• 대한전기학회논문지:시스템및제어부문D
• /
• 제49권8호
• /
• pp.423-431
• /
• 2000

This paper presents a systematic approach to the input-output data-based fuzzy modeling for the complex and uncertain nonlinear systems, in which the conventional mathematical models may fail to give the satisfying results. To do this, we propose a new method that can yield a successful fuzzy model using a mGA hybrid schemes with a fine-tuning method. We also propose a new coding method fo chromosome for applying the mGA to the structure and parameter identifications of fuzzy model simultaneously. During mGA search, multi-purpose fitness function with a penalty process is proposed and adapted to guarantee the accurate and valid fuzzy modes. This coding scheme can effectively represent the zero-order Takagi-Sugeno fuzzy model. The proposed mGA hybrid schemes can coarsely optimize the structure and the parameters of the fuzzy inference system, and then fine tune the identified fuzzy model by using the gradient descent method. In order to demonstrate the superiority and efficiency of the proposed scheme, we finally show its applications to two nonlinear systems.

• 대한간호학회지
• /
• 제38권6호
• /
• pp.779-788
• /
• 2008

Purpose: This study was designed to construct a structural model explaining depression in university students. Methods: Data were collected from 1,640 university students by questionnaire, and analyzed using AMOS 5.0 to test the hypothetical model. Results: Fitness statistics for the modified model were GFI=.93, AGFI=.89, NFI=.91, and RMSEA=.081. All the 12 paths in the modified model proved to be statistically significant. Depression of university students accounted for 52% of the covariance by the factors. The factor that had the most influence on depression was individual vulnerability, and followed by sequence order, stress, social support, coping, and self-efficacy. Depression was influenced directly by individual vulnerability, stress, social support, and coping, and indirectly by individual vulnerability, stress, social support, and self-efficacy. Conclusion: A screening and management system for the high risk group is needed to effectively prevent depression and reduce rate of depression in university students. Detailed support programs which specifically deal with prevailing stressors should be developed to effectively reduce the harmful effects of individual vulnerability and stress. It is anticipated that the model constructed in this study could be utilized as a reference in developing various strategies to prevent and intervene depression in university students.

• Earthquakes and Structures
• /
• 제13권4호
• /
• pp.397-407
• /
• 2017

With the growing demand for metallic dampers in engineering practice, it is urgent to establish a reasonable approach to evaluating the mechanical performance of metallic dampers under seismic excitations. This paper introduces an effective method for parameter identification of the modified Bouc-Wen model and its application to evaluating the fatigue performance of metallic dampers (MDs). The modified Bouc-Wen model which eliminates the redundant parameter is used to describe the hysteresis behavior of MDs. Relations between the parameters of the modified Bouc-Wen model and the mechanical performance parameters of MDs are studied first. A modified Genetic Algorithm using real-integer hybrid coding with relative fitness as well as adaptive crossover and mutation rates (called RFAGA) is then proposed to identify the parameters of the modified Bouc-Wen model. A reliable approach to evaluating the fatigue performance of the MDs with respect to the Chinese Code for Seismic Design of Buildings (GB 50011-2010) is finally proposed based on the research results. Experimental data are employed to demonstrate the process and verify the effectiveness of the proposed approach. It is shown that the RFAGA is able to converge quickly in the identification process, and the simulation curves based on the identification results fit well with the experimental hysteresis curves. Furthermore, the proposed approach is shown to be a useful tool for evaluating the fatigue performance of MDs with respect to the Chinese Code for Seismic Design of Buildings (GB 50011-2010).

