• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.4
• /
• pp.354-358
• /
• 2001

This paper presents a fuzzy neural network model which solves the underutilization problem. This fuzzy neural network has both stability and flexibility because it uses the control structure similar to AHT(Adaptive Resonance Theory)-l neural network. And this fuzzy nenral network does not need to initialize weights and is less sensitive to noise than ART-l neural network is. The learning rule of this fuzzy neural network is the modified and fuzzified version of Kohonen learning rule and is based on the fuzzification of leaky competitive leaming and the fuzzification of conditional probability. The similarity measure of vigilance test, which is performed after selecting a winner among output neurons, is the relative distance. This relative distance considers Euclidean distance and the relative location between a datum and the prototypes of clusters. To compare the performance of the proposed fuzzy neural network with that of Kohonen Self-Organizing Feature Map the IRIS data and Gaussian-distributed data are used.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.207-210
• /
• 2000

학습법칙은 신경회로망의 성능을 좌우하는 중요한 요소의 하나이다. Kohonen의 합습법칙등이 개발되어 사용되어 왔으나 Underutilization 문제가 있어 실제 사용사에 문제가 있어 왔다. 본 논문에서 제시하는 학습법칙은 이를 부분적으로 해결하였다. 또한 이 학습법칙을 ART(Adaptive Resonance Theory)-1과 Kohonen의 자기 구조 특징 지도의 장점을 조합한 개선된 IAFC(Integrated Adaptive Fuzzy Clustering) 신경회로망에 적용하였고, 성능을 평가하기 위해 가우시안 분포의 데이터와 IRIS 데이터를 각각 사용하여 실험하였다.

• Korean Journal of Social Welfare Studies
• /
• v.43 no.2
• /
• pp.319-344
• /
• 2012

This study decomposed Concentration Index(CI) and Hiwv Index(HI) of medical care utilization by subgroups: sex, age group, and region. CI and HI were decomposed into "the between group" component, "within group" component, and a residual. The results of analysis are summarized as follows; First, there was no influence of sex on the equity of medical care utilization measured by the numbers of visiting clinic. However, "within group" component of female explained .0441 among HI, .1035. This means that poor women's underutilization of medical care is the important factor in determining its degree of equity. Second, age groups had a decisive effect on the equity of medical care utilization measured by the numbers of visiting clinic. they explained -.0085 among HI, -.0170. Third, internal equality within elderly group was the most important factor in determining HI measured by the medical care cost. Finally, "within group" component of urban area explained .0535 amomg HI, ,1035 measured by medical care cost. This indicated that the urban poor's underutilization of medical care was very important factor in explaining its degree of equity. There was the poor's underutilization of medical care within the groups as female, the elderly, and urban areas. This significantly explained the equity of medical care costs.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.6B
• /
• pp.553-558
• /
• 2009

There have been various research efforts to support the fairness between uplink and downlink of TCP streams in IEEE 802.11 networks. Existing methods, which have been effective for the fairness, however could not provide the solution for the unfairness caused by the situation in which a station which is having multiple TCP uplink streams monopolizes the uplink bandwidth. This paper proposes a method that AP allocates token buckets for each uplink TCP station. The proposed method is also able to support the fairness between the uplink and downlink. To remedy the underutilization which may happen under token bucket-based schemes, it allows the movement of redundant tokens among the token buckets. By controlling the token movements, it can balance the fairness and the utilization. Simulation results show that the proposed method is able to support the fairness of the TCP uplink stations, as well as the fairness between the uplink and downlink.

• Journal of Labour Economics
• /
• v.33 no.3
• /
• pp.89-127
• /
• 2010

This paper explores the causes and solutions of the problem that the official unemployment rate does not adequately represent the reality of the employment situation in Korea. First, compared to ILO's international standards, there are several differences in the measurement of unemployment in Korea, for example, the treatment of unpaid family workers working less than 18 hours per week, the classification of persons who are waiting for a new job or temporarily laid-off, and the criteria of job search activities. The questionnaire structure of the Labor Force Survey in Korea also misleads the judgment of economic activity state. Comparing the responses of the basic survey to those of the supplementing survey, approximately 90% of the responses show discrepancies and this indicates the possibility of misclassification. Next, this paper suggests the extended unemployment indicators as alternative, based on the current survey. The extended unemployment indicators support the presence of significant amounts of hidden unemployed and underemployed. And, it is found that the analyses using those indicators are very useful for the investigation of many aspects of employment dynamics.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.2
• /
• pp.191-195
• /
• 2008

This paper proposes a technique for improving IEEE 802.11e EDCA's performance by dynamically adjusting each class's contention window size based on each class's traffic amount. For providing differentiated service differently from 802.11, 802.11e EDCA maintains four classes each of which specifies different static minimum and maximum contention window sizes. Since the initial window sites significantly affect the 802.11e performance, several window adjustment schemes have been proposed. One of the schemes known as CWminAS (CWmin Adaptation Scheme) dynamically and synchronously determines the four windows' site based on the periodically measured collision rate. This method, however, can lower the send probability of high priority classes since it can't differentiate their collisions from those of low priority classes, leading to the channel underutilization. For solving this problem, we propose ACATICT(Adaptive Contention-window Adjustment Technique based on Individual Class Traffic) algorithm which adapts each class window size based on each individual collision rate rather than one average collision rate. Our simulation experiments show that ACATICT achieves better utilization by around 10% at maximum.

• The Journal of the Korea Contents Association
• /
• v.13 no.3
• /
• pp.9-21
• /
• 2013

Due to increased computing power and flexibility of GPU, recent GPUs execute general purpose parallel applications as well as graphics applications. Programmers can use GPGPU by using the APIs from GPU vendors. Unfortunately, computational resources of GPU are not fully utilized when executing general purpose applications because of frequent branch instructions. To handle the branch problem, several warp formations have been proposed. Intuitively, we expect that the warp formations providing higher computational resource utilization show higher performance. Contrary to our expectations, according to simulation results, the performance of the warp formation providing better utilization is lower than that of the warp formation providing worse utilization. This is because warp formation providing high utilization causes serious memory bottleneck due to increased memory request. Therefore, warp formation providing high computation utilization cannot guarantee high performance without proper hardware resources. For this reason, we will analyze the correlation between hardware configuration and warp formation. Our simulation results present the guideline to solve the underutilization problem due to branch instructions when designing recent GPU.

• KIPS Transactions on Software and Data Engineering
• /
• v.13 no.1
• /
• pp.1-16
• /
• 2024

Over recent years, 6 Sigma has become a key methodology in manufacturing for quality improvement and cost reduction. However, challenges have arisen due to the difficulty in analyzing large-scale data generated by smart factories and its traditional, formal application. To address these limitations, a big data-based 6 Sigma approach has been developed, integrating the strengths of 6 Sigma and big data analysis, including statistical verification, mathematical optimization, interpretability, and machine learning. Despite its potential, the practical impact of this big data-based 6 Sigma on manufacturing processes and management performance has not been adequately verified, leading to its limited reliability and underutilization in practice. This study investigates the efficiency impact of DX SS, a big data-based 6 Sigma, on manufacturing processes, and identifies key success policies for its effective introduction and implementation in enterprises. The study highlights the importance of involving all executives and employees and researching key success policies, as demonstrated by cases where methodology implementation failed due to incorrect policies. This research aims to assist manufacturing companies in achieving successful outcomes by actively adopting and utilizing the methodologies presented.