Monitoring of drinking-water quality by means of a multi-objective ensemble learning approach
Abstract
This paper proposes the use of multi-objective ensemble learning to monitor drinking-water quality. Such problem consists of a data set with an extreme imbalance ratio where the events, the minority class, must be correctly detected given a time series denoting water quality and operative data on a minutely basis. First, the given data set is preprocessed for imputing missing data, adjusting concept drift and adding new statistical features, such as moving average, moving standard deviation, moving maximum and moving minimum. Next, two ensemble learning techniques are used, namely SMOTEBoost and RUSBoost. Such techniques have been developed specifically for dealing with imbalanced data, where the base learners are trained by adjusting the ratio between the classes. The first algorithm focuses on oversampling the minority class, while the second focuses on under-sampling the majority class. Finally, multi-objective optimisation is used for pruning the base models of such ensembles in order to maximise the prediction score without reducing generalisation performance. In the training phase, the model is trained, optimised and evaluated using hold-out validation on a given training data set. At the end, the trained model is inserted into a framework, which is used for online event detection and assessing the model's performance.
Read the paper
Related studies
- Green Chemistry: A Framework for a Sustainable Future
- Nano/micro-plastic, an invisible threat getting into the brain
- Emerging contaminants antibiotic resistance genes and microplastics in the environment: Introduction to 21 review articles published in CREST during 2018–2022
- Water Resources and Sustainable Development
- Nano- and microplastics in the workplace
- Water Enclosure and World-Literature: New Perspectives on Hydro-Power and World-Ecology
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.