A REstfull Approach for Classifying Pollutants in Water Using Neural Networks

E-nose systems are composed by different type of sensors with the capacity of detecting almost any compound or combination of compounds of an odor. In this regard, software approaches can provide learning capacities for classifying odor information. The aim of this paper is to propose a novel approach for on-line classification of pollutants in the water. To extract information about different types of pollutants, a hand-held, lightweight and battery powered instrument with wireless communications has been designed. An Artificial Neural Network (ANNs) is also proposed to classify different types of pollutants in the water, and two different types of ANNs (feedforward with backpropagation) Learning algorithm and Radial Basis Function based networks) have been developed. Furthermore, to support online classification services, a novel framework for developing high performance web applications is also proposed. Two different approaches have been integrated in this framework: the component-based approach is applied to increase the reusability and modularity degree, while RESTful web services provides the architectural style to connect with remote resources. According to this proposal, a web-based application has been developed to detect pollutants in the water.