• 품질경영학회지
• /
• 제48권4호
• /
• pp.567-580
• /
• 2020

Purpose: The purpose of this study is to present a preferred parts list, establish a search tool for common parts, and propose a development plan for parts management. Methods: When selecting the preferred parts list, the weight of the selection of the military parts and the online site of the civilian parts were taken into account. By establishing a database of selected preferred parts list, we have established a system for searching common parts. Results: The results of this study are as follows; In order to establish parts management work in Korea's defense, it is necessary to improve the Defense Acquisition Program Act, Enforcement Decree (Rules), and the Regulations for Defense Acquisition Program Administration. Development of performance indicators for parts management is required, and establishment of procedures and standards for selection of preferred parts lists is required. Considerations for the selection of preferred parts list include whether they are used a lot in civilian products, whether they are used a lot, whether they are certified suppliers, whether they are national and industrial standard products, whether they perform well considering reliability, durability, and quality, and whether they can be supplied continuously. Conclusion: It is necessary to establish policies and systems related to parts management and to establish criteria for selecting preferred parts list for the development of domestic parts management tasks.

• 한국멀티미디어학회논문지
• /
• 제5권5호
• /
• pp.512-522
• /
• 2002

본 논문에서는 GMM(Gaussian Mixture Model)에 기반한 실시간문맥독립화자식별시스템[1][2]의 성능향상을 위하여 프레임선택(Frame Selection)방법과 프레임가중치(Weighting Model Rank)방법을 혼합한 hybrid방법을 제안한다. 본 시스템에서는 GMM의 파라미터를 최적화하기 위하여 MLE(Maximum likelihood estimation)방법과 인식 알고리즘으로 ML(Maximum Likelihood)을 기본적으로 사용하였다. 제안한 hybrid 방법은 두 단계로 이루어진다. 첫째, 화자모델과 테스트 데이터를 이용하여 프레임단위로 유사도를 계산하고, 가장 큰 유사도 값과 두 번째로 큰 유사도 값의 차를 계산한 후, 차가 문턱치보다 큰 프레임만을 선택한다 두 번째로, 선택되어진 프레임에서 계산되어진 유사도 값 대신에 가중치 값을 사용하여 전체 스코어를 계산한다. 특징 파라미터로서는 켑스트럼과 회귀계수를 사용하였으며, 학습과 테스트를 위한 데이터베이스는 채집기간이 다른 여러 데이터베이스들로 구성되어 있으며, 실험을 위한 데이터는 임의의 단어를 선택하여 사용하였다. 화자인식실험은 기본 시스템에 프레임선택방법, 프레임가중치방법, 제안한 Hybrid방법을 각각 적용하여 실험하였다. 실험결과, 프레임선택방법에 비해 평균 4%, 프레임가중치방법에 비해 평균 1%의 인식률 향상을 보여, 본 논문에서 적용한 hybrid방법의 유효성을 확인하였다.

• The Journal of the Acoustical Society of Korea
• /
• 제24권4E호
• /
• pp.144-151
• /
• 2005

We evaluate the performance of emotion recognition via speech signals when a plain speaker talks to an entertainment robot. For each frame of a speech utterance, we extract the frame-based features: pitch, energy, formant, band energies, mel frequency cepstral coefficients (MFCCs), and velocity/acceleration of pitch and MFCCs. For discriminative classifiers, a fixed-length utterance-based feature vector is computed from the statistics of the frame-based features. Using a speaker-independent database, we evaluate the performance of two promising classifiers: support vector machine (SVM) and hidden Markov model (HMM). For angry/bored/happy/neutral/sad emotion classification, the SVM and HMM classifiers yield $42.3\%\;and\;40.8\%$ accuracy, respectively. We show that the accuracy is significant compared to the performance by foreign human listeners.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2002년도 11월 학술대회지
• /
• pp.209-213
• /
• 2002

This paper describes the reduction of DB without degradation of speech quality in Corpus-based Speech synthesizer of Korean language. In this paper, it is proposed that the frequency of every unit in reduced DB should reflect the frequency of units in Korean language. So, the target population of every unit is set to be proportional to their frequency in Korean large corpus(780K sentences, 45Mega phonemes). Second, the frequent instances during synthesis should be also maintained in reduced DB. To the last, it is proposed that frequency of every instance should be reflected in clustering criterion and used as criterion for selection of representative instances. The evaluation result with proposed methods reveals better quality than using conventional methods.

