• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.1-21
• /
• 2020

With the rapid development of artificial intelligence technology, various techniques have been developed to extract meaningful information from unstructured text data which constitutes a large portion of big data. Over the past decades, text mining technologies have been utilized in various industries for practical applications. In the field of business intelligence, it has been employed to discover new market and/or technology opportunities and support rational decision making of business participants. The market information such as market size, market growth rate, and market share is essential for setting companies' business strategies. There has been a continuous demand in various fields for specific product level-market information. However, the information has been generally provided at industry level or broad categories based on classification standards, making it difficult to obtain specific and proper information. In this regard, we propose a new methodology that can estimate the market sizes of product groups at more detailed levels than that of previously offered. We applied Word2Vec algorithm, a neural network based semantic word embedding model, to enable automatic market size estimation from individual companies' product information in a bottom-up manner. The overall process is as follows: First, the data related to product information is collected, refined, and restructured into suitable form for applying Word2Vec model. Next, the preprocessed data is embedded into vector space by Word2Vec and then the product groups are derived by extracting similar products names based on cosine similarity calculation. Finally, the sales data on the extracted products is summated to estimate the market size of the product groups. As an experimental data, text data of product names from Statistics Korea's microdata (345,103 cases) were mapped in multidimensional vector space by Word2Vec training. We performed parameters optimization for training and then applied vector dimension of 300 and window size of 15 as optimized parameters for further experiments. We employed index words of Korean Standard Industry Classification (KSIC) as a product name dataset to more efficiently cluster product groups. The product names which are similar to KSIC indexes were extracted based on cosine similarity. The market size of extracted products as one product category was calculated from individual companies' sales data. The market sizes of 11,654 specific product lines were automatically estimated by the proposed model. For the performance verification, the results were compared with actual market size of some items. The Pearson's correlation coefficient was 0.513. Our approach has several advantages differing from the previous studies. First, text mining and machine learning techniques were applied for the first time on market size estimation, overcoming the limitations of traditional sampling based- or multiple assumption required-methods. In addition, the level of market category can be easily and efficiently adjusted according to the purpose of information use by changing cosine similarity threshold. Furthermore, it has a high potential of practical applications since it can resolve unmet needs for detailed market size information in public and private sectors. Specifically, it can be utilized in technology evaluation and technology commercialization support program conducted by governmental institutions, as well as business strategies consulting and market analysis report publishing by private firms. The limitation of our study is that the presented model needs to be improved in terms of accuracy and reliability. The semantic-based word embedding module can be advanced by giving a proper order in the preprocessed dataset or by combining another algorithm such as Jaccard similarity with Word2Vec. Also, the methods of product group clustering can be changed to other types of unsupervised machine learning algorithm. Our group is currently working on subsequent studies and we expect that it can further improve the performance of the conceptually proposed basic model in this study.

• Journal of Yeungnam Medical Science
• /
• v.16 no.2
• /
• pp.200-207
• /
• 1999

