• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 춘계정기학술대회
• /
• pp.243-252
• /
• 2001

Recently, as most companies recognize the importance of the customer relationship management, they strongly believe that they must know who their customers are. The job of a customer is very important information for us to understand the customer. However, since most customers are reluctant to reveal themselves, they do not let us know their jobs, and even provide false information about their jobs. The target domain of our research is mobile telecommunication. In this research, we developed a system that identifies the customer's job by utilizing the Call Detailed Record. From the Call Detailed Record, we extracted such variables as 'Average Monthly Payment'and 'Age of the Customer'and so forth. Moreover, we generated many summary variables and derived variables such as 'Number of Calls during Work Hours in Weekday', and 'Ratio of Calls from other Mobile Telephone'. Using artificial neural networks, we developed a two-step Job Identification System. In the first step, it identifies the four job classes then in the second step, it subdivides these four job classes into seven jobs. The accuracy of identifying the seven jobs was 69.1%.

• 한국멀티미디어학회논문지
• /
• 제7권7호
• /
• pp.1009-1016
• /
• 2004

시대의 환경적 변화에 따른 소프트웨어 개발의 발달은 빠른 개발과 높은 생산성을 향상시키기 위한 소프트웨어의 재사용 기술의 확산으로 컴포넌트 기반 개발 방법론이 널리 사용되기 시작했다. 이러한 컴포넌트 기반 개발에서 재사용 가능한 독립적인 컴포넌트의 식별은 컴포넌트 기반 시스템 구축을 위하여 가장 중요한 작업이다. 컴포넌트 식별 방법을 제시하고 있는 기존 방법론들에서는 비즈니스 컴포넌트를 식별함에 있어서 개발자의 경험적 토대를 기반으로 독립적인 컴포넌트를 식별하도록 제시하고 있으므로 평이한 개발자에 의한 비즈니스 컴포넌트 식별이 쉽지 않은 문제점을 가지고 있다. 따라서 본 논문에서는 시스템 컴포넌트를 먼저 식별한 후 비즈니스 컴포넌트를 식별하고 비즈니스 컴포넌트를 식별하기 위하여 분석 클래스 간의 메소드 호출 유형과 메소드 호출 방향에 의한 클래스 간의 종속적 특성과 의존의 강도를 부여하여 효율적으로 컴포넌트를 식별할 수 있는 기준과 방법을 제안한다. 또한 사례 연구를 통하여 시스템 컴포넌트를 중심으로 비즈니스 컴포넌트가 효율적으로 식별됨을 검증한다.

• Journal of Forest and Environmental Science
• /
• 제32권1호
• /
• pp.68-73
• /
• 2016

We investigated structure and intensity of 267 echolocation calls that were collected from the five Korean Myotis species (M. nettereri, M. petax, M. ikonnikovi, M. macrodactylus and M. formosus). All the Myotis species produced typical FM call pattern with similar echolocation call shapes and outer shapes, producing steep, downward frequency-modulated calls. A pulse has two harmonies, which consist of the first harmony with wider bandwidth and the second harmony with narrower bandwidth. The PF of the first harmony is higher than that of the second harmony. The typical FM call structure, with two harmonies and wide bandwidth, might be highly related to fast flying and wide screening in the dense forests. In classification of the echolocation calls by DFA, most of calls from the five species could be well correctly classified. All calls of M. nettereri (100% of 17 calls), M. formosus (95.5% of 22 calls) and M. ikonnikovi (85.7% of 70 calls) could be well discriminated from those of the other species, whereas calls of M. petax and M. macrodactylus could be discriminated by 70.4% of 98 calls and 76.7% of 60 calls, respectively. Our results indicate that the five Korean Myotis species can be well identified by the echolocation calls with high correct classification by DFA.

• 정보보호학회논문지
• /
• 제27권1호
• /
• pp.91-101
• /
• 2017

API(Application Program Interface) 콜 시퀀스 분석은 분석 대상 프로그램에서 API 콜 정보를 추출한 후 분석하는 기법으로 다른 기법들에 비해 대상의 행위를 특징할 수 있는 장점이 있다. 하지만 기존의 API 콜 시퀀스 분석기법은 동일한 기능을 수행하는 함수를 상이한 함수로 잘못 식별하여 분석을 수행하는 문제점이 존재한다. 본 연구에서는 API 각각을 추상화시키는 방식을 추가하여 기존의 식별 문제를 해결하고 분석 성능을 향상시키고자 한다. 그 후 분석 대상들에서 획득한 추상화된 API 콜 시퀀스에 LSH(Locality Sensitive Hashing) 기법을 적용하여 각 분석 대상들 간의 유사도를 계산하고 유사한 유형끼리 클러스터를 형성하는 과정을 수행하였다. 본 연구는 악성코드 분석 시 악성코드의 유형을 파악하는 데 요긴하게 사용할 수 있으며, 최종적으로는 해당 유형 정보를 기반으로 악성코드 분석의 정확도를 향상시키는 데 기여할 수 있다.

