http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
신경망을 이용한 만성질병에 영향을 미치는 식이요인 분석연구
이심열,백희영,유송민 대한지역사회영양학회 1999 대한지역사회영양학회지 Vol.4 No.3
A neural network system was applied in order to analyze the nutritional and other factors influencing chronic diseases. Five different nutrition evaluation methods including SD Score, %RDA, NAR INQ and %RDA-SD Score were utilized to facilitate nutrient data for the system. Observing top three chronic disease prediction ratio, WHR using SD Score was the most frequently quoted factor revealing the highest predication rate as 62.0%. Other high prediction rates using other data processing methods are as follows. Prediction rate with %RDA, NAR, INQ and %RDA-SD Score were 58.5%(diabetes), 53.5%(hyperlipidemia), 51.6%(diabetes), and 58.0%(diabetes)respectively. Higher prediction rate was observed using either NAR or INQ for obesity as 51.7% and 50.9% compared to the previous result using SD Score. After reviewing appearance rate for all chronic disease and for various data processing method used, it was found that iron and vitamin C were the most frequently cited factors resulting in high prediction rate.
이심열,박수정,김진아 대한가정학회 2004 Human Ecology Research(HER) Vol.42 No.5
The purpose of this study was to evaluate the meal pattern and the nutritional balance in university foodservices of Seoul. The survey was conducted using a questionnaire with 317 students at five different cafeterias that served 23 meals. We weighed all the meals offered by the university foodservices, separated the foods, and calculated their nutritional content using a computer program「DS24」. We also checked the dishes and those amount students consumed from the menu. The results of this study is summarized as follows.: 1) The most prevalent menu patterns included rice, soup, two side dishes, and kimchi. 2) Most nutrient contents per meal in a given menu was lower than one third of the recommended dietary allowance(RDA). 3) The mean energy content for the amount of rice that was served was 399kcal, for the side dish, it was 107kcal, and for the kimchi, it was 9.9kcal. 4) The number of total dishes and side dishes was five and two, respectively. The dietary variety score was 16.7, and the dietary diversity score was 3. 5) The mean energy intake by students at self-operated managements were 545kcal, and at one contracted management, the energy intake were 494kcal. Both of them did not serve enough to meet one third of the RDA. Nutrient adequacy ration(NAR) was 0.4~0.9, and Index of nutritional quality(INQ) was above 0.9 for most nutrients with the exception of calcium and vitarmin B₂.
이심열,유송민 경희대학교 레이저공학연구소 2000 레이저공학 Vol.11 No.-
In order to diagnose and predict the symptom of hyperlipidemia without resorting to the conventional judgement criteria, a neural network based methodology has been introduced. SD score was used to preprocess the body factors to be suitable for the system and extreme data were excluded. Cross correlation between cholesterol level and each factors were estimated to measure relative dependancy. In order to estimate parameter effectiveness, various learning rate were compared. The neural network was trained by randomizing the arranged order of training data. The network performance with respect to various network structure and number of training data were tested. Number of input node was decreased by eliminating one body factor from the training data list and corresponding prediction rate was compared.
이심열,유송민 경희대학교 산학협력기술연구원 2007 산학협력기술연구논문집 Vol.13 No.-
Current trend toward well-being and concem regarding a healthy life made people start paying lots of attention for the kind of food they are taking. Many studies have been performed to relate the effectiveness of those food intake in term of analyzing its effect on diabetes. Various systematic approaches have been followed to reveal the key roles of the nutrients. A neural network method has been applied to predict the role of 4 individual nutrients as energy, carbohydrate, animal fat and calcium. The optimal structures of the neural network having the best predicting capabilities was used. A sensitivity analysis has been conducted to evaluate the performance of the network by using Hinton diagram. It was revealed that energy consumption was closely related with that of carbohydrate.
이심열,이연숙,박정숙,배영희,박영숙,김영옥 대한지역사회영양학회 2004 대한지역사회영양학회지 Vol.9 No.3
This study was conducted to develop the standard breakfast menu for those weak groups having insufficient breakfast intake. The following three target groups are classified as: 16 - 19 years old high school male student, 20 - 29 years old female who have job or college students, 20 - 29 years old male or female who have job (double income family). While developing menus for each target groups, we applied several basic guidelines for meal planning as follows: Nutrient intake level was set to 1/3 of RDA, while the energy level to 1/4 of RDAs. Most frequent meal pattern of Koreans was adapted; Suitabilities of appropriate serving size and cost for middle-income families were considered; Domestic foods and ingredients were used. We developed 24 menus summed by 2 menus for each season and three target groups. When evaluating the menus, most of the breakfast menus were sufficient of nutrients as a meal for the subjects. Three food groups such as grain/starch group, meat/fish/egg/bean group, vegetable/fruit group were included in all menus. Even though milk/dairy products group was not excluded for some menus, other calcium substitutes like anchovies were used. Oil/nut/sugar group was used to a minimum. The average number of foods for each menu was 12.8, which ranged from 10 to 17 depending on the menus. The average weight of the menus including soup was 822 g, 633 g and 730 g for each target group, respectively. The average price of the menu ranged from 2,000 to 3,500 won per person. The above results could be applied at home as well as foodservice institutes and furthermore could offer information for developing breakfast-substituting food products. (Korean J Community Nutrition 9(3) : 315 ~ 325, 2004)