• Journal of Digital Contents Society
• /
• v.19 no.4
• /
• pp.739-747
• /
• 2018

With a large feature space data, feature selection has become an extremely important procedure in the Data Mining process. But the traditional feature selection methods with single process may no longer fit for this procedure. In this paper, we proposed a hybrid efficient feature selection model for high dimensional data. We have applied our model on KNHNAES data set, the result shows that our model outperforms many existing methods in terms of accuracy over than at least 5%.

• Korean Journal of Community Nutrition
• /
• v.25 no.2
• /
• pp.150-158
• /
• 2020

Objectives: This study was conducted to estimate usual meat intake distribution, which may have been over/underestimated when estimations were made using only the third food codes of the Korea National Health and Nutrition Examination Survey (KNHANES). Methods: For this purpose, 24-hour recall data from the 2009 Korea National Health and Nutrition Examination Survey, which conducted a partial 2-day survey of food intake, were used. The Multiple Source Method (MSM) was used to estimate the distribution of the usual intake of red and processed meats. Results: The results of this study show that the mean intake of red meat was 45.07 g while that of processed meat was 4.33 g. These results are slightly higher than the consumption calculated using only tertiary food code, and the difference was statistically significant. Furthermore, characteristics of the estimated usual intake distribution were a smaller standard deviation, increased lower percentiles, and decreased upper percentiles compared to the 2-day mean intake distribution for both red and processed meats. The proportion of individuals not consuming red meat decreased substantially from approximately 37% to 0.7%. The proportion of consumption that exceeded 90 g, which is the upper limit of red meat intake recommended by the National Health Service (NHS), was only approximately 10% in the distribution of usual intake. Conclusions: As the consumption of processed foods is expected to continuously increase, caution is needed regarding the processes used to calculate food (group) intake to avoid over/underestimation. Moreover, use of KNHANES data to calculate the proportion of the population at risk of insufficiency or excess intake of certain nutrients or food (group), based on one day intake that does not address within-individual variation, may lead to biased estimates.