A novel brain computer interface based on Principle Component Analysis and Fuzzy Logic
Labib S.S.
Date issued:
2016
Publisher:
Institute of Electrical and Electronics Engineers Inc.
Series Info:
2016 6th International Conference on Digital Information Processing and Communications, ICDIPC 2016
Type:
Conference Paper
Keywords:
Brain Computer Interface
,
EEG
,
Principle Component Analysis
,
Support Vector Machine
,
Wavelet Transform
,
Bioelectric phenomena
,
Biomedical signal processing
,
Brain
,
Computer control systems
,
Discrete wavelet transforms
,
Electroencephalography
,
Feature extraction
,
Fuzzy filters
,
Fuzzy logic
,
High pass filters
,
Image retrieval
,
Information science
,
Interfaces (computer)
,
Membership functions
,
Principal component analysis
,
Support vector machines
,
Wavelet transforms
,
Control command
,
Discrete wavelet transform algorithms
,
Electro-encephalogram (EEG)
,
Gaussian membership function
,
Integrated techniques
,
Principle component analysis
,
Root Mean Square
,
Statistical features
,
Brain computer interface
Abstract:
Brain computer interface (BCI) systems measure brain signal and translate it into control commands in an attempt to mimic specific human thinking activities. In recent years, many researchers have shown their interests in BCI systems, which has resulted in many experiments and applications. The main issue to build applicable Brain-Computer Interfaces is the capability to classify the Electroencephalograms (EEG). The purpose behind this research is to improve a model for brain signals analysis. We have used high pass filter to remove artifacts, discrete wavelet transform algorithms for feature extraction and statistical features like Mean Absolute Value, Root Mean Square, and Simple Square Integral are used, also we have used principle component analysis to reduce the size of feature vector and we used fuzzy Gaussian membership function to optimize the classification phase. It has been depicted from results that the proposed integrated techniques outperform a better performance than methods mentioned in literature. � 2016 IEEE.
Show full item record