• 제어로봇시스템학회:학술대회논문집
• /
• 1995.10a
• /
• pp.505-508
• /
• 1995

The automatic interpretation of awake background electroencephalogram (EEG), consisting of quantitative EEG interpretation and EEG report making, has been developed by the authors based on EEG data visually inspected by an electroencephalographer (EEGer). The present study was focused on the adaptability of the automatic EEG interpretation which was accomplished by the constructive neural network with forgetting factor. The artificial neural network (ANN) was constructed so as to give the integrative decision of the EEG by using the input signals of the intermediate judgment of 13 items of the EEG. The feature of the ANN was that it adapted to any EEGer who gave visual inspection for the training data. The developed method was evaluated based on the EEG data of 57 patients. The re-trained ANN adapted to another EEGer appropriately.

• Korean Journal of Clinical Laboratory Science
• /
• v.37 no.2
• /
• pp.96-101
• /
• 2005

Status epilepticus is a medical emergency, so that rapid and vigorous treatment is required to prevent neuronal damage and systemic complication. Status epilepticus is generally defined as a continuous or intermittent seizure or an unconscious condition after the onset of seizure, lasting for 30 minutes or more. We report here the outcome of status epilepticus. We retrospectively reviewed medical record of 15 patients who were diagnosed with status epilepticus at the Asan Medical Center from January 2003 to February 2004. This outcome was evaluated considering various factors such as age of patients, history of seizures, neurologic impairment, etiology, mortality, return to baseline and initial electroencephalogram (EEG) findings. The range of age was between 1 to 79 years old and the longest duration of treatment was 118 days. Most patients were treated by using pentobarbital, midazolam, phenobarbital and other antiepileptic drugs. The overall mortality was 5 (33%) out of 15 patients. The mortality was related to etiology, underlying other medical conditions and initial EEG findings. 5 (55%) out of the 9 patients with acute etiology, 5 (71%) out of the 7 patients with a multifocal or burst-suppression EEG activity, and 3 (60%) out of the 5 patients with other medical disease were related to mortality. This data demonstrate high mortality due to status epilepticus. Mortality is related to etiology, other medical conditions and abnormalities on the initial EEG.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.2
• /
• pp.178-183
• /
• 2013

In this study, we proposed a method for electroencephalogram (EEG) classification using invariant CSP at special channels for improving the accuracy of classification. Based on the naive EEG signals from left and right hand movement experiment, the noises of contaminated data set should be eliminate and the proposed method can deal with the de-noising of data set. The considering data set are collected from the special channels for right and left hand movements around the motor cortex area. The proposed method is based on the fit of the adjusted parameter to decline the affect of invariant parts in raw signals and can increase the classification accuracy. We have run the simulation for hundreds time for each parameter and get averaged value to get the last result for comparison. The experimental results show the accuracy is improved more than the original method, the highest result reach to 89.74%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.11
• /
• pp.1914-1922
• /
• 2008

In this paper, examined characteristics of EEG(electroencephalogram) variation when the stimulation was given to lung-wan(CV12), Shin-gwol(CV8) and Gwan-won(CV4) which were some of the acupuncture point, through indirect moxibustion and No stimulation. The EEG signals were measured before the stimulation, during the stimulation, and 1 hour after the stimulation. The measured time domain data were converted to the frequency domain data FFT(Fast Fourier Transform) and frequency power spectrum. Then the $\alpha,\beta,\delta$, and $\theta$ waves were analyzed for variation to the amplitude of vibration according to the stages of stimulation.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.45 no.2
• /
• pp.305-316
• /
• 2021

In this study, the effect of wearing functional compression pants is verified using a lower-limb wearable robot through a bio-signal analysis and subjective fit evaluation. First, the compression area to be applied to the functional compression pants is derived using the quad method for nine men in their 20s. Subsequently, functional compression pants are prepared, and changes in Electroencephalogram (EEG) and Electrocardiogram (ECG) signals when wearing the functional compression and normal regular pants inside a wearable robot are measured. The EEG and ECG signals are measured with eyes closed and open. Results indicate that the Relative alpha (RA) and Relative gamma wave (RG) of the EEG signal differ significantly, resulting in increased stability and reduced anxiety and stress when wearing the functional compression pants. Furthermore, the ECG analysis results indicate statistically significant differences in the Low frequency (LF)/High frequency (HF) index, which reflect the overall balance of the autonomic nervous system and can be interpreted as feeling comfortable and balanced when wearing the functional compression pants. Moreover, subjective sense is discovered to be effective in assessing wear fit, ease of movement, skin friction, and wear comfort when wearing the functional compression pants.

