• Title/Summary/Keyword: 적중

Search Result 394, Processing Time 0.026 seconds

A Dynamic feature Weighting Method for Case-based Reasoning (사례기반 추론을 위한 동적 속성 가중치 부여 방법)

  • 이재식;전용준
    • Journal of Intelligence and Information Systems
    • /
    • v.7 no.1
    • /
    • pp.47-61
    • /
    • 2001
  • Lazy loaming methods including CBR have relative advantages in comparison with eager loaming methods such as artificial neural networks and decision trees. However, they are very sensitive to irrelevant features. In other words, when there are irrelevant features, larry learning methods have difficulty in comparing cases. Therefore, their performance can be degraded significantly. To overcome this disadvantage, feature weighting methods for lazy loaming methods have been studied. Most of the existing researches, however, were focused on global feature weighting. In this research, we propose a new local feature weighting method, which we shall call CBDFW. CBDFW stores classification performance of randomly generated feature weight vectors. Then, given a new query case, CBDFW retrieves the successful feature weight vectors and designs a feature weight vector fur the query case. In the test on credit evaluation domain, CBDFW showed better classification accuracy when compared to the results of previous researches.

  • PDF

The Implementation Performance Evaluation of PR-File Based on Circular ar Domain (순환도메인을 기반으로 하는 PR-화일의 구현 및 성능 평가)

  • Kim, Hong-Ki;Hwang, Bu-Hyun
    • The Transactions of the Korea Information Processing Society
    • /
    • v.3 no.1
    • /
    • pp.63-76
    • /
    • 1996
  • In this paper, we propose a new dynamic spatial index structure, called PR -file, for handling spatial objects and the modified hierarchical variance which measures the degree of spatial locality at each level. Under the assumption that a multidimensional search space has a circular domain, PR-file uses the modified hierarchical variance for clustering spatially adjacent objects. The insertion and splitting algorithms of PR_file preserve and index which has a low hierarchical variance regardless of object distributions. The simulation result shows that PR- file has a high hit ratio during a retrieval of objects by using an index with low hierarchical variance. And it shows a characteristic that the larger the bucket capacity, the higher the bucket utilization.

  • PDF

A Study on Improvement and Problem of Ready-made Reading Spectacles (상품화된 근용안경의 문제점 및 개선 방안에 관한 연구)

  • Lee, Hark Jun
    • Journal of Korean Ophthalmic Optics Society
    • /
    • v.1 no.1
    • /
    • pp.85-91
    • /
    • 1996
  • This is a study of the measurement of inter papillary constance (P.D) in 702 old aged farmers (aged over 45) and the comparision of frame size and distance space of optical center (O.C) from 240 Ready-made Reading spectacles. The average of P.D in male (62.83mm) is greater than in female (61.18mm), and the O.C of Ready-made Reading spectacles of Plastic lens (71.2mm) longer than glass lens (70.8mm). The correction prism power by wearing Reading spectacles in male was 0.7prism to 3.6prism and in female was 0.9prism to 4.4prism. So the prism power in female is greater than in male.

  • PDF

Development of Engineering Program for APR1400 Feedwater Supplying System (APR1400 급수공급계통 엔지니어링 프로그램 개발)

  • Yeom, Dong Un;Ju, Tae Young;Hyun, Jin Woo
    • Journal of Energy Engineering
    • /
    • v.26 no.2
    • /
    • pp.12-22
    • /
    • 2017
  • Korea Hydro & Nuclear Power Co. (KHNP) has implemented engineering programs for operating nuclear power plants. Engineering programs are maintenance rule (MR), functional importance determination (FID), single point vulnerability (SPV) and functional equipment group (FEG). Recently, KHNP has developed engineering programs for APR1400 feedwater supplying system to establish the advanced engineering system and will verify the suitability of engineering programs through implementing in new nuclear power plant. Consequently, it is expected that the reliability of APR1400 feedwater supplying system will be improved by implementing engineering programs.

A Study on the Estimation of Economic Population Statistical Model by Computer Simulation (컴퓨터 시뮬레이션에 의한 경제인구 예측 통계 모형에 관한 연구)

  • 정관희
    • Journal of the Korea Computer Industry Society
    • /
    • v.4 no.12
    • /
    • pp.1033-1042
    • /
    • 2003
  • In this study, the economic population prediction by computer simulation has been studied by using statistical model. The forecast of future population based on that of the past is a very difficult problem as uncertain conditions are modeled in it. Even if a thought forecast is possible, world-wide cultures and the local culture emotion the cultures of the world and out country can not be predicted due to rapid change and the estimation of population is ‘nowadays more and more’ difficult to be made good guess. In the estimation of economic population, by using the census population from 1960 to 1990, and using ARIMA model developed by Box and Jenkins, the estimation has been done on the economic population until 2021 according to age as appeared table and appendix. This kind of forecast would have both good point and weak point of ARIMA model theory saying that prediction can be done only by the economic population.

