• The Transactions of the Korea Information Processing Society
• /
• v.3 no.3
• /
• pp.449-459
• /
• 1996

The main goal of this paper is to introduce a novel definition for fuzzy mathematical morphology and a neural network implementation. The generalized- mean operator plays the key role for the definition. Such definition is well suited for neural network implementation. The first stage of the shared-weight neural network has adequate architecture to perform morphological operation. The shared- weight network performs classification based on the features extracted with the fuzzy morphological operation defined in this paper. Therefore, the parameters for the fuzzy definition can be optimized using neural network learning paradigm. Learning rules for the structuring elements, degree of membership, and weighting factors are precisely described. In application to handwritten digit recognition problem, the fuzzy morphological shared-weight neural network produced the results which are comparable to the state-of art for this problem.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.189-189
• /
• 2019

도시화에 따른 토지이용패턴의 변화로 불투수면적이 증가하여 빗물의 침투량이 감소하고, 유출량은 증가하는 등 집중호우시 침수피해를 야기하게 된다. 또한 오염원의 증가로 수질오염과 지하수고갈에 따른 건천화 등 부정적 효과를 초래하는 것으로 알려져 있다. 최근 기후변화에 따라 물순환 체계가 변화하고 있으며, 이로 인해 도시의 홍수 및 가뭄이 극심해지고 시민의 삶의 질도 위협받고 있다. 우리나라의 경우 지속적으로 도시화 및 불투수면적이 증가하고 있으며, 집중호우의 발생빈도 또한 높아 심각한 수자원 물재와 홍수피해위험이 높다. 이에 도시의 물환경 변화 및 왜곡된 물순환 체계를 지속가능하도록 개선해야 할 필요성이 제기되었다. 환경부 및 국토부 등 정부기관에서는 물환경지속가능성을 위하여 저영향개발 기술요소를 도입하고 적용하고 있다. 본 연구에서는 침수위험지역의 저영향개발기법을 도입하여 유출저감 효과를 모의하고, 경제성 분석을 하였다. 본 연구의 대상지역은 경상남도 김해시 안동지구이며, 면적 364.2ha, 투수층면적 160.7ha, 불투수층면적 203.5ha로 불투수율은 55.90%로 산정되었다. 대상지역인 안동지구 우수관로현황 조사결과 (30년빈도 강우강도 적용) 관로의 통수능 검토시 전체관로 26.97km 중 통수능 부족관로는 15.60km로 전체대비 약 57.8%로 나타났다. 안동지구 내 우수관거는 간선관로의 경우 10년빈도, 지선관로의 경우 5년빈도로 설계, 시공되어 있으므로 각종 공단이 입지한 시가지인 안동지구는 도로포장등으로 인해 불투수층이 대부분을 차지해, 강우시 도로표면 유출수의 증대로 침수피해가 가중되는 것으로 판단되었다. 이에 저영향개발기법을 적용하여 맨홀로 유입되는 직접유출(DCIA, Directly Connected Impervious Area)를 줄이고, 유지관리 등을 고려하여 경제성을 평가하여 향후 침수위험지구 관거개량시 저영향개발기법을 활용할 수 있도록 하고자 한다.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.9 no.4
• /
• pp.813-823
• /
• 2019

Supplier Relationship Management (SRM) is a strategic partnership activity for an enterprise and is expected to be a significant performance element in the current enterprise environment where uncertainty is growing. Despite the effective SRM allows companies to manage quality and inventory throughout their logistics procurement process with their suppliers and increase the profitability of the company, there is a scarce of theory about supplier relationship management (SRM) and many companies are not aware of the importance of SRM and depend only on simple electronic purchasing methods. Therefore, I analyze the H Company as a case company, which is a large domestic company and has reached 2,500 domestic and overseas suppliers. SRM process and its effects are evaluated as (1) Purchasing strategy division 2) Process division (3) IT infrastructure division. By analyzing SRM as one of the management strategies that bring the overall value of enterprise performance up, and by looking at how domestic large corporations manage their suppliers, I hope that manufacturers with many suppliers will recognize the importance of SRM and build an SRM tailored to their business.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.149-156
• /
• 2021

Among various implementation techniques of recommender systems, collaborative filtering selects nearest neighbors with high similarity based on past rating history, recommends products preferred by them, and has been successfully utilized by many commercial sites. Accurate estimation of similarity is an important factor that determines performance of the system. Various similarity measures have been developed, which are mostly based on integrating traditional similarity measures and several indices already developed. This study suggests a similarity measure of a novel approach. It separates the common rating area between two users by the magnitude of ratings, estimates similarity for each subarea, and integrates them with weights. This enables identifying similar subareas and reflecting it onto a final similarity value. Performance evaluation using two open datasets is conducted, resulting in that the proposed outperforms the previous one in terms of prediction accuracy, rank accuracy, and mean average precision especially with the dense dataset. The proposed similarity measure is expected to be utilized in various commercial systems for recommending products more suited to user preference.

• Cross-Cultural Studies
• /
• v.44
• /
• pp.393-410
• /
• 2016

This paper examines why Japan's nation branding strategy is not working in South Korea in spite of expanding relations between Korea and Japan. Japan has successfully managed its national reputation, which altered its image around the world. However, Japan's nation-image in South Korea has not kept up with its efforts internationally. Political and economic interactions between Korea and Japan have increased throughout the past decades since the normalization of diplomatic relations in 1965. Also, the normalization of cultural-social relations emerged after the Korean government policy restricting Japanese popular culture was removed in the 1990s and overseas travel was liberalized in 1989. In spite of the improvement in politico-cultural-social relations, trust-building efforts still stagnate between the two countries. This paper discusses the reasons behind this phenomenon and provides some suggestions to solve this issue.

