Search Results (4)

Machine learning (ML) has been used in different ways in the fight against COVID-19 disease. ML models have been developed, e.g., for diagnostic or prognostic purposes and using various modalities of data (e.g., textual, visual, or structured). Due to the many specific aspects of this disease and its evolution over time, there is still not enough understanding of all relevant factors influencing the course of COVID-19 in particular patients. In all aspects of our work, there was a strong involvement of a medical expert following the human-in-the-loop principle. This is a very important but usually neglected part of the ML and knowledge extraction (KE) process. Our research shows that explainable artificial intelligence (XAI) may significantly support this part of ML and KE. Our research focused on using ML for knowledge extraction in two specific scenarios. In the first scenario, we aimed to discover whether adding information about the predominant COVID-19 variant impacts the performance of the ML models. In the second scenario, we focused on prognostic classification models concerning the need for an intensive care unit for a given patient in connection with different explainability AI (XAI) methods. We have used nine ML algorithms, namely XGBoost, CatBoost, LightGBM, logistic regression, Naive Bayes, random forest, SGD, SVM-linear, and SVM-RBF. We measured the performance of the resulting models using precision, accuracy, and AUC metrics. Subsequently, we focused on knowledge extraction from the best-performing models using two different approaches as follows: (a) features extracted automatically by forward stepwise selection (FSS); (b) attributes and their interactions discovered by model explainability methods. Both were compared with the attributes selected by the medical experts in advance based on the domain expertise. Our experiments showed that adding information about the COVID-19 variant did not influence the performance of the resulting ML models. It also turned out that medical experts were much more precise in the identification of significant attributes than FSS. Explainability methods identified almost the same attributes as a medical expert and interesting interactions among them, which the expert discussed from a medical point of view. The results of our research and their consequences are discussed. Full article

The process industries rely on various software systems and use a wide range of technologies. Predictive modeling techniques are often applied to data obtained from these systems to build the predictive functions used to optimize the production processes. Therefore, there is a need to provide a proper representation of knowledge and data and to improve the communication between the data scientists who develop the predictive functions and domain experts who possess the expert knowledge of the domain. This can be achieved by developing a semantic model that focuses on cross-sectorial aspects rather than concepts for specific industries, and that specifies the meta-classes for the formal description of these specific concepts. This model should cover the most important areas including modeling the production processes, data analysis methods, and evaluation using the performance indicators. In this paper, our primary objective was to introduce the specifications of the Cross-sectorial domain model and to present a set of tools that support data analysts and domain experts in the creation of process models and predictive functions. The model and the tools were used to design a knowledge base that could support the development of predictive functions in the green anode production in the aluminum production domain. Full article

This paper describes the architecture of a cross-sectorial Big Data platform for the process industry domain. The main objective was to design a scalable analytical platform that will support the collection, storage and processing of data from multiple industry domains. Such a platform should be able to connect to the existing environment in the plant and use the data gathered to build predictive functions to optimize the production processes. The analytical platform will contain a development environment with which to build these functions, and a simulation environment to evaluate the models. The platform will be shared among multiple sites from different industry sectors. Cross-sectorial sharing will enable the transfer of knowledge across different domains. During the development, we adopted a user-centered approach to gather requirements from different stakeholders which were used to design architectural models from different viewpoints, from contextual to deployment. The deployed architecture was tested in two process industry domains, one from the aluminium production and the other from the plastic molding industry. Full article

The paper describes an approach to semantic interoperability of eGovernment services applied within the 027020 FP6 IST Access-eGov project. The goal of the project was to improve accessibility and connectivity of governmental services for citizens and businesses by means of creating integrated scenarios and providing guidance to users while following this scenario. The scenario helps the user to identify and fulfil any needed electronic or real governmental services in a selected life situation. The Access-eGov project has developed software tools enabling service integration using semantic technologies. In addition to that, a methodology providing guidance to the user-driven process of creating ontologies was developed. Sample ontologies were prepared for trial applications. The developed tools support browsing, discovery, and execution of government services according to a selected life event or goal. The project successfully developed and tested the proposed solutions. The software developed within the project is available as open source software. Full article