• Journal of Electrical Engineering and Technology
• /
• v.9 no.3
• /
• pp.1060-1071
• /
• 2014

Signals of the Electroencephalogram (EEG) can reflect the electrical background activity of the brain generated by the cerebral cortex nerve cells. This has been the mostly utilized signal, which helps in effective analysis of brain functions by supervised learning methods. In this paper, an approach for improving the accuracy of EEG signal classification is presented to detect epileptic seizures. Moreover, Independent Component Analysis (ICA) is incorporated as a preprocessing step and Short Time Fourier Transform (STFT) is used for denoising the signal adequately. Feature extraction of EEG signals is accomplished on the basis of three parameters namely, Standard Deviation, Correlation Dimension and Lyapunov Exponents. The Artificial Neural Network (ANN) is trained by incorporating Levenberg-Marquardt(LM) training algorithm into the backpropagation algorithm that results in high classification accuracy. Experimental results reveal that the methodology will improve the clinical service of the EEG recording and also provide better decision making in epileptic seizure detection than the existing techniques. The proposed EEG signal classification using feed forward Backpropagation Neural Network performs better than to the EEG signal classification using Adaptive Neuro Fuzzy Inference System (ANFIS) classifier in terms of accuracy, sensitivity, and specificity.

• Molecules and Cells
• /
• v.37 no.9
• /
• pp.650-655
• /
• 2014

Mesenchymal stem cells (MSCs) can differentiate into neural cells to treat nervous system diseases. Magnetic resonance is an ideal means for cell tracking through labeling cells with superparamagnetic iron oxide (SPIO). However, no studies have described the neural differentiation ability of SPIO-labeled MSCs, which is the foundation for cell therapy and cell tracking in vivo. Our results showed that bone marrow-derived mesenchymal stem cells (BM-MSCs) labeled in vitro with SPIO can be induced into neural-like cells without affecting the viability and labeling efficiency. The cellular uptake of SPIO was maintained after labeled BM-MSCs differentiated into neural-like cells, which were the basis for transplanted cells that can be dynamically and non-invasively tracked in vivo by MRI. Moreover, the SPIO-labeled induced neural-like cells showed neural cell morphology and expressed related markers such as NSE, MAP-2. Furthermore, whole-cell patch clamp recording demonstrated that these neural-like cells exhibited electrophysiological properties of neurons. More importantly, there was no significant difference in the cellular viability and $[Ca^{2+}]_i$ between the induced labeled and unlabeled neural-like cells. In this study, we show for the first time that SPIO-labeled MSCs retained their differentiation capacity and could differentiate into neural-like cells with high cell viability and a good cellular state in vitro.

• Annals of Clinical Neurophysiology
• /
• v.1 no.2
• /
• pp.160-167
• /
• 1999

Although somatosensory evoked potentials(SSEPs) have been utilized as the useful diagnostic tools in evaluating the wide variety of pathological conditions, such as focal lesions affecting the somatosensory pathways, demyelinating diseases, and detecting the clinically occult abnormality, their neural generators is still considerably uncertain. To appreciate the basis for uncertainties about the origins of SSEPs, consider criteria that must be met to establish a causal relationship between activity in a neural structure and a spine/ scalp-recorded potential. Electrode locations and channel derivations for SSEPs recordings are based on two principles:(1) the waveforms are best recorded from electrode sites on the body surface closest to the presumed generator sources along the somatosensory pathways, and(2) studies of the potential-field distribution of each waveform of interest dictate the best techniques to be used. In this article, authors will describe followings focused on ;(1) the concepts of near field potentials(NFPs) and far field potentials(FFPs) - the voltage of NFPs is highly dependent upon recording electrode position, FFPs are unlike NFPs in that they are widely distributed, their latencies and amplitudes are independent of recording electrode.(2) appropriate montage settings to detect the significant potentials in the median nerve and posterior tibial nerve SSEPs(3) neural generators of various potentials(P9, N13, P14, N18, N20, P37) and their clinical significance in interpretating the results of SSEPs. Especially, Characteristics of N18(longduration, small superimposed inflection) suggested that N18 is a complex wave with multiple generators including brainstem structures and thalamic nuclei. And N18 might be used as the parameter of braindeath. Precise understanding on these facts provide an adequate basis utilizing SSEPs for numerous clinical purposes.

• Journal of the Korean Society for Precision Engineering
• /
• v.22 no.5 s.170
• /
• pp.80-86
• /
• 2005

Optical performance evaluation results and an interference fringe pattern analysis of alignment errors for an optical head of a near-field receding (NFR) system are presented. The focusing unit is an optical head of a NFR system and is composed of a solid immersion lens (SIL) and an objective lens (OL). Generally, the size of the focusing unit is smaller than that of the conventional optical recording head. Hence there are difficulties to assemble the small focusing unit precisely. We composed an evaluation system with an interferometer and evaluated some focusing unit samples aligned and assembled by manual and present the obtained results. Using the conventional optical tool, Code V, a tolerance analysis of the alignment error between the SIL and the objective lens and an interference pattern analysis for the assembly error are executed. Then, through an analysis of the simulation results, the conceptual auto-alignment methodology using a neural network approach is considered.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.11
• /
• pp.31-34
• /
• 1997

A semiconductor microelectrode array has been successfully used in obtaining single unit recordings from medial giant nerve of clay fish, rat saphenous nerve and abdominal ganglia of aplysia. The recording device fabricated using silicon microfabrication techniques is a depth-probe type and, previously, has been mostly used to record from central nerve system of vertebrates. From invertebrates, and also from peripheral nerves of vertebrates, however, the quality of the recorded signal depends heavily on the recording conditions, such as the proximity of the electrode site to the nerve cells and the size of the neuron. We have modeled the signal to noise ratio as unctions of these parameters and compared the experimental data with the calculated values thus obtained.

