• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.113-127
• /
• 2016

Among the techniques for recommendation, collaborative filtering (CF) is commonly recognized to be the most effective for implementing recommender systems. Until now, CF has been popularly studied and adopted in both academic and real-world applications. The basic idea of CF is to create recommendation results by finding correlations between users of a recommendation system. CF system compares users based on how similar they are, and recommend products to users by using other like-minded people's results of evaluation for each product. Thus, it is very important to compute evaluation similarities among users in CF because the recommendation quality depends on it. Typical CF uses user's explicit numeric ratings of items (i.e. quantitative information) when computing the similarities among users in CF. In other words, user's numeric ratings have been a sole source of user preference information in traditional CF. However, user ratings are unable to fully reflect user's actual preferences from time to time. According to several studies, users may more actively accommodate recommendation of reliable others when purchasing goods. Thus, trust relationship can be regarded as the informative source for identifying user's preference with accuracy. Under this background, we propose a new hybrid recommender system that fuses CF and social network analysis (SNA). The proposed system adopts the recommendation algorithm that additionally reflect the result analyzed by SNA. In detail, our proposed system is based on conventional memory-based CF, but it is designed to use both user's numeric ratings and trust relationship information between users when calculating user similarities. For this, our system creates and uses not only user-item rating matrix, but also user-to-user trust network. As the methods for calculating user similarity between users, we proposed two alternatives - one is algorithm calculating the degree of similarity between users by utilizing in-degree and out-degree centrality, which are the indices representing the central location in the social network. We named these approaches as 'Trust CF - All' and 'Trust CF - Conditional'. The other alternative is the algorithm reflecting a neighbor's score higher when a target user trusts the neighbor directly or indirectly. The direct or indirect trust relationship can be identified by searching trust network of users. In this study, we call this approach 'Trust CF - Search'. To validate the applicability of the proposed system, we used experimental data provided by LibRec that crawled from the entire FilmTrust website. It consists of ratings of movies and trust relationship network indicating who to trust between users. The experimental system was implemented using Microsoft Visual Basic for Applications (VBA) and UCINET 6. To examine the effectiveness of the proposed system, we compared the performance of our proposed method with one of conventional CF system. The performances of recommender system were evaluated by using average MAE (mean absolute error). The analysis results confirmed that in case of applying without conditions the in-degree centrality index of trusted network of users(i.e. Trust CF - All), the accuracy (MAE = 0.565134) was lower than conventional CF (MAE = 0.564966). And, in case of applying the in-degree centrality index only to the users with the out-degree centrality above a certain threshold value(i.e. Trust CF - Conditional), the proposed system improved the accuracy a little (MAE = 0.564909) compared to traditional CF. However, the algorithm searching based on the trusted network of users (i.e. Trust CF - Search) was found to show the best performance (MAE = 0.564846). And the result from paired samples t-test presented that Trust CF - Search outperformed conventional CF with 10% statistical significance level. Our study sheds a light on the application of user's trust relationship network information for facilitating electronic commerce by recommending proper items to users.

• Journal of Nutrition and Health
• /
• v.53 no.3
• /
• pp.319-328
• /
• 2020

Purpose: This study was conducted to evaluate the validity of the Gene-Health application in terms of estimating energy and macronutrients. Methods: The subjects were 98 health adults participating in a weight-control intervention study. They recorded their diets in the Gene-Health application, took photographs before and after every meal on the same day, and uploaded them to the Gene-Health application. The amounts of foods and drinks consumed were estimated based on the photographs by trained experts, and the nutrient intakes were calculated using the CAN-Pro 5.0 program, which was named 'Photo Estimation'. The energy and macronutrients estimated from the Gene-Health application were compared with those from a Photo Estimation. The mean differences in energy and macronutrient intakes between the two methods were compared using paired t-test. Results: The mean energy intakes of Gene-Health and Photo Estimation were 1,937.0 kcal and 1,928.3 kcal, respectively. There were no significant differences in intakes of energy, carbohydrate, fat, and energy from fat (%) between two methods. The protein intake and energy from protein (%) of the Gene-Health were higher than those from the Photo Estimation. The energy from carbohydrate (%) for the Photo Estimation was higher than that of the Gene-Health. The Pearson correlation coefficients, weighted Kappa coefficients, and adjacent agreements for energy and macronutrient intakes between the two methods ranged from 0.382 to 0.607, 0.588 to 0.649, and 79.6% to 86.7%, respectively. Conclusion: The Gene-Health application shows acceptable validity as a dietary intake assessment tool for energy and macronutrients. Further studies with female subjects and various age groups will be needed.

