• Title/Summary/Keyword: Evaluation models

Search Result 3,737, Processing Time 0.028 seconds

Perceptual Evaluation of Duration Models in Spoken Korean

  • Chung, Hyun-Song
    • Speech Sciences
    • /
    • v.9 no.1
    • /
    • pp.207-215
    • /
    • 2002
  • Perceptual evaluation of duration models of spoken Korean was carried out based on the Classification and Regression Tree (CART) model for text-to-speech conversion. A reference set of durations was produced by a commercial text-to-speech synthesis system for comparison. The duration model which was built in the previous research (Chung & Huckvale, 2001) was applied to a Korean language speech synthesis diphone database, 'Hanmal (HN 1.0)'. The synthetic speech produced by the CART duration model was preferred in the subjective preference test by a small margin and the synthetic speech from the commercial system was superior in the clarity test. In the course of preparing the experiment, a labeled database of spoken Korean with 670 sentences was constructed. As a result of the experiment, a trained duration model for speech synthesis was obtained. The 'Hanmal' diphone database for Korean speech synthesis was also developed as a by-product of the perceptual evaluation.

  • PDF

Development of the Evaluation Model of Location Suitability for Protected Horticulture - Comparative Study on Significance Determination Techniques - (시설원예의 적지평가모델 개발 -중요도 평가기법의 비교 고찰-)

  • 황한철;이남호;전우정;남상운;홍성구;김정식
    • Proceedings of the Korean Society of Agricultural Engineers Conference
    • /
    • 1998.10a
    • /
    • pp.186-191
    • /
    • 1998
  • It is necessary to evaluate the location suitability of protected horticulture facilities to guide and/or to plan new protected horticulture facilities in rural areas. For objective and systematic evaluation of location suitability of protected horticulture, three different evaluation models were constructed based on grading, proportion, and analytic hierarchy process(AHP). The models were used to evaluated the suitability of protected horticulture in three selected regions; suburban, plain, and mountainous. The results showed that there were significant differences in evaluation results of each model among the three regions.

  • PDF

A Study on the Emotional Evaluation of fabric Color Patterns

  • Koo, Hyun-Jin;Kang, Bok-Choon;Um, Jin-Sup;Lee, Joon-Whan
    • Science of Emotion and Sensibility
    • /
    • v.5 no.3
    • /
    • pp.11-20
    • /
    • 2002
  • There are Two new models developed for objective evaluation of fabric color patterns by applying a multiple regression analysis and an adaptive foray-rule-based system. The physical features of fabric color patterns are extracted through digital image processing and the emotional features are collected based on the psychological experiments of Soen[3, 4]. The principle physical features are hue, saturation, intensity and the texture of color patterns. The emotional features arc represented thirteen pairs of adverse adjectives. The multiple regression analyses and the adaptive fuzzy system are used as a tool to analyze the relations between physical and emotional features. As a result, both of the proposed models show competent performance for the approximation and the similar linguistic interpretation to the Soen's psychological experiments.

  • PDF

Developing the Stage Evaluation Model for e-Business Company using Analytic Hierarchy Process (분석적 계층기법을 활용한 e-Business 기업의 초기투자단계 및 성장단계별 평가모형의 개발)

  • Choi, Hye-Jin;Han, In-Goo;Oh, Kyong-Joo
    • Asia pacific journal of information systems
    • /
    • v.15 no.1
    • /
    • pp.45-61
    • /
    • 2005
  • This study develops the evaluation model for e-Business company using analytic hierarchy process. As the first step of this study, we derived the appraisal standards based on the previous literature and the knowledge of experts from venture capitalists, security companies, credit evaluation companies, and consulting firms. In order to validate the evaluating factors in the models, this study was supported by analysts of top ranked venture capitalists in Korea. Through their assistance, this study can determine necessary evaluating factors that refined and deepened the models. Four expert groups, such as venture capitalists, credit analysts, analysts of security company and e-Business consultants, provide their knowledge for the determination of the weights of evaluating factors in the hierarchical model through the questionnaires and interviews. The results show that the weights of the evaluating factors differed by the maturity of e-Business company.

