• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.5
• /
• pp.512-519
• /
• 2003

In this paper, we propose a neuro-fuzzy modeling to improve the performance using the hierarchical clustering and Gaussian Mixture Model(GMM). The hierarchical clustering algorithm has a property of producing unique parameters for the given data because it does not use the object function to perform the clustering. After optimizing the obtained parameters using the GMM, we apply them as initial parameters for Adaptive Network-based Fuzzy Inference System. Here, the number of fuzzy rules becomes to the cluster numbers. From this, we can improve the performance index and reduce the number of rules simultaneously. The proposed method is verified by applying to a neuro-fuzzy modeling for Box-Jenkins s gas furnace data and Sugeno's nonlinear system, which yields better results than previous oiles.

• Journal of Digital Convergence
• /
• v.12 no.3
• /
• pp.127-140
• /
• 2014

This study is performed to measure a performance of IMS using Delone & McLean's Information Success Model as a practical analysis for IMS implementation and their effects. For this, I reviewed the pre-research literatures to attain the measurement factors for IMS implementation and information system success model. For inspecting the hypotheses, answered the questionaries to the IMS managers. The results are as follows: the first, to improve the user's will, they have to focus on the service quality. The second, to improve the user's satisfaction, focus on the system quality. Finally, which affect on the performance is user's will rather than satisfaction.

• Journal of the Korean Dietetic Association
• /
• v.23 no.1
• /
• pp.64-77
• /
• 2017

This study was conducted to develop a nutritional education program based on the health belief model to improve nutritional status among Vietnamese female marriage immigrants in Korea. The education program was developed through literature review, focus group interviews, expert consultation, and pilot tests. Based on theoretical requirements and needs of beneficiaries, the education program was consisted of 16 sessions with nine topics: 'how to evaluate own dietary habits and nutritional status', 'health problems according to dietary habits and nutritional status', 'understanding six food groups', 'healthy eating plan', 'understanding food cultures of Korea and Vietnam', 'traditional and seasonal Korean foods', 'how to cook Korean food', 'nutrition management of family members', and 'practicing of healthy dietary life'. Program contents in each session consisted of activities that could induce outcome and value expectations, self-efficacy, perceived benefits, and barriers and cues to actions regarding dietary behavior. This nutritional education program based on the health belief model would be helpful to implement healthy diet behaviors in Vietnamese marriage immigrants and their families. Extension of these nutritional education programs to health centers and multicultural family support centers would improve the current poor nutrition status of Vietnamese marriage immigrant women. Further studies are needed to validate our program.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.3
• /
• pp.465-470
• /
• 2011

Recently fault currents are increasing in a network. It is caused by increase in electric demand and high penetration of distributed generation with renewable energy sources. Moreover, distribution network has become more and more complex as mesh network to improve the distribution system reliability and increase the flexibility and agility of network operation. Accordingly, the fault current will exceed capacity of circuit breakers soon and all the various rational solutions to solve this problem are taken into account. Under these circumstances, superconducting fault current limiter(SFCL) is a new alternative in the viewpoint of technical and economic aspects. This study presents operation processes for a resistive-type of SFCL, and it proposes reliability model for the SFCL. When a SFCL is installed into a network, the contribution of decreased fault currents to failure for distribution equipments can be quantified. As a result, it is expected that a SFCL makes the reliability of adjacent equipments on existing network improve and these changes are analyzed. We propose a methodology to evaluate the reliability in the distribution network where a SFCL is installed considering a reliability model for resistive-type of SFCL and reliability changes for adjacent equipments which are proposed in this paper.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.12
• /
• pp.2793-2799
• /
• 2013

This paper proposes an effective feature compensation method to improve speech recognition performance in time-varying background noise condition. The proposed method employs principal component analysis to improve the variational model composition method. The proposed method is employed to generate multiple environmental models for the PCGMM-based feature compensation scheme. Experimental results prove that the proposed scheme is more effective at improving speech recognition accuracy in various SNR conditions of background music, compared to the conventional front-end methods. It shows 12.14% of average relative improvement in WER compared to the previous variational model composition method.

• Structural Engineering and Mechanics
• /
• v.78 no.2
• /
• pp.209-218
• /
• 2021

For engineering, there are two major challenges in reliability analysis. First, to ensure the accuracy of simulation results, mechanical products are usually defined implicitly by complex numerical models that require time-consuming. Second, the mechanical products are fortunately designed with a large safety margin, which leads to a low failure probability. This paper proposes an efficient and high-precision adaptive active learning algorithm based on the Kriging surrogate model to deal with the problems with low failure probability and time-consuming numerical models. In order to solve the problem with multiple failure regions, the adaptive kernel-density estimation is introduced and improved. Meanwhile, a new criterion for selecting points based on the current Kriging model is proposed to improve the computational efficiency. The criterion for choosing the best sampling points considers not only the probability of misjudging the sign of the response value at a point by the Kriging model but also the distribution information at that point. In order to prevent the distance between the selected training points from too close, the correlation between training points is limited to avoid information redundancy and improve the computation efficiency of the algorithm. Finally, the efficiency and accuracy of the proposed method are verified compared with other algorithms through two academic examples and one engineering application.

