• Journal of Information Processing Systems
• /
• v.2 no.1
• /
• pp.23-27
• /
• 2006

This paper presents a feature selection technique based on distributional differences for efficient machine learning. Initial training data consists of data including many features and a target value. We classified them into positive and negative data based on the target value. We then divided the range of the feature values into 10 intervals and calculated the distribution of the intervals in each positive and negative data. Then, we selected the features and the intervals of the features for which the distributional differences are over a certain threshold. Using the selected intervals and features, we could obtain the reduced training data. In the experiments, we will show that the reduced training data can reduce the training time of the neural network by about 40%, and we can obtain more profit on simulated stock trading using the trained functions as well.

• Communications for Statistical Applications and Methods
• /
• v.22 no.6
• /
• pp.647-653
• /
• 2015

Extreme value theory concerns the distributional properties of the maximum of a random sample; subsequently, it has been significantly extended to stationary random sequences satisfying weak dependence restrictions. We focus on distributional mixing condition $D(u_n)$ and the Berman condition based on covariance among weak dependence restrictions. The former is assumed for general stationary sequences and the latter for stationary normal processes; however, both imply the same distributional limit of the maximum of the normal process. In this paper $D(u_n)$ condition is shown weaker than Berman's covariance condition. Examples are given where the Berman condition is satisfied but the distributional mixing is not.

• Journal of Distribution Research
• /
• v.1 no.1
• /
• pp.41-63
• /
• 1996

In spite of economy has a critical cycle such as, production, distribution and consumption, we hardly concentrated our study to distributional system and behavior. Especially in Korea, Traditional idea had tried to ignore the people who work in this economic value at all. Manufacturers, other than retailers and wholesalers, had a belief that the manufacturing can control distributional channels forever. Unfortunately, technological and educational advances caused the quality equalization among developing and developed countries as well as among big and small manufacturers in their products. By this reason, economists are searching the economists dark continet' mentioned by Peter Drucker as a new source of wealth. According to a report by well-known economic research institute in Switzerland, Korea has classified in the lower level group in terms of international compatitive power. At the same time, business firms complain that they are suffering from lack of SOC and infrastructures. As an important mean to overcome the economic bottleneck, economists suggest in improve our distributional atmosphere. Basically, distributional study has two sub-fields as: commercial and physical distributions, Distributional system mainly concerns about to shorten the distances of time and space between production and consumption. The closer the distances, the higher efficiency can be achieved. Building distributional system will cost, but tile results will save social costs. Based on this idea, economists proposed several ways to cut the distances and to save costs, Naturally, they hope their beliefs can be adapted by business firms and governments. But frequently, their theories doesn't make any fruit. This paper has studied about the composition of joint transportational and distributional systems. And, even though there's no Marshall in tile real world at this point authors are trying to define the transportational and physical distributional costs, the most powerful factor that can impact to economic decision making.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1990.04a
• /
• pp.272-288
• /
• 1990

The uncertainty quantification process in probabilistic Risk Assessment usually involves a specification of the uncertainty in the input data and the propagation of this uncertainty to the final risk results. The distributional sensitivity analysis is to study the impact of the various assumptions made during the quantification of input parameter uncertainties on the final output uncertainty. The uncertainty importance of input parameters, in this case, should reflect the degree of changes in the whole output distribution and not just in a point estimate value. A measure of the uncertainty importance is proposed in the present paper. The measure is called the distributional sensitivity measure(DSM) and explicitly derived from the definition of the Kullback's discrimination information. The DSM is applied to three typical discrimination information. The DSM is applied to three typical cases of input distributional changes: 1) Uncertainty is completely eliminated, 2) Uncertainty range is increased by a factor of 10, and 3) Type of distribution is changed. For all three cases of application, the DSM-based importance ranking agrees very well with the observed changes of output distribution while other statistical parameters are shown to be insensitive.

• Journal of Sasang Constitutional Medicine
• /
• v.23 no.3
• /
• pp.361-373
• /
• 2011

1. Objectives: The purpose of this study was done to learn the Sasang constitutional distribution and to find out if there are differences in the type of diseases and symptoms according to the Sasang constitution in Japan. 2. Methods: We collected data from 366 patients who visited the Department of Oriental Medicine, Keio University and recruited 132 healthy persons in Tokyo, Japan. For sasang constitution diagnosis, they all have done SSCQ-P(Sasang Constitution Questionaire for Patients) questionnaire. and a sasang constitution specialist diagnosed the sasang constitution of them. And We classify the diseases and symptoms of 313 patients according to KCD(Korean Standard Classification of Diseases) and learn the prevalences of diseases and symptoms according to Sasang Constitution. 3. Results: 1) Among the total 498 subjects, distributional rate of Taeyangin, Soyangin, Taeeumin, and Soeumin were 2.0%, 26.3%, 29.9%, and 41.8%. Among the 366 patients, distributional rate of Taeyangin, Soyangin, Taeumin, and Soeumin were 0.8%, 27.3%, 28.7%, and 43.2%. Among the 132 healthy group, distributional rate of Taeyangin, Soyangin, Taeeumin, and Soeumin were 5.3%, 23.5%, 33.3%, and 37.9%. 2) The prevalences of 'V.Mental and behavioural disorders', 'XI.Diseases of the digestive system', 'XV.Pregnancy, childbirth and the puerperium' and 'feeling of coldness(X VIII.Symptoms, signs and abnormal clinical and laboratory findings, NEC)' of Soeumin were significantly higher than those of the other constitutions.(p-value<0.05) 4. Conclusions: The distributional rate of Sasangin of Japanese was different from that of Korean and especially the distributional rate of Soeumin of Japanese was significantly higher than that of Korean. There were significant differences on the prevalences of some diseases and symtoms according to KCD in Soeumin.

