• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.10
• /
• pp.887-895
• /
• 2014

Drowsy driving is a large proportion of the total car accidents. For this reason, drowsiness detection and warning system for drivers has recently become a very important issue. Monitoring physiological signals provides the possibility of detecting features of drowsiness and fatigue of drivers. Many researches have been published that to measure electroencephalogram(EEG) signals is the effective way in order to be aware of fatigue and drowsiness of drivers. The aim of this study is to extract drowsiness-related features from a set of EEG signals and to classify the features into three states: alertness, transition, and drowsiness. This paper proposes a drowsiness detection system using errors-in-variables(EIV) for extraction of feature vectors and multilayer perceptron (MLP) for classification. The proposed method evaluates robustness for noise and compares to the previous one using linear predictive coding (LPC) combined with MLP. From evaluation results, we conclude that the proposed scheme outperforms the previous one in the low signal-to-noise ratio regime.

• Korean Journal of Remote Sensing
• /
• v.14 no.4
• /
• pp.325-342
• /
• 1998

Two RADARSAT SAR images with different modes acquired by Canadian Space Agency to test the effectiveness of geological lineament extraction and spring water detection over the Cheju Island. Geological lineaments are poorly developed this basalt dominant volcanic island, but more linear features can be extracted when SAR and TM images are simultaneously analyzed than when TM image alone is used. This results mainly owe to the facts that RADARSAT SAR systems are able to provide data with different frequencies, azimuth, and incidence angles. Distribution of spring water along coast is poorly correlated with geological lineaments or drainage pattern, but those in middle range of mountain region are developed along geological lineaments. Detection of spring water using remotely sensed images are turned out to be very difficult to achieve. Radial shaped sea surface temperature anomaly derived from TM thermal band should be the best candidate for spring water, but the resolution is not high enough. We also investigate the normalized radar cross section (or sigma naught) converted from RADARSAT and ERS-1 SAR data but to discriminate the spring water effectively except where relatively large water mass is observed on land side. Speckle noise and irregularity in physical sea surface condition are the serious obstacles for this application. ERS-1 SAR image acquired in low incidence angle was more useful for geological lineament estimation and water body study than RADARSAT SAR images with high incidence angles. Therefore the selection of incidence angle is critical in geological and spring water applications of SAR images, and low incidence angles less than about 30$^{\circ}$ are recommended to monitor the Cheju volcanic island.

• Journal of Radiation Protection and Research
• /
• v.29 no.4
• /
• pp.257-261
• /
• 2004

A coded-aperture gamma camera was developed to increase the sensitivity of a pin hole camera made with a pixellated CsI(Tl) scintillator and a position-sensitive photomultiplier tube. The modified round-hole uniformly redundant array of pixel size $13{\times}11$ was chosen as a coded mask considering the detector spatial resolution. The performance of the coded-aperture camera was compared with the pin hole camera using various forms of Tc-99m source to see the improvement of signal-to-noise ratio or the improvement of the sensitivity. The image quality is much improved despite of a slight degradation of the spatial resolution. Though the camera and the test were made for low energy case, but the concept of the coded-aperture gamma camera could be effectively used for the radioactive environmental monitoring and other applications.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.4
• /
• pp.543-548
• /
• 2021

The higher the resolution of the image, the higher the satisfaction of the viewers of the image, and the super-resolution imaging has a considerable increase in research value among the fields of computer vision and image processing. In this study, the main features of low-resolution image LR are extracted mainly using deep learning super-resolution models. It learns and reconstructs the extracted features, and focuses on reconstruction-based algorithms that generate high-resolution image HR. In this paper, we investigate SRCNN and VDSR in a super-resolution algorithm model based on reconstruction. The structure and algorithm process of the SRCNN and VDSR model are briefly introduced, and the multi-channel and special form are also examined in the improved performance evaluation function, and understand the performance of each algorithm through experiments. In the experiment, an experiment was performed to compare the results of the SRCNN and VDSR models with the peak signal-to-noise ratio and image structure similarity, so that the results can be easily judged.

• Journal of the Korean Society of Radiology
• /
• v.14 no.3
• /
• pp.211-220
• /
• 2020

High-quality computed tomography (CT) images enable precise lesion detection and accurate diagnosis. A lot of studies have been performed to improve CT image quality while reducing radiation dose. Recently, deep learning-based techniques for improving CT image quality have been developed and show superior performance compared to conventional techniques. In this study, a super-resolution convolutional neural network (SRCNN) model was used to improve the spatial resolution of CT images, and image quality according to the hyperparameters, which determine the performance of the SRCNN model, was evaluated in order to verify the effect of hyperparameters on the SRCNN model. Profile, structural similarity (SSIM), peak signal-to-noise ratio (PSNR), and full-width at half-maximum (FWHM) were measured to evaluate the performance of the SRCNN model. The results showed that the performance of the SRCNN model was improved with an increase of the numbers of epochs and training sets, and the learning rate needed to be optimized for obtaining acceptable image quality. Therefore, the SRCNN model with optimal hyperparameters is able to improve CT image quality.

