An Embedded Machine Learning-Based Spoiled Leftover Food Detection Device for Multiclass Classification

Aug 2, 2026

Upload by Liam

Food waste’s negative environmental repercussions drive global concern about how contamination forms and how freshness can be assessed after cooking and storage. Limited prior work addresses the combination of machine learning and electronic noses for detecting spoilage in leftover cooked food. This study proposes a multi-class approach that evaluates freshness after five days using an electronic nose with four MQ gas sensors (MQ-2, MQ-136, MQ-137, MQ-138) and machine-learning classifiers, achieving average accuracy between 90% and 100%.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages40

Reading Time1 h 41 min

AccessFree to download

Introduction

Food loss vs. food waste and global impacts

Food waste issues in Malaysia

Consumer perception and storage practices

Proposed Detection Approach

Electronic nose with gas sensors

Machine learning classifiers and multi-class classification

Conclusion

Model performance and relevance to reducing food waste

JOURNAL OF INFORMATION AND COMMUNICATION TECHNOLOGY [https://e-journal.uum.edu.my/index.php/jict](https://e-journal.uum.edu.my/index.php/jict) How to cite this article: Wan Azman, W. N. F. S. , Ku Azir, K. N. F. , & Mohd Khairuddin, A. (2024) . An embedded machine learning-based spoiled leftover food detection device for multiclass classification. Journal of Information and Communication Technology, 23(2), 253-292. [https://doi.org/10.32890/jict2024.23.2.4](https://doi.org/10.32890/jict2024.23.2.4) An Embedded Machine Learning-Based Spoiled Leftover Food Detection Device for Multiclass Classification 1Wan Nur Fadhlina Syamimi Wan Azman, 2Ku Nurul Fazira Ku Azir & 3Adam Mohd Khairuddin 1,2&3Faculty of Electronic Engineering & Technology Universiti Malaysia Perlis, Malaysia. 1,2&3Centre of Excellence for Advanced Computing, Universiti Malaysia Perlis, Malaysia. * [1](1 syamimifadhlina@gmail.com)[ syamimifadhlina@gmail.com](1 syamimifadhlina@gmail.com) [2](2 fazira@unimap.edu.my)[ fazira@unimap.edu.my](2 fazira@unimap.edu.my) [3](3 adamkhairuddin@unimap.edu.my)[ adamkhairuddin@unimap.edu.my](3 adamkhairuddin@unimap.edu.my) *Corresponding author Received: 24/3/2024 Revised:14/4/2024 Accepted: 15/4/2024 Published: 30/4/2024 ABSTRACT Food waste’s negative environmental repercussions are causing it to become a global concern. Several studies have examined the factors influencing food waste behaviour and management. This work was motivated by the lack of previous research on machine learning and electronic noses to detect contamination from leftover cooked food. This work proposes using machine learning algorithms and electronic nose technology to recognise and forecast the contamination in leftover cooked food. After five days of storage, the freshness of cooked leftovers was evaluated using an electronic nose combined with machine learning algorithms. Most food samples used in this work were from Malaysian’s leftover lunch and dinner dishes. Four (4) gas sensors—MQ- 2, MQ-136, MQ-137, and MQ-138—are used in developing the electronic nose to identify the presence of gas in the food sample. The data from the gas sensors was analysed using machine learning methods, namely Random Forest, k-nearest Neighbors, Support Vector Machine, and Linear Discriminant Analysis. Based on the results, a multi-classification technique yielded a greater accuracy rate in classifying and identifying the level of contamination in the cooked food leftovers, with average accuracy ranging from 90 percent to 100 percent. In conclusion, the work demonstratesa novel method for using machine learning algorithms to classify, identify, and predict the contamination level of leftover cooked food, contributing to reducing food waste generated primarily by Malaysians. Keywords: Classification, electronic nose, food safety, food waste, machine learning. INTRODUCTION The socioeconomic costs, waste management, and climate change consequences of food loss and waste (FLW) make it a substantial issue (Chauhan et al. , 2021) . Food loss, which typically happens in the food value chain, is the term used to describe food that deteriorates or is lost before reaching customers. It frequently results from unintended farming techniques or technical shortcomings in infrastructure, packaging, marketing, storage, or other areas. Contrarily, food that is of good quality but is rejected before or beyond expiration and is not consumed is food waste. It usually happens at the retail and consuming phases of the food value chain, frequently due to carelessness or intentional disposal (Lipinski, 2013) . The issue of food waste has grown significantly on a global scale, particularly in developing nations like Malaysia. It has contributed substantially to climate change’s effects (Toniniet al. , 2018) . Some scholars have equated “food loss” with “food waste.” However, those who distinguish between the two define “food loss” as food wasted at the start

FAQs

What problem does the study address?

The study targets the growing issue of food waste by enabling earlier detection of contamination in leftover cooked food.

How does the proposed system detect spoilage?

It combines an electronic nose with four gas sensors (MQ-2, MQ-136, MQ-137, MQ-138) and machine learning algorithms to recognize contamination levels after storage.

Which machine learning methods are used and how accurate is the classification?

Random Forest, k-nearest Neighbors, Support Vector Machine, and Linear Discriminant Analysis are used, and the multi-class classification reaches average accuracy from about 90% to 100%.

Aug 2, 2026

Upload by Liam