• Journal of Convergence for Information Technology
• /
• v.9 no.7
• /
• pp.8-13
• /
• 2019

Recently, In line with the recent trend of the fourth industrial revolution, many companies and institutions have been increasingly applying automated technologies using artificial intelligence to various tasks. Particularly, due to the government's 52-hour workweek system, companies are increasingly struggling with manpower management. Therefore, they are interested in RPA (Robotic Process Automation) for office environment automation for efficient manpower management. It is being introduced in the back-office business in credit card companies, bank, insurance. These RPA solutions require AI-based recognition technology, scripting technology, business software API-related technologies, and various solutions such as Automate One, Automation Anywhere, UiPath, and Blue Prism are provided. This paper analyzes and describes the technology of RPA solution, the market trend, and the efficiency of RPA adoption.

• Journal of Aerospace System Engineering
• /
• v.16 no.6
• /
• pp.8-17
• /
• 2022

This paper presents a novel geometric modeling technique to predict the mechanical properties of an aircraft wing's skin-stringer integrated panel. Due to mechanical and adhesive fastening, this panel is vulnerable to stress concentration and debonding, so we designed it to integrate the skin and stringer using three-dimensional woven composites. Geometric modeling was conducted by measuring the geometric parameters of the specimen and defining the pattern of the yarns as functions. We used a weighted average model with iso-strain and iso-stress assumptions to predict the mechanical properties of the panel parts. We then compared the results of a finite element analysis with a compression test to verify the accuracy of our model. Our proposed technique proved to be more efficient than the traditional experimental method for predicting the mechanical properties of skin-stringer integrated panels.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.3
• /
• pp.555-564
• /
• 2022

Recently, cyberattacks are using hacking techniques utilizing intelligent and advanced malicious codes for non-face-to-face environments such as telecommuting, telemedicine, and automatic industrial facilities, and the damage is increasing. Traditional information protection systems, such as anti-virus, are a method of detecting known malicious URLs based on signature patterns, so unknown malicious URLs cannot be detected. In addition, the conventional static analysis-based malicious URL detection method is vulnerable to dynamic loading and cryptographic attacks. This study proposes a technique for efficiently detecting malicious URLs by dynamically learning malicious URL data. In the proposed detection technique, malicious codes are classified using machine learning-based feature selection algorithms, and the accuracy is improved by removing obfuscation elements after preprocessing using Weighted Euclidean Distance(WED). According to the experimental results, the proposed machine learning-based malicious URL detection technique shows an accuracy of 89.17%, which is improved by 2.82% compared to the conventional method.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.364-364
• /
• 2023

최근 환경부에서 발표한 「제3차(2021~2025) 강우유출 비점오염관리 종합대책(2020)」에 의하면, 우리나라는 지난 50년간 급격한 도시화, 산업화 과정을 거치면서 불투수면적이 전 국토의 약 22.4%에 달한다고 보고되고 있다. 특히 전체 소권역의 6%에 해당하는 51개 소권역의 경우 불투수 면적률 25%를 넘어서고 있는 것으로 조사되었다. 이러한 불투수면의 증가는 기후변화에 의한 영향으로 토양 침투량과 기저유출량을 감소, 갈수기 하천건천화 심화, 우기 표면유출수 증가를 가중시키며 이로인한 비점오염물질 유입 증가, 수질 악화의 원인으로 작용 될 수 있다. 이에 정부에서는 저영향개발(Low Impact Development, LID) 사업 및 친환경그린인프라(Green Infrastructure, GI) 기술요소를 적용하여 도시지역 기후위기 대응 수단의 일원으로 우수유출 저감, 물순환 구조 개선, 비점오염원을 관리하고자 '그린빗물인프라(Green Stormwater Infrastructure, GSI) 조성 사업'을 추진하여 공공청사를 중심으로 학교, 도서관, 체육시설, 공원 등 적용 범위를 확대하고 있다. 이에 본 연구에서는 기후변화에 가장 취약한 해안도시지역인 경상남도에 위치하고 있으며, 불투수면적이 높고 노후화된 소규모 청사 2곳을 시범 구역으로 선정하였다. 각 시범 구역별 GSI 시설 적용이 가능한 주차장, 화단, 옥상 등의 개선방안을 제시하였으며, 적용 규모를 달리하여 물순환·물 환경 개선 효과를 검증하였다. 검증에는 국내에서 개발된 K-LIDM 모형을 활용한 우수유출저감 및 직접유출체적 산정결과를 통해 물순환 효과를, 국립환경과학원에서 제시되고 있는 '토지계 지목별 발생부하원단위', 수질환경개선 보고서에서 제시된 침투형, 식생형 비점오염저감시설의 저감효율을 활용하여 물순환 저감효과를 분석하여 비교하였다.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.6 no.1
• /
• pp.39-48
• /
• 2016

The tacit knowledge transfer cultivate the value and mount of tacit knowledge. The tacit knowledge transfer plays the most important role for improving the competitiveness of the organization. Despite the tacit knowledge transfer is very important, the research related with tacit knowledge transfer has not been actively carried out. The barriers to tacit knowledge transfer interfere with the tacit knowledge transfer. The barriers to tacit knowledge transfer are lack of understanding knowledge experts, heavy over-work, insufficient compensation, trust shortage and knowledge stickiness. In order to overcome the barrier of the tacit knowledge transfer, it is necessary to promote knowledge broker. The knowledge broker is the foundation for the tacit knowledge transfer and the critical success factor for efficient tacit knowledge transfer. However, most research related on the knowledge broker had focused on the degree, centrality and density of the knowledge network. The framework is needed to performance indicator for diagnosing the tacit knowledge transfer. Therefore, we suggest the knowledge broker framework based on the social network analysis.