• 한국데이타베이스학회:학술대회논문집
• /
• 한국데이타베이스학회 1999년도 춘계공동학술대회: 지식경영과 지식공학
• /
• pp.125-133
• /
• 1999

The objective of knowledge discovery and data mining lies in the generation of useful insights from a store of data. This paper presents a framework for knowledge mining to provide a systematic approach to the selection and deployment of tools for automated learning. Every methodology has its strengths and limitations. Consequently, a multistrategy approach may be required to take advantage of the strengths of disparate technique while circumventing their individual limitations. For concreteness, the general framework for data mining in marketing is examined in the context of developing agents for optimizing a supply chain network.

• 한국자원식물학회지
• /
• 제20권1호
• /
• pp.89-92
• /
• 2007

The purpose of this study was to establish basic database on Sorbus alnifolia by investigating, analyzing and comparing characteristics of leaf, and then foster good cultivar on each morphological characteristics - leaf length, leaf width, petiole length, left lateral vein, right lateral vein. Leaf length and leaf width in Osan showed distinct tendency in comparison with the whole mean : 103.4mm and 63.3mm, 86.4mm and 62.9mm, respectively. Populations of Mt. Dukyoo and Mt. Halla showed leaf length of 52.8mm and 58.2mm respectively 32.6% and 39% lower than the mean of ten population. Leaf width of Mt. Gwangyang and Mt. Chink was 52.8mm and 51.9mm, respectively 17.6% and 16.2% lower than whole mean, respectively, and showed the lowest tendency among ten selected populations.

• 한국데이타베이스학회:학술대회논문집
• /
• 한국데이타베이스학회 1997년도 International Conference MULTIMEDIA DATABASES on INTERNET
• /
• pp.438-454
• /
• 1997

본 논문에서는 정보기술을 활용하고자 하는 정부 관리자들의 보다 전술적인 문제로써 정보 기술사업의 선정방안에 대해서 미국 뉴욕주의 사례를 중심으로 논하였다. 뉴욕주의 정보기술사업 선정에 대한 분석은 선정절차, 선정기준, 평점방법, 그리고 선정조직의 측면에서 이루어졌다. 뉴욕주 기술사업 선정은 평가절차가 정확성에 보다 치중하고 있으며, 평가기준도 제안조직의 능력보다는 제안된 사업의 개발로 인한 영향 평가에 초점을 두고 있다. 평점모형에서는 구체적인 가중치를 부여하여 계량화하기보다는 영향의 (+)와 (-)를 밝히고 있다. 평가조직은 내ㆍ외부 전문가를 충분히 혼합하여 활용하고 있다. 이러한 특징은 의사결정의 문화성, 합리성, 그리고 합법성의 측면에서 다시 논의되었다. 뉴욕주정부의 정보 기술 사업 선정과정에서의 특징이 정보정책에 갖는 함의 또한 논의되었다.

• 대한음성학회지:말소리
• /
• 제44호
• /
• pp.145-156
• /
• 2002

This paper describes the reduction of DB without degradation of speech quality in Corpus-based Speech synthesizer of the Korean language. In this paper, it is proposed that the frequency of every unit in reduced DB reflect the frequency of units in the Korean language. So, the target population of every unit is set to be proportional to its frequency in Korean large corpus (780k sentences, 45Mega phones). Secondly, the frequent instances during synthesis should be also maintained in reduced DB. To the last, it is proposed that frequency of every instance be reflected in clustering criteria and used as another important criterion for selection of representative instances. The evaluation result with proposed methods reveals better quality than that using conventional methods.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1997년도 춘계학술대회
• /
• pp.410-413
• /
• 1997

The most important wave set in ECG is the QRS complex. Automatic classification of the QRS complex is very useful in the diagnosis of cardiac dysfunction. Also, diagnosis is influenced by selection of dominant beat. In this paper, we propose simple algorithm for QRS detection. And we determine correlation between significan attributes of QRS complexs. We evaluated the efficiency of proposed method with the CSE database.

• Journal of Information Technology Applications and Management
• /
• 제12권1호
• /
• pp.35-48
• /
• 2005

An architectural framework is developed for integrating geospatial and temporal data with relational information from which a spatio-temporal data warehouse (STDW) system is built. In order to implement the STDW, a generic conceptual model was designed that accommodated six dimensions: spatial (map object), temporal (time), agent (contractor), management (e.g. planting) and tree species (specific species) that addressed the 'where', 'when', 'who', 'what', 'why' and 'how' (5W1H) of the STDW information, respectively. A formal algebraic notation was developed based on a triplet schema that corresponded with spatial, temporal, and relational data type objects. Spatial object structures and spatial operators (spatial selection, spatial projection, and spatial join) were defined and incorporated along with other database operators having interfaces via the generic model.