• 한국디자인학회:학술대회논문집
• /
• 한국디자인학회 2001년도 Bulletin of The 5th Asian Design Conference International Symposium on Design Science
• /
• pp.70.2-70
• /
• 2001

• 한국응급구조학회지
• /
• 제6권1호
• /
• pp.77-86
• /
• 2002

The purposes of this research which was conducted by surveying lost/added unit hours reports, unit hour demand analysis worksheets from prehospital care reports of two squads in Kyonggi Provincial Fire and Disaster Headquarters for 20 weeks (January 1, 2002 - May 20, 2002) are to get Unit Hour Utilizations. Call Demands such as Unit Hour Demand, Simple Average Demand, High Average Demand, Peak Average Demand, the High Actual Demand. The conclusions from this analysis were summarized as follows: (1) By revealing Unit Hour Produced 3223.9, Call Volume 964, Unit Hour Utilization 0.299 at the Squad A and Unit Hour Produced 3328.4, Call Volume 901, Unit Hour Utilization 0.271 at the Squad B induced Korean Squads to chance identification, definition, direction of Unit Hour Utilization. (2) By revealing Simple Average Demand 7.4 on Monday Tuesday, High Average Demand 9.6 on Tuesday Friday. Peak Average Demand 11.5 on Tuesday, the High Actual Demand 12 on Tuesday Wednesday at the Squad A and Simple Average Demand 6.8 on Sunday, High Average Demand 10.4 on Monday, Peak Average Demand 11.5 on Monday, the High Actual Demand 13 on Monday at the Squad B enabled Korean Squads to utilize System Status Management. (3) The Maximum Calls per Unit Hour were 115 for 23:00~23:59, the Minimum Calls per Unit Hour were 46 for 05:00~05:49 in two squads. The Maximum Calls per Unit Hour were 7.4 on Tuesday Saturday, the Minimum Calls per Unit Hour were 6.1 on Thursday at the Squad A. The Maximum Calls per Unit Hour were 7.3 on Monday Saturday, the Minimum Calls per Unit Hour were 5.6 on Thursday at the Squad B. (4) Analyzing demand for EMTs in the optimum emergency medical service of Korea, we have been able to utilize this Unit Hour Utilization in company with the established estimation methods such as international comparisons or the number of ambulances for scientific reasonable estimation. (5) These Call Demands which were limited to the demand time in this study will make us expect some following studies including demand time, demand time, demand map for Strategic Deployment.

• 산업경영시스템학회지
• /
• 제19권38호
• /
• pp.169-179
• /
• 1996

The object of this paper is to give an overview of one method of modeling and analysing situations involving inter-identification. Hypergame analysis is used as this approach. Hypergame analysis is one of what we call soft system approaches. In this paper, We first reformulate concept of the simple hypergame and define the hypergames with inter-identification as a system consisting of simple hypergames connected by the mutual identification. We propose a definition of solutions for them. Based on the formulation, We derives existence conditions of the solutions. We then apply the framework to a realistic problem. i. e, America-North korea conference problem to demonstrate the validity of the derived theoretical results as well as In obtain some suggestions to improve the problematic situation.

• 한국화재소방학회논문지
• /
• 제30권4호
• /
• pp.135-140
• /
• 2016

구급 신고 전화를 받는 상황요원의 신속하고 정확한 신고자 상태 파악과 적확한 조치 판단을 돕고, 정확한 다중출동을 위한 한국형 응급상황관제 시스템의 음성인식 시스템의 자동적인 처리를 지원하기 위하여 실제 구급 신고 전화의 음성 자료 분석을 통해 한국어의 응급 증상 표현 목록을 작성하고 실제 신고전화에 나타난 증상 언어표현의 특징을 파악하였다. 이러한 언어 목록과 특성들은 일선 현장의 상황요원의 교육에도 유용할 것이다.

• 한국IT서비스학회지
• /
• 제15권3호
• /
• pp.115-125
• /
• 2016

Novels includes various character names, depending on the genre and the spatio-temporal background of the novels and the nationality of characters. Besides, characters and their names in a novel are created by the author's pen and imagination. As a result, any proper noun dictionary cannot include all kind of character names which have been created or will be created by authors. In addition, since Korean does not have capitalization feature, character names in Korean are harder to detect than those in English. Fortunately, however, Korean has postpositions, such as "-ege" and "hante", used by a sentient being or an animate object (noun). We call such postpositions as animate postpositions in this paper. In a previous study, the authors manually selected character names by referencing both Wikipedia and well-known people dictionaries after utilizing Korean morpheme analyzer, a proper noun dictionary, postpositions (e.g., "-ga", "-eun", "-neun", "-eui", and "-ege"), and titles (e.g., "buin"), in order to extract social networks from three novels translated into or written in Korean. But, the precision, recall, and F-measure rates of character identification are not presented in the study. In this paper, we evaluate the quantitative contribution of animate postpositions to character identification from novels, in terms of precision, recall, and F-measure. The results show that utilizing animate postpositions is a valuable and powerful tool in character identification without a proper noun dictionary from novels translated into or written in Korean.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2017년도 춘계학술발표대회
• /
• pp.728-730
• /
• 2017

The proposed application design for emergency medical system includes the functions that help securing the window of opportunity for the patients in an emergency situation and efficiently link rescue agency, emergency medical treatment center and patients together. First, the treatment time can be saved at the emergency room by understanding the patient's condition by entering his/her health information such as anamnesis, family history, social history and blood type together with an identification number. Also, if the siren function which signals whereabouts of patients to the rescue crew is used, it will be much easier to find the location of the patient in need. The design allows rescue crew to call the patient to check whether he/she is conscious or not. Just by receiving the call, he/she will be deemed conscious.