• Journal of Oral Medicine and Pain
• /
• v.30 no.3
• /
• pp.337-344
• /
• 2005

A tactile sensor employs a piezoelectric element to detect contact frequency shifts and thereby measure the stiffness or softness of material such as tissue, which allows the sensor to be used in many fields of research for urology, cardiology, gynecology, sports medicine and caner detection and especially for cosmetics and skin care. In this study, reliability of the tactile sensor system was investigated with its manual application to the muscles susceptible to temporomandibular disorders. Stiffness and elasticity of anterior temporalis, masseter and trapezius muscles were calibrated bilaterally from 5 healthy men with an average of 24.5$\pm$0.94 years. The tactile sensor used in this study had a computer-controlled and motor-driven sensor unit which automatically pressed down on the skin surface over the muscles being measured and retracted, thereby providing the hysteresis curve. The slope of the tangent of the hysteresis curve (${\Delta}f/{\Delta}x$) is defined as stiffness of the muscle being measured and the distance between the two parts of the curve as its elasticity. To determine inter-examiner reliability, all the measurements were performed by the two examiners A and B, respectively and the same examination were repeated with an interval of 2 days for intra-examiner reliability. The results from this study demonstrated high reliability in measuring stiffness and elasticity of anterior temporalis, masseter and upper trapezius muscles using a tactile sensor system. It is suggested that the tactile sensor system can be a highly reproducible and effective instrument for quantitative evaluation of the muscle in head and neck region.

• Journal of Nutrition and Health
• /
• v.45 no.4
• /
• pp.324-335
• /
• 2012

The purpose of this study was to examine the relationship of dietary self-efficacy and illness beliefs, perceived benefits, and perceived barriers for the reduction of sodium intake in the elderly. A cross-sectional study was performed on 252 elderly people, aged 65 yrs and above, living in Daejeon Metropolitan city and Jecheon city, Chungbuk from March 21 to March 30, 2011. Dietary self-efficacy of three factors (resisting relapse, reducing salt and behavioral skills), perceived benefits and barriers, accurate and inaccurate illness beliefs were measured by 5 or 4 point Likert scale. With the increasing education level of the elderly, dietary self-efficacy, and accurate illness belief score increased and perceived barrier score decreased. Perceived benefits score was higher in the subject living alone compared to those living with siblings or spouses. Among three factors of dietary self-efficacy, reducing salt was scored highest and behavioral skills scored lowest in the elderly. Recording meal diary and reading labels for salt content in the items of behavioral skills showed lower score than other items. Accurate illness beliefs and perceived benefits were more scored than inaccurate illness beliefs and perceived barriers respectively in the subjects. The subjects with higher accurate illness beliefs, lower inaccurate illness beliefs, higher perceived benefits, and lower perceived barriers for the reduction of sodium intake showed higher dietary self-efficacy. In summary, accurate illness beliefs and perceived benefits positively correlated with dietary self-efficacy for the reduction of sodium intake in the elderly, whereas inaccurate illness beliefs and perceived barriers are negatively correlated.

• Journal of Nutrition and Health
• /
• v.43 no.5
• /
• pp.433-442
• /
• 2010

The study aim was to examine the effect of sensory responses of subjects after 6-month dietary sodium reduction with the aid of nutritional education. Fourteen female college students voluntarily restricted their sodium intake for 6 months, during which time they received nutritional education on the low sodium diet. As a control group, 10 students, whose anthropometric measurement, sodium intake behavior, and blood pressure were not different from those of the experimental group, were maintained on a normal diet. For the sensory responses of subjects, the salt taste perception and pleasantness for graded (0.15-1.3%) NaCl solutions were measured by a 9-point hedonic scale. The optimum sodium concentration, urinary sodium excretion, and blood pressure were measured. All the measurements were done at the beginning and end of the experiment. The sensory evaluation revealed an absence of any difference between the two groups in salt taste perception and pleasantness responses at the beginning. After 6-month adaptation, the experimental group subjects showed higher responses to low NaCl solution (0.15, 0.3, 0.5%) in salt taste perception and pleasantness evaluation while the control group subjects exhibited the opposite response. The optimum sodium concentration was reduced from 105.6 mmol to 80.7 mmol (p = 0.015) and the urinary sodium excretion was also reduced from 1,398 mg to 906 mg (p = 0.041) only in the experimental group. Systolic blood pressure was significantly reduced in the experimental group, although there was no correlation between the urinary sodium excretion and blood pressure. The optimum sodium concentration was negatively correlated with the urinary sodium excretion (r = 0.418, p = 0.053), indicating that adaptation to low sodium diet can reduce sodium intake. Further study on the individual responses of subjects on a low sodium diet by periodical evaluation may provide useful data for setting the duration needed to stabilize a lowered appetite for sodium.

