Eva Ramos-Martínez

Application of graph-spectral methods in the vulnerability assessment of water supply networks

We introduce a methodology based on spectral measurements of graph theory to establish the relative importance of areas in water supply networks (WSNs). To achieve an efficient vulnerability analysis, we have made a prospective study to establish the importance of areas based on two popular ranking algorithms — PageRank and HITS. These areas are analysed using a flexible method of semi-supervised clustering. This approach enables better control because it works top–down from the whole network to the detail of a particular area; and provides valuable additional support for assessing vulnerability in WSNs.

Ensemble of naïve Bayesian approaches for the study of biofilm development in drinking water distribution systems

Various studies have been performed in relation to the influence that a number of characteristics of drinking water distribution systems (DWDSs) have on biofilm development. Nevertheless, their joint influence, apart from a few exceptions, has scarcely been studied due to the complexity of the community and the environment. In this paper, we apply various machine learning algorithms based on naïve Bayesian networks. Alternatives for the base naïve Bayesian model to outperform individual performances while maintaining simplicity are suggested. These alternatives include augmentation of the arcs in the graph, and initial bagging approaches. Finally, a combination of different naïve approaches in a bagging process that produces explanatory hybrid decision trees is proposed. As a result, it is possible to achieve a deeper understanding of the consequences that the interaction of the relevant hydraulic and physical factors of DWDSs has on biofilm development.

Graph constrained label propagation on water supply networks

In many real-world applications we have at our disposal a limited number of inputs in a theoretical database with full information, and another part of experimental data with incomplete knowledge for some of their features. These are cases that can be addressed by a label propagation process. It is a widely studied approach that may acquire complexity if new constraints in the new unlabeled data that should be taken into account are found. A kernel embedding process together with a simple label propagation algorithm will be the main tools to propagate labels by the use of all types of available information. An experimental study of biofilm development in drinking water pipes propagated through pipes belonging to a complete water supply network is approached. As a result, the proposal is a suitable and efficient way to deal with practical data, based on previous theoretical studies by the constrained label propagation process introduced.

Metadata on biofilm development in drinking water distribution systems

Biofilm is formed by complex communities of microorganisms that grow within a drinking water distribution system (DWDS) and can lead to various undesirable problems. Nowadays, biofilm represents a paradigm in the management of all DWDSs. In this context, we focus on how the physical and hydraulics characteristics of DWDSs affect the development of these communities of microorganisms, looking for the problematic points associated with biofilm development within a DWDS. Various studies have been performed in relation to the influence that a number of characteristics of DWDSs have on biofilm development. Nevertheless, their joint influence, apart from few exceptions, has been scarcely studied, due to the complexity of the community and the environment under study. To achieve this goal we have compiled biofilm data from different sources and pre-processed it, applying some machine learning methods, to get a complete and extensive enough database to perform inference by posterior analysis. In this case, an agent-based label negotiation technique is applied to the obtained database to identify important pre-relationships between the physical and the hydraulic characteristics of the pipes, their specific location, and biofilm development in a given DWDS.