172 research outputs found
EEG sub-band frequency analysis of spectrogram image for balanced brainwave and IQ applications / Mahfuzah Mustafa
Get PDFThis thesis introduces new methods in analyzing Electroencephalogram (EEG) signal by utilizing EEG spectrogram image and image processing texture analysis called Gray level Co-occurrence Matrices (GLCM). The methods attempt to apply in balanced brain and Intelligence Quotient (IQ) applications. The relationship between balanced brain and IQ application also proposed in this thesis. Collection of EEG signals were recorded from 101 volunteers. EEG signals recorded for the balanced brain application contain closed eyes state meanwhile for the IQ application contains closed eyes and opened eyes state. Before processing the information from the EEG signals, signal preprocessing is done to remove artefacts and unwanted signal frequencies. A time frequency based technique called EEG spectrogram image was used to generate an image from EEG signal. The spectrogram image was produced for each EEG signals sub-band frequency Delta, Theta, Alpha and Beta. The GLCM texture analysis derives features from EEG spectrogram image. Then, Principal Component Analysis (PCA) was applied to reduce the results and selected principal components features were used as inputs to the classifier. Two classifiers involved in this experiment are K-Nearest Neighbor (KNN) and Artificial Neural Network (ANN). The number of training and testing ratio is assessed at 70 to 30 and 80 to 20 to find the best model based on percentage of accuracy, sensitivity, specificity as well as Mean Squared Error (MSE). The relationship pattern of balanced brain and IQ application were observed via histogram and then Scatterplot. The strength and significant of the relationship was evaluated by using Pearson correlation test. The percentage of correctness classification for balanced brain application is 90% and MSE 0.1. The sensitivity and specificity of this application is ranging from 66.67% to 100%. The accuracy for IQ application is 94.44% and MSE 0.0752. Meanwhile, the sensitivity and specificity of this application is ranging from 0% to 100%. The relationship between balanced brain and IQ achieved with positive and strong correlation with r ranging between 0.860 to 1.000 and p < 0.05 for some cases. The experiments reported in this thesis showed that the proposed technique were highly successful in indexing the balanced brain level and IQ
EEG sub-band frequency analysis of spectogram image for balanced brainwave and IQ applications / Mahfuzah Mustafa
Get PDFThis thesis introduces new methods in analysing Electroencephalogram (EEG) signal by utilizing EEG spectrogram image and image processing texture analysis called Graylevel Co-occurrence Matrices (GLCM). The methods attempt to apply in balanced brain and Intelligence Quotient (IQ) applications. The relationship between balanced brain and IQ application also proposed in this thesis. Collection of EEG signals were recorded from 101 volunteers. EEG signals recorded for the balanced brain application contain closed eyes state meanwhile for the IQ application contains closed eyes and opened eyes state. Before processing the information from the EEG signals, signal pre-processing is done to remove artefacts and unwanted signal frequencies. A time frequency based technique called EEG spectrogram image was used to generate an image from EEG signal. The spectrogram image was produced for each EEG signals sub-band frequency Delta, Theta, Alpha and Beta. The GLCM texture analysis derives features from EEG spectrogram image. Then, Principal Component Analysis (PCA) was applied to reduce the results and selected principal components features were used as inputs to the classifier. Two classifiers involved in this experiment are K-Nearest Neighbor (KNN) and Artificial Neural Network (ANN). The number of training and testing ratio is assessed at 70 to 30 and 80 to 20 to find the best model based on percentage of accuracy, sensitivity, specificity as well as Mean Squared Error (MSE). The relationship pattern of balanced brain and IQ application were observed via histogram and then Scatterplot. The strength and significant of the relationship was evaluated by using Pearson correlation test. The percentage of correctness classification for balanced brain application is 90% and MSE 0.1. The sensitivity and specificity of this application is ranging from 66.67% to 100%. The accuracy for IQ application is 94.44%o and MSE 0.0752. Meanwhile, the sensitivity and specificity of this application is ranging from 0%> to 100%). The relationship between balanced brain and IQ achieved with positive and strong correlation with r ranging between 0.860 to 1.000 and for some cases. The experiments reported in this thesis showed that the proposed technique were highly successful in indexing the balanced brain level and IQ
