Applying TOPSIS algorithm for odour classification model

Mozamir, Muhammad Shahkhir and Abdullah, Asniyani Nur Haidar and Abdullah, M Fuad and Jamaluddin, M Faizan (2024) Applying TOPSIS algorithm for odour classification model. In: 2024 International Conference on TVET Excellence & Development (ICTeD), 16 December 2024 through 17 December 2024, Melaka, Malaysia.

Text Applying TOPSIS Algorithm for Odour Classification Model.pdf Restricted to Registered users only Download (584kB)

Abstract

Odour classification is a complex task with significant implications across various industries in Industrial Evolution 4.0 (IR4.0), including food and beverage, environmental monitoring, and perfumery. Traditional methods often struggle with subjectivity and the multidimensional nature of odour data. This paper introduces an approach by applying the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) algorithm for odour classification. TOPSIS, a widely-used as multi-criteria decision-making (MCDM) method, ranks alternatives based on their proximity to an ideal solution, effectively handling both qualitative and quantitative data. In this study, we outline the integration of TOPSIS for odour classification that can be applied in application for future. Simulation datasets comprising sensory evaluations were utilised to validate the approach. The idea is the highest ranking, the closeness of testing data to the model trained. The results demonstrate that the TOPSIS-based classification method proved can be applied for odour classification. By systematically evaluating multiple criteria influencing odour perception, our approach offers a robust, reliable, and efficient solution for odour classification challenges.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	TOPSIS algorithm, Odour classification, Classification model, Multi-Criteria Decision Making (MCDM), Sensor technology
Divisions:	Faculty of Information and Communication Technology
Depositing User:	NUR FARISAH JAFRIN
Date Deposited:	08 Jul 2026 04:50
Last Modified:	08 Jul 2026 04:50
URI:	http://eprints.utem.edu.my/id/eprint/29773
Statistic Details:	View Download Statistic

Actions (login required)

View Item