Real-Time Oil Authentication Leveraging K-Nearest Neighbors and Random Forest Techniques

View at publisher Summarise with VIRAT
Authors: K. Vignesh, Balakrishnan Baranitharan, K. Ram Charan, U. Sravanthi, D.Sammerah D. Sammerah, L. V. Nishanth
Cited by: 0
References: 9

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Oil adulteration is a significant challenge for food safety and industrial quality standards. This paper presents a machine learning framework that uses sensors to detect oil purity without chemical testing. The system employs capacitive, optical, thermal, and density sensors to gather important physical information from oil samples. An ESP8266 microcontroller processes these readings. It analyzes the data using K-Nearest Neighbors (KNN) and Random Forest algorithms to classify oils as pure or adulterated. A web interface built in Flask offers real-time predictions and visualizations. This method achieves high accuracy while remaining low-cost and portable, making it a good choice for smart food quality monitoring applications.

Fields of Study & Subjects

Spectroscopy and Chemometric Analyses Arduino and IoT Applications Smart Agriculture and AI

Publication details

Journal / source
IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS)
Pages
1–5
Publication date
31 January 2026
Language
EN