Analysis and Evaluation of a Nursing Research Paper on Secondary Prevention Program for Stroke (일 뇌졸중 이차예방프로그램 논문의 분석 및 평가)

  • Seo, Eun Hui;Park, Seon-Il
    • Journal of Korean Academy of Rural Health Nursing
    • /
    • v.5 no.1
    • /
    • pp.16-24
    • /
    • 2010
  • Nursing theory is used to explain the goals and functions of nursing and improve practical affairs by providing information and knowledge about the principles which become the foundation of nursing practical affairs. Theoretical analytical compliance with C-T-E (Conceptual-Theoretical-Empirical) structures by Fawcett (1999) whose evaluation method illustrates the relationship of conceptual models, theory, research and structure. The evaluation allows the nurse to visualize the connection, evaluate research, and reduce errors in research. Consequently present doctorate dissertations in nursing science are theoretical propriety, connection in the structure of concepts, theory, research methods, and evaluation to reduce errors in future research plans and division of theoretical development process. So the following verifies logicality, propriety, and reliability which must apply to research in various different fields.

Evaluating Predictive Ability of Classification Models with Ordered Multiple Categories

  • Oong-Hyun Sung
    • Communications for Statistical Applications and Methods
    • /
    • v.6 no.2
    • /
    • pp.383-395
    • /
    • 1999
  • This study is concerned with the evaluation of predictive ability of classification models with ordered multiple categories. If categories can be ordered or ranked the spread of misclassification should be considered to evaluate the performance of the classification models using loss rate since the apparent error rate can not measure the spread of misclassification. Since loss rate is known to underestimate the true loss rate the bootstrap method were used to estimate the true loss rate. thus this study suggests the method to evaluate the predictive power of the classification models using loss rate and the bootstrap estimate of the true loss rate.

  • PDF

Shaking Table Test of Full Scale Parapet Models for the Evaluation of Intensities of Historical Earthquakes (성첩 모델의 진동대 실험과 역사지진의 세기 평가)

  • 김재관
    • Proceedings of the Earthquake Engineering Society of Korea Conference
    • /
    • 2001.04a
    • /
    • pp.461-467
    • /
    • 2001
  • Shaking table tests were performed with full scale models of stone parapet on the ancient rampart. The objectives of these tests are to study the seismic behavior of the parapet and to obtain quantitative estimation of the intensities of historical earthquakes. Two test models were made based on the structure of the parapet remnant of a mountain fortress in Bukhan-San located in Seoul. Two types of infilling material are considered. The responses to models were tested subjected to three kinds of input motion.

  • PDF

A Study of Data Mining Optimization Model for the Credit Evaluation

  • Kim, Kap-Sik;Lee, Chang-Soon
    • Journal of the Korean Data and Information Science Society
    • /
    • v.14 no.4
    • /
    • pp.825-836
    • /
    • 2003
  • Based on customer information and financing processes in capital market, we derived individual models by applying multi-layered perceptrons, MDA, and decision tree. Further, the results from the existing single models were compared with the results from the integrated model that was developed using genetic algorithm. This study contributes not only to verifying the existing individual models and but also to overcoming the limitations of the existing approaches. We have depended upon the approaches that compare individual models and search for the best-fit model. However, this study presents a methodology to build an integrated data mining model using genetic algorithm.

  • PDF

The Performance of Time Series Models to Forecast Short-Term Electricity Demand

  • Park, W.G.;Kim, S.
    • Communications for Statistical Applications and Methods
    • /
    • v.19 no.6
    • /
    • pp.869-876
    • /
    • 2012
  • In this paper, we applied seasonal time series models such as ARIMA, FARIMA, AR-GARCH and Holt-Winters in consideration of seasonality to forecast short-term electricity demand data. The results for performance evaluation on the time series models show that seasonal FARIMA and seasonal Holt-Winters models perform adequately under the criterion of Mean Absolute Percentage Error(MAPE).

The Robustness of Queueing Network Models in FMS Production Plans (FMS 생산계획에서의 대기 네트워크 모델의 적용 가능성에 관한 연구)

  • 박진우
    • Journal of the Korea Society for Simulation
    • /
    • v.1 no.1
    • /
    • pp.48-54
    • /
    • 1992
  • This study discusses the performance evaluation of queueing network methodologies as used for the planning of FMS production systems. The possibility of applications and utilities of queueing network models is investigated for FMS producton plans. Experimental results by queueing network models such as CAN-Q, MVAQ and results by detailed simulation models written in SIMAN are compared and some propositions are presented based on the results of the experiments.

  • PDF