On-line classification of pollutants in water using wireless portable electronic noses. (June 2016)

• Record Type: Journal Article
• Authors: Herrero, José Luis; Lozano, Jesús; Santos, José Pedro; Suárez, José Ignacio
• Is Part Of: Chemosphere. Volume 152(2016)
• Page Start: 107
• Page End: 116
• Publication Date: 2016-06
• Subjects: Electronic nose -- Neural networks -- Web applications -- Components -- Web services; Pollution -- Periodicals; Pollution -- Physiological effect -- Periodicals; Environmental sciences -- Periodicals; Atmospheric chemistry -- Periodicals; 551.511
• DOI: 10.1016/j.chemosphere.2016.02.106
• Languages: English
• ISSNs: 0045-6535

Abstract

Abstract: A portable electronic nose with database connection for on-line classification of pollutants in water is presented in this paper. It is a hand-held, lightweight and powered instrument with wireless communications capable of standalone operation. A network of similar devices can be configured for distributed measurements. It uses four resistive microsensors and headspace as sampling method for extracting the volatile compounds from glass vials. The measurement and control program has been developed in LabVIEW using the database connection toolkit to send the sensors data to a server for training and classification with Artificial Neural Networks (ANNs). The use of a server instead of the microprocessor of the e-nose increases the capacity of memory and the computing power of the classifier and allows external users to perform data classification. To address this challenge, this paper also proposes a web-based framework (based on RESTFul web services, Asynchronous JavaScript and XML and JavaScript Object Notation) that allows remote users to train ANNs and request classification values regardless user's location and the type of device used. Results show that the proposed prototype can discriminate the samples measured (Blank water, acetone, toluene, ammonia, formaldehyde, hydrogen peroxide, ethanol, benzene, dichloromethane, acetic acid, xylene and dimethylacetamide) with a 94% classification success rate. Highlights: A portable electronic nose with wireless communication has been designed. 12 water samples with different pollutants have been detected and identified. A web-based application is proposed for classifying pollutants in water. The use of a server allows external users to perform data classification. The remote classification increases the capacity of memory and the computing power of the classifier.