Parvez, Mohammad ZavidAfroz, SharminShimanto, Zubaed HassanJahan, Ra qua Sifat2019-07-142019-07-1420192019-04ID 15101041ID 14301057ID 14101123http://hdl.handle.net/10361/12352Cataloged from PDF version of thesis.Includes bibliographical references (pages 34-39).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2019.Cognitive load and emotional states may impact for designing an assistive navigation aid for the Visually Impaired Peoples (VIPs). In this study, electroencephalogram (EEG) signals were captured from participants with di erent degree sight loss peoples (DDSLPs). EEG signals were then used to measure various cognitive loads and emotions to test the usability of an intelligent navigation aids. To support the argument of testing the usability of a navigation aids, the complexity of the tasks in terms of cognitive load and emotions were quanti ed considering diverse factors by extracting features from various well established entropies when DDSLPs will navigate unfamiliar indoor environments with di erent obstacles. Experimental results show that classi cation accuracy for narrow space is 97.61% for cognitive load. Moreover, the experiment achieves that 90.40% and 50.60% classi cation accuracy for arousal and valence in the open space and stairs, respectively.40 pagesenBrac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.Cognitive loadEmotional statesEEGHuman brainEntropySVMMachine learningThesis