• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.7
• /
• pp.1-8
• /
• 2017

As the IT environment becomes more sophisticated, various threats and their associated serious risks are increasing. Threats such as DDoS attacks, malware, worms, and APT attacks can be a very serious risk to enterprises and must be efficiently managed in a timely manner. Therefore, the government has designated the important system as the main information communication infrastructure in consideration of the impact on the national security and the economic society according to the 'Information and Communication Infrastructure Protection Act', which, in particular, protects the main information communication infrastructure from cyber infringement. In addition, it conducts management supervision such as analysis and evaluation of vulnerability, establishment of protection measures, implementation of protection measures, and distribution of technology guides. Even now, security consulting is proceeding on the basis of 'Guidance for Evaluation of Technical Vulnerability Analysis of Major IT Infrastructure Facilities'. There are neglected inspection items in the applied items, and the vulnerability of APT attack, malicious code, and risk are present issues that are neglected. In order to eliminate the actual security risk, the security manager has arranged the inspection and ordered the special company. In other words, it is difficult to check against current hacking or vulnerability through current system vulnerability checking method. In this paper, we propose an efficient method for extracting diagnostic data regarding the necessity of upgrading system vulnerability check, a check item that does not reflect recent trends, a technical check case for latest intrusion technique, a related study on security threats and requirements. Based on this, we investigate the security vulnerability management system and vulnerability list of domestic and foreign countries, propose effective security vulnerability management system, and propose further study to improve overseas vulnerability diagnosis items so that they can be related to domestic vulnerability items.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.241-254
• /
• 2011

Financial time-series forecasting is one of the most important issues because it is essential for the risk management of financial institutions. Therefore, researchers have tried to forecast financial time-series using various data mining techniques such as regression, artificial neural networks, decision trees, k-nearest neighbor etc. Recently, support vector machines (SVMs) are popularly applied to this research area because they have advantages that they don't require huge training data and have low possibility of overfitting. However, a user must determine several design factors by heuristics in order to use SVM. For example, the selection of appropriate kernel function and its parameters and proper feature subset selection are major design factors of SVM. Other than these factors, the proper selection of instance subset may also improve the forecasting performance of SVM by eliminating irrelevant and distorting training instances. Nonetheless, there have been few studies that have applied instance selection to SVM, especially in the domain of stock market prediction. Instance selection tries to choose proper instance subsets from original training data. It may be considered as a method of knowledge refinement and it maintains the instance-base. This study proposes the novel instance selection algorithm for SVMs. The proposed technique in this study uses genetic algorithm (GA) to optimize instance selection process with parameter optimization simultaneously. We call the model as ISVM (SVM with Instance selection) in this study. Experiments on stock market data are implemented using ISVM. In this study, the GA searches for optimal or near-optimal values of kernel parameters and relevant instances for SVMs. This study needs two sets of parameters in chromosomes in GA setting : The codes for kernel parameters and for instance selection. For the controlling parameters of the GA search, the population size is set at 50 organisms and the value of the crossover rate is set at 0.7 while the mutation rate is 0.1. As the stopping condition, 50 generations are permitted. The application data used in this study consists of technical indicators and the direction of change in the daily Korea stock price index (KOSPI). The total number of samples is 2218 trading days. We separate the whole data into three subsets as training, test, hold-out data set. The number of data in each subset is 1056, 581, 581 respectively. This study compares ISVM to several comparative models including logistic regression (logit), backpropagation neural networks (ANN), nearest neighbor (1-NN), conventional SVM (SVM) and SVM with the optimized parameters (PSVM). In especial, PSVM uses optimized kernel parameters by the genetic algorithm. The experimental results show that ISVM outperforms 1-NN by 15.32%, ANN by 6.89%, Logit and SVM by 5.34%, and PSVM by 4.82% for the holdout data. For ISVM, only 556 data from 1056 original training data are used to produce the result. In addition, the two-sample test for proportions is used to examine whether ISVM significantly outperforms other comparative models. The results indicate that ISVM outperforms ANN and 1-NN at the 1% statistical significance level. In addition, ISVM performs better than Logit, SVM and PSVM at the 5% statistical significance level.

