A Novel Method to Perform Search Query using Brainwave Signals 
Deekonda Sai Manish1, Nabeel Shahid2, Anand Raj3, P. Mohamed Fathimal4
1Deekonda Sai Manish, Department of Computer Science, SRM Institute of Science & Technology, Chennai (Tamil Nadu), India.
2Nabeel Shahid, Department of Computer Science, SRM Institute of Science & Technology, Chennai (Tamil Nadu), India.
3Anand Raj, Department of Computer Science, SRM Institute of Science & Technology, Chennai (Tamil Nadu), India.
4Dr. P. Mohamed Fathimal, Department of Computer Science, SRM Institute of Science & Technology, Chennai (Tamil Nadu), India.
Manuscript received on 25 August 2019 | Revised Manuscript received on 01 September 2019 | Manuscript Published on 14 September 2019 | PP: 23-27 | Volume-8 Issue-5S3, July 2019 | Retrieval Number: E10090785S319/19©BEIESP | DOI: 10.35940/ijeat.E1009/0785S319
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The main aim of the proposed paper is to search the information using brain waves instead of searching using the text query. Electroencephalography (EEG) is an electrophysiological checking strategy to record the electrical activity of the mind. EEG estimates voltage changes coming about because of ionic current inside the neurons of the mind. EEG alludes to the account of the mind’s unconstrained electrical movement over a time frame, as recorded from different nodes put on the scalp. For training, When the user has read a question, the brain waves are recorded with the help of sensors like Neurosky device in the form of EEG signals values like Alpha, Beta, and Gamma and are stored in a dataset. The brainwaves of different persons are recorded for different questions and are stored. The features are reduced using PCA and the centroid of the values are calculated using the K-means clustering algorithm. For testing, when the user thinks about a question in the list, the brain waves are recorded and compared with the values available in the dataset. Using KNN Algorithm, the proposed system outputs the respective question which will be submitted to the search engine. K-Means clustering algorithm is used to calculate the cluster centroid. Once the centroid is calculated for each question, we plot each centroid in a 2-D plane. For a random question from the pool of existing questions, we use the KNN algorithm to find the nearest match. When the match is found, the question corresponding to it is submitted to the search engine.
Keywords: Brain Waves, EEG (Electroencephalography), PCA, K-Means, KNN, Neurosky Device.
Scope of the Article: Search-Based Software Engineering