Jongin Kim

Electronic system with memristive synapses for pattern recognition

Memristive synapses, the most promising passive devices for synaptic interconnections in artificial neural networks, are the driving force behind recent research on hardware neural networks. Despite significant efforts to utilize memristive synapses, progress to date has only shown the possibility of building a neural network system that can classify simple image patterns. In this article, we report a high-density cross-point memristive synapse array with improved synaptic characteristics. The proposed PCMO-based memristive synapse exhibits the necessary gradual and symmetrical conductance changes, and has been successfully adapted to a neural network system. The system learns, and later recognizes, the human thought pattern corresponding to three vowels, i.e. /a /, /i /, and /u/, using electroencephalography signals generated while a subject imagines speaking vowels. Our successful demonstration of a neural network system for EEG pattern recognition is likely to intrigue many researchers and stimulate a new research direction.

EEG classification in a single-trial basis for vowel speech perception using multivariate empirical mode decomposition

OBJECTIVE The objective of this study is to find components that might be related to phoneme representation in the brain and to discriminate EEG responses for each speech sound on a trial basis. APPROACH We used multivariate empirical mode decomposition (MEMD) and common spatial pattern for feature extraction. We chose three vowel stimuli, /a/, /i/ and /u/, based on previous findings, such that the brain can detect change in formant frequency (F2) of vowels. EEG activity was recorded from seven native Korean speakers at Gwangju Institute of Science and Technology. We applied MEMD over EEG channels to extract speech-related brain signal sources, and looked for the intrinsic mode functions which were dominant in the alpha bands. After the MEMD procedure, we applied the common spatial pattern algorithm for enhancing the classification performance, and used linear discriminant analysis (LDA) as a classifier. MAIN RESULTS The brain responses to the three vowels could be classified as one of the learned phonemes on a single-trial basis with our approach. SIGNIFICANCE The results of our study show that brain responses to vowels can be classified for single trials using MEMD and LDA. This approach may not only become a useful tool for the brain-computer interface but it could also be used for discriminating the neural correlates of categorical speech perception.

A Real-Time Pinch-to-Zoom Motion Detection by Means of a Surface EMG-Based Human-Computer Interface

In this paper, we propose a system for inferring the pinch-to-zoom gesture using surface EMG (Electromyography) signals in real time. Pinch-to-zoom, which is a common gesture in smart devices such as an iPhone or an Android phone, is used to control the size of images or web pages according to the distance between the thumb and index finger. To infer the finger motion, we recorded EMG signals obtained from the first dorsal interosseous muscle, which is highly related to the pinch-to-zoom gesture, and used a support vector machine for classification between four finger motion distances. The powers which are estimated by Welchs method were used as feature vectors. In order to solve the multiclass classification problem, we applied a one-versus-one strategy, since a support vector machine is basically a binary classifier. As a result, our system yields 93.38% classification accuracy averaged over six subjects. The classification accuracy was estimated using 10-fold cross validation. Through our system, we expect to not only develop practical prosthetic devices but to also construct a novel user experience (UX) for smart devices.

EEG-Based Prediction of Epileptic Seizures Using Phase Synchronization Elicited from Noise-Assisted Multivariate Empirical Mode Decomposition

In this study, we examined the phase locking value (PLV) for seizure prediction, particularly, in the gamma frequency band. We prepared simulation data and 65 clinical cases of seizure. In addition, various filtering algorithms including bandpass filtering, empirical mode decomposition, multivariate empirical mode decomposition and noise-assisted multivariate empirical mode decomposition (NA-MEMD) were used to decompose spectral components from the data. Moreover, in the case of clinical data, the PLVs were used to classify between interictal and preictal stages using a support vector machine. The highest PLV was achieved with NA-MEMD with 0-dB white noise algorithm (0.9988), which exhibited statistically significant differences compared to other filtering algorithms. Moreover, the classification rate was the highest for the NA-MEMD with 0-dB algorithm (83.17%). In terms of frequency components, examining the gamma band resulted in the highest classification rates for all algorithms, compared to other frequency bands such as theta, alpha, and beta bands. We found that PLVs calculated with the NA-MEMD algorithm could be used as a potential biological marker for seizure prediction. Moreover, the gamma frequency band was useful for discriminating between interictal and preictal stages.

Vowel Imagery Decoding toward Silent Speech BCI Using Extreme Learning Machine with Electroencephalogram

The purpose of this study is to classify EEG data on imagined speech in a single trial. We recorded EEG data while five subjects imagined different vowels, /a/, /e/, /i/, /o/, and /u/. We divided each single trial dataset into thirty segments and extracted features (mean, variance, standard deviation, and skewness) from all segments. To reduce the dimension of the feature vector, we applied a feature selection algorithm based on the sparse regression model. These features were classified using a support vector machine with a radial basis function kernel, an extreme learning machine, and two variants of an extreme learning machine with different kernels. Because each single trial consisted of thirty segments, our algorithm decided the label of the single trial by selecting the most frequent output among the outputs of the thirty segments. As a result, we observed that the extreme learning machine and its variants achieved better classification rates than the support vector machine with a radial basis function kernel and linear discrimination analysis. Thus, our results suggested that EEG responses to imagined speech could be successfully classified in a single trial using an extreme learning machine with a radial basis function and linear kernel. This study with classification of imagined speech might contribute to the development of silent speech BCI systems.

