• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.57-59
• /
• 1998

소프트웨어의 고품질화를 추구하는 것은 필수적인 일이다. 좋은 품질의 소프트웨어를 획득 또는 개발하기 위해서는 S/W 품질평가에 대한 효율적인 방법이 요구되고 있다. S/W 품질평가는 객관적이고 정량적으로 평가되어야 하므로 본 논문에서는 S/W 품질평가에 대한 표준 및 기준, 방침과 전문가의 지식을 반영한 규칙기반 시스템을 이용하여 평가함으로써 정확하고 신뢰성을 보장하도록 설계하였다. 특히 쉽게 지식을 변경 또는 추가할 수 있도록 규칙기반 시스템으로 설계하였으며, 이러한 규칙기반 시스템을 이용하여 질의 응답을 통해 쉽고 효율적으로 S/W 품질을 평가할 수 있는 기반/기초기술을 제공하였다.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.12
• /
• pp.124-131
• /
• 1994

In this paper, we propose a new approach of solving the stereopsis problem with a discrete-time cellular neural network(DTCNN) where each node has connections only with its local neithbors. Because the matching process of stereo correspondence depends on its geometrically local characteristics, the DTCNN is suitable for the stereo correspondence. Moreover, it can be easily implemented in VLSI. Therefore, we employed a two-layer DTCNN with dual templates, which are determined with the back propagation learning rule. Based on evaluation of the proposed approach for several random-dot stereograms, its performance is better than that of the Marr-Poggio algorithm.

• Journal of the military operations research society of Korea
• /
• v.28 no.1
• /
• pp.67-82
• /
• 2002

In this paper, we consider a rule of application of PRICE(Parametric Review of Information for Costing and Evaluation) model to the environment of Korean defense industry. The PRICE model which is a computer model to estimate the cost of an acquisition program, was developed for the regulation of defense acquisition program in the United States. Therefore, it is essential for us to figure out how we can adopt it under our defense acquisition regulations. We will give an alternative method to apply the PRICE model to the mapping problem between two regulations.

• 한국신재생에너지학회:학술대회논문집
• /
• 2011.05a
• /
• pp.195.2-195.2
• /
• 2011

The borehole heat exchanger of Geothermal Heat Pump (GHP) system should be sustainable and cost effective for long term operation. To guaranty the performance of the system thermal Response Tests (TRTs) with simple recommended procedures have been applied in many countries. Korea government developed a standard TRT procedure in order to control the quality on GHP projects. In the TRT procedure interpretation method has a rule that data set has to be interpreted by the line source model(LSM). The LSM employes some assumptions that surrounding medium is homogeneous and the line source is infinite and constant heat flux, however real ground condition is unisotropic and heterogeneous, and showing regional or local ground water flows in many cases. We need to develope improved evaluation models to estimate accurate ground thermal conductivity with respect to geological and influence of ground water because current TRT standard test procedure has limitations to be applied for every locations and system. This study surveyed the uncertainty of the thermal parameters from the interpretation method considering different evaluation period. The interpretation of 208 TRT data sets represents limitations of LSM application that some obtained ground thermal conductivities are statistically unstable and convergence time of ground thermal conductivity over test period shows trends responding the length of test period. This evaluation study will be helpful to provide some effective procedure for the thermal parameter estimation and to complement current TRT standard procedure.

• Korean Management Science Review
• /
• v.29 no.3
• /
• pp.45-65
• /
• 2012

Test and evaluation of weapon system is an important task to evaluate the performance of overseas weapon system purchasing project. Especially, quantitative evaluation of performances is hardly completed in defense projects where multiple criteria are conflicted each other. In order to solve this problem, we apply Axiomatic Design (AD) and Inner Dependence AHP method. First, finite functional requirements (FRs) are categorized in hierarchy structure by selecting proper design parameters (DPs) to implement their corresponding FRs. If there are no ways to select DPs when design is coupled between FRs and DPs, then inner dependence is allowed to overcome the strict rule of independence in AHP. Second, the weights of DPs are calculated by applying both Inner Dependence AHP method for coupled design and normal AHP method for uncoupled or decoupled design. Finally, information axiom of AD is applied to the proposed weapon systems by calculating information contents for all parameters. Weapon system with minimum sum of information contents is considered as the best solution. The proposed method in this study should be used in multiple criteria decision making problems involving various conflicting criteria.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.19 no.2
• /
• pp.89-95
• /
• 2008

Subjective voice evaluation is necessary and important to assess the voice disorders in addition to objective voice evaluation. Subjective voice evaluation is divided into examiner and examinee subjective voice assessment. The examiner assessment represents perceptual judgment to the patient's voice such as GRBAS scale, Buffalo voice profile, consensus auditory perceptual evaluation of voice (CAPE- V) and so on. The examinee assessment consists of indirect method including voice handicap index (VHI), voice outcome survey (VOS), voice symptom scale (VoiSS), voice related quality of life (V-ROQL) and direct method which is called patient's self-subjective voice rating. This review article describes a general rule, advantages and pitfalls about GRBAS scale, VHI and patient's self-subjective voice rating which are presently most representative voice assessment tools.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.1
• /
• pp.32-40
• /
• 2008