  • PDF

An Efficient Load Balancing Algorithm for Web Server Cluster (웹 서버 클러스터를 위한 효율적인 부하 분배 알고리즘)

  • Kim, Sung-Soo;Chung, Ji-Yung
    • Journal of KIISE:Information Networking
    • /
    • v.28 no.4
    • /
    • pp.550-558
    • /
    • 2001
  • Although the web is becoming a widely accepted medium, it provides relatively poor performance and low availability. A cluster consists of a collection of interconnected stand-alone computers working together and provides a high-availability solution in application area such as web services or information systems. In this paper, we propose a load balancer architecture under the web server cluster that provides high-availability, high performance and scalability. In addtion, we propose an efficient load balancing algorithm that considers access rate and size of documents. Specially, our algorithm does not require the nodes running under similar configurations and the same operating system. Also, server cache can be utilized more efficiently.

  • PDF

A Study on the Performance of Prefetching Web Cache Proxy (Prefetch하는 웹 캐쉬 프록시의 성능에 대한 연구)

  • 백윤철
    • Journal of the Korea Computer Industry Society
    • /
    • v.2 no.11
    • /
    • pp.1453-1464
    • /
    • 2001
  • Explosive growth of Internet populations results performance degradations of web service. Popular web sites cannot provide proper level of services to many requests, and such poor services cannot give user a satisfaction. Web caching, the remedy of this problem, reduces the amount of network traffic and gives fast response to user. In this paper, we analyze the characteristics of web cache traffics using traces of NLANR(National Laboratory for Applied Network Research) root caches and Education network cache in Seoul National University. Based on this analysis, we suggest a method of prefetching and we discuss the gains of our prefetching. As a result, we find proposed prefetching enhances hit rate up to 3%, response time up to 5%.

  • PDF

Verifying the Validity of the Qualitative Evaluation Indexes for Venture Firms' Investment Review: Case Study (벤처기업 투자 심사를 위한 정성 평가 지표의 유효성 검증: 사례연구)

  • Kim, Byounggwan;Kim, Wanki
    • Journal of Technology Innovation
    • /
    • v.25 no.4
    • /
    • pp.79-105
    • /
    • 2017
  • As the size of venture firm's operating funds continues to increase, the scope of work of the investment jurisdiction is increasing dramatically as well. However, investment decisions vary widely, depending on the competence of the judges. This follow-up study recommends verifying the validity of the effectiveness of venture investments by validating the efficacy of assessing venture investment indexes. After verifying the assessment indexes for 100 venture firms, the study noted that the efficacy of the survey as a qualitative evaluation measure was approximately 85% hit, which can act as a yardstick for investment decisions. The results of this study can contribute toward the decision making power of venture companies in terms of investments.

An Effective Backtracking Search Algorithm for the P2P Resources (효과적인 역 추적 P2P 자원 검색 알고리즘)

  • Kim, Boon-Hee
    • Journal of the Korea Society of Computer and Information
    • /
    • v.12 no.6
    • /
    • pp.49-57
    • /
    • 2007
  • The P2P distributed systems are proceeded various studies lively to use the idleness computing resources under the network connected computing environments. It's a general mean to communication from the peer of the shortest downloaded time among same target files to be searched. The P2P search algorithms are very important primary factor to decide a real downloaded time in the criteria to select the peer of a shortest downloaded time. However the peer to give resources could be changed into offline status because the P2P distributed systems have very weakness connection. In these cases. we have a choice to retransmit resources mainly. In this study, we suggested an effective backtracking search algorithm to improve the performance about the request to retransmit the resource.

  • PDF

An Efficient Spatial Data Cache Algorithm for a Map Service in Mobile Environment (모바일 환경에서 지도 서비스를 위한 효율적인 공간 데이터 캐시 알고리즘)

  • Moon, Jin-Yong
    • Journal of Digital Contents Society
    • /
    • v.16 no.2
    • /
    • pp.257-262
    • /
    • 2015
  • Recently, the interests of mobile GIS technology is increasing with the spread of wireless network, the improvement of mobile device's performances, and the growth of demands about mobile services. Providing services in a wireless environment with existing wired-based GIS solutions have many limitations such as slow communication, processing rates and screen size. In this paper, we propose a cache algorithm on client side to solve the above problems. The proposed algorithm demonstrates the performance improvement over known studies by utilizing unit time and spatial proximity. In addition, this paper conducts a performance evaluation to measure the improvement in algorithm efficiency and analyzes the results of the performance evaluation. When spatial data queries are conducted, according to our performance evaluation, hit rate has been improved over the existing algorithms.