• The korean journal of orthodontics
• /
• v.29 no.4 s.75
• /
• pp.457-466
• /
• 1999

It has been reported that skeletal relapse and dental change after mandibular setback do occur not only after intermaxillary fixation(IMF) removal but also during IMF The side effects of skeletal relapse during IMF have clinical importance because they can cause many Postoperative orthodontic Problems. Generally, the Prevention of solid union between segments, compensatory tooth movement, anterior openbite, etc. have been cited as the side effects of jaw displacement. The purpose of this study was to evaluate the skeletal relapse and dental change during IMF. The material consisted of 28 patients who were treated by BSSRO(bilateral sagittal split ramus osteotomy), wire osteosynthesis, IMF for correction of mandibular prognathism. Through cephalometric analysis, the amount and direction of surgical movement, skeletal relapse and dental change during IMF were measured. The correlation between surgical movement and skeletal relapse, between skeletal relapse and dental changes were evaluated. The following conclusions were obtained; 1. Distal segment was repositioned backward and upward, proximal segment showed clockwise rotation during surgery. 2. During ]m, anterior portion of distal segment was displaced backward and posterior portion was displaced upward. Proximal segment was displaced upward with forward movement of p-Go(gonion of proximal segment). Backward surgical movement of p-GO was significantly correlated with forward displacement of p-Go. 3. Overjet and overbite were not changed during IMF. The compensatory tooth movements during IMF were characterized by retroclination of upper incisors md retroclination, extrusion of lower incisors. These compensatory tooth movements had statistically significant correlation with upward displacement of d-Go (gonion of distal segment).

• Cartoon and Animation Studies
• /
• s.35
• /
• pp.329-346
• /
• 2014

Art is the product from the combination of politics, economy, and social and cultural aspects. Recent development of digital media has affected on the expansion of visual expression in art. Digital media allow artists to use sound and physical interaction as well as image as an plastic element for making a work of art. Also, digital media help artists create an interactive, synaesthetic and visual perceptive environment by combining viewers' physical interaction with the reconstruction of image, sound, light, and among other plastic elements. This research was focused on the analysis of the relationship between images in art work and the viewer and data visualization using sound from the perspective of visual perception. This research also aimed to develop an interactive art by visualizing physical data with sound generating from outer stimulus or the viewer. Physical data generating from outer sound can be analyzed in various aspects. For example, Sound data can be analyzed and sampled within pitch, volume, frequency, and etc. This researcher implemented a new form of media art through the visual experiment of LED light triggered by sound frequency generating from viewers' voice or outer physical stimulus. Also, this researcher explored the possibility of various visual image expression generating from the viewer's reaction to illusionary characteristics of light(LED), which can be transformed within external physical data in real time. As the result, this researcher used a motif from Piet Mondrian's Broadway Boogie Woogie in order to implement a visual perceptive interactive work reacting with sound. Mondrian tried to approach at the essence of visual object by eliminating unnecessary representation elements and simplifying them in painting and making them into abstraction consisting of color, vertical and horizontal lines. This researcher utilized Modrian's simplified visual composition as a representation metaphor in oder to transform external sound stimulus into the element of light(LED), and implemented an environment inducing viewers' participation, which is a dynamic composition maximizing a synaesthetic expression, differing from Modrian's static composition.

