Please use this identifier to cite or link to this item:
Full metadata record
|dc.description.abstract||In order to survive, the creatures need water, food, air, and residency. However, there are many water crises that influence water quality or cause water shortages. Rivers, which are important freshwater sources for human consumption, are often waste caused by their activities. This research utilizes data mining techniques to create classification models for water quality issues. The results are used in the application to alert the public about water quality problems that are aimed at changing their behavior. The data set consists of nine input features to identify dissolved oxygen in the next quarter, divided into two levels: 'good' and 'bad'. The process of data preparation using various methods applies to the raw data before creating the classification model. This research proposes neural networks with a multilayer perceptron and k-nearest neighbor as a classifier called MLP-kNN. The results show that the proposed model is more effective when compared to various MLP algorithms. The classification rate is more than 0.95 while the F-score of both two classes is more than 0.9. Finally, the proposed model is implemented on the web application to report and prepare for water utilization planning. Contribution-Application of data mining classifies a water quality on the Wang River, Thailand.||en_US|
|dc.subject||Physics and Astronomy||en_US|
|dc.title||Water Quality Classification Using Data Mining Techniques: A Case Study on Wang River in Thailand||en_US|
|article.title.sourcetitle||2020 Joint 9th International Conference on Informatics, Electronics and Vision and 2020 4th International Conference on Imaging, Vision and Pattern Recognition, ICIEV and icIVPR 2020||en_US|
|article.stream.affiliations||Chiang Mai University||en_US|
|Appears in Collections:||CMUL: Journal Articles|
Files in This Item:
There are no files associated with this item.
Items in CMUIR are protected by copyright, with all rights reserved, unless otherwise indicated.