Fuzzy rules are very useful and efficient to describe classification rules especially when the attribute values are continuous and fuzzy in nature. However, it is generally difficult to determine membership functions for generating efficient fuzzy classification rules. In this paper, we propose a method of automatic generation of efficient fuzzy classification rules using evolutionary algorithm. In our method we generate a set of initial membership functions for evolutionary algorithm by supervised clustering the training data set and we evolve the set of initial membership functions in order to generate fuzzy classification rules taking into consideration both classification accuracy and rule comprehensibility. To reduce time to evaluate an individual we also propose an evolutionary algorithm with data partition evaluation in which the training data set is partitioned into a number of subsets and individuals are evaluated using a randomly selected subset of data at a time instead of the whole training data set. We experimented our algorithm with the UCI learning data sets, the experiment results showed that our method was more efficient at average compared with the existing algorithms. For the evolutionary algorithm with data partition evaluation, we experimented with our method over the intrusion detection data of KDD'99 Cup, and confirmed that evaluation time was reduced by about 70%. Compared with the KDD'99 Cup winner, the accuracy was increased by 1.54% while the cost was reduced by 20.8%.

• Journal of Korean Society for Geospatial Information Science
• /
• v.22 no.4
• /
• pp.81-89
• /
• 2014

In Korea, National spatial data infrastructure has implemented in order to integrated manage and share the national spatial information producted by public agencies and local governments. The necessities of systematic quality management are raised, because information, which is generated by different agencies, is integrative managed by national level. In this paper, the establishment of BPR(Business Process Reengineering) for national spatial data infrastructure quality management system. Quality management business is defined as quality management object definition, quality measuring, evaluation and analysis, and quality enhancement process. Next, activities for each process are designed. For the quality management business, business rule(BR) is required for determining error. We derive the BR for six objects(legal-dong, railway boundary, railway centerline, road boundary, road centerline, building) among the basic spatial information. Other information's BR can be generated by using the derivation method described in this paper. Based on the BPR of this paper and derived BR, national spatial data infrastructure quality management system can be implemented in the future.

• Journal of Intelligence and Information Systems
• /
• v.15 no.4
• /
• pp.123-140
• /
• 2009

Fuzzy neural network is an integrated model of artificial neural network and fuzzy system and it has been successfully applied in control and forecasting area. Recently ANFIS(Adaptive Network-based Fuzzy Inference System) has been noticed widely among various fuzzy neural network models because of outstanding performance of control and forecasting accuracy. ANFIS has capability to refine its fuzzy rules interactively with human expert. In particular, when we use initial rule structure for machine learning which is generated from human expert, it is highly probable to reach global optimum solution as well as shorten time to convergence. We propose metrics to evaluate interpretability of generated rules as a means of acquiring domain knowledge and compare level of interpretability of ANFIS fuzzy rules to those of C5.0 classification rules. The proposed metrics also can be used to evaluate capability of rule generation for the various machine learning methods.

• Korean Journal of Agricultural Science
• /
• v.37 no.3
• /
• pp.481-490
• /
• 2010

Baekgog reservoir is located in Jincheon county, Chungbuk province, of which full water levels will be heightened from EL. 100.1 m to EL. 102.1 m, and total storages from 21.75 $Mm^3$ to 26.67 $Mm^3$. The simulation for reservoir inflow was conducted by DAWAST model. The annual average irrigation water was estimated to 33.19 $Mm^3$ supplied to 2,975 ha and the instream flows could be allocated with 0.14 mm/d from October to April with annual average of 2.52 $Mm^3$. The operation rule curve was drawn using inflow, irrigation, and instream flow requirements data. The reservoir water storage was simulated on a daily basis in case of both normal and withdrawal limit operation. In case of normal operation, the annual average irrigation water supply increased from 31.95 $Mm^3$ to 33.32 $Mm^3$, the instream water supply from 2.40 $Mm^3$ to 2.44 $Mm^3$, the water storages from 15.74 $Mm^3$ to 19.88 $Mm^3$, and the water supply reliability from 77.3 % to 81.6 %. In case of operation with withdrawal limit, the amount of instream water supply was 2.52 $Mm^3$ from reservoir regardless of the condition while the water storage increased from 16.77 $Mm^3$ to 20.65 $Mm^3$. The irrigation water supply capacity was appropriate for the case of normal operation with 2 m heightened condition. The present instream water supply capacity was 35,000 $m^3$/d (6.86 $Mm^3$/y) while 42,000 $m^3$/d (8.36 $Mm^3$/y) in 2 m heightened condition in case of withdrawal limit operation.