• 대한산업공학회지
• /
• 제40권4호
• /
• pp.375-381
• /
• 2014

Data mining is a process of discovering useful patterns or information from large amount of data. Decision tree is one of the data mining algorithms that can be used for both classification and prediction and has been widely used for various applications because of its flexibility and interpretability. Decision trees for classification generally generate a number of rules that belong to one of the predefined category and some rules may belong to the same category. In this case, it is necessary to determine the significance of each rule so as to provide the priority of the rule with users. The purpose of this paper is to propose a rule selection method in classification tree models that accommodate the umber of observation, accuracy, and effectiveness in each rule. Our experiments demonstrate that the proposed method produce better performance compared to other existing rule selection methods.

• 한국지능시스템학회논문지
• /
• 제21권1호
• /
• pp.86-99
• /
• 2011

사용자의 행동에 따른 의도 인식의 불확실성 때문에 사용자가 동일한 행동을 하더라도 상황에 따라 그 의도는 다르게 해석되며, 불확실성을 최소화함으로써 사용자 의도 인식의 정확성을 향상 시킬 수 있다. 본 논문에서는 사용자 의도 인식을 위한 온톨로지 기반의 새로운 방법을 제안하고, 불확실성을 최소화하는 방법을 제안한다. 제안하는 방법은 사용자 의도에 대한 온톨로지를 생성하고, 사용자 의도간 계층적 구조와 관계를 RuleML과 동적 베이지안 네트워크를 이용해서 정의하며, 온도, 습도, 시각 등의 수집된 센서 데이터와 정의된 RuleML을 통해 사용자 의도 인식을 보다 정확하게 하는 것이다. 로봇의 능동적 계획수립 방법의 성능을 평가하기 위해 시뮬레이터를 개발했고, 밝생 가능한 모든 상황에 대해 의도인식의 정확도를 측정하는 실험을 했으며, 이에 대한 결과를 제시하였다. 실험결과 비교적 높은 수준의 의도인식 정확도를 나타냈다. 그러나 불확실성을 내재한 행동이 보다 정확한 의도 인식을 방해한다는 것을 알 수 있었다.

• 지능정보연구
• /
• 제4권1호
• /
• pp.115-131
• /
• 1998

Customer service process is one of the most important processes in today's competitive business environment. Among the various activities of customer service process, equipment malfunction diagnosis activity should be performed fast and accurately. When a customer calls the service center and reports the observed symptoms, he/she describes them in layman's terms. Therefore, the customer-reported symptoms have not been considered helpful information for service representatives. However, in order to perform diagnosis activity fast and accurately, we need to make use of the customer-reported symptoms actively. In this research, we developed three systems called R-EMD (Rule-based Equipment Malfunction Diagnostic system), C-EMD (Case-based Equipment Malfunction Diagnostic system) and R&C-EMD (Rule & Case-based Equipment Malfunction Diagnostic system), each of which diagnoses equipment malfunctions using the customer-reported symptoms. R&C-EMD is a hybrid system that utilizes both rule-based and case-based technologies. The diagnosis rules used in R&C-EMD and R-EMD were not acquired from service manuals or interviews with service representatives. Rater, we extracted them directly from the past diagnosis cases based on symptoms' frequencies. By this way, we were able to overcome the knowledge acquisition bottleneck. Using the real 100 malfunction diagnosis cases, we evaluated the performances of R&C-EMC, R-EMD and C-EMD in terms of speed and accuracy. In diagnosis time, R&C-EMD took longer than R-EMD and shorter than C-EMD. However, R&C-EMC was the best in accuracy.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.126-128
• /
• 2004

As e-mail is becoming increasingly important in every day life activity, mail users spend more and more time organizing and classifying the e-mails they receive into folder. Many existing recommendation systems or text classification are mostly focused on recommending the products for the commercial purposes or web documents. So this study aims to apply these application to e-mail more necessary to users. This paper suggests a dynamic recommendation agent system based on Rule Filtering Component recommending the relevant category to enable users directly to manage the optimum classification when a new e-mail is received as the effective method for E-Mail Management. Moreover we try to improve the accuracy as eliminating the limits of misclassification that can be key in classifying e-mails by category. While the existing Bayesian Learning Algorithm mostly uses the fixed threshold, we prove to improve the satisfaction of users as increasing the accuracy by changing the fixed threshold to the dynamic threshold. We designed main modules by rule filtering component for enhanced scalability and reusability of our system.

• 한국항만학회지
• /
• 제15권1호
• /
• pp.87-97
• /
• 2001

The calculation of earthwork plays a major role in plan or design of many civil engineering projects, and thus it has become very important to advanced the accuracy of earthwork calculation. Current method used for estimating the volume of pit excavation assumes that the ground profile between the grid points is linear(trapezoidal rule), or nonlinear(simpson's formulas). In this paper the spot height method, least square method, and chamber formulas, Chen and Lin method are compared with the volumes of the pits in these examples. As a result of this study, algorithm of chen and Lin me쇙 by spline method should provide a better accuracy than the spot height method, least square method, chamber formulas. The Chen and Lin formulas can be used for estimating the excavation volume of a pit divide into a grid with unequal intervals. From the characteristics of the cubic spline polynomial, the modeling curve of the Chen and Lin method is smooth and matches the ground profile well. Generally speaking, the nonlinear profile formulas provide better accuracy than the linear profile formulas. The mathematical model mentioned make an offer maximum accuracy in estimating the volume of a pit excavation.

