scholarly journals Empirical Comparison of Approaches for Mitigating Effects of Class Imbalances in Water Quality Anomaly Detection

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 218015-218036
Author(s):  
Eustace M. Dogo ◽  
Nnamdi I. Nwulu ◽  
Bhekisipho Twala ◽  
Clinton Ohis Aigbavboa
Keyword(s):  
Water Quality ◽  
Anomaly Detection ◽  
Empirical Comparison

A novel dynamic multi-criteria ensemble selection mechanism applied to drinking water quality anomaly detection

2020 ◽  
Vol 749 ◽  
pp. 142368
Author(s):  
Victor Henrique Alves Ribeiro ◽  
Steffen Moritz ◽  
Frederik Rehbach ◽  
Gilberto Reynoso-Meza
Keyword(s):  
Water Quality ◽  
Drinking Water ◽  
Anomaly Detection ◽  
Drinking Water Quality ◽  
Selection Mechanism ◽  
Ensemble Selection

scholarly journals Improving Water Quality Assessment through Anomaly Detection Using Hybrid Convolutional Neural Network Approach

2021 ◽  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Water Quality ◽  
Deep Learning ◽  
Anomaly Detection ◽  
Convolutional Neural Network ◽  
Quality Assessment ◽  
Water Quality Assessment ◽  
Machine Learning Algorithms ◽  
Quality Analysis

<p>Water being a precious commodity for every person around the world needs to be quality monitored continuously for ensuring safety whilst usage. The water data collected from sensors in water plants are used for water quality assessment. The anomaly present in the water data seriously affects the performance of water quality assessment. Hence it needs to be addressed. In this regard, water data collected from sensors have been subjected to various anomaly detection approaches guided by Machine Learning (ML) and Deep Learning framework. Standard machine learning algorithms have been used extensively in water quality analysis and these algorithms in general converge quickly. Considering the fact that manual feature selection has to be done for ML algorithms, Deep Learning (DL) algorithm is proposed which involve implicit feature learning. A hybrid model is formulated that takes advantage of both and presented it is data invariant too. This novel Hybrid Convolutional Neural Network (CNN) and Extreme Learning Machine (ELM) approach is used to detect presence of anomalies in sensor collected water data. The experiment of the proposed CNN-ELM model is carried out using the publicly available dataset GECCO 2019. The findings proved that the model has improved the water quality assessment of the sensor water data collected by detecting the anomalies efficiently and achieves F1 score of 0.92. This model can be implemented in water quality assessment.</p>

scholarly journals Accessing Imbalance Learning Using Dynamic Selection Approach in Water Quality Anomaly Detection

Symmetry ◽  
2021 ◽  
Vol 13 (5) ◽  
pp. 818
Author(s):  
Eustace M. Dogo ◽  
Nnamdi I. Nwulu ◽  
Bhekisipho Twala ◽  
Clinton Aigbavboa
Keyword(s):  
Water Quality ◽  
Anomaly Detection ◽  
Distribution Systems ◽  
Ensemble Classification ◽  
Imbalanced Datasets ◽  
Dynamic Selection ◽  
Ensemble Models ◽  
Classifier Selection ◽  
Local Accuracy ◽  
Homogeneous Ensemble

Automatic anomaly detection monitoring plays a vital role in water utilities’ distribution systems to reduce the risk posed by unclean water to consumers. One of the major problems with anomaly detection is imbalanced datasets. Dynamic selection techniques combined with ensemble models have proven to be effective for imbalanced datasets classification tasks. In this paper, water quality anomaly detection is formulated as a classification problem in the presences of class imbalance. To tackle this problem, considering the asymmetry dataset distribution between the majority and minority classes, the performance of sixteen previously proposed single and static ensemble classification methods embedded with resampling strategies are first optimised and compared. After that, six dynamic selection techniques, namely, Modified Class Rank (Rank), Local Class Accuracy (LCA), Overall-Local Accuracy (OLA), K-Nearest Oracles Eliminate (KNORA-E), K-Nearest Oracles Union (KNORA-U) and Meta-Learning for Dynamic Ensemble Selection (META-DES) in combination with homogeneous and heterogeneous ensemble models and three SMOTE-based resampling algorithms (SMOTE, SMOTE+ENN and SMOTE+Tomek Links), and one missing data method (missForest) are proposed and evaluated. A binary real-world drinking-water quality anomaly detection dataset is utilised to evaluate the models. The experimental results obtained reveal all the models benefitting from the combined optimisation of both the classifiers and resampling methods. Considering the three performance measures (balanced accuracy, F-score and G-mean), the result also shows that the dynamic classifier selection (DCS) techniques, in particular, the missForest+SMOTE+RANK and missForest+SMOTE+OLA models based on homogeneous ensemble-bagging with decision tree as the base classifier, exhibited better performances in terms of balanced accuracy and G-mean, while the Bg+mF+SMENN+LCA model based on homogeneous ensemble-bagging with random forest has a better overall F1-measure in comparison to the other models.

scholarly journals A framework for automated anomaly detection in high frequency water-quality data from in situ sensors

2019 ◽  
Vol 664 ◽  
pp. 885-898 ◽  
Author(s):  
Catherine Leigh ◽  
Omar Alsibai ◽  
Rob J. Hyndman ◽  
Sevvandi Kandanaarachchi ◽  
Olivia C. King ◽  
...  
Keyword(s):  
Water Quality ◽  
Anomaly Detection ◽  
High Frequency ◽  
Quality Data ◽  
Water Quality Data ◽  
In Situ Sensors
Sign in / Sign up

Export Citation Format

Share Document