Background: The objective of this study is to evaluate the effect of the dental and general health in relation to the state of dentition and chewing ability by surveying oral condition and anthropometric measure in order to provide primary statistics for the development of a program which may lead to an improvement in the long-lived elderly health status in a rural community. Materials and Methods: The subjects of this study were 97 rural long-lived elderly(27 males and 70 females) who were over 85 years-old (average age of subjects are $88.14{\pm}3.20$ year old) in Sungju-Gun, Kyungpook Province. Data were collected by using questionnaires and direct measurement of anthropometrics, and oral examination from all 97 subjects on July, 1999. Results: The following results were obtained: 1. 53.6% of all subjects believe that they are healthy. The average values of height, weight, BMI, body fat, lean body fat and total water were $148.8{\pm}11.2cm$, $46.9{\pm}10.5kg$, $21.2{\pm}3.5kg/m^2$, $26.7{\pm}6.9%$, $73.0{\pm}7.1%$, and $53.4{\pm}5.2%$, respectively. 2. The average number of teeth remaining in the subjects were $3.50{\pm}5.71$; the number of maxillary teeth remaining were $1.08{\pm}2.88$; and the number of mandibular teeth remaining were $2.41{\pm}3.76$. The maximum number of teeth remaining among subjects were 22 teeth, and the fully edentulous(no natural teeth) people were 76.3%. The oral conditions of the subjects were 52.6% using denture, 23.7% using natural teeth, and 23.7% masticating edentulous ridge without denture. 3. In terms of oral condition in self-assessment of health, digestive ability, and chewing ability ; On self-assessment of health, 47.1% of those wearing denture group responded as feeling good, 56.5% of those in the group of edentulous without denture, and 65.2% in group of natural teeth only. On self-assessment of digestive ability, 82.4% of those in group of denture responded as feeling good, 65.2% of those in group of no teeth and no denture, and 73.9% of those in group of natural teeth only. On self-assessment of chewing ability, 90.2% of those in the group wearing a denture, 60. 9% of those in the group of no teeth and no denture, and 65.2% of those in the group of natural teeth only. 4. In terms of oral condition in anthropometric measurements; The height, weight, body fat, lean body mass, and total water according to oral conditions were $150.0{\pm}10.7cm$, $49.0{\pm}10.9kg$, $26.9{\pm}6.6%$, $72.7{\pm}7.0%$, $53.2{\pm}5.1%$, respectively, in group wearing a denture, $142.7{\pm}6.0cm$, $43.2{\pm}5.5kg$, $29.5{\pm}7.2%$, $70.8{\pm}6.9%$, $51.8{\pm}5.0%$, respectively, in the group of no teeth and no denture, and $152.3{\pm}14.1cm$, $45.9{\pm}12.6kg$, $23.4{\pm}6.0%$, $75.9{\pm}6.9%$, $55.6{\pm}5.1%$, respectively, in the group of natural teeth only. Conclusion: The subjective measurements of good health were higher denture user, and natural teeth.

• Journal of the East Asian Society of Dietary Life
• /
• v.21 no.6
• /
• pp.934-947
• /
• 2011

The purpose of this study is to analyze products for good taste and convenience, which become an engine to constantly create customers. In addition, this study is aimed at investigating the relationship between the selective attributes of Home Meal Replacement, the perceived utilitarian value, and the repurchase intention, and drawing new suggestions on the Home Meal Replacement market from a new marketing perspective. Based on a total of 215 samples, this study reviewed the reliability and fitness of the research model and verified a total of 5 hypothesized using the Amos program. The result of study modeling was GFI=0.905, AGFI=0.849, NFI=0.889, CFI=0.945, and RMR=0.0.092 at the level of $x^2$=230.22 (df=126, p<0.001). First, the food quality (${\beta}$=0.221), convenience (${\beta}$=0.334), packing (${\beta}$=0.278), and employee service (${\beta}$=0.204) of home meal replacement consideration attributes had a positive (+) influence on perceived utilitarian value. Second, perceived utilitarian value (${\beta}$=0.584) had a positive (+) influence on repurchase intention. The factors to differentiate one company from other competitors in terms of the utilitarian value are the quality of food, convenience, wrapping, and services by employees. This study has illustrated the need to focus on the development of a premium menu to compete with other companies and to continue to research and develop nutritious foods that are easy to cook. Moreover, the key factors to have a distinct and constant competitive edge over other companies are the alleviation of consumer anxiety over wrapping container materials, the development of more designs, and the accumulation of service know-how. Therefore, it is necessary for a company to strongly develop the key factors based on its resources as a core capability.