EEG sub-band frequency analysis of spectrogram image for balanced brainwave and IQ applications / Mahfuzah Mustafa
Get PDFThis thesis introduces new methods in analyzing Electroencephalogram (EEG) signal by utilizing EEG spectrogram image and image processing texture analysis called Gray-level Co-occurrence Matrices (GLCM). The methods attempt to apply in balanced brain and Intelligence Quotient (IQ) applications. The relationship between balanced brain and IQ application also proposed in this thesis. Collection of EEG signals were recorded from 101 volunteers. EEG signals recorded for the balanced brain application contain closed eyes state meanwhile for the IQ application contains closed eyes and opened eyes state. Before processing the information from the EEG signals, signal preprocessing is done to remove artefacts and unwanted signal frequencies. A time-frequency based technique called EEG spectrogram image was used to generate an image from EEG signal. The spectrogram image was produced for each EEG signals sub-band frequency Delta, Theta, Alpha and Beta. The GLCM texture analysis derives features from EEG spectrogram image
Observation of the effects of playing games with the human brain waves
No full textThe purpose of this paper is to observe the human brain waves when a person playing video games. The game proposed is Counter Strike (CS) 1.6. There are 30 samples of human brain wave will be collected. The EEG signal will be recorded before playing a game and after playing a game. The threshold value is used to filter the data collected to acquire clean brain waves. Then, extraction of sub-band Alpha and Beta is done by Bandpass filter. Power Spectral Density (PSD) is performed in analysing the brain waves to acquire peak amplitude of the Alpha and Beta sub-band frequencies. The pattern of Alpha and Beta is carried out by using the histogram to observe the relationship between games and mind state of humanity. It is observed that the Beta-band increase and Alphaband decrease after the samples playing game
PSO based optimal reactive power dispatch (ORPD) considering multi-contingencies
No full textA stable power system can be subjected to voltage fluctuations due to poorly regulated reactive power flow that causes system instability. Reactive power is closely related to system voltage control, therefore, it is crucial to ensure the correct amount of reactive power is supplied to the system loads to achieve smooth power system operation and avoid voltage collapse from occurring. This paper presents the implementation of Particle Swarm Optimization (PSO) technique for solving ORPD problem considering multiple contingencies (N-m). The technique was implemented with the aim to improve voltage stability and minimize total transmission losses of the system. The IEEE 30-bus system was tested with generator outage in order to simulate the impact of disturbance to the power system transmission and distribution
Connection siemens PLC (programmable logic control) to labview using OPC (ole for process control)
Get PDFThe project is to enable the Siemens PLC (Programmable Logic Control) S7-300 to
communicate with the Lab VIEW. The communication between S7-300 and Lab VIEW is
via OPC (OLE for Process Control). Development of OPC using SIMA TIC NET OPC
Server. OPC is industry standard provides real plug-and-play software technology for
process control and factory automation. OPC integrate software and hardware across
spectrum of vendors easily. Visualization of Festo Didactic process developed using
Lab VIEW. Festo Didactic is small system which consist actuators and sensors . The
process of Festo is to make hole for three different material red plastic, black plastic and
metal. PROFIBUS is a medium to transfer data from PLC to Lab VIEW or Lab VIEW to
PLC
Connection of siemens PLC to labview using OPC
Get PDFThe project is to enable the Siemens PLC (Programmable Logic Control) S7-300 to
comlllzlI1icate ll'ith the Lab VIETY. The cOllllllunication between S7-300 and LabT/lEW is
via OPC (OLE for Process Control).Development of OPC Zlsing SI1vfATlC NET OPC
Server. OPC is indusfly standard provides real plug-and-play software technology for
process control and factor), alltomat ioll. OPC integrate software and hardware across
spectrum of vendors easi~v. Vislla/i~ation of Festa Didactic process developed llsing
LahI/l EW Festo Didactic is small .\ystem which consist actuators and sensors . The
process of Festa is to make hole for three different material red plastic. black plastic and
metal. PROFIBUS is a medium to tramJer datu from PLC to Lab VIEW or Lab VlEJ;V to
PLC
kNN Classification of Epilepsy Brainwaves
Get PDFEpilepsy is a disorder of the normal brain function by the existence of abnormal synchronous discharges in large groups of neurons in brain structures and it is estimated about 1% of the world’s population suffers from this disease [Tzallas et al., 2009]. It has been reported that the brainwave of
