Abstract
Markov Logic is an expressive and widely used knowledge representation formalism that combines logic and probabilities, providing a powerful framework for inference and learning tasks. Most Markov Logic implementations perform inference by transforming the logic representation into a set of weighted propositional formulae that encode a Markov network, the ground Markov network. Probabilistic inference is then performed over the grounded network. Constructing, simplifying, and evaluating the network are the main steps of the inference phase. As the size of a Markov network can grow rather quickly, Markov Logic Network (MLN) inference can become very expensive, motivating a rich vein of research on the optimization of MLN performance. We claim that parallelism can have a large role on this task. Namely, we demonstrate that widely available Graphics Processing Units (GPUs) can be used to improve the performance of a state-of-the-art MLN system, Tuffy, with minimal changes. Indeed, comparing the performance of our GPU-based system, TuGPU, to that of the Alchemy, Tuffy and RockIt systems on three widely used applications shows that TuGPU is up to 15x times faster than the other systems.

Abstract
In this paper it is presented a music application for people with intellectual disabilities, called "Professor Piano". We created this application to be a solution for music education for this group of people. For that we present the development and implementation of the app. We choose the virtual piano and the mobile devices as the basis for our solution. It was conducted an assessment of the current status and features of mobile applications also using this paradigm, from which we concluded that, currently, there is not a virtual piano application oriented to people with intellectual disabilities so we design, develop and tested a new application, the "Professor Piano". To validate the "Professor Piano" application approach, we evaluated the application usage by a group of people with intellectual disabilities, without having too much user experience with mobile technologies, with the aim to measure the effectiveness, efficiency and satisfaction. We registered the following variables: success in a conclusion of a level (effectiveness); the percentage of correct notes played versus all notes of that level (efficiency); and the motivation at the end of the experience (satisfaction). The results obtained shows the interest and motivation of the users in playing with the application. In the four tests, three persons completed and wanted to continue the testing experience. This results also shows the importance of using an intuitive design and also of displaying the score at the end of each level, giving an extra boost to the user to replay or advance to the next level.

Abstract
Many spreadsheets in the wild do not have documentation nor categorization associated with them. This makes difficult to apply spreadsheet research that targets specific spreadsheet domains such as financial or database. We introduce with this paper a methodology to automatically classify spreadsheets into different domains. We exploit existing data mining classification algorithms using spreadsheet-specific features. The algorithms were trained and validated with cross-validation using the EUSES corpus, with an up to 89% accuracy. The best algorithm was applied to the larger Enron corpus in order to get some insight from it and to demonstrate the usefulness of this work.

Abstract

Abstract
This paper presents a methodology based on genetic Algorithms (GA) to solve the problem of optimal participation in multiple electricity markets. With the emergence of new requirements for electrical power markets, it has become fundamental to develop tools to aid in decision making, understanding the functioning of markets and forecast iterations that occur between the different entities in the market. Artificial intelligence plays a crucial role in the development of these tools. Using artificial intelligence techniques, it is possible to simulate the different existing players in the market, to enable these players to be adaptive to any situation, and to model any type of trading. Artificial intelligence based metaheuristic optimization tools allow solving problems in a short time, and with very close results to those that deterministic techniques are able to achieve, at the cost of a high execution time. The achieved results, using a simulation scenario based on real data from the Iberian electricity market, show that the proposed method is able to reach better results than previous implementations of a Particle Swarm Optimization (PSO) and a Simulated Annealing (SA) methods, while achieving very similar objective function results to those of a deterministic approach, in a much faster execution time.

Abstract
This Spring Issue will discuss about big data and multiple aspects of its usability and applicability. Many of us have seen blockbuster movies Back to the future (premiere in 1985), The Terminator (1984) or Minority report (2002). The unifying element of the above mentioned movies is that manuscripts are introducing a superior competitive advantage factor. The protagonists create an advantage by having either real-time data (sometimes from the future) or all relevant (big and historical) data with enormous computing capacity over competitors. A bit after first two of those movies premiered, NASA scientists Cox and Ellsworth (1997) published an article where term ‘big data’ appeared first time (Press, 2014). Intelligence needs to be topped up in a way to create advantage. Data has been there for a long time, in all forms and sizes. It is applied in almost single every business sector and it is getting faster in sense of usability. The data storage capacity has been exponentially increasing over time, but the usability of this wealth of data remains a critical issue.(...)