• 스마트미디어저널
• /
• 제8권1호
• /
• pp.82-91
• /
• 2019

This study provides the analysis and prediction of fruits diseases related to weather conditions (temperature, wind speed, solar power, rainfall and humidity) using Linear Model and Poisson Regression. The main goal of the research is to control the method of fruits diseases and also to prevent diseases using less agricultural pesticides. So, it is needed to predict the fruits diseases with weather data. Initially, fruit data is used to detect the fruit diseases. If diseases are found, we move to the next process and verify the condition of the fruits including their size. We identify the growth of fruit and evidence of diseases with Linear Model. Then, Poisson Regression used in this study to fit the model of fruits diseases with weather conditions as an input provides the predicted diseases as an output. Finally, the residuals plot, Q-Q plot and other plots help to validate the fitness of Linear Model and provide correlation between the actual and the predicted diseases as a result of the conducted experiment in this study.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권4호
• /
• pp.1426-1447
• /
• 2021

The payoff game between task publishers and users in the mobile crowdsensing environment is a hot topic of research. A optimal payoff selection model based on stochastic evolutionary game is proposed. Firstly, the process of payoff optimization selection is modeled as a task publisher-user stochastic evolutionary game model. Secondly, the low-quality data is identified by the data quality evaluation algorithm, which improves the fitness of perceptual task matching target users, so that task publishers and users can obtain the optimal payoff at the current moment. Finally, by solving the stability strategy and analyzing the stability of the model, the optimal payoff strategy is obtained under different intensity of random interference and different initial state. The simulation results show that, in the aspect of data quality evaluation, compared with BP detection method and SVM detection method, the accuracy of anomaly data detection of the proposed model is improved by 8.1% and 0.5% respectively, and the accuracy of data classification is improved by 59.2% and 32.2% respectively. In the aspect of the optimal payoff strategy selection, it is verified that the proposed model can reasonably select the payoff strategy.

• 품질경영학회지
• /
• 제51권4호
• /
• pp.691-700
• /
• 2023

Purpose: This study aims to analyze the diffusion pattern of the Mongolian mobile phone market. In particular, we used a generalized diffusion model to explore the factors affecting market potenial. Methods: We used three diffusion models to estimate the number of mobile subscribers in Mongolia. Based on the Logistic model with the best fitness, we introduced time-varying market potential and explored the influence of various independent variables such as GDP and inflation. Results: Among the basic diffusion models, the Logistic model was the best in terms of estimation performance and statistical significance. The estimation results of the Generalized Logistic model confirm that investment in the telecommunication sector has a significant positive effect on market potential. The estimation of the Generalized Logistic model effectively describes the continuous growth of the Mongolian telecommunications market until recently. Conclusion: We have analyzed the diffusion pattern of the Mongolian telecommunications market and found that the amount of investment in the sector leads to the growth of the market size. This study is original in terms of its subject - Mongolian telecommunications market and methodology - time-varying market potential.

• 한국통신학회논문지
• /
• 제29권2B호
• /
• pp.217-227
• /
• 2004

인터넷의 발달로 네트워크 트래픽은 현저하게 증가되었다. 트래픽의 폭증은 전체 네트워크의 성능에 크게 영향을 미치게 되었으며 트래픽의 관리가 망 관리의 중요한 이슈로 되었다. 본 논문에서는 네트워크 트래픽을 분석하여 효율적인 대응을 수립하기 위해 예측하는 시계열 모형의 적합성을 검증한다. 네트워크 트래픽을 예측하기 위해서는 시간적 흐름에 따라 자료간의 상관 관계를 유추하고, 이 관계를 이용하여 예측을 수행한다. 상관 관계를 유추하는 과정에서 필연적으로 확률적 오류를 포함하게 되는데, 정확한 예측을 위해서는 확률적 오차를 최소화해야 한다. 따라서, 통계학 분야에서 예측 방법으로 널리 쓰이는 시계열 모형인 AR, MA, ARMA, ARIMA 모형을 사용하여 네트워크 트래픽을 예측함과 동시에, 예측하는 과정에서 정확한 예측을 수행할 수 있는지에 대한 적합성을 검증하고자 한다. 적합성 검증은 모형 식별 단계에서 초기 단계인 정상성 가정을 만족하는지의 여부로 판단하며. 정상성 가정은 자기상관함수와 편자기상관함수를 통해 구할 수 있다. 정상성 가정을 만족하지 못하는 모형은 비정상 시계열 자료로 분류되는데 이 경우의 예측은 정확하다고 볼 수 없다. 따라서, 정확한 예측을 수행할 수 있도록 시계열 자료의 정상성 가정을 만족하도록 모형을 분류하는 방안을 제시하고자 한다. 정확한 예측을 수행하면, 네트워크 트래픽을 좀 더 나은 방법으로 관리하며, 예측 결과를 이용하여 동적인 트래픽의 관리가 가능하게 된다.

