• Journal of the Korea Society of Computer and Information
• /
• v.20 no.1
• /
• pp.93-101
• /
• 2015

In modern society, various crimes is occurred. It is necessary to predict the criminal in order to prevent crimes, various studies on the prediction of crime is in progress. Crime-related data, is announced to the statistical processing of once a year from the Public Prosecutor's Office. However, relative to the current point in time, data that has been statistical processing is a data of about two years ago. It does not fit to the data of the crime currently being generated. In This paper, crime prediction data was apply with Naver trend data. By using the Web traffic Naver trend, it is possible to obtain the data of interest level for crime currently being generated. It was constructed a modeling that can predict the crime by using traffic data of the Naver web search. There have been applied to Markov chains prediction theory. Among various crimes, murder, arson, rape, predictive modeling was applied to target. And the result of predictive modeling value was analyzed. As a result, it got the same results within 20%, based on the value of crime that actually occurred. In the future, it plan to advance research for the predictive modeling of crime that takes into the characteristics of the season.

• Korean Journal of Psychosomatic Medicine
• /
• v.24 no.1
• /
• pp.9-19
• /
• 2016

Many patients with dizziness present with a symptom pattern that does not reveal the cause by neurotologic diagnostic approaches. In such cases, the physician frequently diagnoses psychogenic dizziness. Psychogenic dizziness is not characterized by true vertigo, and occurs in combination with other psychiatric symptom cluster. One out of two to four patients with dizziness are psychogenic dizziness. But there are few concern about this including clinical practice and study in Korea. I wrote this paper to increase concerning and attending to this for psychiatrists in Korea. I reviewed etiology including biological and psychological relations between dizziness and psychiatric disorder(especially anxiety), diagnostic approaches of, characteristics of dizziness of various psychiatric disorders related to, and the treatment of psychogenic dizziness. I also briefly reviewed the central and peripheral dizziness for psychiatrists. I suggest psychiatrists and clinicians in the psychosomatic field in Korea to acknowledge, concern, and attend to psychogenic dizziness. In turn, it will be helpful to well treat the patients with psychogenic dizziness.

• Journal of Korea Society of Industrial Information Systems
• /
• v.26 no.5
• /
• pp.95-111
• /
• 2021

This paper is a study to check the flow of how addiction to media services has been studied from a long-term perspective, and to identify variables that can be the basis for future addiction research. Researchers noted the addiction of media services in adolescents in particular, and identified a combination of factors depending on the background of the times. Addiction variables were largely aggregated into four properties: adolescent properties, personal properties, media properties, and media-dependent properties. Addiction variables belonging to the attribute were influenced by major media and divided into four periods. During the study period, the frequency of variables was most related to personal attributes, followed by media attributes, adolescent attributes, and media-dependent attributes. Also Individual attribute variables gradually shifted from object-relationship to individual psychological factors. Variants in media attributes were influenced by the introduction and spread of new media. Variations in adolescent and media-dependent attributes have been weak in studies that observe teenagers' motivations for media use or are related to addiction, and no papers have been published since 2020. Although addiction research on media services is important in terms of industry, there has been an emphasis on social aspects, based on the results of this study, we hope to continue to study the variables of service users who can be used in terms of industry.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.41-49
• /
• 2021

All application programs, including malware, call the Application Programming Interface (API) upon execution. Recently, using those characteristics, attempts to detect and classify malware based on API Call information have been actively studied. However, datasets containing API Call information require a large amount of computational cost and processing time. In addition, information that does not significantly affect the classification of malware may affect the classification accuracy of the learning model. Therefore, in this paper, we propose a method of extracting a essential feature set after reducing the dimensionality of API Call information by applying various feature selection methods. We used CICAndMal2020, a recently announced Android malware dataset, for the experiment. After extracting the essential feature set through various feature selection methods, Android malware classification was conducted using CNN (Convolutional Neural Network) and the results were analyzed. The results showed that the selected feature set or weight priority varies according to the feature selection methods. And, in the case of binary classification, malware was classified with 97% accuracy even if the feature set was reduced to 15% of the total size. In the case of multiclass classification, an average accuracy of 83% was achieved while reducing the feature set to 8% of the total size.

• The Journal of the Korea Contents Association
• /
• v.19 no.4
• /
• pp.218-226
• /
• 2019

As the shoes industry has been strengthened due to the contemporary fashion industry becoming segmented more and more, it is necessary to provide the basic data for the shoes industry through more in-depth research on the relevant fields. Accordingly, this study investigated the research trends related to shoes in Korea on the aspect of the publication methods, research contents and research methodologies for identifying the existing research status. In accordance with the analysis, the researches had been published since 2015 and presented by one author or two co-authors. The authors of researches were mostly affiliated to the colleges. Thus, it was identified that the professional research should be implemented in cooperation with the industry. For the research contents, the researches related to the shoes industry focused on the 21st century in the period field and marketing and design in the theme field. Then, it is required to investigate the converged interdisciplinary themes in wider areas in more diverse periods. Next, the case study accounted for the highest ratio in the methodology. Moreover, the methodology applied per theme showed the significant difference. Accordingly, the researches need to be conducted through more diverse viewpoints and methodologies. In case of the difference per research type, the significant difference was found only in the research approaches. Furthermore, the specific methodology was preferred per theme regardless of the research types. Then, it was found that the methodology played the significant role in the researches on the shoes industry.