• The Korean Journal of Nuclear Medicine
• /
• v.39 no.3
• /
• pp.174-181
• /
• 2005

Purpose: Reduction of respiratory motion artifacts in PET images was studied using respiratory-gated PET (RGPET) with moving phantom. Especially a method of generating simulated helical CT images from 4D-CT datasets was developed and applied to a respiratory specific RGPET images for more accurate attenuation correction. Materials and Methods: Using a motion phantom with periodicity of 6 seconds and linear motion amplitude of 26 mm, PET/CT (Discovery ST: GEMS) scans with and without respiratory gating were obtained for one syringe and two vials with each volume of 3, 10, and 30 ml respectively. RPM (Real-Time Position Management, Varian) was used for tracking motion during PET/CT scanning. Ten datasets of RGPET and 4D-CT corresponding to every 10% phase intervals were acquired. from the positions, sizes, and uptake values of each subject on the resultant phase specific PET and CT datasets, the correlations between motion artifacts in PET and CT images and the size of motion relative to the size of subject were analyzed. Results: The center positions of three vials in RGPET and 4D-CT agree well with the actual position within the estimated error. However, volumes of subjects in non-gated PET images increase proportional to relative motion size and were overestimated as much as 250% when the motion amplitude was increased two times larger than the size of the subject. On the contrary, the corresponding maximal uptake value was reduced to about 50%. Conclusion: RGPET is demonstrated to remove respiratory motion artifacts in PET imaging, and moreover, more precise image fusion and more accurate attenuation correction is possible by combining with 4D-CT.

• Horticultural Science & Technology
• /
• v.28 no.3
• /
• pp.456-461
• /
• 2010

A study was conducted to investigate the effect of topophysis, and uniting method of rootstock and scion on rooting and subsequent growth of stenting-propagated cut rose ($Rosa$ $hybrida$ Hort.) in an effort to develop an efficient stenting propagation method for domestic rose cultivars. Four cultivars used in this study were two standard type cultivars 'Sweet Yellow' and 'Hanmaum', and two spray type cultivars 'Chelsi' and 'May'. Scions were grafted on cuttings of a rootstock $Rosa$ $indica$ 'Major'. The stenting-propagated scion-rootstock unions were planted in rockwool cubes ($50{\times}50{\times}50mm$, Delta, Grodan, Denmark) and were placed in a graft-take chamber for five days before being placed on misted greenhouse beds. The rootstock was removed of all leaves and nodes. Both the base of scions and top of stocks were simultaneously cut at a $45^{\circ}$ angle for grafting. Scions were prepared as single node cuttings, each with a five-leaflet leaf. Three positions of topophysis used were 7-9th (top), 4-6th (middle), and 1st-3rd (bottom) nodes from the stem base. Four uniting materials used were tube, tube + parafilm wrap, tube + clothespin, and clothespin. Rooting and growth were affected by the topophysis and cultivar. The best topophysis for rooting was 7-9th (top) nodes in all cultivars. Topophysis affected percent rooting, and number of roots, length of the longest root, and but not weight, shoot length and graft-take. Rooting and growth were affected by the uniting method and cultivar. Tube uniting method generally showed higher percentage graft-take, percent rooting, and number of roots than other methods. However, rootstock and scion union was not complete in this treatment. On the whole, the greatest rooting and subsequent growth of stenting-propagated plants were found in the tube + clothespin method. Except 'Sweet Yellow', rooting and growth were not adequate in the clothespin method. The results suggested that a tube + clothespin method was the most effective, and this method may be used as a substitute to save labor compared to a tube + parafilm wrap method which is currently being used in commercial nurseries.

• Korean Journal of Social Welfare Studies
• /
• v.49 no.2
• /
• pp.125-157
• /
• 2018