• 한국수자원학회논문집
• /
• 제57권4호
• /
• pp.289-300
• /
• 2024

본 연구의 목적은 물리적 분포형 유출 모형인 GRM (Grid based rainfall-Runoff Model)을 이용하여 댐 유입량을 모의함으로써 연속형 모의에 대한 GRM 모형의 적용성을 평가하는 것이다. GRM 모형은 기존에 강우-유출 사상의 모의를 위해서 개발되었으나, 최근에 연속형 모의가 가능하도록 개선되었다. 대상 유역은 충주댐 유역, 안동댐 유역, 용담댐 유역, 섬진강댐 유역이며, 500 m × 500 m의 공간 해상도로 유출 모형을 구축하였다. 모의 기간은 21년(2001년~2021년)이다. 모의결과의 평가는 17년 기간(2005년~2021년)에 대해서 수행하였으며, 17년 전체 자료(total duration), 풍수기(6월~9월, wet season), 갈수기(10월~5월, dry season)의 3개 자료 기간으로 구분하고, 각 댐의 관측된 일유입량과 비교하였다. 모의결과의 적합도 평가는 Nash-Sutcliffe efficiency 계수(NSE), Kling-Gupta efficiency 계수(KGE), 상관계수(CC), 총용적 오차(VE)를 사용하였다. 모의된 댐 유입량의 평가결과 total duration과 wet season에서 관측자료를 잘 재현할 수 있었으며, dry season에서도 저유량 자료의 불확실성을 고려할 때 양호한 모의결과를 나타내었다. 연구결과 GRM 모형의 연속형 모의기법은 적절히 구현된 것으로 판단되었으며, 본 연구의 댐 유입량 모의에 충분히 적용성이 있는 것으로 나타났다.

• 한국의류학회지
• /
• 제24권5호
• /
• pp.628-639
• /
• 2000

The purpose of this study is to propose a model of private brands proneness form-ation considering the six private brands proneness-related variables simultaneously. Since the theoretical framework is based on previous research in various areas, it serves as an integrative one. Data were collected via intercept surveys conducted at nine regional branches of two major department stores situated in Seoul. Participants(n=1,120), who had previously purchased women's private brand apparel, were asked to complete a questionnaire during two weeks from March 15, 1999 to March 28, 1999. LISREL and SPSS PC+ were used to test the model and analyze its variables. The fitness of the model show the reasonable fit between all indices(RMSR=.036, GFI=.99, AGFI=.92, and NFI=.95). The proposed model supports all the hypothesized relationships. Private brands proneness increases as perceived money value of products, familiarity, positive store image of private brands, and satisfaction of individuals' differentiated needs increase. Furthermore, perceived money value of products increase as perceived risk of private brand purchase and perceived quality variation between private brand products and manufacture's products decrease.

• 대한간호학회지
• /
• 제46권5호
• /
• pp.630-641
• /
• 2016

Purpose: This study was designed to construct a model which explains drug misuse behaviors in community-dwelling older adults. Methods: The design of this research is a cross-sectional study using structure equation modeling. The hypothetical model consisted of two types of variables: the exogenous variables of health status, cognitive ability, and negative emotion, and the endogenous variables of number of drugs, and drug misuse behaviors. The data collection was conducted from September 2 to September 21, 2013 through self-report questionnaires. Participants were 320 community-dwelling adults over the age of 65 living in J city. Data were analyzed with SPSS 21.0 program and Amos 18.0 program. Results: The results of the model fitness analysis were satisfied. The predictor variables for the hypothetical model explained 62.3% of variance regarding drug misuse behaviors. Drug misuse behaviors were directly affected by health status, cognitive ability, negative emotion and number of drugs and indirectly affected by health status, and negative emotion through number of drugs. Conclusion: These findings indicate factors that should be used in developing effective nursing interventions for safe and proper drug use and the prevention of drug misuse behaviors in community-dwelling older adults.