Search

Abstract: Knowledge graphs become a de facto standard for representing data in situations where relations between individual pieces of information are important. These semantically rich data structures provide opportunities to develop methods and algorithms for new ways of analyzing and utilizing data. In this work, we illustrate benefits of representing data as knowledge graphs. We develop a number of algorithms that augment data via processing graph-based information. We show how these enriched structures can be utilized for further processing, and discovering of `unseen' relations. In particular, we focus on two very different In particular, we focus on two very different domains of interest: power systems, and aspect-based sentiment analysis. For a power system application, we construct a knowledge graph that combines topological data with information about technical details of electrical components, as well as past events that occurred in the system. We utilize the graph for extracting details needed for the analysis of different events. We develop methods that enable us to analyze an impact of events on different parts of the system. For a case of aspect-based sentiment analysis, we are interested in emotional-based representation of reviews. Firstly, we identify words and simple phrases that describe different aspects of the reviewed items. Secondly, we create a knowledge graph that combines the reviews with the description words and phrases, as well as with the Hourglass model of emotions. The graph allows us to identify emotions linked with the reviewed aspects. Further, we aggregate these emotions across all words and phrases that describe individual aspects to obtain an `emotional summary' of the reviews.

Electricity consumption is on the rise as the global population is increasing. The need of energy has been discussed in length over the years. Oil and gas have been the primary resource for generators fuel. As oil and gas are a finite resource, an alternative resource that does not harm the environment is needed to generate energy. The Middle East and North Africa have a huge potential for using solar and wind energy to generate electricity as MENA region has one of the highest levels on solar irradiation. A new system of transferring the power through the MENA region is proposed. HVDC can be utilized to transfer energy over large distance with minimal losses where it is used for an interconnection grid between the MENA countries. Moreover, factors affecting future project, in the MENA region, such as the political atmosphere of the MENA countries, and how it affects the decision of constructing a project are analyzed. Secondly, the infrastructure and readiness of the MENA countries toward building Renewable energy and HVDC substation. Thirdly, risks and constrains of implementing these projects. Fourthly, the financial cost of the RE and HVDC projects. Fifthly, how social media and news orient the people thinking and decision making. Sixthly, existing rules and regulations in the energy sector are investigated. Finally, recommendations were given to each factor to ensure the smooth transition to produce green energy by utilizing renewable energy.