• 대한공업교육학회지
• /
• v.42 no.2
• /
• pp.67-88
• /
• 2017

The purpose of this research was educational needs of experts for revitalizing youth entrepreneurship education and creating effective conditions for such education. The subjects of the survey were chosen 100 teachers who had participated in entrepreneurship-related professional training for teachers were selected and surveyed. A total of 100 questionnaires were collected, of which 92 (92.00%) were used for the analysis. Eight were excluded as they were not properly answered. As for the used survey tool, a total of 8 areas and 30 items were derived from the review of the literature, and the validity of the contents was examined through expert meetings. The data were analyzed using the SPSS (ver. 20.0) statistical program. The analysis was conducted in terms of the required competency level, perceived competency level and educational needs. As for the used analytical methods, first, the averages of the required competency level and perceived competency level were calculated and the education needs were calculated using Borich's formula, and then the averages were compared through paired t-test. The results turned out to be statistically significant (p<.000). The details are as follows: As a result of the calculation of the educational needs the educational needs in all areas turned out to be very high with the average being 4.94 points, which indicates that the teachers strongly feel the need for educational strengthening in relation to entrepreneurship. These results show that all the educational conditions such as entrepreneurship-related curriculum, teacher professionalism, educational environment, educational support and the perception among school community members are insufficient in the current school settings. For the improvement of the current status, the education conditions in the following areas should be improved: the cooperation from school community members including principals, teacher support such as an exclusive responsibility teacher system, the development of an entrepreneurship curriculum, the securing of teacher professionalism through the implementation of the curriculum, teacher training support for the enhancement of their professionalism and the provision of educational environment and facilities. For enhancing the perception of parents and society regarding entrepreneurship, it is necessary to establish the precise concept of entrepreneurship and promote it based on such work.

• Journal of Korean Ophthalmic Optics Society
• /
• v.17 no.2
• /
• pp.185-194
• /
• 2012

Purpose: The changes of phoria and subjective asthenopia before and after viewing were compared based on 2D image and two ways of 3D images, and presented for references of 3D image watching and production. Methods: Change in phoria was measured before and after watching 2D image, 3D-FPR and 3D-SG images for 30 minutes with a target of 41 university students at 20-30 years old (male 26, female 15). Paired t-test and Pearson correlation between changed phoria and subjective symptoms which were measured using questionnaires were evaluated by before and after watching each images. Results: Right after watching 2D image, exophoria was increased by 0.5 $\Delta$, in distance and near, but it was not a significant level. Right after watching 3D image, exophoria was increased by 1.0~1.5 $\Delta$, and 1.5~2.0 $\Delta$, in distance and near, respectively when compared with before watching. In the significant level, exophoria tended to increase. Changes in near was increased more by 0.5 $\Delta$, compared with those in distance. Changes based on way of 3D-FPR and 3D-SG image were less than 0.5 $\Delta$, and there was almost no difference. In terms of visual subjective symptoms, eye strain was increased in 3D image compared with that in 2D image. In addition, there was no difference depending on way of image. In terms of Pearson correlation between phoria change and eye strain, as exophoria was increased, eye strain was increased. Conclusions: Watching 3D image increased eye strain compared with watching 2D image, and accordingly exophoria tended to increase.

• Journal of Nutrition and Health
• /
• v.42 no.4
• /
• pp.397-405
• /
• 2009

A trienzyme extraction method (use of ${\alpha}$-amylase, protease and folate conjugase) for food folate assay has been used to release folate from the food matrix. In order to reduce the incubation time with three enzymes, folate values were compared between two incubation protocols; separate incubation (SI, incubated with ${\alpha}$-amylase and conjugase separately for 2 hours after protease treatment) and combined incubation (CI, incubated with ${\alpha}$-amylase and conjugase together for 2 hours after protease treatment) using 88 food items from 12 kinds of fast foods and processed foods. We found that folate values by CI were comparable to or higher than those by SI, indicating that CI might be a better extraction procedure to shorten the entire incubation time. We measured folate contents in 49 fast foods and 26 processed foods by microbiological assay after CI. Mean folate contents of one serving of various burgers ranged from 43.1 to 62.0 ${\mu}g$. One serving of French fries, pizza, sandwich and triangled kimbab contained a mean of 53.3, 28.4, 47.4, and 25.7 ${\mu}g$ of folate, respectively. Folate contents of non-alcoholic beverages were very low, ranging from 1.0 to 5.2 ${\mu}g$/100 g. Some of our values were comparable to the values in the folate database published in Korean Nutrition Society, however, some of the published values were 140 times higher than the measured values in this study. Folate values measured by the more recent modifications here can be used to update Korean folate database to accurately estimate dietary folate intake.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.1-18
• /
• 2015