• International Journal of Contents
• /
• v.9 no.4
• /
• pp.1-10
• /
• 2013

The electroencephalogram (EEG) time series is a measure of electrical activity received from multiple electrodes placed on the scalp of a human brain. It provides a direct measurement for characterizing the dynamic aspects of brain activities. These EEG signals are formed from a series of spatial and temporal data with multiple dimensions. Missing data could occur due to fault electrodes. These missing data can cause distortion, repudiation, and further, reduce the effectiveness of analyzing algorithms. Current methodologies for EEG analysis require a complete set of EEG data matrix as input. Therefore, an accurate and reliable imputation approach for missing values is necessary to avoid incomplete data sets for analyses and further improve the usage of performance techniques. This research proposes a new method to automatically recover random consecutive missing data from real world EEG data based on Linear Dynamical System. The proposed method aims to capture the optimal patterns based on two main characteristics in the coevolving EEG time series: namely, (i) dynamics via discovering temporal evolving behaviors, and (ii) correlations by identifying the relationships between multiple brain signals. From these exploits, the proposed method successfully identifies a few hidden variables and discovers their dynamics to impute missing values. The proposed method offers a robust and scalable approach with linear computation time over the size of sequences. A comparative study has been performed to assess the effectiveness of the proposed method against interpolation and missing values via Singular Value Decomposition (MSVD). The experimental simulations demonstrate that the proposed method provides better reconstruction performance up to 49% and 67% improvements over MSVD and interpolation approaches, respectively.

• Journal of Internet of Things and Convergence
• /
• v.9 no.1
• /
• pp.25-31
• /
• 2023

The brain-machine interface(BMI) is a next-generation interface that controls the device by decoding brain waves(also called Electroencephalogram, EEG), EEG is a electrical signal of nerve cell generated when the BMI user thinks of a command. The brain-machine interface can be applied to various smart devices, but complex computational process is required to decode the brain wave signal. Therefore, it is difficult to implement a brain-machine interface in an embedded system implemented in the form of an edge device. In this study, we proposed a new type of brain-machine interface system using IoT technology that only measures EEG at the edge device and stores and analyzes EEG data in the cloud computing. This system successfully performed quantitative EEG analysis for the brain-machine interface, and the whole data transmission time also showed a capable level of real-time processing.

• Korean Journal of Clinical Laboratory Science
• /
• v.49 no.3
• /
• pp.294-299
• /
• 2017

The aim of this study was to detect the status of epilepticus and seizure based on the initial patterns observed in the first 30 minutes of continuous electroencephalogram (cEEG) monitoring. An cEEG was recorded digitally using electrodes applied according to the International 10~20 System. The EEG data were reviewed from January 2014 to December 2015. The baselines of the EEG patterns were characterized by lateralized periodic discharges, generalized periodic discharges, burst suppression, focal epileptiform, asymmetric background, generalized slowing, and generalized periodic discharges with a triphagic wave. The etiology was classified into five categories. The subjects of this study were 128 patients (age: $56.9{\pm}17.5years$, male:female, 74:54). The mean cEEG monitoring duration was $5.5{\pm}5.1$ (min:max, 1:33) days. The EEG pattern categories included lateralized periodic discharges (N=7), generalized periodic discharges (N=10), burst suppression (N=6), focal epileptiform (N=19), asymmetric background (N=24), generalized slowing (N=51), and generalized periodic discharges with a triphagic wave (N=11). The etiological classifications of the patients with status epilepticus were remote symptomatic (N=4), remote symptomatic with acute precipitant (N=9), acute symptomatic (N=6), progressive encephalopathy (N=2), and febrile seizure (N=1). cEEG monitoring was found to be useful for the diagnosis of non-convulsive epileptic seizures or status epilepticus. The seizure was confirmed by the EEG pattern.

• Journal of Biomedical Engineering Research
• /
• v.18 no.4
• /
• pp.389-396
• /
• 1997

Several types of electrical artifact seen on electroencephalogram( EEG) records are described. Those are the EOG and the PVC roller pump noise, and so on. An adaptive digital filtering of the electroencephalogram( EEG) is a successful way of suppressing mains interference, but it affects some of the frequency components of the signal, whore artifacts may not be acceptable in some cafes of automatic EEG processing. Thus we studied the method for cancelling these artifacts. This proposed method does not use the reference channel, and is realized by connecting the linear predictor and the fixed FIR filter for the EOG artifact, and by cascading the linear predictor and the noise canceller for the pump artifact. The simulation results illustrate the performances of the proposed method in terms of the capability of interferences suppression. In the results we obtained about 20 dB noise reduction.

• 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.