Modelling of Binary Coyote Optimization Algorithm with Deep Learning based Ground Water Index Classification

Groundwater quality fundamentally defines the utility of water in a source related to the nature and attention of the impurities present in the instance. An interaction influence of the uninterrupted decline in water quantity and quality, around one billion people globally face a lack of satisfactor...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2023 Second International Conference on Augmented Intelligence and Sustainable Systems (ICAISS) S. 428 - 433
Hauptverfasser: R, Soundharyaa Shri Harini, Amudha, V., Lakshmi, S. Vidhya
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 23.08.2023
Schlagworte:
Artificial intelligence
Binary Coyote Optimization Algorithm1
Classification algorithms
Data normalization
Deep learning
Feature extraction
Gated recurrent unit
Impurities
Indexes
Logic gates
Water quality
Water quality index
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Groundwater quality fundamentally defines the utility of water in a source related to the nature and attention of the impurities present in the instance. An interaction influence of the uninterrupted decline in water quantity and quality, around one billion people globally face a lack of satisfactory and safer water supply. The most effective technique for categorizing water quality is utilizing the Water Quality Index (WQI). Water quality can frequently be evaluated dependent on WQIs. A tool can be widely exploited for assessing the efficiency of water quality management algorithms. The study offers the modelling of Binary Coyote Optimization Algorithm with Deep Learning based Ground Water Index Classification (BCOADL-GWIC) technique. The presented BCOADL-GWIC technique classifies the WQI into different levels. To achieve this, the BCOADL-GWIC technique follows an initial stage of data normalization. In addition, the BCOADL-GWIC technique comprises BCOA based feature selection technique to generate a collection of feature vectors. For WQI classification, the BCOADL-GWIC technique uses gated recurrent unit (GRU) model. Finally, the experimental outcome of the BCOADL-GWIC method is tested on WQI dataset, collected from Thiruvallur district, India. The comprehensive results highlighted the outperforming results of the BCOADL-GWIC technique.
DOI:10.1109/ICAISS58487.2023.10250576