Show simple item record

dc.contributor.advisorHu, Jingtong
dc.contributor.authorVang, Cher Wa
dc.date.accessioned2017-02-22T22:16:39Z
dc.date.available2017-02-22T22:16:39Z
dc.date.issued2016-07-01
dc.identifier.urihttps://hdl.handle.net/11244/49172
dc.description.abstractWhen a neuron within the brain fires, small traces of electrical activity can be measured. Electroencephalography (EEG) is one such method of measuring that electrical activity. With the emergence of inexpensive, and portable so called �Wearable EEG� devices, such as the Emotiv EPOC+, what is traditionally used for clinical diagnosis and cognitive neuroscience is now more readably available for the consumer. The growth of computing power has grown exponentially since the implementation of the first semiconductor in 1947. The average household computer has more computing power than the computer used to take Apollo 11 to the moon. Computers have grown powerful enough that they can run a machine learning algorithm to see patterns that to the human perception, may appear to be random.One of the first expressions of human art and culture was first expressed as paintings on cavern walls, then through language, writing, the radio, the television, the internet, and soon to be virtual reality (VR). The human race is at the dawn of the age of VR. With the explosive success of commercial VR such as the Oculus Rift, and the HTC VIVE, VR is here to stay. The purpose of this research is to go over the practicability of EEG technology and machine learning in brain-computer interface to allow a person to play video games with their mind. By reading EEG brain signals during video gaming activities, a machine learning algorithm will attempt to produce a model to predict future video game actions. This research also offers a brief future potential capabilities, and further improvements to the system.
dc.formatapplication/pdf
dc.languageen_US
dc.rightsCopyright is held by the author who has granted the Oklahoma State University Library the non-exclusive right to share this material in its institutional repository. Contact Digital Library Services at lib-dls@okstate.edu or 405-744-9161 for the permission policy on the use, reproduction or distribution of this material.
dc.titleEeg and Machine Learning in Brain-computer Interface
dc.contributor.committeeMemberStine, James E
dc.contributor.committeeMemberRajamani, Vignesh
osu.filenameVang_okstate_0664M_14710.pdf
osu.accesstypeOpen Access
dc.description.departmentElectrical Engineering
dc.type.genreThesis
dc.type.materialtext


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record