• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.143-163
• /
• 2016

The demographics of Internet users are the most basic and important sources for target marketing or personalized advertisements on the digital marketing channels which include email, mobile, and social media. However, it gradually has become difficult to collect the demographics of Internet users because their activities are anonymous in many cases. Although the marketing department is able to get the demographics using online or offline surveys, these approaches are very expensive, long processes, and likely to include false statements. Clickstream data is the recording an Internet user leaves behind while visiting websites. As the user clicks anywhere in the webpage, the activity is logged in semi-structured website log files. Such data allows us to see what pages users visited, how long they stayed there, how often they visited, when they usually visited, which site they prefer, what keywords they used to find the site, whether they purchased any, and so forth. For such a reason, some researchers tried to guess the demographics of Internet users by using their clickstream data. They derived various independent variables likely to be correlated to the demographics. The variables include search keyword, frequency and intensity for time, day and month, variety of websites visited, text information for web pages visited, etc. The demographic attributes to predict are also diverse according to the paper, and cover gender, age, job, location, income, education, marital status, presence of children. A variety of data mining methods, such as LSA, SVM, decision tree, neural network, logistic regression, and k-nearest neighbors, were used for prediction model building. However, this research has not yet identified which data mining method is appropriate to predict each demographic variable. Moreover, it is required to review independent variables studied so far and combine them as needed, and evaluate them for building the best prediction model. The objective of this study is to choose clickstream attributes mostly likely to be correlated to the demographics from the results of previous research, and then to identify which data mining method is fitting to predict each demographic attribute. Among the demographic attributes, this paper focus on predicting gender, age, marital status, residence, and job. And from the results of previous research, 64 clickstream attributes are applied to predict the demographic attributes. The overall process of predictive model building is compose of 4 steps. In the first step, we create user profiles which include 64 clickstream attributes and 5 demographic attributes. The second step performs the dimension reduction of clickstream variables to solve the curse of dimensionality and overfitting problem. We utilize three approaches which are based on decision tree, PCA, and cluster analysis. We build alternative predictive models for each demographic variable in the third step. SVM, neural network, and logistic regression are used for modeling. The last step evaluates the alternative models in view of model accuracy and selects the best model. For the experiments, we used clickstream data which represents 5 demographics and 16,962,705 online activities for 5,000 Internet users. IBM SPSS Modeler 17.0 was used for our prediction process, and the 5-fold cross validation was conducted to enhance the reliability of our experiments. As the experimental results, we can verify that there are a specific data mining method well-suited for each demographic variable. For example, age prediction is best performed when using the decision tree based dimension reduction and neural network whereas the prediction of gender and marital status is the most accurate by applying SVM without dimension reduction. We conclude that the online behaviors of the Internet users, captured from the clickstream data analysis, could be well used to predict their demographics, thereby being utilized to the digital marketing.

• Journal of Nutrition and Health
• /
• v.9 no.1
• /
• pp.7-15
• /
• 1976

The Purpose of this study was to determine every possible correlation between food habits and body statures of primary school children, aged ten years old. This study was conducted from July to October of 1975. In July, prepared questionaires concerning life style, anthropometry, food preference, and food behavior were distributed through school teachers to 425 children; 219 boys and 206 girls, in the 5th grade of three elementary schools in the city of Seoul. Then, in October, when subjects had been classified into underweight/obese by statistical analysis, mothers of obese or underweight children were interviewed by the authors to determine weaning history, daily food consumption of their children, and opinions of various snacks for children. Analysis of results in terms of correlation coefficient, chisquare test and percentage calculations, are as follows: 1. Physical growth and development Boys Girls Height (cm) $134.8{\pm}5.74\;134.4{\pm}5.97$ Weight (kg) $30.0{\pm}4.27\;29.5{\pm}5.16$ Chestgirth (cm) $64.1{\pm}3.59\;63.3{\pm}3.81$ Arm circumference (cm) $18.3{\pm}1.61\;18.2{\pm}1.70$ Triceps skinfold thickness (mm) $10.9{\pm}5.13\;12.7{\pm}4.86$ Various indices of nutrition such as relative weight, relative chestgirth, $R{\ddot{o}}hrer's$ index, Kaup index, Vervaeck index were determined. 2. Food habits 1) Food $preference{\cdots}{\cdots}A$ varying number of foods were selected from 60 items were accepted. It was found that the food which children liked best was fruit and snacks were popular one. Lowest ranking among LIKED foods were from strongly flavored vegetables and organ meat. In general, girls had more food dislikes than did boys. Selected as liked foods were fruits, rice noodle soup, biscuits, and peanuts. Disliked foods were liver, green onions, onions, green pepper, mushrooms, oysters, shellfish, and pork. Items which children never ate before were liver, mushrooms, fish cake, boiled rice mixed with sorghum, mayonnaise, and fresh water firsh. Reasons which children gave for dislike were undesirable flavor and odor. 2) Food $behavior{\cdots}{\cdots}It$ was found that boys liked sweet and salty flavors more than did the girls who more often liked sour flavor. The majority of children enjoyed evening meals more than lunch and breakfast. A number of children skipped breakfast because of lack of appetite or lack of time before going to school. Snacks were the most popular food, especially among girls. Their snacking habits were formed by the encouragement of the mother, and the relieve boredom. Educational backgrounds of mothers and family economical levels of children were remarkable correlated with mothers' attitudes toward feeding of children. There were several interesting findings relating body stature to some other responses; such as that the obese child has a small number of brothers, higher birth order, higher educated mothers and higher family cultural background. It was also discovered that food perference, except for fat and oil group foods was not related to body stature. Sweet taste was liked best and pepperly taste was mostly disliked. Sour taste was popular in the group of underweight. Underweight children were more finicky, disliked snacking, and didn't get much attention from their mothers. 3) Correlation between body stature and nutrition during their infancy. The majority of children, both from obese and underweight, were breast fed as infant. Twenty five per cent of obese children and 17.4 per cent of underwight children started weaning at $1{\sim}6$ months old. The most popular supplemental food of weaning was cereal gruel for the obese group, while boiled white rice and cereal gruel were most common for the underweight group. Highly significant relationships were found between stature of parents and their children. In the obese group 47.8 per cent of fathers and 45.9 per cent of mothers were overweight; however, none of the fathers and only one mother was found to be underweight. In daily food consumption patterns, meals consisting of bread or noodle were popular in the obese group but disliked by the underweight group. The study found clear contrast in that the obese group liked meat and fish while the underweight group liked fruits and vegetables, especially kimchee. The obese children desired to eat cereal foods, milk and milk products, and fat foods while the underweight group desired to eat fruits and vegetables. Frequency of snacks per day was much greater in the obese group. Foods which mothers believed to be good for the health were carrots, cucumbers, fruits, milk, potatoes, sweet potatoes, and breads, while sweet foods such as candies, drinks. chocolate were considered not good for the teeth. Watching television was not significantly related to statures of children. Most significant relationships were found beween frequencies of family guest meals/and eating-out, and children's statures. Nutritional problems which have been considered for the malnourished children in addition to those of children who have a tendency toward obesity, must be taken into consideration in the development of proper nutrition education through the channels of regular school teaching and teaching by parents in the homes. Korean standards of anthropometric measurements for children should be revised, current measurements show much higher figures than present Korean standards.

