• Tuberculosis and Respiratory Diseases
• /
• v.62 no.6
• /
• pp.523-530
• /
• 2007

Background: A ThinPrep$^{(R)}$ Processor was developed to overcome the limitations of conventional cytology and is widely used to diagnose various cancers. This study compared the diagnostic efficacy of conventional cytology for lung cancer with that of the ThinPrep$^{(R)}$ cytology using the bronchial washing fluid. Methods: The bronchial washing fluid of 790 patients from Jan. 2002 to Dec. 2006, who were suspected of gaving a lung malignancy, was evaluated. Both ThinPrep$^{(R)}$ and conventional cytology were performed for all specimens. Result: Four hundred forty-six men and 344 women were enrolled in this study, and 197 of them were diagnosed with cancer from either a bronchoscopic biopsy or a percutaneous needle aspiration biopsy. ThinPrep$^{(R)}$ cytology showed a sensitivity, specificity, positive predictive value, negative predictive value and false negative error rate of 71.1%, 98.0%, 92.1%, 91.1%, 8.9%, respectively. The conventional cytology showed sensitivity, specificity, positive predictive value, nagative predictive value and false negative error rate of 57.9%, 98.0%, 90.5%, 87.5%, 12.5%, respectively. For central lesions, the sensitivity of conventional cytology and ThinPrep$^{(R)}$ were 70.1% and 82.8%, respectively. Conclusion: ThinPrep$^{(R)}$ cytology showed a higher sensitivity and lower false negative error rate than conventional cytology. This result was unaffected by the histological classification of lung cancer. Therefore, ThinPrep$^{(R)}$ cytology appears to be a useful method for increasing the detection rate of lung cancer in bronchial washing cytology test.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.5
• /
• pp.949-959
• /
• 2012

This article is to find the right size of decision trees that performs better for boosting algorithm. First we defined the tree size D as the depth of a decision tree. Then we compared the performance of boosting algorithm with different tree sizes in the experiment. Although it is an usual practice to set the tree size in boosting algorithm to be small, we figured out that the choice of D has a significant influence on the performance of boosting algorithm. Furthermore, we found out that the tree size D need to be sufficiently large for some dataset. The experiment result shows that there exists an optimal D for each dataset and choosing the right size D is important in improving the performance of boosting. We also tried to find the model for estimating the right size D suitable for boosting algorithm, using variables that can explain the nature of a given dataset. The suggested model reveals that the optimal tree size D for a given dataset can be estimated by the error rate of stump tree, the number of classes, the depth of a single tree, and the gini impurity.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.8 no.2
• /
• pp.31-43
• /
• 2005

Four time points of the fractional area data during the 15 years of the highest group of land surface temperature and the lowest group of NDVl of the Kunsan city Chollabuk_do, Korea located beneath the Yellow sea coast, are observed and analyzed their correlations for the intention to detect the changes of urban land cover. As long as the effective contributions of satellite images in the continuous monitoring of the wide area for wide range of time period, Landsat-5 TM and Landsat-7 ETM+ artificial satellite images, acquisited over the Kunsan city area, are surveyed by the compared calibration after quantization and classification of the deviations between TM and ETM+ images substituted approved error correction thresholds such as gains and biases or offsets. This experiment and research applied Landsat-5 TM and Landsat-7 ETM+ artificial satellite images in change detection of urban land cover in urbanized Kunsan city, then detected strong and proportional correlation relationship between the highest group of land surface temperature and the lowest group of NDVI which exceeded R=(+)0.9478, so the proposed Correlation Analysis Model between the highest group of land surface temperature and the lowest group of NDVI will be able to give proof an effective suitability to the land city change detection monitoring.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.5 s.305
• /
• pp.27-34
• /
• 2005

Ventricular fibrillation(VF) is generally caused by chaotic behavior of electrical propagation in heart and may result in sudden cardiac death. In this study, we proposed a ventricular fibrillation detection algorithm based on support vector machine classifier, which could offer benefits to reduce the teaming costs as well as good classification performance. Before the extraction of input features, raw ECG signal was applied to preprocessing procedures, as like wavelet transform based bandpass filtering, R peak detection and segment assignment for feature extraction. We selected input features which of some are related to the rhythm information and of others are related to wavelet coefficients that could describe the morphology of ventricular fibrillation well. Parameters for SVM classifier, C and ${\alpha}$, were chosen as 10 and 1 respectively by trial and error experiments. Each average performance for normal sinus rhythm ventricular tachycardia and VF, was 98.39%, 96.92% and 99.88%. And, when the VF detection performance of SVM classifier was compared to that of multi-layer perceptron and fuzzy inference methods, it showed similar or higher values. Consequently, we could find that the proposed input features and SVM classifier would one of the most useful algorithm for VF detection.

