• Korean Journal of Psychosomatic Medicine
• /
• v.29 no.2
• /
• pp.144-152
• /
• 2021

Objectives : The purpose of this study is to identify differences between suicide attempters who used zolpidem and others who used different methods in emergency department. Methods : This study classified 2,734 suicide attempters, who went to emergency department from 2009 to 2018, into zolpidem user group, another drug user group and non-drug user group. For these three groups, chisquare test and logistic regression analysis were conducted regarding sociodemographic feature and clinical feature related with suicide. Results : In the result of logistic regression analysis of a variable, which showed meaningful difference between suicide attempter group who used zolpidem and the other group who did not use the drug, the occurrence of zolpidem-using suicide attempers was related with the case where anxiolytics/hypnotics was used or the case where lethality and intention was low. In the drug intoxication group which showed similar feature, there was also a relevance between anxiolytics/hypnotics and the occurrence of zolpidem-using suicide attempts. Conclusions : This study identified significant difference of sociodemographic and clinical feature in suicide attempter group who used zolpidem and the other group. This result can contribute to plan further medicinal treatment in using zolpidem.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.11
• /
• pp.435-442
• /
• 2018

Outlier detection means to detect data samples that deviate significantly from the distribution of normal data. Most outlier detection methods calculate an outlier score that indicates the extent to which a data sample is out of normal state and determine it to be an outlier when its outlier score is above a given threshold. However, since the range of an outlier score is different for each data and the outliers exist at a smaller ratio than the normal data, it is very difficult to determine the threshold value for an outlier score. Further, in an actual situation, it is not easy to acquire data including a sufficient amount of outliers available for learning. In this paper, we propose a clustering-based outlier detection method by constructing a model representing a normal data region using only normal data and performing binary classification of outliers and normal data for new data samples. Then, by dividing the given normal data into chunks, and constructing a clustering model for each chunk, we expand it to the ensemble method combining the decision by the models and apply it to the streaming data with dynamic changes. Experimental results using real data and artificial data show high performance of the proposed method.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.22 no.5
• /
• pp.1191-1204
• /
• 2012

As attackers try to paralyze information security systems, many researchers have investigated security testing to analyze vulnerabilities of information security products. Penetration testing, a critical step in the development of any secure product, is the practice of testing a computer systems to find vulnerabilities that an attacker could exploit. Security testing like penetration testing includes gathering information about the target before the test, identifying possible entry points, attempting to break in and reporting back the findings. Therefore, to obtain maximum generality, re-usability and efficiency is very useful for efficient security testing and vulnerability hunting activities. In this paper, we propose a threat analysis based software security testing technique for evaluating that the security functionality of target products provides the properties of self-protection and non-bypassability in order to respond to attacks to incapacitate or bypass the security features of the target products. We conduct a security threat analysis to identify vulnerabilities and establish a testing strategy according to software modules and security features/functions of the target products after threat analysis to improve re-usability and efficiency of software security testing. The proposed technique consists of threat analysis and classification, selection of right strategy for security testing, and security testing. We demonstrate our technique can systematically evaluate the strength of security systems by analyzing case studies and performing security tests.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.1
• /
• pp.83-97
• /
• 2021

Wireless sensors that make up the Wireless Sensor Network generally have extremely limited power and resources. The wireless sensor enters the sleep state at a certain interval to conserve power. The Sleep deflation attack is a deadly attack that consumes power by preventing wireless sensors from entering the sleep state, but there is no clear countermeasure. Thus, in this paper, using clustering-based binary search tree structure, the Sleep deprivation attack detection model is proposed. The model proposed in this paper utilizes one of the characteristics of both attack sensor nodes and normal sensor nodes which were classified using machine learning. The characteristics used for detection were determined using Long Short-Term Memory, Decision Tree, Support Vector Machine, and K-Nearest Neighbor. Thresholds for judging attack sensor nodes were then learned by applying the SVM. The determined features were used in the proposed algorithm to calculate the values for attack detection, and the threshold for determining the calculated values was derived by applying SVM.Through experiments, the detection model proposed showed a detection rate of 94% when 35% of the total sensor nodes were attack sensor nodes and improvement of up to 26% in power retention.

