The thesis is part of a bigger project, the HEPGAME (High Energy Physics Game). The main objective for HEPGAME is the utilization of AI solutions, particularly by using MCTS for simplification of... Show moreThe thesis is part of a bigger project, the HEPGAME (High Energy Physics Game). The main objective for HEPGAME is the utilization of AI solutions, particularly by using MCTS for simplification of HEP calculations. One of the issues is solving mathematical expressions of interest with millions of terms. These calculations can be solved with the FORM program, which is software for symbolic manipulation. Since these calculations are computationally intensive and take a large amount of time, the FORM program was parallelized to solve them in a reasonable amount of time.Therefore, any new algorithm based on MCTS, should also be parallelized. This requirement was behind the problem statement of the thesis: “How do we design a structured pattern-based parallel programming approach for efficient parallelism of MCTS for both multi-core and manycore shared-memory machines?”.To answer this question, the thesis approached the MCTS parallelization problem in three levels: (1) implementation level, (2) data structure level, and (3) algorithm level.In the implementation level, we proposed task-level parallelization over thread-level parallelization. Task-level parallelization provides us with efficient parallelism for MCTS to utilize cores on both multi-core and manycore machines.In the data structure level, we presented a lock-free data structure that guarantees the correctness. A lock-free data structure (1) removes the synchronization overhead when a parallel program needs many tasks to feed its cores and (2) improves both performance and scalability.In the algorithm level, we first explained how to use pipeline pattern for parallelization of MCTS to overcome search overhead. Then, through a step by step approach, we were able to propose and detail the structured parallel programming approach for Monte Carlo Tree Search. Show less
A P300-based Brain Computer Interface character speller, also known as P300 speller, has been an important communication pathway, under extensive research, for people who lose motor ability, such... Show moreA P300-based Brain Computer Interface character speller, also known as P300 speller, has been an important communication pathway, under extensive research, for people who lose motor ability, such as patients with Amyotrophic Lateral Sclerosis or spinal-cord injury because a P300 speller allows human-beings to directly spell characters using eye-gazes, thereby building communication between the human brain and a computer. Unfortunately, P300 spellers are still not used in human’s daily life and remain in an experimental stage at research labs. The reason for this situation is that the performance and the efficiency of current P300 spellers are unacceptably low for BCI users in their daily life. Therefore, in this thesis, we have focused our attention on developing high performance and efficient P300 spellers in order to bring P300 spellers into practical use. More specifically, in order to increase the performance of a P300 speller, we have developed methods to increase the character spelling accuracy and the Information Transfer Rate. In order to improve the efficiency of a P300 speller, we have developed methods to reduce the number of sensors needed to acquire EEG signals as well as to reduce the complexity of the classifier used in a P300 speller without losing the performance. Show less
Mining time series is a machine learning subfield that focuses on a particular data structure, where variables are measured over (short or long) periods of time. In this thesis we focus on... Show moreMining time series is a machine learning subfield that focuses on a particular data structure, where variables are measured over (short or long) periods of time. In this thesis we focus on multivariate time series, with multiple vari- ables measured over the same period of time. In most cases, such variables are collected at different sampling rates. When combined, these variables can be explored with machine learning methods for multiple purposes.Firstly, we consider the possibility of unsupervised learning. In this case, we propose a pattern recognition method that discovers subsets of variables that show consistent behavior in a number of shared time segments. Fur- thermore, when in a supervised setting, given a dependent variable (target),we propose a method that aggregates independent variables into meaningful features.Additionally to the methods above, we provide two tools in the form of Software as a Service, where users without programming background can intuitively follow the learning and testing methodologies for both methods.Finally, we present an applied study of machine learning to improve speed skating athletes performance. Here, we make a deep analysis of historical data, in order to help optimize performance results. Show less
Many databases do not consist of a single table of fixed dimensions, but of objects that are related to each other: the databases are relational, or structured. We study the discovery of patterns... Show moreMany databases do not consist of a single table of fixed dimensions, but of objects that are related to each other: the databases are relational, or structured. We study the discovery of patterns in such data. In our approach, a data analyst specifies constraints on patterns that she believes to be of interest, and the computer searches for patterns that satisfy these constraints. An important constraint on which we focus, is the constraint that a pattern should have a significant number of occurrences in the data. Constraints like this allow the search to be performed reasonably efficiently. We develop algorithms for searching ppatterns taht are represented in formal first order logic, tree data structures and graph data structures. We perform experiments in which these algorithms, and algorithms proposed by other researchers, are compared with each other, and study which properties determine the efficiency of the algorithms. As a result, we are able to develop more efficient algorithms. As application we study the discovery of fragments in molecular datasets. The aim is to discover fragments that relate the structure of molecules to their activity. Show less