• Journal of Internet Computing and Services
• /
• v.24 no.2
• /
• pp.19-26
• /
• 2023

Humans have adapted and evolved to natural light. However, as humans stay in indoor longer in modern times, the problem of biorhythm disturbance has been induced. To solve this problem, research is being conducted on lighting that reproduces the correlated color temperature(CCT) of natural light that varies from sunrise to sunset. In order to reproduce the CCT of natural light, multiple LED light sources with different CCTs are used to produce lighting, and then a control index DB is constructed by measuring and collecting the light characteristics of the combination of input currents for each light source in hundreds to thousands of steps, and then using it to control the lighting through the light characteristic matching method. The problem with this control method is that the more detailed the steps of the combination of input currents, the more time and economic costs are incurred. In this paper, an LED lighting control method that applies interpolation and combination calculation based on the minimum spectral power distribution information for each light source is proposed to reproduce the CCT of natural light. First, five minimum SPD information for each channel was measured and collected for the LED lighting, which consisted of light source channels with different CCTs and implemented input current control function of a 256-steps for each channel. Interpolation calculation was performed to generate SPD of 256 steps for each channel for the minimum SPD information, and SPD for all control combinations of LED lighting was generated through combination calculation of SPD for each channel. Illuminance and CCT were calculated through the generated SPD, a control index DB was constructed, and the CCT of natural light was reproduced through a matching technique. In the performance evaluation, the CCT for natural light was provided within the range of an average error rate of 0.18% while meeting the recommended indoor illumination standard.

• Korean Journal of Soil Science and Fertilizer
• /
• v.18 no.3
• /
• pp.265-275
• /
• 1985

Present studies were carried out to investigate the distribution and formation of organic tiers contained paddy soils in Honam area characteristics to give basic informations on the effective utilization, management and improvement of the soils. The results obtained were summarized as follows; 1. The extent of organic tiers contained paddy soils in Honam area were 6.538㏊ and the amount of peat deposits were presumed about 2.41 million M/T. 2. Out of the total extent of the organic tiers contained paddy soils, about 97.6% was distributed in Honam plains (water-sheds of Mangyeong-Dongjin river), while about 1.5% in the Naju plains (water-sheds of Yeongsan river), and 0.9% in the Wando and Yeocheon areas. 3. The period of peat formation was presumed to be about the early of Seung Moon period (B.C. 4,250), and the Gongdeog series and the Bongnam series were formed in the bog conditions close to the valley mouth of near rolling and hill with small steram channels, and the Gimje series was formed in the out-skirts plains of the Gongdeog and Bongnam soils. 4. In the casue of peat formation, it was presumed to be the Gimje series that accumulated the fibrous peat out of the autochthonous peat such as reeds and grasses etc, to be the Gongdeog and Bongnam series that accumulated the autochtonous peat and the xylem and fibrous peat out of first allochthonous peat. 5. In the Organic horizons of these soils, the range of muck and peat horizons were in 62-68cm and 68-137cm of soil profile in the Gongdeog series, 52-84cm and 84-113cm in the Bongnam series respectively, one of muck horizon was in 46-71cm in the Gimje series. 6. The marks of soil horizons of the soils were expressed that the lower soils than the horizon of muck and peat were formed Cg, Aag for the muck horizon, 0 for the peat horizon, 0 of peat horizon were distingushed with Oag and Oig according to Organic forms. 7. The depthe occurred the muck and peat horizons were positively correlated with the width of local in the Gongdeog series ($r=0.881^{**}$, $r=0.827^{**}$), but not in the Bongnam series and Gimje series.