KNN Algorithm Implementation in Real-World Problem of Water Quality Classification

Veljanovska, Kostandina and Trajkovska, Aneta and Veljanovski, Nikolce (2024) KNN Algorithm Implementation in Real-World Problem of Water Quality Classification. In: 14th International conference on Applied Internet and Information Technologies (AIIT2024), November 8th 2024, Zrenjanin, Serbia.

Text aiit2024_paper_KostandinaVeljanovska.pdf - Published Version Download (1MB)

Abstract

Technological evolution is increasingly focused on developing intelligent machine learning solutions that improve the efficiency, functionality and adaptability of everyday systems and processes. Effective utilization of algorithms fundamentally enables systems to learn, adapt to environmental conditions and make decisions based on the knowledge, characteristics that define intelligent agents. This capability includes classifying various processes and refining data through user-defined characteristics to produce accurate results. This paper focuses on determining water quality. Water bodies are essential part of our environment and our aim is to contribute to maintain healthy environment for humans, animals and plants. To maintain water quality on high level is very important in order to protect human and all live creatures’ health, to avoid the costs related to medical care, costs of productivity loss, and even loss of life. We have implemented the K-Nearest Neighbors (KNN) algorithm to learn from the dataset and develop a classification process based on various parameters. The algorithm quantifies water quality levels based on the concentration of constituent substances. The KNN algorithm is utilized to train the model with the provided data and its performance is evaluated using predefined coefficient values. Results from the implementation of the model yields an accuracy percentage, demonstrating its effectiveness in determining water quality.

Item Type:	Conference or Workshop Item (Paper)
Subjects:	Scientific Fields (Frascati) > Natural sciences > Computer and information sciences
Divisions:	Faculty of Information and Communication Technologies
Depositing User:	Prof. d-r. Kostandina Veljanovska
Date Deposited:	11 Dec 2024 22:07
Last Modified:	11 Dec 2024 22:07
URI:	https://eprints.uklo.edu.mk/id/eprint/10534

Actions (login required)

View Item