Entity

Time filter

Source Type


Farmaki E.G.,National and Kapodistrian University of Athens | Farmaki E.G.,Supply SA | Thomaidis N.S.,National and Kapodistrian University of Athens | Efstathiou C.E.,National and Kapodistrian University of Athens
International Journal of Environmental Analytical Chemistry | Year: 2010

Artificial Neural Networks (ANNs) have seen an explosion of interest over the last two decades and have been successfully applied in all fields of chemistry and particularly in analytical chemistry. Inspired from biological systems and originated from the perceptron, i.e. a program unit that learns concepts, ANNs are capable of gradual learning over time and modelling extremely complex functions. In addition to the traditional multivariate chemometric techniques, ANNs are often applied for prediction, clustering, classification, modelling of a property, process control, procedural optimisation and/or regression of the obtained data. This paper aims at presenting the most common network architectures such as Multi-layer Perceptrons (MLPs), Radial Basis Function (RBF) and Kohonen's self-organisations maps (SOM). Moreover, back-propagation (BP), the most widespread algorithm used today and its modifications, such as quick-propagation (QP) and Delta-bar-Delta, are also discussed. All architectures correlate input variables to output variables through non-linear, weighted, parameterised functions, called neurons. In addition, various training algorithms have been developed in order to minimise the prediction error made by the network. The applications of ANNs in water analysis and water quality assessment are also reviewed. Most of the ANNs works are focused on modelling and parameters prediction. In the case of water quality assessment, extended predictive models are constructed and optimised, while variables correlation and significance is usually estimated in the framework of the predictive or classifier models. On the contrary, ANNs models are not frequently used for clustering/classification purposes, although they seem to be an effective tool. ANNs proved to be a powerful, yet often complementary, tool for water quality assessment, prediction and classification. © 2010 Taylor & Francis. Source


Farmaki E.G.,National and Kapodistrian University of Athens | Farmaki E.G.,Supply SA | Thomaidis N.S.,National and Kapodistrian University of Athens | Simeonov V.,Sofia University | Efstathiou C.E.,National and Kapodistrian University of Athens
Environmental Monitoring and Assessment | Year: 2012

The aim of the present study is to compare the application of unsupervised and supervised pattern recognition techniques for the quality assessment and classification of the reservoirs used as the source for the domestic and industrial water supply of the city of Athens, Greece. A new optimization strategy for sampling, monitoring, and water management is proposed. During the period of October 2006 to April 2007, 89 samples were collected from the three water reservoirs (Iliki, Mornos, and Marathon), and 13 parameters (metals and metalloids) were analytically determined. Generally, all the elements were found to fluctuate at very low levels, especially for Mornos that comprises the main water reservoir of Athens. Iliki and Marathon showed relatively elevated values, compared toMornos, but below the legislative limits. Multivariate unsupervised statistical techniques, such as factor analysis/principal components analysis, and cluster analysis and supervised ones, like discriminant analysis and classification trees, were applied to the data set, and their classification abilities were compared. All the chemometric techniques successfully revealed the critical variables and described the similarities and dissimilarities among the sampling points, emphasizing the individual characteristics in every sample and revealing the sources of elements in the region. New data from posterior samplings (November and December 2007) were used for the validation of the supervised techniques. Finally, water management strategies were proposed concerning the sampling points and representative parameters. © Springer Science+Business Media B.V. 2012. Source


Fotiou T.,Advanced Materials and Processes | Triantis T.M.,Advanced Materials and Processes | Kaloudis T.,Supply SA | Pastrana-Martinez L.M.,University of Porto | And 4 more authors.
Industrial and Engineering Chemistry Research | Year: 2013