• The Journal of the Korea Contents Association
• /
• v.21 no.11
• /
• pp.135-144
• /
• 2021

Recently, data-driven decision-making technology has become a key technology leading the data industry, and machine learning technology for this requires high-quality training datasets. However, real-world data contains missing values for various reasons, which degrades the performance of prediction models learned from the poor training data. Therefore, in order to build a high-performance model from real-world datasets, many studies on automatically imputing missing values in initial training data have been actively conducted. Many of conventional machine learning-based imputation techniques for handling missing data involve very time-consuming and cumbersome work because they are applied only to numeric type of columns or create individual predictive models for each columns. Therefore, this paper proposes a new data imputation technique called 'Denoising Self-Attention Network (DSAN)', which can be applied to mixed-type dataset containing both numerical and categorical columns. DSAN can learn robust feature expression vectors by combining self-attention and denoising techniques, and can automatically interpolate multiple missing variables in parallel through multi-task learning. To verify the validity of the proposed technique, data imputation experiments has been performed after arbitrarily generating missing values for several mixed-type training data. Then we show the validity of the proposed technique by comparing the performance of the binary classification models trained on imputed data together with the errors between the original and imputed values.

• Journal of Korean Society of Forest Science
• /
• v.111 no.4
• /
• pp.538-547
• /
• 2022

In this study, the population and community structure of Berchemia berchemiaefolia stands located at Mt. Naeyon (Gyeongbuk, Korea) were quantified, and multivariate analysis was done to determine the correlations between vegetation group types and environmental factors and to have reference data for the conservation and restoration of this species. In total, there were 164 B. berchemiaefolia trees in Mt. Naeyon. The average DBH of the trees was 24.5 cm, forming a normal distribution. It rarely appeared in an understory vegetation height of 3 m. About37.1% of the trees were branched. B. berchemiaefolia stands were classified into two groups: B. berchemiaefolia-Quercus serrata community and B. berchemiaefolia-Carpinus laxiflora community. Canopy gap, organic matter, exchangeable Ca, and cation exchange capacity were the major site characteristics affecting the distribution pattern of the stands. Currently, B. berchemiaefolia trees dominate in Mt. Naeyon, but depending on different habitat positions, the species was in a natural successional stage to C. laxiflora or C. cordata, which is a shade-tolerant species.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.347-364
• /
• 2022

Fraudulent companies or sellers strategically manipulate reviews to influence customers' purchase decisions; therefore, the reliability of reviews has become crucial for customer decision-making. Since customers increasingly rely on online reviews to search for more detailed information about products or services before purchasing, many researchers focus on detecting manipulated reviews. However, the main problem in detecting manipulated reviews is the difficulties with obtaining data with manipulated reviews to utilize machine learning techniques with sufficient data. Also, the number of manipulated reviews is insufficient compared with the number of non-manipulated reviews, so the class imbalance problem occurs. The class with fewer examples is under-represented and can hamper a model's accuracy, so machine learning methods suffer from the class imbalance problem and solving the class imbalance problem is important to build an accurate model for detecting manipulated reviews. Thus, we propose an OpenAI-based reviews generation model to solve the manipulated reviews imbalance problem, thereby enhancing the accuracy of manipulated reviews detection. In this research, we applied the novel autoregressive language model - GPT-3 to generate reviews based on manipulated reviews. Moreover, we found that applying GPT-3 model for oversampling manipulated reviews can recover a satisfactory portion of performance losses and shows better performance in classification (logit, decision tree, neural networks) than traditional oversampling models such as random oversampling and SMOTE.

