environmental condition monitoring. This research aims to design and implement an Internet of Things (IoT) based monitoring system to optimize the maintenance of BSF larvae by analyzing the influence of environmental variables in real-time. The method involves developing ESP32-based hardware with Temperature (DHT22), Humidity (DHT22), Light Intensity (BH1750), and CO₂ (MQ135) sensors connected to a MySQL database, along with a web interface e for visualization. A hybrid prediction model based on a Decision Tree with a k-Nearest Neighbors fallback mechanism was implemented to predict the pH value of the larvae's medium based on sensor data. Testing results show that the designed hardware is highly reliable, with sensor accuracy rates of 98.82% for Temperature, 98.30% for Humidity, and 98.92% for CO₂. The developed pH prediction model achieved an accuracy of 97.55% with an average error rate of only 2.45%. All system functionalities, from data transmission to web visualization, were proven to be valid and performed as expected. This research successfully demonstrates that an IoT-based monitoring system equipped with a predictive model can be an effective solution for analyzing and optimizing the BSF cultivation environment, thereby supporting a more efficient organic waste bioconversion process.
References
R. Muhammad, "Municipal solid waste management in major Indonesian cities: Current status and crucial issues," Journal of Indonesian Urban Studies, vol. 6, no. 1, pp. 12–25, 2024.
M. T. Ali et al., "Environmental impacts of inefficient organic waste management on greenhouse gas emissions," International Journal of Climate Change Strategies, vol. 16, no. 3, pp. 290–305, 2024.
E. Kurniawati and M. T. Ali, "Technical challenges and community awareness in organic waste segregation and recycling in urban areas," Journal of Waste Management and Sustainability, vol. 12, no. 2, pp. 115–124, 2024.
N. Ribeiro et al., "Capacity of Hermetia illucens larvae to decompose diverse organic materials: From food scraps to agricultural waste," Waste Management, vol. 142, pp. 67–76, 2022.
S. Lestari, Bioconversion Mechanisms of Organic Waste: Principles and Microbial Actions. Jakarta, Indonesia: Academic Press, 2022.
M. Faisal et al., "Value-added byproducts from organic waste bioconversion using black soldier fly larvae," Indonesian Journal of Environmental Management, vol. 8, no. 1, pp. 45–54, 2023.
A. Amandanisa and P. Suryadarma, "Potential of black soldier fly (Hermetia illucens) larvae as an alternative protein source in animal feed," Journal of Tropical Agriculture and Development, vol. 18, no. 2, pp. 75–83, 2020.
A. Nugroho et al., "Extraction and application of lauric acid from black soldier fly maggot oil for the cosmetics industry," Journal of Oleo Science and Technology, vol. 31, no. 2, pp. 88–96, 2024.
J. C. Kim et al., "Automation challenges in large-scale rearing of black soldier fly larvae (Hermetia illucens): A review," Biomass and Bioenergy, vol. 150, p. 106112, 2021.
L. Breiman, "Classification and regression trees for interpretable machine learning models," Data Mining and Knowledge Discovery, vol. 36, no. 2, pp. 412–435, 2022.
T. Haynes and R. Kumar, "Extraction of explicit if-then logical rules from decision tree architectures," IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 7, pp. 6712–6724, 2023.
S. Rahmawati and H. Wijaya, "Predictive modeling of substrate pH using environmental parameters in organic decomposition," Indonesian Journal of Agricultural Engineering, vol. 14, no. 1, pp. 45–53, 2024.
M. T. Santos et al., "Understanding biological decomposition dynamics through transparent machine learning algorithms," Bioresource Technology, vol. 372, p. 128640, 2023.
J. Zhang and X. Wang, "Modeling complex non-linear biochemical relationships in insect farming environments using tree-based classifiers," Computers and Electronics in Agriculture, vol. 211, p. 108015, 2023.
A. G. Smith, "Lightweight machine learning algorithms for real-time edge computing applications," IEEE Embedded Systems Letters, vol. 15, no. 3, pp. 118–121, 2023.
F. Al-Obeidat et al., "Deploying computational tree models on 8-bit microcontrollers for low-cost smart farming systems," IoT and Cyber-Physical Systems, vol. 4, pp. 89–98, 2024.