Collaborative filtering(CF) algorithm has been popularly used for recommender systems in both academic and practical applications. A general CF system compares users based on how similar they are, and creates recommendation results with the items favored by other people with similar tastes. Thus, it is very important for CF to measure the similarities between users because the recommendation quality depends on it. In most cases, users' explicit numeric ratings of items(i.e. quantitative information) have only been used to calculate the similarities between users in CF. However, several studies indicated that qualitative information such as user's reviews on the items may contribute to measure these similarities more accurately. Considering that a lot of people are likely to share their honest opinion on the items they purchased recently due to the advent of the Web 2.0, user's reviews can be regarded as the informative source for identifying user's preference with accuracy. Under this background, this study proposes a new hybrid recommender system that combines with users' review mining. Our proposed system is based on conventional memory-based CF, but it is designed to use both user's numeric ratings and his/her text reviews on the items when calculating similarities between users. In specific, our system creates not only user-item rating matrix, but also user-item review term matrix. Then, it calculates rating similarity and review similarity from each matrix, and calculates the final user-to-user similarity based on these two similarities(i.e. rating and review similarities). As the methods for calculating review similarity between users, we proposed two alternatives - one is to use the frequency of the commonly used terms, and the other one is to use the sum of the importance weights of the commonly used terms in users' review. In the case of the importance weights of terms, we proposed the use of average TF-IDF(Term Frequency - Inverse Document Frequency) weights. To validate the applicability of the proposed system, we applied it to the implementation of a recommender system for smartphone applications (hereafter, app). At present, over a million apps are offered in each app stores operated by Google and Apple. Due to this information overload, users have difficulty in selecting proper apps that they really want. Furthermore, app store operators like Google and Apple have cumulated huge amount of users' reviews on apps until now. Thus, we chose smartphone app stores as the application domain of our system. In order to collect the experimental data set, we built and operated a Web-based data collection system for about two weeks. As a result, we could obtain 1,246 valid responses(ratings and reviews) from 78 users. The experimental system was implemented using Microsoft Visual Basic for Applications(VBA) and SAS Text Miner. And, to avoid distortion due to human intervention, we did not adopt any refining works by human during the user's review mining process. To examine the effectiveness of the proposed system, we compared its performance to the performance of conventional CF system. The performances of recommender systems were evaluated by using average MAE(mean absolute error). The experimental results showed that our proposed system(MAE = 0.7867 ~ 0.7881) slightly outperformed a conventional CF system(MAE = 0.7939). Also, they showed that the calculation of review similarity between users based on the TF-IDF weights(MAE = 0.7867) leaded to better recommendation accuracy than the calculation based on the frequency of the commonly used terms in reviews(MAE = 0.7881). The results from paired samples t-test presented that our proposed system with review similarity calculation using the frequency of the commonly used terms outperformed conventional CF system with 10% statistical significance level. Our study sheds a light on the application of users' review information for facilitating electronic commerce by recommending proper items to users.

• Journal of Nutrition and Health
• /
• v.42 no.6
• /
• pp.577-595
• /
• 2009

This study aimed to reanalyze energy and nutrient intakes of 2007 Korean Nutrition and Health Examination Survey (KNHANES) using CAN-Pro 3.0, a commonly used nutrient analysis software in Korea. Food items and their codes were selected from 2007 KNHANES dietary intake file and converted to food codes of CAN-Pro 3.0 nutrient database (NDB). Of the 1,324 total food items, 1,155 items were converted by direct matching, 123 items were matched using other items in CAN-Pro 3.0 NDB and 42 items were matched using external sources. Consumption frequencies of items converted by direct matching contributed 94.5% of total consumption. Nutrient intakes of 4,091 participants of 2007 KNHANES, over 1 year old, were recalculated using CAN-Pro 3.0 NDB and compared with intakes in 2007 KNHANES dietary intake file. Intakes for energy and all nutrients except protein and Vitamin C calculated by two NDBs were significantly different by paired t-test (p < 0.001), but significantly correlated by Pearson' correlation coefficients (p < 0.001). Percent differences between the NDBs ranged from 0.3% to 15.1%, low for protein, energy, vitamin C, iron, vitamin B$_2$ (below 5%) but high for phosphorus, retinol, vitamin A, and $\beta$-carotene (over 10%). Age group, sex, and their interactions significantly influenced six nutrients (p < 0.05). Intake levels of zinc, vitamin B6, vitamin E, folate and cholesterol were not available in 2007 KNHANES but were calculated by CAN-Pro 3.0. Mean intake levels of zinc, vitamin B$_6$, vitamin E, and folate by age and sex groups revealed that some groups had mean levels below RI (Recommended Intake) or AI (Adequate Intake) levels. Intake level of cholesterol was higher than the recommended level (below 300 mg/day) in some groups, especially males. Results of the present study indicate the need for comparable and more comprehensive NDB to be used for dietary assessment of KNHANES and other researches. More rigorous evaluation of nutrients which have not been reported in KNHANES is needed.