Epilepsy patient mostly in sharp, spike and complex wave pattern [Tzallas et al., 2009]. In addition, Epilepsy brainwaves pattern lies in wide variety of Electroencephalogram (EEG) signals in formed of low-amplitude and polyspikes activity [Vargas et al., 2011]. Generally, this disease was examined through the brainwaves or EEG signals by clinical neurulogists. An EEG is a device to record the brainwaves in term of electrical activity from the brain. Brain patterns from wave shapes that are commonly sinusoidal and measured from peak to peak that range from 0.5 μV to 100 μV in amplitude. Moreover, the brainwaves have been categorized into four frequency bands, Beta (>13 Hz), Alpha (8-13 Hz), Theta (4-8 Hz) and Delta (0.5-4 Hz). All
the frequency bands will be used to characterize the Epilepsy brainwave in terms of amplitude (voltage) and frequency [Mustafa et al., 2013]. The Epilepsy brainwaves were downloaded from http://www.vis.caltech.edu/~rodri/data.htm of Fp1 and Fp2 channels which is from rats. The brainwaves consists Epilepsy and non-Epilepsy samples. Then, the brainwaves were pre-processed to remove artefact (noise). Various methods had been introduced to detect spike-wave discharge in Epilepsy patient brainwave. Brainwave is nonstationary signal, therefore, time-frequency analysis is appropriate methods to analyse the signals[Tzallas et al., 2009, Vargas et al., 2011]. One of the most popular time-frequency analyses is ShortTime Fourier Transform (STFT). After the brainwaves were pre-processed, STFT was employed to
the clean brainwaves. The STFT spectrogram was generated for four frequency bands of the samples
Eeg sub-band frequency analysis of spectrogram image for balanced brainwave and iq applications
Get PDFThis thesis introduces new methods in analyzing Electroencephalogram (EEG) signal by utilizing EEG spectrogram image and image processing texture analysis called Graylevel Co-occurrence Matrices (GLCM). The methods attempt to apply in balanced brain and Intelligence Quotient (IQ) applications. The relationship between balanced brain and IQ application also proposed in this thesis. Collection of BEG signals were recorded from 101 volunteers. BEG signals recorded for the balanced brain application contain closed eyes state meanwhile for the IQ application contains closed eyes and opened eyes state. Before processing the information from the EEG signals, signal preprocessing is done to remove artefacts and unwanted signal frequencies. A time frequency based technique called EEG spectrogram image was used to generate an image from EEG signal. The spectrogram image was produced for each EEG signals
sub-band frequency Delta, Theta, Alpha and Beta. The GLCM texture analysis derives features from EEG spectrogram image. Then, Principal Component Analysis (PCA) was applied to reduce the results and selected principal components features were used as inputs to the classifier. Two classifiers involved in this experiment are K-Nearest Neighbor (KNN) and Artificial Neural Network (ANN). The number of training and testing ratio is assessed at 70 to 30 and 80 to 20 to find the best model based on percentage of accuracy, sensitivity, specificity as well as Mean Squared Error (MSE). The relationship pattern of balanced brain and IQ application were observed via histogram and then Scatterplot. The strength and significant of the relationship was evaluated by using Pearson correlation test. The percentage of correctness classification for balanced brain application is 90% and MSE 0.1. The sensitivity and specificity of this application is ranging from 66.67% to 100%. The accuracy for IQ application is 94.44% and MSE 0.0752. Meanwhile, the sensitivity and specificity of this application is ranging from 0% to 100%. The relationship between balanced brain and IQ achieved with positive and strong correlation with r ranging between 0.860 to 1.000 and p<0.05 for some cases. The experiments reported in this thesis showed that the proposed technique were highly successful in indexing the balanced brain level and IQ
Classification of EEG Spectrogram Using ANN for IQ Application
Get PDFThe intelligence term can be view in many areas
such as linguistic, mathematical, music and art. In this paper, the Intelligence Quotient (IQ) is measured using Electroencephalogram (EEG) from the human brain. The spectrogram images were formed from EEG signals, then the Gray Level Co-occurrence Matrix (GLCM) texture feature were extracted from the images. This texture feature produced big matrix data, thus Principal Component Analysis (PCA) is used to reduce the big matrix. Then, ANN algorithm is employed to classify the EEG spectrogram image in IQ application. The
results will be validated based on the concept of Raven's Standard Progressive Matrices (RPM) IQ test. The results showed that the ANN was able to classify the EEG spectrogram image with 88.89% accuracy and 0.0633 MS
- …
