• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.7
• /
• pp.779-785
• /
• 2019

By applying an ergonomically developed Bismuth shield to the endovascular treatment of cerebral aneurysm the radiation dose of the scalp and lens from the medical radiation exposure was reduced. The enrtance surface dose was analyzed by measuring the occipital parts, bilateral temporal parts, bilateral quadriceps, and nasal tip of the developed bismuth shield using a photostimulable fluorescence dosimeter before (Group A) before use (Group B). Signal to noise ratio (SNR) and contrast to noise ratio (CNR) analysis were used to evaluate the image quality when Bismuth shielding was used. The mean entrance surface dose of A group and B group was 26.92% lower than that of A group. The analysis of CNR and SNR was the same for both Roadmap and DSA. The use of Bismuth shielding is an alternative that can reduce the radiation impairment due to temporary hair loss and other stochastic effects that may occur after cerebrovascular intervention.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.6
• /
• pp.1-8
• /
• 2005

In this paper, we propose a two-stage head tracking algorithm adequate for real-time active camera system having pan-tilt-zoom functions. In the color convergence stage, we first assume that the shape of a head is an ellipse and its model color histogram is acquired in advance. Then, the min-shift method is applied to roughly estimate a target position by examining the histogram similarity of the model and a candidate ellipse. To reflect the temporal change of object color and enhance the reliability of mean-shift based tracking, the target histogram obtained in the previous frame is considered to update the model histogram. In the updating process, to alleviate error-accumulation due to outliers in the target ellipse of the previous frame, the target histogram in the previous frame is obtained within an ellipse adaptively shrunken on the basis of the model histogram. In addition, to enhance tracking reliability further, we set the initial position closer to the true position by compensating the global motion, which is rapidly estimated on the basis of two 1-D projection datasets. In the subsequent stage, we refine the position and size of the ellipse obtained in the first stage by using shape information. Here, we define a robust shape-similarity function based on the gradient direction. Extensive experimental results proved that the proposed algorithm performs head hacking well, even when a person moves fast, the head size changes drastically, or the background has many clusters and distracting colors. Also, the propose algorithm can perform tracking with the processing speed of about 30 fps on a standard PC.

• Journal of Sericultural and Entomological Science
• /
• v.46 no.2
• /
• pp.77-79
• /
• 2004

To investigate whether BF-7, extracted from Bombyx mori, improved learning and memory of ordinary people, K-WAIS (Korean version of Wechsler adult intelligence scale) was performed in 4 normal students. Treatment with 400 mg of BF-7 increased mean IQ from 103 to 114. To know how BF-7 plays such a positive role, we measured the blood flow to brain, especially for the area concerned with learning and memory, with Single Photon Emission Computed Tomography(SPECT). Our result showed that the blood flow to parahippocampal gyrus and medial temporal area was increased. Also, our results showed the image representing the increase of blood supply in this area. So, our results suggest that BF-7 effectively help to use brain concerning with learning and memory.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.23 no.2
• /
• pp.70-82
• /
• 2020

Recently, a lot of damages have been caused by urban flooding, and heavy rainfall that temporarily occur are the main causes of these phenomenons. The damages caused by urban flooding are identified as the change in the water balance in urban areas. To indirectly identify it, this research analyzed the change in the remote sensing indices on each land cover before and after heavy rainfall by utilizing daily precipitation data and multi-temporal Sentinel-2 satellite imagery. Cases of heavy rain advisory and warning were selected based on the daily precipitation data. And statistical fluctuation were compared by acquiring Sentinel-2 satellite images during the corresponding period and producing them as NDVI, NDWI and NDMI images about each land cover with a radius of 1,000 m based on the Seoul Weather Station. As a result of analyzing the maximum value, minimum value, mean and fluctuation of the pixels that were calculated in each remote sensing index image, there was no significant changes in the remote sensing indices in urban areas before and after heavy rainfall.

• Korean Journal of Clinical Laboratory Science
• /
• v.47 no.1
• /
• pp.46-50
• /
• 2015

The previous studies showed that the visual imagery activated the occipital and posterior inferior temporal area of the brain, and the damage to the occipital cortex impaired the visual mental imagery. We studied current-source distribution of electroencephalography (EEG) to observe neuronal activity during imagery tennis playing. Eleven healthy volunteers were enrolled. All volunteers were right-handed males and novices for tennis playing. The mean age of them was 24.9 years. The EEGs were recorded on the scalp electrodes located according to the International 10~20 System. The number of electrodes was 25 channels including subtemporal electrodes. The EEG recording session was 13 min including 5 segments: resting-I, scenery-slide show, resting-II, watching tennis-game video, and imagery-tennis playing. The recoding durations were 3, 2, 3, 2, and 3 min respectively. Five 'artifact free 3-sec segments' were selected in each segment of 'imagery-tennis playing' and 'resting-II'. We did the frequency domain analysis with the EEG segments using a distributed model of current-source analysis. The statistical-nonparametric maps (SnPMs) were obtained between the segments of 'imagery-tennis playing' and the segments of 'resting-II' (p<0.01). The significant change of current-source density was observed only in alpha-2 frequency band (10~12 Hz). The current-sourcedensity was increased in the hippocampus, parahippocampus, and occipital fusiform gyrus in the right cerebral hemisphere (p<0.01). Imaginary-tennis playing may activate the hippocampal-occipital alpha networks of nondominant hemisphere.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.6
• /
• pp.536-542
• /
• 2023