In the reality that the seriousness and concern about the youth problem is increasing, this study focuses on the vision plan project supporting the NEET youth in the social welfare field. Therefore, this study analyzed how the social workers recognized the NEET problem before participating in the project, what difficulties they experienced in the process of the project, and how they coped with these difficulties. The results of the study are as follows. Social workers were saddened by the seriousness of the youth problem before their participation, but they recognized that there was no way to solve it and many social workers were not fully aware of the youth or NEET issues. In this context, in the course of running a project with NEET youth, social workers experienced difficulties due to the nature of the NEET youth, difficulty in forming a relationship with NEET youth, and difficulties for young people not to spend time in the program. And social workers also faced difficulties due to the lack of know-how in the project, difficulties in operating the center alone, and difficulty in achieving employment goals. In the process of coping with these difficulties, social workers have actively sought, persuaded and supported the NEET youths to participate in the project, adapted the time, place and method to the youth, and removed the stigmatization element in the project. They also worked closely with local residents, local institutions and municipalities, formed networks, and changed the viewpoint of providing work experience rather than getting young people, but seeing long-term outcome. As a result, social workers have experienced not only individual change but also social welfare organization, field, community and local institutional change. Based on these results, this study suggested that the social welfare practice field should provide various activities in the process of supporting the youth gap year policy. In addition, this study suggests that the social workers play a role in connecting various actors rather than suppliers when working with young people, and that the social welfare field should expand the scope of project to include youth.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_1
• /
• pp.497-510
• /
• 2022

Agricultural reservoirs are essential structures for water supplies during dry period in the Korean peninsula, where water resources are temporally unequally distributed. For efficient water management, systematic and effective monitoring of medium-small reservoirs is required. Synthetic Aperture Radar (SAR) provides a way for continuous monitoring of those, with its capability of all-weather observation. This study aims to evaluate the applicability of SAR in monitoring medium-small reservoirs using Sentinel-1 (10 m resolution) and Capella X-SAR (1 m resolution), at Chari (CR), Galjeon (GJ), Dwitgol (DG) reservoirs located in Ulsan, Korea. Water detected results applying Z fuzzy function-based threshold (Z-thresh) and Chan-vese (CV), an object detection-based segmentation algorithm, are quantitatively evaluated using UAV-detected water boundary (UWB). Accuracy metrics from Z-thresh were 0.87, 0.89, 0.77 (at CR, GJ, DG, respectively) using Sentinel-1 and 0.78, 0.72, 0.81 using Capella, and improvements were observed when CV was applied (Sentinel-1: 0.94, 0.89, 0.84, Capella: 0.92, 0.89, 0.93). Boundaries of the waterbody detected from Capella agreed relatively well with UWB; however, false- and un-detections occurred from speckle noises, due to its high resolution. When masked with optical sensor-based supplementary images, improvements up to 13% were observed. More effective water resource management is expected to be possible with continuous monitoring of available water quantity, when more accurate and precise SAR-based water detection technique is developed.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.2
• /
• pp.129-152
• /
• 2024

In the application of deep learning object detection via CCTV in tunnels, a large number of false positive detections occur due to the poor environmental conditions of tunnels, such as low illumination and severe perspective effect. This problem directly impacts the reliability of the tunnel CCTV-based accident detection system reliant on object detection performance. Hence, it is necessary to reduce the number of false positive detections while also enhancing the number of true positive detections. Based on a deep learning object detection model, this paper proposes a false positive data training method that not only reduces false positives but also improves true positive detection performance through retraining of false positive data. This paper's false positive data training method is based on the following steps: initial training of a training dataset - inference of a validation dataset - correction of false positive data and dataset composition - addition to the training dataset and retraining. In this paper, experiments were conducted to verify the performance of this method. First, the optimal hyperparameters of the deep learning object detection model to be applied in this experiment were determined through previous experiments. Then, in this experiment, training image format was determined, and experiments were conducted sequentially to check the long-term performance improvement through retraining of repeated false detection datasets. As a result, in the first experiment, it was found that the inclusion of the background in the inferred image was more advantageous for object detection performance than the removal of the background excluding the object. In the second experiment, it was found that retraining by accumulating false positives from each level of retraining was more advantageous than retraining independently for each level of retraining in terms of continuous improvement of object detection performance. After retraining the false positive data with the method determined in the two experiments, the car object class showed excellent inference performance with an AP value of 0.95 or higher after the first retraining, and by the fifth retraining, the inference performance was improved by about 1.06 times compared to the initial inference. And the person object class continued to improve its inference performance as retraining progressed, and by the 18th retraining, it showed that it could self-improve its inference performance by more than 2.3 times compared to the initial inference.