Issue |
ITM Web Conf.
Volume 70, 2025
2024 2nd International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2024)
|
|
---|---|---|
Article Number | 04012 | |
Number of page(s) | 6 | |
Section | AI and Advanced Applications | |
DOI | https://doi.org/10.1051/itmconf/20257004012 | |
Published online | 23 January 2025 |
Evaluating the Performance of SVM, Isolation Forest, and DBSCAN for Anomaly Detection
WLSA Shanghai Academy, 200940 Shanghai, China
Corresponding author: linsonglin@ldy.edu.rs
With the advancement of computer technologies, various data models and algorithms have been integrated into industrial processes, significantly improving the efficiency of anomaly detection in datasets while reducing time and energy consumption. Identifying the most effective algorithm for anomaly detection is essential for enhancing nidustrial productivity. This study evaluates the suitability of three algorithms—Support Vector Machine (SVM), Isolation Forest, and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) by comparing their accuracy and time efficiency in detecting outliers in different types of datasets. The algorithms are tested across various datasets, and their performance is systematically compared. The results are then analysed in relation to the structure of each algorithm to identify their respective advantages and disadvantages. The study finds that each algorithm performs differently depending on the dataset type. Specifically, SVM demonstrates superior performance in detecting point anomalies, while DBSCAN is more effective when the dataset is pre-processed. Additionally. Isolation Forests are most efficient at identifying collective anomalies within the dataset.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.