• Journal of the Institute of Convergence Signal Processing
• /
• v.5 no.4
• /
• pp.263-270
• /
• 2004

Recently, wavelet transform have been applied to various kinds of problems in many fields. In this paper, we propose method of Daubechies wavelet to detect several kinds of important characteristic waves in tasks EEG that are needed to diagnose EEG. We show that our system could be attained higher performance in detecting characteristic waves than the other methods. In this system, the architecture of the neural network is a three layered feed-forward networks with one hidden layer which implements the error back propagation teaming algorithm. Applying the algorithms to 4 subjects show 92% classification rates. The proposed system shows a little more accurate diagnosis for task EEG by Wavelet and neural network. From the simulation results by the implemented system, we demonstrated this research can be reduce doctor's labors and quantitative diagnosis of task EEG.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1109-1114
• /
• 2018

Electroencephalogram (EEG) is a tool used to study brain activity caused by external stimuli. In this process, artifacts are mixed and it is easy to distort the signal, so post-processing is necessary to remove it. Independent Component Analysis (ICA) is a widely used method for removing artifact. This method has a disadvantage in that it has excellent performance but some loss of brain wave information. In this paper, we propose a method to reduce EEG information loss by restricting the filter coverage using eye blink information obtained from Eyetracker. We then compared the results of the proposed method with the conventional method using quantization methods such as Signal to Noise Ratio (SNR) and Spectral Coherence (SC).

• Journal of Biomedical Engineering Research
• /
• v.20 no.2
• /
• pp.205-212
• /
• 1999

When we want to observe and record a patient's EEG in an operating room, the operation of electrosurgical unit(ESU) causes undesirable artifacts with high frequency and high voltage. These artifacts make the amplifiers of the conventional EEG system saturated and prevent the system from measuring the EEG signal. This paper describes a high-performance bipolar EEG amplifier for a CSA (compressed spectral array ) system with reduced ESU artifacts. The designed EEG amplifier uses a balanced filter to reduce the ESU artifacts, and isolates the power supply and the signal source of the preamplifier from the ground to cut off the current from the ESU to the amplifier ground. To cancel the common mode noise in high frequency, a high CMRR(common mode rejection ratio) diffferential amplifier is used. Since the developed bipolar EEG amplifier shows high gain, low noise, high CMRR, high input impedance, and low thermal drift, it is possible to observe and record more clean EEG signals in spite of ESU operation. Therefore the amplifier may be applicable to a high-fidelity CSA system.

• The KIPS Transactions:PartB
• /
• v.9B no.1
• /
• pp.35-46
• /
• 2002

The EEG is a time series of electrical potentials representing the sum of a very large number of neuronal dendrite potentials in the brain. The collective dynamic behavior of neural mass of different brain structures can be assessed from EEG with depth electrodes measurements at regular time intervals. In recent years, the theory of nonlinear dynamics has developed methods for quantitative analysis of brain function. In this paper, we considered it is reasonable or not for ICA apply to EEG analysis. Then we applied ICA to EEG for big toe movement and separated the independent components for 15 samples. The strength of each independent component can be represented on the topological map. We represented ICA can be applied for time and spatial analysis of EEG.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.8
• /
• pp.1637-1642
• /
• 2015

Next-generation applications using technology IT fused to biological signals from the emotional state to extract a lot of research has been, and the sensitivity of the human sensory functions influences the physiological condition known to be the fact that. In this paper, Propose an Emotional-lighting control algorithm using bio-signals. LED lighting for Emotion light is environmentally friendly and has a high efficiency and long life. In particular, LED lights are different colors represent the possible single light sphere advantages. And, Human sensitivity for determining a more accurate biological signals using EEG was collected using EEG equipment sensitivity was determined to analyze the EEG.

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.1
• /
• pp.7-12
• /
• 2020

Various parameters are used to measure anesthetic depth during surgery using brain waves, and in actual clinical use, the linear analysis SEF is widely used. However, with recent studies showing that biological signals including EEG, contain nonlinear properties interest in nonlinear analysis of brain signals is increasing and parameters based on these are being developed. In this study, we are going to develop a parameter that can measure EEG using the nonlinear analysis method and extract noise that can be mixed with external electronic equipment and EEG instrumentation by comparing it with the data from the bispectrum analysis of static waves.

• Journal of the Korea Institute of Building Construction
• /
• v.20 no.1
• /
• pp.93-102
• /
• 2020

The purpose of this study is to find out how to measure the stress related to accidents at the construction site promptly and conveniently to prevent safety accidents of construction workers. Accordingly, we analyzed the correlations between the questionnaire tool index that measures the stress associated with complex psychology of humans by integrating emotion, cognition, physical and behavioral responses, and basic brain waves, SEF-90, concentration, stress index from brain wave. As a result, which had the highest correlation with the stress measured through the questionnaire, was the SEF-90, and the regression analysis between two independent variables yielded a specific regression equation. This suggests the possibility of measuring the integrated stress of construction workers through the EEG signal at the construction site, and it can be used for the safety management of the construction site in the future.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.5
• /
• pp.518-524
• /
• 2022

In this paper, we propose a method for combining convolutional neural networks and attention mechanism to improve the recognition performance of emotional stress from Electroencephalogram (EGG) signals. In the proposed method, EEG signals are decomposed into five frequency domains, and spatial information of EEG features is obtained by applying a convolutional neural network layer to each frequency domain. As a next step, salient frequency information is learned in each frequency band using a gate transformer-based attention mechanism, and complementary frequency information is further learned through inter-frequency mapping to reflect it in the final attention representation. Through an EEG stress recognition experiment involving a DEAP dataset and six subjects, we show that the proposed method is effective in improving EEG-based stress recognition performance compared to the existing methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.249-251
• /
• 2022

In this paper, we present machine learning to control drone flight using EEG signals. We defined takeoff, forward, backward, left movement and right movement as control targets and measured EEG signals from the frontal lobe for controlling using Fp1. Fp2 Fp2 two-channel dry electrode (NeuroNicle FX2) measuring at 250Hz sampling rate. And the collected data were filtered at 6~20Hz cutoff frequency. We measured the motion image of the action associated with each control target open for 5.19 seconds. Using Matlab's classification learner for the measured EEG signal, the triple layer neural network, logistic regression kernel, nonlinear polynomial Support Vector Machine(SVM) learning was performed, logistic regression kernel was confirmed as the highest accuracy for takeoff and forward, backward, left movement and right movement of the drone in learning by class True Positive Rate(TPR).

• Journal of Korea Multimedia Society
• /
• v.6 no.1
• /
• pp.167-175
• /
• 2003

In this paper, a new electrode configuration and EOG removal method are proposed in order to measure EEG effectively on the frontal lobe and remove EOG in the measured raw EEG. The method of measuring EEG is proposed using four electrodes and a ground electrode on the frontal lobe with a reference electrode at the left earlobe. And also, the separation method using ICA is proposed for EOG removal from the measured EEG, Through the experiments of measuring EEG it was demonstrated that a subject can attach the electrodes by himself easily to measure his own EEG without any assistant and the proposed methods were suitable for removing EOG signal from the measured EEG.