Prediction and early detection of delirium in the intensive care unit by using heart rate variability and machine learning

OBJECTIVE Delirium is an important syndrome found in patients in the intensive care unit (ICU), however, it is usually under-recognized during treatment. This study was performed to investigate whether delirious patients can be successfully distinguished from non-delirious patients by using heart rate variability (HRV) and machine learning. APPROACH Electrocardiography data of 140 patients was acquired during daily ICU care, and HRV data were analyzed. Delirium, including its type, severity, and etiologies, was evaluated daily by trained psychiatrists. HRV data and various machine learning algorithms including linear support vector machine (SVM), SVM with radial basis function (RBF) kernels, linear extreme learning machine (ELM), ELM with RBF kernels, linear discriminant analysis, and quadratic discriminant analysis were utilized to distinguish delirium patients from non-delirium patients. MAIN RESULTS HRV data of 4797 ECGs were included, and 39 patients had delirium at least once during their ICU stay. The maximum classification accuracy was acquired using SVM with RBF kernels. Our prediction method based on HRV with machine learning was comparable to previous delirium prediction models using massive amounts of clinical information. SIGNIFICANCE Our results show that autonomic alterations could be a significant feature of patients with delirium in the ICU, suggesting the potential for the automatic prediction and early detection of delirium based on HRV with machine learning.

Identification of Alzheimer's disease and mild cognitive impairment using multimodal sparse hierarchical extreme learning machine

Different modalities such as structural MRI, FDG‐PET, and CSF have complementary information, which is likely to be very useful for diagnosis of AD and MCI. Therefore, it is possible to develop a more effective and accurate AD/MCI automatic diagnosis method by integrating complementary information of different modalities. In this paper, we propose multi‐modal sparse hierarchical extreme leaning machine (MSH‐ELM). We used volume and mean intensity extracted from 93 regions of interest (ROIs) as features of MRI and FDG‐PET, respectively, and used p‐tau, t‐tau, and Aβ42 as CSF features. In detail, high‐level representation was individually extracted from each of MRI, FDG‐PET, and CSF using a stacked sparse extreme learning machine auto‐encoder (sELM‐AE). Then, another stacked sELM‐AE was devised to acquire a joint hierarchical feature representation by fusing the high‐level representations obtained from each modality. Finally, we classified joint hierarchical feature representation using a kernel‐based extreme learning machine (KELM). The results of MSH‐ELM were compared with those of conventional ELM, single kernel support vector machine (SK‐SVM), multiple kernel support vector machine (MK‐SVM) and stacked auto‐encoder (SAE). Performance was evaluated through 10‐fold cross‐validation. In the classification of AD vs. HC and MCI vs. HC problem, the proposed MSH‐ELM method showed mean balanced accuracies of 96.10% and 86.46%, respectively, which is much better than those of competing methods. In summary, the proposed algorithm exhibits consistently better performance than SK‐SVM, ELM, MK‐SVM and SAE in the two binary classification problems (AD vs. HC and MCI vs. HC).

Changes in heart rate variability of patients with delirium in intensive care unit

Delirium is an important syndrome in intensive care unit (ICU) patients, however, its characteristics are still unclear. Many evidences showed that this syndrome can be related to the autonomic instability. In this study, we aimed to investigate the possible alterations of autonomic nervous system (ANS) in delirium patients in ICU. Electrocardiography (ECG) of every ICU patient was measured during routine daily ICU care, and the data were gathered to evaluate the heart rate variability (HRV). HRV of total 60 patients were analyzed in time, frequency and non-linear domains. As a result, we found that heart rates of delirium patients were more variable and irregular than non-delirium patients. These findings may facilitate early detection and prevention of delirium in ICU.Delirium is an important syndrome in intensive care unit (ICU) patients, however, its characteristics are still unclear. Many evidences showed that this syndrome can be related to the autonomic instability. In this study, we aimed to investigate the possible alterations of autonomic nervous system (ANS) in delirium patients in ICU. Electrocardiography (ECG) of every ICU patient was measured during routine daily ICU care, and the data were gathered to evaluate the heart rate variability (HRV). HRV of total 60 patients were analyzed in time, frequency and non-linear domains. As a result, we found that heart rates of delirium patients were more variable and irregular than non-delirium patients. These findings may facilitate early detection and prevention of delirium in ICU.

EEG classification of word perception using common spatial pattern filter

The purpose of this study is to classify perceptual electroencephalography (EEG) data of words into appropriate class. We recorded EEG data from six native Korean speakers at Gwangju Institute of Science and Technology. Three words (/Lemon/, /Mother/, and /Toilet/) were chosen for stimuli. We applied IIR bandpass filter for extracting alpha bands activities from raw EEG data and common spatial pattern filter to enhance classification performance. We used pairwise classification method and mean classification rates corresponding to /Lemon/ vs /Mother/, /Lemon/ vs /Toilet/, and /Mother/ vs /Toilet/ were 54.31 ± 4.31, 59.66 ± 3.11, and 59.88 ± 5.70 respectively for all the subjects.

Classifying the speech response of the brain using Gaussian hidden markov model (HMM) with independent component analysis (ICA)

The purpose of this paper is to determine whether electroencephalograpy (EEG) can be used as a tool for hearing impairment tests such as hearing screening. For this study, we recorded EEG responses to two syllables, /a/ and /u/, in Korean from three subjects at Gwangju Institute of Science and Technology. The ultimate goal of this study is to classify speech sound data regardless of their size using EEG; however, as an initial stage of the study, we classified only two different speech syllables using Gaussian hidden markov model. The result of this study shows a possibility that EEG could be used for hearing screening and other diagnostic tools related to speech perception.