Design and Implementation of Water Quality Management Middleware based on Big Data and Neural Networks

• Published in: Journal of Digital Contents Society Vol. 22; no. 4; pp. 705 - 710
• Main Authors: Park, Sung-Hoon, Yoo, Su-Chung, Pang, Seung-Peom
• Format: Journal Article
• Language: English
• Published: 한국디지털콘텐츠학회 30.04.2021
• Subjects: 컴퓨터학; Neural Network; 뉴럴 네트워크; Water Quality Management System; Sensor Network; Big Data; 미들웨어; 수질관리 시스템; Middleware; 센서네트워크; 빅데이터
• ISSN: 1598-2009; 2287-738X
• DOI: 10.9728/dcs.2021.22.4.705

As there is a growing concern that the scale of damage caused by water pollution accidents due to urbanization and industrialization is increasing, the demand for water safety in society is increasing. In the last five years, many water pollution accidents have occurred in the four major river basins, and this has caused direct and indirect damage to public health, such as stopping water supply and drinking contaminated tap water. Therefore, there has been a constant demand for a water quality environment management system that can minimize the uncertainty of the water quality environment. In the Ubiquitous Sensor Network environment, the water quality management system transmits data measured in real time from the terminal node to the server, and the middleware of the received system has secured and stored data integrity and redundancy. However, the biggest problem in this processing is that the generated source data contains many errors and cannot be used as it is. Therefore, the assistance of experts is required to ensure the integrity of the water quality data, and there is a difficulty in paying money economically. As a solution to this problem, building a multilayer neural network using a machine learning model is the best solution. In this study, we design a real-time water quality data verification middleware based on multi-layer neural networks and propose to develop it as a monitoring system. KCI Citation Count: 0