A Comparison of Machine Learning Methods for Knowledge Extraction Model in a LoRa-Based Waste Bin Monitoring System

Aug 5, 2026

Upload by Eliana

Knowledge Extraction Model (KEM) is presented as an IoT-driven smart waste bin solution using LoRa network media to support efficient scheduling of waste-emptying. The study compares Decision Tree, Naïve Bayes, K-Nearest Neighbor, Support Vector Machine, and Multi-Layer Perceptron for the classification task required to choose optimal emptying schedules. Evaluation uses accuracy, recall, precision, F-measure, and ROC curves with ten-fold cross-validation. Results indicate Decision Tree leads accuracy, recall, precision, and ROC performance, while K-NN delivers the highest F-measure, enabling broader knowledge extraction across IoT datasets.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Introduction

Knowledge Extraction Model (KEM) and system design

Related work on IoT and waste management

Machine learning classification approaches

A comparison of machine learning methods for knowledge extraction model in a LoRa-based waste bin monitoring system Aa Zezen Zaenal Abidin a,b, 1,*, Mohd Fairuz Iskandar Othman b,2, Aslinda Hassan b,3 , Yuli Murdianingsih a,4, Usep Tatang Suryadi a,5, Timbo Faritchan Siallagan a,6 a Informatics Departement, Universitas Mandiri, Jl.Marsinu no 5 Subang, Subang 41211 Jawa Barat, Indonesia b Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, 76100 Durian Tunggal, Melaka, Malaysia [1](1 zezen@universitasmandiri.ac.id)[ zezen@universitasmandiri.ac.id](1 zezen@universitasmandiri.ac.id); [2](2 mohdfairuz@utem.edu.my)[ mohdfairuz@utem.edu.my](2 mohdfairuz@utem.edu.my); [3](3 aslindahassan@utem.edu. my)[ aslindahassan@utem.edu. my](3 aslindahassan@utem.edu. my); [4](4 yuli@universitasmandiri.ac.id)[ yuli@universitasmandiri.ac.id](4 yuli@universitasmandiri.ac.id); [5](5usep@universitasmandiri.ac.id)[usep@universitasmandiri.ac.id](5usep@universitasmandiri.ac.id); [6](6 timbosiallagan@universitasmandiri.ac.id)[ timbosiallagan@universitasmandiri.ac.id](6 timbosiallagan@universitasmandiri.ac.id) * corresponding author ARTICLE INFO ABSTRACT | Article history
Received February 13, 2023 Revised July 19, 2023
Accepted September 30, 2023 Available online February 29, 2024
Keywords
IoT
Knowledge extraction model LoRa
Machine Learning Waste management | Knowledge Extraction Model (KEM) is a system that extracts knowledge through an IoT-based smart waste bin emptying scheduling classification Classification is a difficult problem and requires an efficient classification method. This research contributes in the form of the KEM system in the classification of scheduling for emptying waste bins with the best performance of the Machine Learning method. The research aims to compare the performance of Machine Learning methods in the form of Decision Tree, Naïve Bayes, K-Nearest Neighbor, Support Vector Machine, and Multi-Layer Perceptron, which will be recommended in the KEM system. Performance testing was performed on accuracy, recall, precision, F-Measure, and ROCS curves using the cross-validation method with ten observations. The experimental results show that the Decision Tree performs best for accuracy, recall, precision, and ROCS curve. In contrast, the K-NN method obtains the highest F-measure performance. KEM can be implemented to extract knowledge from data sets created in various other IoT-based systems.

This is an open access article under the CC–BY-SA license
| | --- | --- | 1. Introduction The Knowledge Extraction Model (KEM) is a system designed to monitor IoT-based waste bins using LoRa network media, facilitating sorting organic, inorganic, and metal waste. KEM enables the extraction of insights from waste management data to schedule waste disposal from intelligent bins efficiently. Constructed using an IoT-based framework utilizing LoRa network media, KEM employs Machine Learning techniques for data analysis, including Decision Tree (DT), Naïve Bayes (NB), KNearest Neighbor (K-NN), Support Vector Machine (SVM), and Multi-Layer Perceptron (MLP) methods. KEM aims to optimize waste management in rural areas, mainly by enhancing knowledge extraction to schedule the emptying of smart waste bin points. Waste continues to increase daily, per the population growth rate [1]–[4] . Waste is a problem in many countries. Therefore, a solution is required for collecting, sorting, and disposing waste [2] . Waste is not only a problem in urban areas but also in rural areas [5], [6] . Even rural communities tend to have poor, dangerous waste disposal practices such as burning waste and littering [7] . Internet of Things (IoT) technology based on LoRa network media could be an alternative solution to optimize waste management [6] . IoT using LoRa network media in a waste monitoring system and system modeling using the Machine Learning method is highly recommended [8], [9] . IoT has become an enabling tech

FAQs

What is the Knowledge Extraction Model (KEM) used for in this study?

KEM extracts insights from IoT-based smart waste bin data to classify scheduling decisions for emptying waste bins efficiently.

Which machine learning methods are compared for the knowledge extraction task?

Decision Tree, Naïve Bayes, K-Nearest Neighbor, Support Vector Machine, and Multi-Layer Perceptron are compared for recommending the best method in KEM.

How is model performance evaluated, and what were the key findings?

Performance is measured using accuracy, recall, precision, F-measure, and ROC curves with ten observations via cross-validation. Decision Tree performs best on accuracy, recall, precision, and ROC, while K-NN achieves the highest F-measure.

Aug 5, 2026

Upload by Eliana