• Journal of Korean Home Economics Education Association
• /
• v.18 no.3 s.41
• /
• pp.1-22
• /
• 2006

The purpose of this study is that I should look for a desirous directions about home economics by studying the requirements and perception of the high school parents who have finished the course of home economics. It was about 600 parents whom I have searched Seoul-Pusan, Ganwon. Ghynggi province, Choongcheong-Gyungsang province, Cheonla and Jeju province of 600, I chose only 560 as apparently suitable research. The questions include 61 requirements about home economics and one which we never fail to keep among the contents, whenever possible and one about the perception of home economics aims 11 about the perception of home economics courses and management. The collections were analyzed frequency, percent, mean. standard deviation t-test by using SAS program. The followings is the summary result of studying of it. 1. All the boys and girls learning together about the Idea of healthy lives and desirous human formulation and knowledge together are higher. 2. Among the teaching purposes of home economics, the item of the scientific principle and knowledge for improvements of home life shows 15.7% below average value. 3. The recognition degree about the quality of home economics is highly related with the real life, and about the system. we recognize lacking in periods and contents of home economics field and about guiding content, accomplishment and application qualities are higher regardless of sex. 4. The important term which we should emphasize in the subject of home economics is family part. 5. Among the needs of home economic requirement in freshman, in the middle unit, their growth and development are higher than anything else, representing 4.11, and by contrast the basic principle and actuality is 3.70, which is lowest among them. 6. In the case of second grade requirement of home economics content for parents in the middle unit young man and consuming life is 4.09 highest. 7. In the case of 3rd grade requirement of economics contents in the middle unit the choice of coming direction and job ethics is highest 4.16, and preparing meals and evaluation is lowest 3.50.

• Journal of Intelligence and Information Systems
• /
• v.20 no.3
• /
• pp.45-58
• /
• 2014

The Korean Culture Contents spread out to Worldwide, because the Korean wave is sweeping in the world. The contents stand in the middle of the Korean wave that we are used it. Each country is ongoing to keep their Culture industry improve the national brand and High added value. Performing contents is important factor of arousal in the enterprise industry. To improve high arousal confidence of product and positive attitude by populace is one of important factor by advertiser. Culture contents is the same situation. If culture contents have trusted by everyone, they will give information their around to spread word-of-mouth. So, many researcher study to measure for person's arousal analysis by statistical survey, physiological response, body movement and facial expression. First, Statistical survey has a problem that it is not possible to measure each person's arousal real time and we cannot get good survey result after they watched contents. Second, physiological response should be checked with surround because experimenter sets sensors up their chair or space by each of them. Additionally it is difficult to handle provided amount of information with real time from their sensor. Third, body movement is easy to get their movement from camera but it difficult to set up experimental condition, to measure their body language and to get the meaning. Lastly, many researcher study facial expression. They measures facial expression, eye tracking and face posed. Most of previous studies about arousal and interest are mostly limited to reaction of just one person and they have problems with application multi audiences. They have a particular method, for example they need room light surround, but set limits only one person and special environment condition in the laboratory. Also, we need to measure arousal in the contents, but is difficult to define also it is not easy to collect reaction by audiences immediately. Many audience in the theater watch performance. We suggest the system to measure multi-audience's reaction with real-time during performance. We use difference image analysis method for multi-audience but it weaks a dark field. To overcome dark environment during recoding IR camera can get the photo from dark area. In addition we present Multi-Audience Engagement Index (MAEI) to calculate algorithm which sources from sound, audience' movement and eye tracking value. Algorithm calculates audience arousal from the mobile survey, sound value, audience' reaction and audience eye's tracking. It improves accuracy of Multi-Audience Engagement Index, we compare Multi-Audience Engagement Index with mobile survey. And then it send the result to reporting system and proposal an interested persons. Mobile surveys are easy, fast, and visitors' discomfort can be minimized. Also additional information can be provided mobile advantage. Mobile application to communicate with the database, real-time information on visitors' attitudes focused on the content stored. Database can provide different survey every time based on provided information. The example shown in the survey are as follows: Impressive scene, Satisfied, Touched, Interested, Didn't pay attention and so on. The suggested system is combine as 3 parts. The system consist of three parts, External Device, Server and Internal Device. External Device can record multi-Audience in the dark field with IR camera and sound signal. Also we use survey with mobile application and send the data to ERD Server DB. The Server part's contain contents' data, such as each scene's weights value, group audience weights index, camera control program, algorithm and calculate Multi-Audience Engagement Index. Internal Device presents Multi-Audience Engagement Index with Web UI, print and display field monitor. Our system is test-operated by the Mogencelab in the DMC display exhibition hall which is located in the Sangam Dong, Mapo Gu, Seoul. We have still gotten from visitor daily. If we find this system audience arousal factor with this will be very useful to create contents.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.26 no.3
• /
• pp.221-229
• /
• 1990