Satellites represent cutting-edge technology, of ering significant advantages in spatial and temporal observations. National agencies worldwide harness satellite data to respond to marine accidents and analyze ocean fluctuations effectively. However, challenges arise with high-resolution satellite-based sea surface temperature data (Operational Sea Surface Temperature and Sea Ice Analysis, OSTIA), where gaps or empty areas may occur due to satellite instrumentation, geographical errors, and cloud cover. These issues can take several hours to rectify. This study addressed the issue of missing OSTIA data by employing LaMa, the latest deep learning-based algorithm. We evaluated its performance by comparing it to three existing image processing techniques. The results of this evaluation, using the coefficient of determination (R²) and mean absolute error (MAE) values, demonstrated the superior performance of the LaMa algorithm. It consistently achieved R² values of 0.9 or higher and kept MAE values under 0.5 ℃ or less. This outperformed the traditional methods, including bilinear interpolation, bicubic interpolation, and DeepFill v1 techniques. We plan to evaluate the feasibility of integrating the LaMa technique into an operational satellite data provision system.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.3
• /
• pp.223-235
• /
• 2020

In this study, we propose an approach for calibrating the elevation of a DEM (Digital Elevation Model), one of the key data in realizing unmanned aerial vehicle image-based precision agriculture. First of all, radiometric correction is performed on the orthophoto, and then ExG (Excess Green) is generated. The non-vegetation area is extracted based on the threshold value estimated by applying the Otsu method to ExG. Subsequently, the elevation of the DEM corresponding to the location of the non-vegetation area is extracted as EIFs (Elevation Invariant Features), which is data for elevation correction. The normalized Z-score is estimated based on the difference between the extracted EIFs to eliminate the outliers. Then, by constructing a linear regression model and correcting the elevation of the DEM, high-quality DEM is produced without GCPs (Ground Control Points). To verify the proposed method using a total of 10 DEMs, the maximum/minimum value, average/standard deviation before and after elevation correction were compared and analyzed. In addition, as a result of estimating the RMSE (Root Mean Square Error) by selecting the checkpoints, an average RMSE was derivsed as 0.35m. Comprehensively, it was confirmed that a high-quality DEM could be produced without GCPs.

• The Korean Journal of Nuclear Medicine
• /
• v.36 no.2
• /
• pp.91-101
• /
• 2002

Purpose : The aim of this study was to identify the brain areas in which reductions of regional cerebral blood flow (rCBF) were correlated with decline of general mental function, measured by Mini-Mental State Examination (MMSE). Materials and Methods : Tc-99m HMPAO brain SPECT was peformed in 9 probable AD patients at the initial and follow-up periods of 1.8 years (average) after the first study. MMSE scores were also measured in both occasions. The mean MMSE score of the initial study 16.4 (range: 5 - 24) and the mean MMSE score of the follow-up was 8.1 (range: 0 - 17). Each SPECT image was normalized to the cerebellar activity and a correlation analysis was peformed between the level of rCBF in AD patients and the MMSE scores by voxel-based analysis using SPM99 software. Results : Significant correlation was found between the blood-flow decrease in left inferior prefrontal region (BA 47) and left middle temporal legion (BA 21) and the MMSE score changes. Additional areas such as anterior and posterior cingulate cortices, precuneus, and bilateral superior and middle prefrontal regions showed the similar trends. Conclusions : A relationship was found between reduction of regional cerebral blood flow in left prefrontal and temporal areas and decline of cognitive function in Alzheimer's disease(AD) patients. This voxel-based analysis is useful in evaluating the progress of cognitive function in Alzheimer's disease.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.4
• /
• pp.110-122
• /
• 2014

As multimedia technologies develop, three-dimensional (3D) technologies are attracting increasing attention from researchers. In particular, video quality assessment (VQA) has become a critical issue in stereoscopic image/video processing applications. Furthermore, a human visual system (HVS) could play an important role in the measurement of stereoscopic video quality, yet existing VQA methods have done little to develop a HVS for stereoscopic video. We seek to amend this by proposing a 3D visual attention (3DVA) model which simulates the HVS for stereoscopic video by combining multiple perceptual stimuli such as depth, motion, color, intensity, and orientation contrast. We utilize this 3DVA model for pooling on significant regions of very poor video quality, and we propose no-reference (NR) stereoscopic VQA (SVQA) method. We validated the proposed SVQA method using subjective test scores from our results and those reported by others. Our approach yields high correlation with the measured mean opinion score (MOS) as well as consistent performance in asymmetric coding conditions. Additionally, the 3DVA model is used to extract information for the region-of-interest (ROI). Subjective evaluations of the extracted ROI indicate that the 3DVA-based ROI extraction outperforms the other compared extraction methods using spatial or/and temporal terms.