Konstantinos Tsiakas
    Ph.D. Candidate
    HERACLEIA Human-Centered Computing Laboratory
    Computer Science and Engineering Department
    University of Texas at Arlington
    Intitute of Informatics and Telecommunications, NCSR Demokritos

    Office: ERB 306, CSE@UTA
    Office Hours: TuTh 12:30pm - 2:00pm
    Phone: 817-805-9043
    Email: konstantinos.tsiakas@mavs.uta.edu
    LinkedIn Google Scholar ResearchGate


Home Research Publications CV

Designing a Socially Assistive Robot for Personalized and Adaptive Cognitive Training

Problem Definition
Data Collection and Analysis
Project Outcomes and Ongoing Work

Data Collection and Analysis

During each round (one sequence), the system keeps the following information: user ID, task design, task mode, round ID, robot action, sequence length, completion time, user performance and EEG raw data. More specifically, the system stores all absolute and relative EEG band and concentration values, as well as the headband connection status indicators (as derived by MUSE). More detailed information can be found in the submitted paper.
In order to get an insight of how we can leverage the collected data to develop personalized models for the sequence learning task, we provide an extensive and multi-aspect analysis, including data mining, machine learning and statistical analysis. The zipped file with the dataset, the analysis scripts and a README file can be found here.