• Composites Research
• /
• v.21 no.5
• /
• pp.9-14
• /
• 2008

Carbon nanofibers (CNFs) were used as dielectric lossy materials and NiFe particles were used as magnetic lossy materials. Total twelve specimens for the three types such as dielectric, magnetic and mixed radar absorbing materials (RAMs) were fabricated. Their complex permittivities and permeabilities in the range of $2{\sim}18$ GHz were measured using the transmission line technique. The parametric studios for reflection loss characteristics of each specimen to design the single-layered RAMs were performed. The mixed RAMs generally showed the improved absorbing characteristics with thinner matching thickness. One of the mixed RAMs, MD3with the thickness of 2.00 mm had the 10 dB absorbing bandwidth of 4.0 GHz in the X-band ($8.2{\sim}12.4$ GHz). It also showed very broad 10 dB absorbing bandwidth as wide as 6.0 GHz in the Ku-band ($12.0{\sim}18.0$ GHz) with the thickness tuning to 1.49 mm. The experimental results for selected several specimens were in very good agreements with simulation ones in terms of the overall reflection loss characteristics and 10 dB absorbing bandwidth.

• Journal of Korean Society of Forest Science
• /
• v.111 no.1
• /
• pp.36-49
• /
• 2022

The purpose of this study was to analyze domestic research trends related to the Baekdudaegan Mountains in the last two decades. In total, 551 academic papers and keyword data related to the Baekdudaegan Mountains were collected using the "Research and Information Service Section" and analyzed using "big data" analysis programs, such as Textom and UCINET. Papers related to the Baekdudaegan Mountains were published in 177 academic journals, and 229 papers (41.6% of all published papers) were published between 2011 and 2015. According to word frequency data (N-gram analyses), the major research topic over the past 20 years was "species diversity." According to CONCOR analysis results, the main research could be divided into 15 areas, the most important of which was "species diversity," followed by "vegetation restoration and management," and "culture." Ecological research comprised 12 groups with a frequency of 78.8%; humanities and social research comprised 2 groups with a frequency of 15.6%. Overall, our study of research areas and quantitative data analyses provides valuable information that could help establish policy formulation.

• Korean Association of Arts Management
• /
• no.51
• /
• pp.75-102
• /
• 2019

This study aims to figure out the progression of Hyundai motor's corporate cultural marketing by conducting semantic network analysis. Although the previous research has focused on conception, categorization, impact, and performance of cultural marketing, they hardly pay attention to changes in cultural marketing over time. To explore the identified gap, we collected 2,315 articles concerning Hyundai motor's cultural marketing on daily newspapers printed from 2001 to 2018. The 18-year time period was classified into four periods, and lists of words were extracted and analyzed by Korean language analysis program, Textom and social network analysis program, called 'UCINET'. The outcome of our analysis indicates that Hyundai Motor's cultural marketing has been developed from the strategy of merely increasing sales to the means of distinguishing their corporate and brand identity. In the early 2000s, the words 'customer', 'The Age of Great Paintings: Rembrandt and the 17th century Dutch paintings', and 'performances' were extracted with high frequency. It shows Hyundai Motor held performance-oriented events and provided benefits to specific consumer groups under the type of 'Cultural Promotion'. In addition, as the exhibition sponsored by Hyundai motor was reported in the media with high publicity effect, the concept of 'Cultural Support' is also emerged. In the late 2000s, the top exposures were 'Seoul Arts Center' and 'Seoul Metropolitan Symphony Orchestra'. Under the concept of 'Cultural Support', both organizations and cultural events were sponsored by Hyundai motor. Hyundai Motor has the tendency to cooperate with high profile parties who have already accomplished high publicities to attract social interests and issues. In the early 2010s, Hyundai Motor created cultural marketing brand and space ('Brilliant' and 'Hyundai Art Hall') that broadened the potential target groups, which represented both 'Cultural Support' and 'Cultural Enterprise'. In the middle and late of the 2010s, as shown by the high frequency of 'brand' and 'global', Hyundai Motor has focused on the global market and viewpoint has expanded to brand building focusing on the type of 'Cultural Enterprise'.