• Journal of the Korean Society of Radiology
• /
• v.18 no.1
• /
• pp.27-36
• /
• 2024

In this study, When acquisition thyroid scintigraphy images, a parallel hole collimator was applied, and the difference from the pinhole collimator was quantitatively analyzed under each image acquisition condition. Visual size, resolution, sensitivity, signal to noise ratio (SNR), and contrast to noise ratio (CNR) were evaluated using thyroid phantom and point source. When comparing visual size, it was confirmed that an image similar to the size of the pinhole collimator could be obtained only when a magnification ratio of about 2.00 to 2.09 times when applying a parallel hole collimator. There was no tendency in FWHM(mm) measurement using a point source, and sensitivity was high in the parallel hole collimator. SNR and CNR were high when using a low magnification ratio, matrix size of 128×128, and a parallel hole collimator. In images of similar size to the naked eye, when the matrix size was the same, both SNR and CNR were high in the pinhole collimator. Therefore, when performing a thyroid scintigraphy test, if appropriate conditions are set according to the situation of each hospital and a parallel hole collimator is applied, it can be a good option in terms of equipment utilization and work efficiency.

• Geophysics and Geophysical Exploration
• /
• v.14 no.4
• /
• pp.289-297
• /
• 2011

Chirp sub-bottom profilers (SBP) data are comparatively higher-resolution data than other seismic data and it's raw signal can be used as a final section after conducting basic filtering. However, Chirp SBP signal has possibility to include various noise in high-frequency band and to provide the distorted image for the complex geological structure in time domain. This study aims at the goal to establish the workflow of Chirp SBP data processing for enhanced image and to analyze the proper parameters for the domestic continental shelf. After pre-processing, we include the dynamic S/N filtering to eliminate the high-frequency component noise, the dip scan stack to enhance the continuity of reflection events and finally the post-stack depth migration to correct the distorted structure on the time domain sections. We demonstrated our workflow on the data acquired by domestically widely used equipments and then we could obtain the improved seismic sections of depth domain. This workflow seems to provide the proper seismic section to interpretation when applied to data processing of Chirp SBP that are largely used for domestic acquisition.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2002.09a
• /
• pp.67-84
• /
• 2002

A shallow high-resolution seismic reflection survey was carried out at the Mineopo tidal flat on the western coast of Korea. The purpose of the survey was to investigate shallow sedimentary structure of the tidal (fat associated with the recent sea level change. A total of 795 shots were generated at 1 m interval from a 5-kg hammer source and recorded on 48 channels of 100 Hz geophones along two mutually perpendicular profiles. The water-saturated ground condition resulted in suppressed ground rolls by significantly decreasing rigidity. In addition, seismic velocities over 1500 m/s provided easy segregation of reflected arrivals from lower velocity noise. As a consequence, seismic sections were created that are high in resolution and signal to noise ratio as well. The stack sections show that the tidal flat consists of 5 sedimentary sequences above acoustic basement. Although deposition is largely characterized by the transgressive sedimentary facies resulting from sea level rise, erosional surfaces are well-resolved within the sequences.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.9
• /
• pp.2073-2078
• /
• 2014

Based on the DGPS radio wave measurement in the coast of the yellow-sea, south-sea and east-sea, the DGPS service regions in the korean coastal ferry route are analyzed in this paper. The impact of obstacles on the propagation due to the archipelago and island regions are measured and analyzed in the point of service region. The ocean-based DGPS reference stations provide the wide DGPS ocean service regions with signal strength more than $40dB{\mu}V/m$ and signal-to-noise ratio more than 10 dB. Based on the overlapping of the service regions between the DGPS reference stations, the DGPS services with good quality are provided in the coastal ferry route segments. In case of regions where the propagation obstacles are scattered, the increasingly good service can be provided under conditions of output power reinforcement and antenna efficiency enhancement.

• Progress in Medical Physics
• /
• v.26 no.1
• /
• pp.28-35
• /
• 2015

In this study, we investigated the effects of an iterative reconstruction algorithm and an automatic exposure control (AEC) technique on image quality and radiation dose through phantom experiments with coronary computed tomography (CT) angiography protocols. We scanned the AAPM CT performance phantom using 320 multi-detector-row CT. At the tube voltages of 80, 100, and 120 kVp, the scanning was repeated with two settings of the AEC technique, i.e., with the target standard deviations (SD) values of 33 (the higher tube current) and 44 (the lower tube current). The scanned projection data were reconstructed also in two ways, with the filtered back projection (FBP) and with the iterative reconstruction technique (AIDR-3D). The image quality was evaluated quantitatively with the noise standard deviation, modulation transfer function, and the contrast to noise ratio (CNR). More specifically, we analyzed the influences of selection of a tube voltage and a reconstruction algorithm on tube current modulation and consequently on radiation dose. Reduction of image noise by the iterative reconstruction algorithm compared with the FBP was revealed eminently, especially with the lower tube current protocols, i.e., it was decreased by 46% and 38%, when the AEC was established with the lower dose (the target SD=44) and the higher dose (the target SD=33), respectively. As a side effect of iterative reconstruction, the spatial resolution was decreased by a degree that could not mar the remarkable gains in terms of noise reduction. Consequently, if coronary CT angiogprahy is scanned and reconstructed using both the automatic exposure control and iterative reconstruction techniques, it is anticipated that, in comparison with a conventional acquisition method, image noise can be reduced significantly with slight decrease in spatial resolution, implying clinical advantages of radiation dose reduction, still being faithful to the ALARA principle.