• 품질경영학회지
• /
• 제23권3호
• /
• pp.126-139
• /
• 1995

We describe a formal approach to the construction of optimal classification rule for the two-group normal classification with equal population mean problem. Based on the utility function of Bernardo, we suggest a balanced design for the classification and construct the optimal rule under the balanced design condition. The rule is characterized by a constrained minimization of total risk of misclassification, the constraint of which is constructed by the process of equation between expected utilities of the two group conditional densities. The efficacy of the suggested rule is examined through numerical studies. This indicates that, in case little is known about the relative population sizes, dramatic gains in accuracy of classification result can be achieved.

• 한국측량학회지
• /
• 제30권4호
• /
• pp.397-404
• /
• 2012

농업과 관광이 주요 산업인 제주지역은 소득 증대를 위해 노지재배에서 시설재배로의 전환이 활발하게 진행되고 있으므로 하우스재배지에 대한 지속적인 현황 파악이 필요하다. 이에 본 연구에서는 고해상도 위성영상을 이용하여 하우스재배지 탐지를 위한 효과적인 영상분류 방법을 제시하고자 하였다. Formosat-2 위성영상을 대상으로 감독분류와 규칙기반분류 방법을 적용하여 하우스재배지를 분류하였으며, 두 가지 결과를 연계하여 하우스재배지 탐지를 위한 정확도 향상 방안을 모색하였다. 각 분류 방법별 결과는 육안 탐지 결과와의 비교를 통해 정확도를 산출하였다. 연구 결과, 감독분류 방법 중 마하라노비스 거리법이 가장 높은 탐지 결과를 얻을 수 있었으며 감독분류 결과와 규칙기반분류 결과의 연계 시 탐지 정확도가 향상됨을 확인하였다. 향후 감독분류 결과와 규칙기반분류 결과의 연계 과정에 대한 추가적인 연구가 이루어진다면 하우스재배지의 효율적인 탐지가 가능할 것으로 기대된다.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.128-132
• /
• 2001

In this paper, we evaluate and contrast four neural network rule extraction approaches for credit scoring. Experiments are carried our on three real life credit scoring data sets. Both the continuous and the discretised versions of all data sets are analysed The rule extraction algorithms, Neurolonear, Neurorule. Trepan and Nefclass, have different characteristics, with respect to their perception of the neural network and their way of representing the generated rules or knowledge. It is shown that Neurolinear, Neurorule and Trepan are able to extract very concise rule sets or trees with a high predictive accuracy when compared to classical decision tree(rule) induction algorithms like C4.5(rules). Especially Neurorule extracted easy to understand and powerful propositional if -then rules for all discretised data sets. Hence, the Neurorule algorithm may offer a viable alternative for rule generation and knowledge discovery in the domain of credit scoring.

• 전자공학회논문지CI
• /
• 제41권4호
• /
• pp.59-66
• /
• 2004

본 논문은 정적 분석을 하기 위해서 SG(String Graph)를 정의하고 ASG(Alive String Graph)를 정의한다. String의 사활의 판단을 위해 돌이 포함되지 않은 상태와 돌이 포함된 상태로 나누어 Rule을 적용한다. 돌이 포함되지 않은 상태에서 SR(String Reduction), ER(Empty Reduction), ET(Edge Transform), 그리고 CG(Circular Graph) Rule을 정의한다. 돌이 포함되어진 상태에서 DESR(Dead Enemy Strings Reduction)과 SCSR(Same Color String Reduction) Rule을 정의한다. 이러한 Rule을 사용하여 SG(String Graph)가 ASG(Alive String Graph)인지를 평가한다. 그리고 관절점의 개수에 따라 사활을 판단하기 위해 APC(Articulation Point Check)를 사용하였다. 우리의 방법에 대한 성능은 Computer Go Test Collection의 IGS_31_counted 문제 집합에 대해 실험했다. 이 Test set은 11,191 Points와 1,123 Strings을 가진다. 우리는 실험 결과에서 Points에 대해 92.5% 정확성과 Strings에 대해 95.7%의 정확성을 얻었다.

• ETRI Journal
• /
• 제25권4호
• /
• pp.219-230
• /
• 2003

This paper describes a rule-based approach for syntactic disambiguation used by the English sentence parser in E-TRAN 2001, an English-Korean machine translation system. We propose Parser's Ambiguity Type Information (PATI) to automatically identify the types of ambiguities observed in competing candidate trees produced by the parser and synthesize the types into a formal representation. PATI provides an efficient way of encoding knowledge into grammar rules and calculating rule preference scores from a relatively small training corpus. In the overall scoring scheme for sorting the candidate trees, the rule preference scores are combined with other preference functions that are based on statistical information. We compare the enhanced grammar with the initial one in terms of the amount of ambiguity. The experimental results show that the rule preference scores could significantly increase the accuracy of ambiguity resolution.