Theory and Algorithms Commons^™

Exploration Of Computational Methods For Classification Of Movement Intention During Human Voluntary Movement From Single Trial Eeg, Ou Bai, Peter Lin, Sherry Vorbach, Jiang Li, Steve Furlani, Mark Hallett

Electrical & Computer Engineering Faculty Publications

Objective: To explore effective combinations of computational methods for the prediction of movement intention preceding the production of self-paced right and left hand movements from single trial scalp electroencephalogram (EEG).

Methods: Twelve naïve subjects performed self-paced movements consisting of three key strokes with either hand. EEG was recorded from 128 channels. The exploration was performed offline on single trial EEG data. We proposed that a successful computational procedure for classification would consist of spatial filtering, temporal filtering, feature selection, and pattern classification. A systematic investigation was performed with combinations of spatial filtering using principal component analysis (PCA), independent component analysis …

Mining Frequent Patterns From Sequences: Theory, Algorithm, Implementation, And Performance, Markus Petteri Turkia

Theses and Dissertations

Mining frequent patterns from sequences is an important data mining problem which has direct applications in many areas. In this thesis, we make three contributions to the state-of-the-art of the sequential frequent pattern mining. First of all, we propose a fast pattern-growth mining algorithm using a novel sequence database representation called First-Occurrence Linked WAP-tree (FLWAP-tree). The pattern-growth mining algorithm using the Pre-Order Linked WAP-tree (PLWAP-tree) was reported in the literature to be faster than other algorithms. We show that our pattern-growth using our FLWAP-tree outperforms the PLWAP-tree mining significantly and consistently. Secondly, we extend the pattern-growth algorithm with partial enumeration …

Dual Constraint Problem Optimization Using A Natural Approach: Genetic Algorithm And Simulated Annealing, James P. Sweeney

UNF Graduate Theses and Dissertations

Constraint optimization problems with multiple constraints and a large solution domain are NP hard and span almost all industries in a variety of applications. One such application is the optimization of resource scheduling in a "pay per use" grid environment. Charging for these resources based on demand is often referred to as Utility Computing, where resource providers lease computing power with varying costs based on processing speed. Consumers using this resource have time and cost constraints associated with each job they submit. Determining the optimal way to divide the job among the available resources with regard to the time and …

Solving The Teacher Assignment-Course Scheduling Problem By A Hybrid Algorithm, Aldy Gunawan, Kien Ming Ng, Kim Leng Poh

Research Collection School Of Computing and Information Systems

This paper presents a hybrid algorithm for solving atimetabling problem, which is commonly encountered in manyuniversities. The problem combines both teacher assignment andcourse scheduling problems simultaneously, and is presented as amathematical programming model. However, this problem becomesintractable and it is unlikely that a proven optimal solution can beobtained by an integer programming approach, especially for largeproblem instances. A hybrid algorithm that combines an integerprogramming approach, a greedy heuristic and a modified simulatedannealing algorithm collaboratively is proposed to solve the problem.Several randomly generated data sets of sizes comparable to that ofan institution in Indonesia are solved using the proposed algorithm.Computational results …

An Improvement Heuristic For The Timetabling Problem, Aldy Gunawan, Kien Ming Ng, Kim Leng Poh

Research Collection School Of Computing and Information Systems

This paper formulates a timetabling problem, which is often encountered in a university, as a mathematical programming model. The proposed model combines both teacher assignment and course scheduling problems simultaneously, which causes the entire model to become more complex. We propose an improvement heuristic algorithm to solve such a model. The proposed algorithm has been tested with several randomly generated datasets of sizes that are comparable to those occurring in a university in Indonesia. The computational results show that the improvement heuristic is not only able to obtain good solutions, but is also able to do so within reasonable computational …