• (The) Research of the performance art and culture
• /
• no.36
• /
• pp.649-691
• /
• 2018

A number of studies on the educational influence of drama and theatre have increased since the 1990s in South Korea. These days, more Korean researchers seem to have recognised the educational influence of drama and theatre than before. At this time, it is meaningful to look into how the domestic trend of studies has changed and developed over the past thirty years. This paper especially adopted a bibliometric method to analyse the trend by time of studies from the late 1990s to 2017. In addition, target age, research topic and research approach of each study were investigated. Some of terminologies particularly used in South Korea were also defined to help young researchers' understanding in this paper. In detail, the total number of studies for the last thirty years is 225 and the first domestic study on the educational power of drama and theatre was published in 1994. In the 2000s, there was quantitative expansion in terms of the number of studies and topics. Eventually pragmatic and integrated features of the studies were found in the 2010s. It is anticipated that the pragmatic and integrated features of the studies will be stimulated to fit into the need of the time. Until now, the most fevered research target age was mainly primary school students. However, it would be possible to widen a target age range in the future. It should be considered having collaboration among researchers who have different expertises for conducting higher quality studies.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.12
• /
• pp.485-496
• /
• 2018

So far, the deep learning, a field of artificial intelligence, has achieved remarkable results in solving problems from unstructured data. However, it is difficult to comprehensively judge situations like humans, and did not reach the level of intelligence that deduced their relations and predicted the next situation. Recently, deep neural networks show that artificial intelligence can possess powerful relational reasoning that is core intellectual ability of human being. In this paper, to analyze and observe the performance of Relation Networks (RN) among the neural networks for relational reasoning, two types of RN-based deep neural network models were constructed and compared with the baseline model. One is a visual question answering RN model using Sort-of-CLEVR and the other is a text-based question answering RN model using bAbI task. In order to maximize the performance of the RN-based model, various performance improvement experiments such as hyper parameters tuning have been proposed and performed. The effectiveness of the proposed performance improvement methods has been verified by applying to the visual QA RN model and the text-based QA RN model, and the new domain model using the dialogue-based LL dataset. As a result of the various experiments, it is found that the initial learning rate is a key factor in determining the performance of the model in both types of RN models. We have observed that the optimal initial learning rate setting found by the proposed random search method can improve the performance of the model up to 99.8%.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.4
• /
• pp.470-478
• /
• 2019

As the growth of the domestic defense industry is remarkable regarding technology level and export size, technology protection is necessary. Particularly, there is a need to apply anti-tamper measures to prevent critical technologies from illegally being taken out of weapon systems. However, there is no security protection strategy and system built yet in ROK. Precedent studies discussed the trend analysis and technical research for specific protective techniques, and the application of anti-tamper using limited procedures was provided. Recently, methods of how to select the technology for protection were studied based on risk management. Nonetheless, these studies cannot be associated with the acquisition process for the whole life-cycle, having difficulty with actual development and evaluation of the weapon systems. The objective of our study is to derive the system requirements of the weapon system for which anti-tamper measures have been determined to apply. Specifically, requirements items suitable for the development of anti-tamper weapon systems were derived based on ISO/IEC 19790, the CMVP standard for the development and verification of cryptographic modules. Also, its utilization in technical reviews and test & evaluations was presented. The usefulness of the research results was confirmed through inductive inference and comparative evaluation. The result can be expected to play a role in initiating extensive activities needed for technology protection of the weapon systems.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.4
• /
• pp.479-488
• /
• 2019

The flight test operational procedure artifact includes mission planning, execution methods, and safety measures for each step of test progress. As the development of guided missiles has become more advanced and strategic, flight test has become increasingly complex and broadened. Therefore, increased reliability of the flight test operation procedures was required to ensure test safety. Particularly, the design of the flight test operational procedures required verification through M&S to predict and prepare for the uncertainty in a new test. The relevant studies have published the optimal framework development for flight tests and the model-based improvements of flight test processes, but they lacked the specificity to be applied directly to the flight test operational procedures. In addition, the flight test operational procedures, which consist of document bases, have caused problems such as limitations of analysis capabilities, insensitive expressions, and lack of scalability for the behavior and performance analysis of test resources. To improve these problems, this paper proposes how to design operational procedure of guided missile flight test system by applying MBSE(Model-based Systems Engineering). This research has improved reliability by increasing the ability to analyze the behavior and performance of test resources, and increased efficiency with the scalability applicable to multiple flight tests. That can be also used continuously for the guided missile flight tests that will be developed in the future.

• Korean Journal of Medical Ethics
• /
• v.21 no.4
• /
• pp.330-343
• /
• 2018

This article explores some of the ethical issues associated with the fourth industrial revolution and suggests new directions for bioethics education in Korean universities. Some countries have recently developed guidelines and regulations based on the legal and ethical considerations of the benefits and social risks of new technologies associated with the fourth industrial revolution. Foreign universities have also created courses (both classroom and online) that deal with these issues and help to ensure that these new technologies are developed in an ethically appropriate fashion. In South Korea too there have been attempts to enhance bioethics education to meet the changing demands of society. However, bioethics education in Korea remains focused on traditional bioethical topics and largely neglects the ethical issues related to emerging technologies. Furthermore, Korean universities offer no online courses in bioethics and the classroom courses that do exist are generally treated as electives. In order to improve bioethics education in Korean universities, we suggest that (a) new course should be developed for interprofessional education; (b) courses in bioethics should be treated as required subjects gradually; (c) online courses should be prepared, and (d) universities should continually revise course contents in response to the development of new technologies.