Open Access

ARTICLE

Outlier Detection for Water Supply Data Based on Joint Auto-Encoder

by Shu Fang, Lei Huang, Yi Wan, Weize Sun, Jingxin Xu

1 Guangdong Laboratory of Artificial-Intelligence and Cyber-Economics (SZ), College of Electronics and Information Engineering, Shenzhen University, Shenzhen, 518061, China.
2 Water Resources Management Center of Ministry of Water Resources, Beijing, China.
3 Departmet of Housing and Public Works, Queensland, Australia.

* Corresponding Author: Weize Sun. Email: .

Computers, Materials & Continua 2020, 64(1), 541-555. https://doi.org/10.32604/cmc.2020.010066

Received 10 February 2020; Accepted 08 March 2020; Issue published 20 May 2020

Abstract

With the development of science and technology, the status of the water environment has received more and more attention. In this paper, we propose a deep learning model, named a Joint Auto-Encoder network, to solve the problem of outlier detection in water supply data. The Joint Auto-Encoder network first expands the size of training data and extracts the useful features from the input data, and then reconstructs the input data effectively into an output. The outliers are detected based on the network’s reconstruction errors, with a larger reconstruction error indicating a higher rate to be an outlier. For water supply data, there are mainly two types of outliers: outliers with large values and those with values closed to zero. We set two separate thresholds, τ₁ and τ₂, for the reconstruction errors to detect the two types of outliers respectively. The data samples with reconstruction errors exceeding the thresholds are voted to be outliers. The two thresholds can be calculated by the classification confusion matrix and the receiver operating characteristic (ROC) curve. We have also performed comparisons between the Joint Auto-Encoder and the vanilla Auto-Encoder in this paper on both the synthesis data set and the MNIST data set. As a result, our model has proved to outperform the vanilla Auto-Encoder and some other outlier detection approaches with the recall rate of 98.94 percent in water supply data.

---

Keywords

---

Citations