IndexIntroductionData AcquisitionDimensional Reduction TechniqueFeature Classification Using SVMConclusionThis paper proposes a modified algorithm for feature classification of imaginary left and right hand movements obtained from the EEG signal. Electroencephalogram (EEG) is the signal acquired by the human brain to monitor and identify human actions to different stimuli. The data was obtained from the BCI III (b) 2003 competition, acquired by the Graz University of Technology. The recorded EEG was sampled at 125 Hz and was filtered between 0.5 and 30 Hz. Say no to plagiarism. Get a tailor-made essay on "Why Violent Video Games Shouldn't Be Banned"? Get Original Essay Features were extracted using discrete wavelet transform (DWT). To obtain precise insights, the EEG signal was processed with dimensionality reduction techniques used such as (i) Singular Value Decomposition and (ii) LDA. Support Vector Machines (SVM) was used for the optimal classification of each motor movement. The result for the SVM binary class was at the 100% accuracy level. The results established that the accuracy of singular value decomposition is the best tool for identifying image movements. Introduction Feature extraction and feature classification have always been the challenging task in EEG signal. The EEG signal provides detailed information about the electrical activity in the brain. Provides an alternative form of communication for people with disabilities. Our work focused on reducing the complexity of the information and, on the other hand, maintaining the vital information resulting from the placement of the C3 and C4 electrodes. C3 and C4 are integral to the transmission of sensorimetric information from the brain. The EEG is obtained from 10–20 international standard electrode placements [11] on the surface of the skull. The C3 and C4 positions are the regions that provide theta rhythms. In our proposed work, the motor imagery movements of the left and right hand were classified. Extensive research on feature extraction and feature classification has been presented with great success. However, managing complexity remains the main problem in EEG signal classification. Xiao-Dong ZHANG, et.al [2] presented the algorithm for prosthetic hand control. The EEG signal was analyzed based on multiple complicated hand movements. The author concluded that the classification achieved by Support Vector Machines was much better than ANN. Andrews S. et al [21] presented singular value decomposition (SVD) for data noise and dimension reduction. The experimental results provided a very low false acceptance rate (FAR) and false rejection rate (FRR) and an almost negligible equal error rate (EER) of 2.91%. Sachin Garg et al [22] demonstrated the use of wavelet transform for feature extraction of EEG signal. The author stated that after extracting the coefficients, it was significantly easier to calculate the statistical parameters of the EEG signal. Another author, Ashwini Nakate et al [24], had also advocated the use of discrete wavelet transform technique to decompose the EEG signal. Priyanka Khatwani et al [25] present the DWT technique to eliminate noise from EEG signal data. Rajesh Singla et al [26] presented the motor imaginary movement of the wrist, rotation of the wrist clockwise/counterclockwise, elbow and ankle backward/forward. It has been argued that the DWT techniquewas the most suitable for extracting the characteristics of the EEG signal. Abdulhamit Subasi et al [27] presented the comparison of different techniques used to manipulate EEG signal data. Principal component analysis (PCA), independent component analysis (ICA), and linear discriminate analysis (LDA) were used to reduce the dimensionality of the signal. Siuli et. Al. [28] proposed the statistical algorithm to correctly classify the function of EEG signal. Thanh et. Al [29] had analyzed the EEG signals using the type 2 fuzzy logic method. The results had shown the low computation cost with good accuracy. ABM Hossain et al [30] proposed Probabilistic Neural Network algorithm for optimal classification of EEG signal function. The author had claimed that the accuracy rate was about 99.7%. The work of MA Hassan et al [31] focused on modifying the back propagation neural network for the EEG signal. The classification rate was between 97 and 100% accuracy. It was also concluded that temporal domain features extracted from EEG were more reliable for function classification. The document is organized as follows (Figure 1.1): Section II is data acquisition. Discusses the detailed database information of left and right hand image movements. Section III focuses on feature extraction using DWT. Section IV discusses dimensionality reduction techniques. Furthermore, Section V discusses the identification of motor movements. Finally, Section VI validates the proposed algorithm. While Swction VII concludes the work. Data acquisition The database was obtained from Graz University of Technology (BCI Competition III(b),2003). The signals and motion of the left and right hand images have been pre-processed to eliminate artifacts due to various noises (biosignals/external). Three electrodes (C3, Cz, and C4) were placed to record EEG data with a sampling rate of 125 Hz. Bandpass filters with a frequency range of 0.5 Hz to 30 Hz were used and it was also used a 50 Hz notch filter to remove artifacts. The dataset was recorded from a normal subject (female, 25 years old). The subject was not provided with registration information. Comfortable chair with armrests was provided. The task was to acquire imaginary left/right hand movements. The experiment consists of 7 runs with 40 trials each. Each trial lasts 9 seconds. After an initial pause of 2 seconds, the recording of the respective motor movements was started. The trials were then selected for random training and testing to classify image movements. In our proposed work, C3 and C4 (electrode placement) were considered for further analysis.[16]Figure 1.3 is the flowchart of feature extraction using DWT. The three motor movements were dispensed to refine the coefficients using Symlet at decomposition level “3” [38], so no useful information needs to be diminished. Using Symlet, the extracted features were nearly symmetric and had the least skewness. The associated scaling filters are close to linear phase filters. Dimensionality Reduction Technique For further analysis, dimensionality reduction, singular value decomposition (SVD), and linear discriminant analysis (LDA) were implemented to increase the computational efficiency of the proposed algorithm. It was helpful to remove any uncorrelated and redundant features from the coefficients extracted from DWT. The SVD theorem is given by:Xnxp= UnxnSnxpVTpxp (1)The column shows the three files and.