• Journal of the Korean earth science society
• /
• v.38 no.7
• /
• pp.535-545
• /
• 2017

Maritime accidents around the Korean Peninsula are increasing, and the ship detection research using remote sensing data is consequently becoming increasingly important. This study presented a new ship detection algorithm using hyperspectral images that provide the spectral information of several hundred channels in the ship detection field, which depends on high resolution optical imagery. We applied a spectral matching algorithm between the reflection spectrum of the ship deck obtained from two field observations and the ship and seawater spectrum of the hyperspectral sensor of an airborne visible/infrared imaging spectrometer. A total of five detection algorithms were used, namely spectral distance similarity (SDS), spectral correlation similarity (SCS), spectral similarity value (SSV), spectral angle mapper (SAM), and spectral information divergence (SID). SDS showed an error in the detection of seawater inside the ship, and SAM showed a clear classification result with a difference between ship and seawater of approximately 1.8 times. Additionally, the present study classified the vessels included in hyperspectral images by presenting the adaptive thresholds of each technique. As a result, SAM and SID showed superior ship detection abilities compared to those of other detection algorithms.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.7 no.2
• /
• pp.190-202
• /
• 1996

This study assessed psychiatrically referred 5-to 13-year-old children who presented inattention or hyperactivity as chief complaints. Demographic characteristics, primary diagnosis, and comorbid psychiatric conditions of them were identified, and they were assessed using questionnaires and neuropsychological tests. Primary diagnoses included ADHD, anxiety disorder, mental retardation, depression, oppositional defiant disorder, developmental language disorder and others. functional enuresis, conduct disorder, and developmental language disorder were among the secondarily diagnosed disorders. In patients diagnosed as ADHD, overall comorbidity rate was 55.3%. The disorders that frequently co-occured with ADHD were specific developmental disorder, conduct disorder, oppositional defiant disorder, anxiety disorder and other. ADHD groups with or without comorbidity differed in performance IQ and CPT scores. ADHD group differed from externalizing disorders group in the information subscore of IQ, MFFT, and CPT scores, and differed in teachers rating scales, the uncommunication factor of CBCL, and CPT card error compared with internalizing disorders group. The authors concluded that inattentive or hyperactive children should be assessed using various instruments to differentiate other disorders and to identify possible presence of comorbid conditions.

• Journal of Korean Neurosurgical Society
• /
• v.63 no.3
• /
• pp.386-396
• /
• 2020

Objective : To generate synthetic spine magnetic resonance (MR) images from spine computed tomography (CT) using generative adversarial networks (GANs), as well as to determine the similarities between synthesized and real MR images. Methods : GANs were trained to transform spine CT image slices into spine magnetic resonance T2 weighted (MRT2) axial image slices by combining adversarial loss and voxel-wise loss. Experiments were performed using 280 pairs of lumbar spine CT scans and MRT2 images. The MRT2 images were then synthesized from 15 other spine CT scans. To evaluate whether the synthetic MR images were realistic, two radiologists, two spine surgeons, and two residents blindly classified the real and synthetic MRT2 images. Two experienced radiologists then evaluated the similarities between subdivisions of the real and synthetic MRT2 images. Quantitative analysis of the synthetic MRT2 images was performed using the mean absolute error (MAE) and peak signal-to-noise ratio (PSNR). Results : The mean overall similarity of the synthetic MRT2 images evaluated by radiologists was 80.2%. In the blind classification of the real MRT2 images, the failure rate ranged from 0% to 40%. The MAE value of each image ranged from 13.75 to 34.24 pixels (mean, 21.19 pixels), and the PSNR of each image ranged from 61.96 to 68.16 dB (mean, 64.92 dB). Conclusion : This was the first study to apply GANs to synthesize spine MR images from CT images. Despite the small dataset of 280 pairs, the synthetic MR images were relatively well implemented. Synthesis of medical images using GANs is a new paradigm of artificial intelligence application in medical imaging. We expect that synthesis of MR images from spine CT images using GANs will improve the diagnostic usefulness of CT. To better inform the clinical applications of this technique, further studies are needed involving a large dataset, a variety of pathologies, and other MR sequence of the lumbar spine.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.617-629
• /
• 2020

