Operational Modes Detection in Industrial Gas Turbines Using an Ensemble of Clustering Methods.

Operational modes of a process are described by a number of relevant features that are indicative of the state of the process. Hundreds of sensors continuously collect data in industrial systems, which shows how the relationship between different variables changes over time and identifies different modes of operation. Gas turbines' operational modes are usually defined regarding their expected energy production, and most research works either are focused a priori on obtaining these modes solely based on one variable, the active load, or assume a fixed number of states and build up predictive models to classify new situations as belonging to the predefined operational modes. However, in this work, we take into account all available parameters based on sensors' data because other factors can influence the system status, leading to the identification of a priori unknown operational modes. Furthermore, for gas turbine management, a key issue is to detect these modes using a real-time monitoring system. Our approach is based on using unsupervised machine learning techniques, specifically an ensemble of clusters to discover consistent clusters, which group data into similar groups, and to generate in an automatic way their description. This description, upon interpretation by experts, becomes identified and characterized as operational modes of an industrial process without any kind of a priori bias of what should be the operational modes obtained. Our proposed methodology can discover and identify unknown operational modes through data-driven models. The methodology was tested in our case study with Siemens gas turbine data. From available sensors' data, clusters descriptions were obtained in an automatic way from aggregated clusters. They improved the quality of partitions tuning one consistency parameter and excluding outlier clusters by defining filtering thresholds. Finally, operational modes and/or sub-operational modes were identified with the interpretation of the clusters description by process experts, who evaluated the results very positively.

Dimensionality reduction and ensemble of LSTMs for antimicrobial resistance prediction.

Bacterial resistance to antibiotics has been rapidly increasing, resulting in low antibiotic effectiveness even treating common infections. The presence of resistant pathogens in environments such as a hospital Intensive Care Unit (ICU) exacerbates the critical admission-acquired infections. This work focuses on the prediction of antibiotic resistance in Pseudomonas aeruginosa nosocomial infections at the ICU, using Long Short-Term Memory (LSTM) artificial neural networks as the predictive method. The analyzed data were extracted from the Electronic Health Records (EHR) of patients admitted to the University Hospital of Fuenlabrada from 2004 to 2019 and were modeled as Multivariate Time Series. A data-driven dimensionality reduction method is built by adapting three feature importance techniques from the literature to the considered data and proposing an algorithm for selecting the most appropriate number of features. This is done using LSTM sequential capabilities so that the temporal aspect of features is taken into account. Furthermore, an ensemble of LSTMs is used to reduce the variance in performance. Our results indicate that the patient's admission information, the antibiotics administered during the ICU stay, and the previous antimicrobial resistance are the most important risk factors. Compared to other conventional dimensionality reduction schemes, our approach is able to improve performance while reducing the number of features for most of the experiments. In essence, the proposed framework achieve, in a computationally cost-efficient manner, promising results for supporting decisions in this clinical task, characterized by high dimensionality, data scarcity, and concept drift.

Decision support systems (DSS) for wastewater treatment plants - A review of the state of the art.

The use of decision support systems (DSS) allows integrating all the issues related with sustainable development in view of providing a useful support to solve multi-scenario problems. In this work an extensive review on the DSSs applied to wastewater treatment plants (WWTPs) is presented. The main aim of the work is to provide an updated compendium on DSSs in view of supporting researchers and engineers on the selection of the most suitable method to address their management/operation/design problems. Results showed that DSSs were mostly used as a comprehensive tool that is capable of integrating several data and a multi-criteria perspective in order to provide more reliable results. Only one energy-focused DSS was found in literature, while DSSs based on quality and operational issues are very often applied to site-specific conditions. Finally, it would be important to encourage the development of more user-friendly DSSs to increase general interest and usability.

Crossing the Death Valley to Transfer Environmental Decision Support Systems to the Water Market.

Environmental decision support systems (EDSSs) are attractive tools to cope with the complexity of environmental global challenges. Several thoughtful reviews have analyzed EDSSs to identify the key challenges and best practices for their development. One of the major criticisms is that a wide and generalized use of deployed EDSSs has not been observed. The paper briefly describes and compares four case studies of EDSSs applied to the water domain, where the key aspects involved in the initial conception and the use and transfer evolution that determine the final success or failure of these tools (i.e., market uptake) are identified. Those aspects that contribute to bridging the gap between the EDSS science and the EDSS market are highlighted in the manuscript. Experience suggests that the construction of a successful EDSS should focus significant efforts on crossing the death-valley toward a general use implementation by society (the market) rather than on development.

[Artificial intelligence in medicine: project of a mobile platform in an intelligent environment for the care of disabled and elderly people]. / Intelligenza artificiale in medicina: progetto di una piattaforma mobile inserita in un ambiente intelligente per l'assistenza ai disabili e agli anziani.

A project based on the integration of new technologies and artificial intelligence to develop a device--e-tool--for disabled patients and elderly people is presented. A mobile platform in intelligent environments (skilled-care facilities and home-care), controlled and managed by a multi-level architecture, is proposed to support patients and caregivers to increase self-dependency in activities of daily living.