• Journal of Distribution Science
• /
• v.21 no.7
• /
• pp.21-31
• /
• 2023

Purpose: The purpose of this study is to investigate how to perceive the role of the slow city and provide policy and managerial implications on the necessity of the slow city management and distributional values based on perspectives of millennials and generation Z. This study examined i) how do millennials and generation Z perceive economic, environment, cultural, community, and quality of life factors on attitude toward the slow city? ii) how does attitude affect overall satisfaction and intention to recommend the slow city to other cities' residents? iii) how do millennials perspectives on proposed factors differ from generation Z? Research design, data and methodology: This study conducted an online survey and applied t-test, factor, ANOVA, and regression analysis. Results: This study found that effects of economic and quality of life factors on attitude toward the slow city showed significance in cases of millennials and generation Z, while effects of environment factor on overall attitude showed significance in the case of generation Z. Conclusions: Governments should foster how millennials and generation Z understand the meanings of the slow city to form a better attitude in a society and put efforts to build a better image and management of the slow city.

• The Journal of the Korea Contents Association
• /
• v.13 no.3
• /
• pp.370-380
• /
• 2013

The research is basically designed to reveal a revisiting behavior for Chung Nam Dae which is inherently characterized sightseeing site. Distributional lag model is tentatively employed to analyze economic factors such as entrance fee and a different level of income. Empirical findings investigate that the revisiting behavior that is associated with a long run effect is more closely connected to the level of national income, but not the level of incomes in Chung Cheong region and Chung Buk province as well. As far as revisiting intention concerns, the entrance fee tends to affect to it by a shorter distributional lag, but the level of income affects to it by way of a pretty much longer distributional lags. To this end, perceived value for Chung Nam Dae should be exposed in order to induce a re-visitor. Such a goal could be attainable by taking care of its system for entrance fee, expanding facilities, re-branding, service improvement, and developing useful programs. Also, setting up an inter-connected networking system with a sightseeing site around is highly recommended.

• The Journal of Industrial Distribution & Business
• /
• v.11 no.11
• /
• pp.39-53
• /
• 2020

Purpose: With a rapid advance of communication technology, distributional systems of sport contents continue to show improvements. In particular, a traditional framework in creating sport cartoon has been influenced by the environment of the communication industry. Despite the development of distributional systems, the current sport cartoon industry still lacks in advancement. To this day, various research about sport contents have been conducted; yet, not many studies of the interaction between sport cartoons and communication technology have been done. In this respect, this study is to review the distributional environment of the sport cartoon industry and provide distributional strategies for developing sport cartoon industry. Research design, data, and methodology: In addition to in-depth interviews with five practitioners in sport cartoon industry, the study employed case study methodology. Interview data were analyzed by qualitative content analysis. Results: With new environments allowing anyone allowing to create and share webtoons, various genres including sports webtoons appear, and this became amotive to the growth of sports webtoons. Today, sports comics acted as a sports advertisement platform which not only created additional profit but also became an opportunity as a marketing method. On the contrary, the formal attributes of webtoons cause hardship in consistently creating sports webtoons. Hence, it is needed that supporting policies need to be established to nurture sport webtoon expertise. For example, Korea Creative Content Agency allows future webtoon authors to have an opportunity to be educated and equipped in producing creative sport webtoon contents. Moreover, revenue systems should be developed for motivating webtoon authors to involve in sport contents in their works. Conclusions: In order to promote the sports cartoon industry based on the findings, it is first necessary to create sports comics that reflect the formal characteristics of webtoons and the changing consumer environment. Second, it is important to acknowledge the industrial value of sports comics and it is necessary to promote policies regarding sports webtoon production and distribution from a national level. Third, by diversifying profits through OSMU and sports advertisements, it is possible to enhance the work environment and the treatment of authors. Implications and future directions were discussed.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.19 no.1
• /
• pp.94-105
• /
• 2016

This study was carried out to assess the distributional probability for Evergreen Broad-Leaved Forests(EBLFs) using the field data and digital climate data that were occurred during the period of 1980 to 2010. For the validation of logistic regression model, the probabilistic value ranged from 33 to 84%, especially the probabilistic value of growing distribution becomes lower patterns with higher altitude. In addition, it has been estimated that the probabilistic value of growing distribution is the highest with 63~83% among the regional units in temperate/warm-temperate forests.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.4
• /
• pp.959-967
• /
• 2016

Distributional assumptions on equity returns play a key role in valuation theories for derivative securities. Elberlein and Keller (1995) investigated the distributional form of compound returns and found that some of standard assumptions can not be justified. Instead, Generalized Hyperbolic (GH) distribution fit the empirical returns with high accuracy. Hu and Kercheval (2007) also show that the normal distribution leads to VaR (Value at Risk) estimate that significantly underestimate the realized empirical values, while the GH distributions do not. We consider saddlepoint approximations to estimate the VaR and the ES (Expected Shortfall) which frequently encountered in finance and insurance as measures of risk management. We supposed GH distributions instead of normal ones, as underlying distribution of linear portfolios. Simulation results show the saddlepoint approximations are very accurate than normal ones.