The horizontal distribution of squid gill-net fishing ground in the North Pacific Ocean was examined within the main fishing season, May to October, during 1986~1989. Data of sea surface temperature were selected from Technical Reports of National Fisheries Research Development Agency of Korea, Data Records of Hokkaido University, Deep-sea Training Reports of Korea Fishing Training centre, Fishing Operation Reports of Daelim Fisheries Co., Ltd., Oyang Fisheries Co., Ltd. and Dong-won Industrial Co., Ltd.. Data of catch were also collected from Deep-sea Training Reports of Korea Fishing Training Centre and Fishing Operation Report of three fisheries companies in Korea. The fishing ground was segmented in every 1 degree of latitude from $34^{\circ}N$ to $46^{\circ}N$ and 2 degree of longitude from $144^{\circ}E$ to $162^{\circ}W.$ The distribution and centeroid of fishing ground, fished and optimum surface temperature, catch per unit effort (CPUE) in the fishing ground were computed, based on the above data. The resulted obtained can be summarized as follows: 1. Range of fishing ground can be estimated as $35^{\circ}~40^{\circ}N,$ $178^{\circ}~166^{\circ}W$ in May, $36^{\circ}~41^{\circ}N,$ $178^{\circ}E~166^{\circ}W$ in June, $38^{\circ}~44^{\circ}N,$ $170^{\circ}E~170^{\circ}W$ in July, $39^{\circ}~44^{\circ}N,$ $144^{\circ}~180^{\circ}E$ in August, $39^{\circ}~44^{\circ}N,$ $144^{\circ}~170^{\circ}E$ in September and $40^{\circ}~44^{\circ}N,$ $144^{\circ}~154^{\circ}E$ in October. 2. Fishing ground in May, June and October is similarly distributed along longitude and latitude, but the range of the former is larger than that of the latter in July, August and September. Monthly centeroids of fishing sectors is estimated as #3888 in May, #3884 in June, #4078 in July, #4154 in August, #4146 in September and #4044 in October respectively. 3. Fished temperature and optimum and temperature are estimated as $14.0~18.5^{\circ}C$ and $15.0~16.0^{\circ}C$ in May, $13.5~18.5^{\circ}C$ and $14.5~16.0^{\circ}C$ in June, $14.0~20.0^{\circ}C$ and $14.5^{\circ}C,$ $19.0^{\circ}C$ in July, $16.0~21.5^{\circ}C$ and $18.0~20.0^{\circ}C$ in August, $14.5~22.0^{\circ}C$ and $17.0~18.5^{\circ}C$ in September, $14.0~18.0^{\circ}C$ and $16.0~17.0^{\circ}C$ in October. 4. Monthly mean CPUE which corresponds to the net weight of catch(kg) divided by the sheet number of operated gillnets is calcuted as 3.2, 4.5, 4.3, 5.1, 6.4 and 5.8 kg/sheet respectively. 5. Considering the monitoring program of the squid gill-net fishery in the North Pacific Ocean during 1989~1990, set by the Korean Government, 12 sectors may be restricted out of 21 fishing sectors in May, 7 out of 24 in June, 4 out of 25 in July. They are free from restriction hereafter August.