• Proceedings of the Korea Contents Association Conference
• /
• 2019.05a
• /
• pp.447-448
• /
• 2019

생명 공학 분야에서는 노이즈가 많고 불완전한 데이터 집합의 사용이 많이 이루어진다. 불완전한 그래프에서 구조적 차이를 고려한 근사 서브 그래프 매칭에 대한 활용이 이루어지고 있다. 본 논문에서는 기존 기법에서 모든 데이터 및 경우의 수를 색인하는 과도한 색인 문제와 계산 비용 감소를 위한 요약 색인 기법을 제안한다. 구조적 차이 정보를 저장하기 위해서 특정 정점간의 최단 거리 값을 관리하고, 색인 부하 감소 및 일관성을 위해 요약 색인에 대한 간결화 작업을 수행한다.

• The KIPS Transactions:PartD
• /
• v.11D no.6
• /
• pp.1287-1294
• /
• 2004

Recently relationships between reliability measures and the coverage have been developed for evaluation of software reliability. Particularly the mean value function of the coverage-based software reliability growth model is important because of its key role in rep-resenting the software reliability growth. In this paper, we first review the problems of the existing mean value functions with respect to the assumptions on which they are based. Then a new mean value function is proposed. The new mean value function is developed for a general testing environment in which imperfect fault detection and repeated construct execution are allowed. Finally performance of the proposed model is empirically evaluated by applying it to a real data set.

• Journal of the Korea Convergence Society
• /
• v.12 no.8
• /
• pp.39-45
• /
• 2021

This paper discusses how to handle incomplete data including missing values. Optimally processing the missing value means obtaining an estimate that is the closest to the original value from the information contained in the training data, and replacing the missing value with this value. The way to achieve this is to use a decision tree that is completed in the process of classifying information by the classifier. In other words, this decision tree is obtained in the process of learning by inputting only complete information that does not include loss values among all training data into the C4.5 classifier. The nodes of this decision tree have classification variable information, and the higher node closer to the root contains more information, and the leaf node forms a classification region through a path from the root. In addition, the average of classified data events is recorded in each region. Events including the missing value are input to this decision tree, and the region closest to the event is searched through a traversal process according to the information of each node. The average value recorded in this area is regarded as an estimate of the missing value, and the compensation process is completed.

• Agrochemical news magazine
• /
• v.21 no.10 s.163
• /
• pp.5-7
• /
• 2000

• Annual Conference on Human and Language Technology
• /
• 1996.10a
• /
• pp.393-399
• /
• 1996

자연언어 대화에서 사용자의 정확한 의도(Intention)를 인지함에 있어서 나타나는 문제는, 자연언어 대화체의 생략성이 강한 문장의 불완전성 외에도, 여러 연속되는 대화체 문장에 분산되어 나타나는 사용자의 의도를 정확히 파악하는 것이다. 이러한 불완전한 대화체 문장 속에 산재되어 있는 사용자의 의도를 빠르고 신뢰성 있게 인지하여, 사용자와 시스템간의 원활한 자연언어 대화 상호작용 (Interaction)을 가능하게 하기 위하여 플랜 인지 시스템의 이용은 매우 효과적으로 보인다. 현재까지 개발된 대부분의 플랜 인지시스템들은 사용자의 액션 분석 및 플랜의 인지를 통하여 HCI를 지원하는 측면에 (예: 지능형 도움말) 집중되어 있다. 본 논문은 지역 광고 신문에 실린 매입-매도광고 데이타베이스의 검색을 위한 Natural language dialogue user interface에서 사용자 의도를 인지할 수 있는 플랜 인지 시스템을 기술하고 있다.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.6
• /
• pp.51-58
• /
• 2015

This paper suggests assignment-swap algorithm with time complexity O(mn) to obtain the optimal solution for large-scale of transportation problem (TP) with incomplete cost lists. Generally, the TP with complete cost lists can be solved with TSM (Transportation Simplex Method). But, we can't be solved for large-scale of TP with TSM. Especially. It is hard to solve for large-scale TP with incomplete cost lists using TSM. Therefore, experts simply using commercial linear programming package. Firstly, the proposed algorithm applies assignment strategy of transportation quantity to ascending order of transportation cost. Then, we reassign from surplus of supply to shortage of demand. Secondly, we perform the 2-opt and 1-opt swap optimization to obtain the optimal solution. Upon application to $31{\times}15$ incomplete cost matrix problem, the proposed assignment-swap algorithm more improves the solution than LINGO of commercial linear programming.

• Journal of Korean Society of Transportation
• /
• v.30 no.5
• /
• pp.83-90
• /
• 2012

Driver ordinarily takes sudden braking when urgent situation is developed or when the vehicle is involved in an unexpected accident. Therefore, the most common trace at a traffic accident scene is skid mark. Currently, in investigating traffic accident, overspeed is determined by the length of skid mark. However, in order to identify accurate cause of accident, estimation of pre-braking speed which takes into account speed reduction during transient time should be considered as a requirement. In a recent study, several ways to estimate pre-braking speed were suggested, but none considered to differentiate the decelerating transient brake section and skidding section. This study analyzed trends of decelerating transient brake section and skidding section by real braking test.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.2
• /
• pp.231-240
• /
• 2010

If only fixed effects exist in a 4 $\times$ 4 balanced incomplete block design, powers of FR statistic for testing a main effect show the highest level with a few replications. Under the exponential and double exponential distributions, FR statistic shows relatively high powers with big differences as compared with the F statistic. Further in a traditional balanced incomplete block design, powers of FR statistic having a fixed main effect and a random block effect show superior preference for all situations without regard to the effect size of a main effect, the parameter size and the type of population distributions of a block effect. Powers of FR statistic increase in a high speed as replications increase. Overall power preference of FR statistic for testing a main effect is caused by unique characteristic of a balanced incomplete block design having one main and block effect with missing observations, which sensitively responds to small increase of main effect and sample size.

• Journal of KIISE
• /
• v.42 no.2
• /
• pp.190-202
• /
• 2015

Much research has been conducted on location-based intelligent personal assistants that can understand a user's intention by learning the user's route model and then inferring the user's destinations and routes using data of GPS and other sensors in a smartphone. The intelligence of the location-based personal assistant is contingent on the accuracy and efficiency of the real-time predictions of the user's intended destinations and routes by processing movement information based on uncertain sensor data. We propose a robust particle filter based on Dynamic Bayesian Network model to infer the user's routes. The proposed robust particle filter includes a particle generator to supplement the incorrect and incomplete sensor information, an efficient switching function and an weight function to reduce the computation complexity as well as a resampler to enhance the accuracy of the particles. The proposed method improves the accuracy and efficiency of determining a user's routes and destinations.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.1
• /
• pp.9-21
• /
• 2022

Mighty is an imperfect information game, similar to the internationally popular four-player card game Bridge, but more complex in terms of game rules and operation. An environment for exploring and analyzing the strategy of the Mighty Game is required, but compared to the development of many simulators for strategy analysis of other card games such as Bridge, there is no analysis tool for the Mighty Game. Even the definition and understanding of the Mighty game at the academic level is lacking. To solve these problems, this paper systematically defined the procedures and rules of the Mighty Game. And based on this definition, we implemented a simulator that can learn Mighty game and analyze various strategies. For the usability and accessibility of the service, the simulator was developed with JavaScript, and various analysis functions are provided in the web environment. Lastly, comparative analysis with other trick-taking games dealt with in the related research domain showed that the Mighty game has its value as an incomplete information game and that there are many characteristics that make it easy to apply AI-based learning methods.