| Issue |
E3S Web Conf.
Volume 625, 2025
5th International Conference on Environment Resources and Energy Engineering (ICEREE 2025)
|
|
|---|---|---|
| Article Number | 02006 | |
| Number of page(s) | 5 | |
| Section | Environmental Pollution Control and Ecological Restoration | |
| DOI | https://doi.org/10.1051/e3sconf/202562502006 | |
| Published online | 17 April 2025 | |
Research on the prediction model of UV spectral water quality parameters based on INFO-LSSVM
School of Mechanical and Materials Engineering, North China University of Technology, Beijing China
* Corresponding author: 793280235@qq.com
In order to meet the requirements of precision and rapid detection of water quality parameters, UV- visible absorption spectroscopy was used for the measurement and INFO-LSSVM was proposed for predic- tive modelling. The common nitrate nitrogen (NO3-N) and nitrite nitrogen (NO2-N) in water quality testing as the solution to be measured, the UV-visible absorption spectral data filtering, spectral data integration, the establishment of INFO-LSSVM nonlinear prediction model; comparison of GA-LSSVM, PSO-LSSVM and LSSVM algorithm models, the results show that the INFO-LSSVM prediction model is effective, and pro- vides a good solution for water quality testing. LSSVM prediction model is effective and provides new re- search value for water quality detection.
© 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.