• Journal of Korean Clinical Nursing Research
• /
• v.27 no.3
• /
• pp.267-278
• /
• 2021

Purpose: This study was attempted to identify the importance and performance of person-centered care in nurses in intensive care units (ICU) at general hospitals and to derive the priority of practical person-centered care needs and intervention by analysing their needs. Methods: A total of 156 ICU nurses who wrote a written consent participated in a survey questionnaire on person-centered critical care nursing (PCCN). The collected data were analyzed using paired t-test, Borich's needs assessment, and the Locus for Focus Model. Results: All 15 items of person-centered care in ICU nurses were found to be significantly higher in perception of importance than performance level (t=17.98, p<.001). According to the analysis of Borich's needs and the Locus of Focus Model, person-centered care items with highest priority in ICU were therapeutic contact, comfort words and actions, and efforts to empathize with patients in the compassion category. Conclusion: As a strategy to improve the person-centered nursing performance of ICU nurses in the 'individuality', it is necessary for ICU nurses to recognize the ICU patients as an individualized person, not as a disease or machine-dependent entity. Also, it is necessary to develop programs to improve the ICU nurses' compassion competence because 'compassion' was a top priority according to Borich's needs assessment model and the Locus for Focus Model.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.28 no.3
• /
• pp.305-316
• /
• 2022

Purpose: The purpose of this study was to construct a structural equation model of organizational commitment in hospital nurses based on a job demands-resources model and to confirm the moderating effect(s) according to the nurses' generation. Methods: The model was constructed of the exogenous variables of social support, emotional intelligence, emotional labor, and job conflict and the endogenous variables of burnout, job engagement, and organizational commitment. The participants were 560 hospital nurses working in 3 general hospitals. Data were collected from August 1 to September 30, 2021, and analyzed using SPSS Window 23.0 and IBM AMOS 23.0. Results: The strongest factor directly influencing hospital nurses' organizational commitment was social support. In a multiple group analysis, nurses' generation had a partial moderating effect. In a generation-specific analysis, the Z generation group was higher than the X and Y generation groups in the variables of emotional labor and burnout related to organizational commitment. Conclusion: Based on the findings of this study, to improve hospital nurses' organizational commitment, social support is needed as an important management strategy. At the organizational level, we need to develop ways to improve organizational commitment by reducing the emotional labor and burnout of Generation Z.

• Korean Journal of Organic Agriculture
• /
• v.30 no.4
• /
• pp.499-516
• /
• 2022

Blueberry producers' management is failing as a result of the price decline caused by an increase in blueberry imports and the accompanying deterioration in management. Consequently, an endeavor was undertaken to verify the measurement and impact from the standpoint of efficiency and productivity of blueberry management, and to offer an indication of management improvement through analysis. Using the Rural Development Administration's income survey data, the data for twenty-four blueberry farms was analyzed. First, the management effectiveness of blueberry cultivators was evaluated. Using the CCR model (0.7297) and the BCC model (08148), the efficiency of a farm was examined. When the efficiency is one, CCR is ten and BCC is fifteen, and in overall, it was found to be ineffective, the efficiency declined from 2018 to 2019, but climbed again in 2020, according to the annual analysis. The MPI index was then used to examine productivity. T2's MPI index was 1.3338, whereas T3's MPI index was 0.8896, demonstrating a considerable decline in TC. This indicates that technological progress is not being accomplished, necessitating the need for countermeasures. In order to improve the management efficiency of blueberry producers, it is necessary to reduce costs and improve receivable prices through producer organization, and to actively introduce new technologies.

• Journal of Animal Science and Technology
• /
• v.65 no.3
• /
• pp.627-637
• /
• 2023

As the population and income levels rise, meat consumption steadily increases annually. However, the number of farms and farmers producing meat decrease during the same period, reducing meat sufficiency. Information and Communications Technology (ICT) has begun to be applied to reduce labor and production costs of livestock farms and improve productivity. This technology can be used for rapid pregnancy diagnosis of sows; the location and size of the gestation sacs of sows are directly related to the productivity of the farm. In this study, a system proposes to determine the number of gestation sacs of sows from ultrasound images. The system used the YOLOv7-E6E model, changing the activation function from sigmoid-weighted linear unit (SiLU) to a multi-activation function (SiLU + Mish). Also, the upsampling method was modified from nearest to bicubic to improve performance. The model trained with the original model using the original data achieved mean average precision of 86.3%. When the proposed multi-activation function, upsampling, and AutoAugment were applied, the performance improved by 0.3%, 0.9%, and 0.9%, respectively. When all three proposed methods were simultaneously applied, a significant performance improvement of 3.5% to 89.8% was achieved.