• Journal of Web Engineering
• /
• v.21 no.2
• /
• pp.497-522
• /
• 2021

Audio event classification refers to the detection and classification of non-verbal signals, such as dog and horn sounds included in audio data, by a computer. Recently, deep neural network technology has been applied to audio event classification, exhibiting higher performance when compared to existing models. Among them, a convolutional neural network (CNN)-based training method that receives audio in the form of a spectrogram, which is a two-dimensional image, has been widely used. However, audio event classification has poor performance on test data when it is recorded by a device (unknown device) different from that used to record training data (known device). This is because the frequency range emphasized is different for each device used during recording, and the shapes of the resulting spectrograms generated by known devices and those generated by unknown devices differ. In this study, to improve the performance of the event classification system, a CNN based on the log mel-spectrogram separation technique was applied to the event classification system, and the performance of unknown devices was evaluated. The system can classify 16 types of audio signals. It receives audio data at 0.4-s length, and measures the accuracy of test data generated from unknown devices with a model trained via training data generated from known devices. The experiment showed that the performance compared to the baseline exhibited a relative improvement of up to 37.33%, from 63.63% to 73.33% based on Google Pixel, and from 47.42% to 65.12% based on the LG V50.

• Journal of Sensor Science and Technology
• /
• v.24 no.1
• /
• pp.22-28
• /
• 2015

This study demonstrates a polyimide nerve cuff electrode with a conductive polymer for improving recording signal quality at peripheral nerve. The nerve cuff electrodes with platinum (Pt), iridium oxide (IrOx), and poly(3,4-ethylenedioxythiophene): p-toluene sulfonate (PEDOT:pTS) were fabricated and investigated their electrical characteristics for improving recorded nerve signal quality. The fabricated nerve cuff electrodes with Pt, IrOx, and PEDOT:pTS were characterized their impedance and CDC by using electrochemical impedance spectroscopy (EIS) and cyclic voltammetry. The impedance of PEDOT:pTS measured at 1 kHz was $257{\Omega}$, which was extremely lower than the value of the nerve cuff electrodes with IrOx ($15897{\Omega}$) and Pt ($952{\Omega}$), respectively. Furthermore, the charge delivery capacity (CDC) of the nerve cuff electrode with PEDOT:pTS was dramatically increased to 62 times than the nerve cuff electrode with IrOx. In ex-vivo test using extracted sciatic nerve of spaque-dawley rat (SD rat), the PEDOT:pTS group exhibited higher signal-to-interference ratio than IrOx group. These results indicated that the nerve cuff electrode with PEDOT:pTS is promising for effective implantable nerve signal recording.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.5
• /
• pp.568-573
• /
• 2019

In the diagnosis of pulmonary diseases, auscultation technique is simpler than the other methods, and lung sounds can be used for predicting the types of pulmonary diseases as well as identifying patients with pulmonary diseases. Therefore, in this paper, we identify patients with pulmonary diseases and classify lung sounds according to their sound characteristics using various convolutional neural networks, and compare the classification performance of each neural network method. First, lung sounds over affected areas of the chest with pulmonary diseases are collected by using a single-channel lung sound recording device, and spectral features are extracted from the collected sounds in time domain and applied to each neural network. As classification methods, we use general, parallel, and residual convolutional neural network, and compare lung sound classification performance of each neural network through experiments.

• Computers and Concrete
• /
• v.25 no.5
• /
• pp.433-445
• /
• 2020

A method is proposed in this paper to estimate the workability of self-compacting concrete (SCC) in different mixing conditions with different mixers and mixing volumes by recording the mixing process based on deep learning (DL). The SCC mixing videos were transformed into a series of image sequences to fit the DL model to predict the SF and VF values of SCC, with four groups in total and approximately thirty thousand image sequence samples. The workability of three groups SCC whose mixing conditions were learned by the DL model, was estimated. One additionally collected group of the SCC whose mixing condition was not learned, was also predicted. The results indicate that whether the SCC mixing condition is included in the training set and learned by the model, the trained model can estimate SCC with different workability effectively at the same time. Our goal to estimate SCC workability in different mixing conditions is achieved.

• Korean Journal of Acupuncture
• /
• v.35 no.4
• /
• pp.187-202
• /
• 2018

Objectives : Non-invasive transcranial electrical stimulation is one of therapeutic interventions to change in neural excitability of the cortex. Transcranial electro-acupuncture (TEA) can modulate brain functions through changes in cortical excitability as a model of non-invasive transcranial electrical stimulation. Some composites of fermented Scutellaria baicalenis (FSB) can activate intercellular signaling pathways for activation of brain-derived neurotrophic factor that is critical for formation of neural plasticity in stroke patients. This study was aimed at evaluation of combinatory treatment of TEA and FSB on behavior recovery and cortical neural excitability in rodent focal stroke model. Methods : Focal ischemic stroke was induced by photothrombotic injury to the motor cortex of adult rats. Application of TEA with 20 Hz and $200{\mu}A$ in combination with daily oral treatment of FBS was given to stroke animals for 3 weeks. Motor recovery was evaluated by rotating bean test and ladder working test. Electrical activity of cortical pyramidal neurons of stroke model was evaluated by using multi-channel extracellular recording technique and thallium autometallography. Results : Compared with control stroke group who did not receive any treatment, Combination of TEA and FSB treatment resulted in more rapid recovery of forelimb movement following focal stroke. This combination treatment also elicited increase in spontaneous firing rate of putative pyramidal neurons. Furthermore expression of metabolic marker for neural excitability was upregulated in peri-infract area under thallium autometallography. Conclusions : These results suggest that combination treatment of TEA and FSB can be a possible remedy for motor recovery in focal stroke.