In order to overcome the limitations of the rule-based intrusion detection system due to changes in Internet computing environments, the emergence of new services, and creativity of attackers, network anomaly detection (NAD) using machine learning and deep learning technologies has received much attention. Most of these existing machine learning and deep learning technologies for NAD use supervised learning methods to learn a set of training data set labeled 'normal' and 'attack'. This paper presents the feasibility of the unsupervised learning AutoEncoder(AE) to NAD from data sets collecting of secured network traffic without labeled responses. To verify the performance of the proposed AE mode, we present the experimental results in terms of accuracy, precision, recall, f1-score, and ROC AUC value on the NSL-KDD training and test data sets. In particular, we model a reference AE through the deep analysis of diverse AEs varying hyper-parameters such as the number of layers as well as considering the regularization and denoising effects. The reference model shows the f1-scores 90.4% and 89% of binary classification on the KDDTest+ and KDDTest-21 test data sets based on the threshold of the 82-th percentile of the AE reconstruction error of the training data set.

• Archives of design research
• /
• v.18 no.1 s.59
• /
• pp.5-16
• /
• 2005

As for the public, it is hard to understand semiotics because of the scope of an enormous semiotics education. This study is making semiotics of Charles Sanders Peirce the subject. I thought that utilization can hold his semiotics study in a visual design field. First of all, this study considered design related papers related to the existing semiotics again and study found an error of the existing semiotics study and understanding did category concept with re-definition about semiotics of Peirce. Explained a symbol mark through understanding of semiotics of Peirce. This study was able to get the following conclusion through these results. 1) A symbol mark means one product, sonics, company oneself with a custom. Therefore, it is a rule symbol in the Representation side. 2) A symbol mark symbolizes an object with one symbol, so a symbol mark is a symbol in an object. 3) Because a symbol mark exists through a social rule, in semiotics definition of Peirce, this must become understanding with a Argument symbol. 4) A symbol mark is what a company or an organization field used from the past, and the public are recognizing this how. Therefore, it works as fact a company attaches a symbol mark to own product, and to show the public a symbol mark. A symbol mark is Dicent Sign in Interpretant. A rule and understanding about a lot of types which have various mutual relation, Peirce classification and understanding of a symbol mark tells to demand is holding that understanding a type of semiotics with the concept that is not an image to us.

• Archives of design research
• /
• v.18 no.2 s.60
• /
• pp.219-232
• /
• 2005

Moderns are living within flood of web contents, animation, reflex data etc. as well as sight, product, environment design. There fore, modern consumer has much options. Designer must provide various result for consumer for this reason. And must invent new sensitivity and propose to consumer. As purpose of this MCC sensitivity palette research takes advantage of the most sensitive color, do. Because applying correct sensitivity more than when design with matter already settled, rid private prejudice, and is thing to convey design intention exactly to user. Excellent culture contents must be able to equip international color design sensitivity. MCC sensitivity palette research studies and carries on the head emotion and sensitivity language that is nationality first, and collect End arranged sensitivity adjective through data analysis and picture data analysis that is the next time research leader Munheonjeok. And distributed collected adjective equally, and arrange distributed adjective by field of each sensitivity and collect system. Do 3 colors, 4 colors color scheme in selected sensitivity adjective and completed Simheom version. Result of beta version research to color specialist and designer last digital palette through question and inquiry compose. Through this process, completed more real and correct digital color sensitivity palette. Completed color scheme is operated in www.mcdri.net on web, and also programs to windows base and developed to software. MCC color scheme palette that research result is made includes sensitivity data database. This database can use directly in industry and continuous development is available. Software can search color scheme in language and idea development through classification search that use 3 attributes of color is available there is cough data of each output device different color error.