Real-time Learning-based Monitoring System for Water Contamination

It is vital for a city to monitor water quality in real time since the quality of water has profound effect on residents’ health. Unfortunately, it is impossible for human to monitor water’s chemical composition frequently, which is an impossibly demanding task, let alone in real time. Thus, taking advantage of a highly efficient system can be an excellent solution. In this paper, we created a system called Real-time Intelligent Monitoring System for Water Quality, which enables a city to be responsive to potential outbreak of contamination and to protect city residents. The system is capable of processing and classifying the data extracted from visual images to considerably save more money and labor. In this case, two features Fast Fourier Transform (FFT) and Color Layout Descriptor (CLD) are introduced for Saliency features and color features respectively. FFT performs well in extracting saliency features and is not computationally intensive; CLD is able to represent the color features with high effectiveness and efficiency. Additionally, this system utilizes Support Vector Machine (SVM) based on such features that needs small size of training sets, trains very fast and can classify floating rubbish and any other scenarios of water pollution with satisfying efficiency. Till now, the accuracy has reached 75%, which encourages us. While the detection performance can be further improved, the efficient features & classifiers would serve as powerful methods to automatically monitor water pollution.