Dwi Esti Kusumandari

Improvement of BCI Performance Through Nonlinear Independent Component Analysis Extraction

Electroencephalogram (EEG) recordings provide an important means of brain-computer communication, but their classification accuracy and transfer rate are limited by unexpected signal variations due to artifacts and noises. In this paper, a nonlinear independent component analysis (NICA) extraction method for brain signal based EEG-P300 are proposed. The performance of the proposed method is investigated through a comparison of well known extraction methods (i.e., AAR, JADE, and SOBI algorithms). Finally, the promising results reported here reflect the considerable potential of EEG for the continuous classification of mental states.

Removal of EOG artifacts: Comparison of ICA algorithm from recording EEG

Electroencephalogram (EEG) is the activity of bioelectrical signals that recorded from electrodes on the scalp. In EEG recording, the signal obtained is not entirely derived from the brain, but may be contaminated by other signals such as Electrooculogram (EOG), Electrocardiogram (ECG) and Electromiogram (EMG). EEG signals that recorded, especially by electrodes located near the eyes, will be affected by EOG. So that necessary action is needed to eliminate or reduce these EEG signals artifacts. This paper proposed a method using ICA for EOG artifact removal and compared which ICA algorithm (JADE and SOBI) is more effective and has better results in the removal of EOG artifacts in EEG recording.

Extraction of mental task in recorded EEG signal using ICA-JADE algorithm

An instrument that has special function to record electrical brain activity in scalp is electroencephalograph (EEG). Recently has various function, one of them is brain computer interface (BCI). BCI application can make human brain interaction with environment without other parts of body. Mental task is the important part in BCI system. Mental task which generate from brain, especially happen in central lobe. In fact, mental task disturbed by other signal which generate from other parts of brain. It is make problem to extract the real mental task from brain. In this research algorithm ICA-JADEis used to extract mental task activity in EEG signal recorded. The experiment was collected in 6 subject people. Stimulus for each subjectto move right hand for generate mental task have been design. Result of this research show ICA-JADE method can extract mental task from EEG signal recorded and the quantity perform of ICA-JADE is compared with the pure mental task signal.

Extraction of ECG signal with adaptive filter for hearth abnormalities detection

This paper demonstrates an adaptive filter method for extraction ofelectrocardiogram (ECG) feature in hearth abnormalities detection. In particular, electrocardiogram (ECG) is a recording of the hearts electrical activity by capturing a tracingof cardiac electrical impulse as it moves from the atrium to the ventricles. The applied algorithm is to evaluate and analyze ECG signals for abnormalities detection based on P, Q, R and S peaks. In the first phase, the real-time ECG data is acquired and pre-processed. In the second phase, the procured ECG signal is subjected to feature extraction process. The extracted features detect abnormal peaks present in the waveform. Thus the normal and abnormal ECG signal could be differentiated based on the features extracted.

Brain Mapping of drug addiction in witdrawal condition based P300 Signals

Drug abuse for a long time will slowly cause changes in brain structure and performance. These changes tend to occur in the front of the brain which is directly interfere the concentration and the decision-making process. In this study an experiment involving 10 drug users was performed. The process of recording data with EEG system is conducted during craving condition and 1 hour after taking methadone. From brain mapping results obtained that brain activity tend to occur in the upper layer of the brain during craving conditions and tend to be in the midle layer of the brain after one hour of taking methadone.

Classification of ECG signal with Support Vector Machine Method for Arrhythmia Detection

An electrocardiogram is a potential bioelectric record that occurs as a result of cardiac activity. QRS Detection with zero crossing calculation is one method that can precisely determine peak R of QRS wave as part of arrhythmia detection. In this paper, two experimental scheme (2 minutes duration with different activities: relaxed and, typing) were conducted. From the two experiments it were obtained: accuracy, sensitivity, and positive predictivity about 100% each for the first experiment and about 79%, 93%, 83% for the second experiment, respectively. Furthermore, the feature set of MIT-BIH arrhythmia using the support vector machine (SVM) method on the WEKA software is evaluated. By combining the available attributes on the WEKA algorithm, the result is constant since all classes of SVM goes to the normal class with average 88.49% accuracy.

Development of new method of drug abuse detection based brain computer interface

A methods of drugs abuse detection is urgently needed. Currently a conventional method such as urine test, hair test, Functional Magnetic Resonance Imaging, Positron Emission Tomography, and others are used. Those methods, instead of expensive and complicated, it is require a medical experts. Furthermore, this tool cannot be used to detect new variations of drug. In this study, a new method of drugs abuse detection based brain computer interface (BCI) which recorded with an electroencephalogram is developed. In principle, as long as the subject is still be able to remember, then the tool will be able to detect whether ever use a drug or not. In the experiment 15 subjects are tested. In the signal processing, the EEG signal is filtered with baseline correction and band-pass filter and extracted using wavelet symlet method. The brain maps of damaged brains are in sharp contrast to those of brains which have not been subjected to drug abuse. This studies could be used to identify drug abusers and alternative tool for rehabilitation.

Deception detection of EEG-P300 component classified by SVM method

This study will explore the differences in brain wave activity while a person is either telling the truth or being deceptive. A subject brain wave activities based EEG-P300 component will be monitored while they first respond truthfully and then falsely to questions in regards to a mock theft scenario. Eleven males whose age are around 24 ± 3 years old were subject to the experiment. For extraction and classification, an independent component analysis and support vector machine methods were adopted. The gathered data were then divided into training and test data to produce several models. The results show that a larger spike in the P300 component when the subject was instructed to conceal which watch they had chosen. The findings of these experiments have been promising in testing the validity of using an EEG in deception detection.

Artifacts Reduction of EEG-SSVEP Signals for Emotion Detection with Robust Principal Component Analysis

Study of brain activity generally raises the difficult of distinguishing between the real activity and the artifacts which is caused by an external influence. Therefore, the classification accuracy is still limited by unpredictable signal variations due to background noise. In this paper, we propose a method of artifacts reduction using robust principal component analysis which is applied for an emotion extraction to identify the EEG-SSVEP signals which are induced by the four short movie stimuli (i.e., sad, angry, happy, and calm emotions). The proposed method was tested in real EEG-SSVEP records acquired from eight subjects. The average of 81.5% classification accuracy is achieved for each stimuli. The classification result shows that the proposed method can effectively reduce the artifacts from all subjects.

The comparison of GVF Snake Active Contour method and Ellipse Fit in optic disc detection for glaucoma diagnosis

The paper proposes a method for automatic analysis of the shape and size of the optic disc and optic cup based on the optic disc and optic cup edge detection, performed by GVF Snake Active Contour, comparing the performance with the Ellipse Fit method. The result shows that the GVF Snake Active Contour system gives better result compared with the Ellipse Fit system, the methods with highest accuracy of performance attained for C/D ratio of area, concretely 84,38% for GVF Snake Active Contour method and 81,25% for Ellipse Fit method.