Microcystin-LR (MC-LR) is the most common and toxic variant of the group of microcystins (MCs) produced during the formation of harmful cyanobacterial blooms. Geosmin (GSM) and 2-methylisoborneol (MIB) may also be produced during cyanobacterial blooms and can taint water causing undesirable taste and odor. The photocatalytic degradation of MC-LR, GSM, and MIB in water under both UV-A and solar light in the presence of reduced graphene oxide-TiO2 composite (GO-TiO2) was studied. Two commercially available TiO 2 materials (Degussa P25 and Kronos) and a reference TiO2 material prepared in the laboratory (ref-TiO2) were used for comparison. Under UV-A irradiation, Degussa P25 was the most efficient photocatalyst for the degradation of all target analytes followed by GO-TiO 2, ref-TiO2, and Kronos. Under solar light irradiation GO-TiO2 presented similar photocatalytic activity to Degussa P25, followed by Kronos and ref-TiO2 which were less efficient. Intermediate products formed during the photocatalytic process with GO-TiO 2 under solar light were identified and were found to be almost identical to those observed by Degussa P25/UV-A. Assessment of the residual toxicity of MC-LR during the course of treatment with GO-TiO2 showed that toxicity is proportional only to the remaining MC-LR concentration. The photocatalytic performance of GO-TiO2 was also evaluated under solar light illumination in real surface water samples, and GO-TiO2 proved to be effective in the degradation of all target compounds. © 2013 American Chemical Society. Source


Farmaki E.G.,National and Kapodistrian University of Athens | Farmaki E.G.,Supply SA | Thomaidis N.S.,National and Kapodistrian University of Athens | Simeonov V.,Sofia University | Efstathiou C.E.,National and Kapodistrian University of Athens
Journal of Water Supply: Research and Technology - AQUA | Year: 2013

Neural networks are powerful tools that could explore the basic structure of environmental data. In this work, the most common artificial neural network (ANN) architectures, multi-layer perceptrons (MLPs), radial basis function (RBF) and Kohonen's self-organizing maps (SOM), are applied in order to assess the quality of the water reservoirs used for the domestic and industrial water supply of the city of Athens, Greece. In parallel, ANN models are optimized and their recognition and predictive accuracy is tested. The data set consisted of 89 samples collected from the three Athenian water reservoirs during a period of 6 months (October 2006 to April 2007). Thirteen metals and metalloids, Fe, B, Al, V, Cr, Mn, Ni, Cu, Zn, As, Cd, Ba, Pb, were determined. For the validation of the optimized ANN models, new data from subsequent sampling campaigns (December 2007) were used. The constructed classification models predicted successfully the origin of the new posterior samples and simultaneously revealed the differences in sample compositions that occurred in that period. Critical comparison of the different architectures in site classification and modeling verified the validity and usefulness of ANNs, as a powerful and effective tool for water quality assessment. © IWA Publishing 2013. Source


Fotiou T.,Advanced Materials and Processes | Triantis T.M.,Advanced Materials and Processes | Kaloudis T.,Supply SA | Papaconstantinou E.,Advanced Materials and Processes | Hiskia A.,Advanced Materials and Processes
Journal of Photochemistry and Photobiology A: Chemistry | Year: 2014

Geosmin (GSM) and 2-methylisoborneol (MIB) are produced by several species of cyanobacteria and actinomycetes. These compounds can taint water and fish causing undesirable taste and odours. Studies have shown that GSM/MIB are resistant in standard water treatments. Polyoxometalates (POM) are efficient photocatalysts in the degradation and mineralization of a great variety of organic pollutants, presenting similar behaviour with the widely published titanium dioxide (TiO2). Photocatalytic degradation of GSM and MIB under UV-A light in the presence of a characteristic POM photocatalyst, SiW 12O40 4-, in aqueous solution has been studied and compared with the photodegradation by TiO2 suspensions. GSM and MIB are effectively degraded in the presence of both photocatalysts. Addition of OH radical scavengers (KBr and tertiary butyl alcohol, TBA) retards the photodegradation rates of both compounds, suggesting that photodegradation mechanism takes place via OH radicals. Intermediates identified using GC-MS in the case of GSM and MIB, are mainly identical in the presence of both photocatalysts, also suggesting a common reaction mechanism. Possible photocatalytic degradation pathway for both GSM and MIB is proposed. © 2014 Elsevier B.V. Source

Discover hidden collaborations