• Title/Summary/Keyword: search area analysis

Search Result 398, Processing Time 0.03 seconds

An Empirical Study on the Oriental Herbal Cosmetics Purchase Behaviors in Women in the Metropolitan Area (한방 화장품 구매행동에 관한 실증적 연구 - 수도권 거주 여성 소비자를 중심으로 -)

  • 엄정녀;김주덕
    • Journal of the Society of Cosmetic Scientists of Korea
    • /
    • v.30 no.1
    • /
    • pp.93-102
    • /
    • 2004
  • Recently, the golden age of herbal cosmetics has come. Along with active introduction of oriental herbal lines, diversification of distribution channels is designated as a major feature. In this background, the present study attempts to consider the domestic market for oriental herbal cosmetics, which is growing rapidly with the introduction of various new brands, and examine the perceptions of this new type of cosmetics by women consumers based on their purchase behaviors, and search for the ways for its promotion and development. A survey was conducted to adult women consumers aged 19∼60 residing in Seoul or Gyeonggi-do. Out of a total of 430 surveys distributed, 350 answer sheets were used for the analysis Among the results, the first-hand information on the herbal cosmetics market, their usage, and the consumer needs obtained in the present study will serve as a fundamental data for planning the marketing strategies for the oriental herbal cosmetics.

A Study on Shape Optimization of Plane Truss Structures (평면(平面) 트러스 구조물(構造物)의 형상최적화(形狀最適化)에 관한 구연(究研))

  • Lee, Gyu won;Byun, Keun Joo;Hwang, Hak Joo
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • v.5 no.3
    • /
    • pp.49-59
    • /
    • 1985
  • Formulation of the geometric optimization for truss structures based on the elasticity theory turn out to be the nonlinear programming problem which has to deal with the Cross sectional area of the member and the coordinates of its nodes simultaneously. A few techniques have been proposed and adopted for the analysis of this nonlinear programming problem for the time being. These techniques, however, bear some limitations on truss shapes loading conditions and design criteria for the practical application to real structures. A generalized algorithm for the geometric optimization of the truss structures which can eliminate the above mentioned limitations, is developed in this study. The algorithm developed utilizes the two-phases technique. In the first phase, the cross sectional area of the truss member is optimized by transforming the nonlinear problem into SUMT, and solving SUMT utilizing the modified Newton-Raphson method. In the second phase, the geometric shape is optimized utilizing the unidirctional search technique of the Rosenbrock method which make it possible to minimize only the objective function. The algorithm developed in this study is numerically tested for several truss structures with various shapes, loading conditions and design criteria, and compared with the results of the other algorithms to examme its applicability and stability. The numerical comparisons show that the two-phases algorithm developed in this study is safely applicable to any design criteria, and the convergency rate is very fast and stable compared with other iteration methods for the geometric optimization of truss structures.

  • PDF

Comparative analysis of RN-BSN Program in Korea and U. S. A. (간호학사 편입학제도의 교과과정 비교분석)

  • Lee Ok-Ja;Kim Hyun-Sil
    • The Journal of Korean Academic Society of Nursing Education
    • /
    • v.3
    • /
    • pp.99-116
    • /
    • 1997
  • In response of the increasing demand for professional degree in nursing, some university in Korea offers RN-BSN program for R. N. from diploma in nursing. However, RN-BSN program in Korea is in formative period. Therefore, the purpose of this survey study is for the comparative analysis of RN-BSN curriculum in Korea and U.S.A. In this study, subjects consisted of 18 department of nursing in university and 5 RN-BSN programs in Korea and 18 department of nursing in university and 12 RN-BSN programs in U.S.A. For earn the degree of Bachelor of Science in Nursing, the student earns 134 of mean credits in U.S.A., whereas 150.3 of mean credits in Korea. The mean credit for clinical pratice is 30.1 in U.S.A., whereas 23.9 in Korea. Students are assigned to individually planned clinical experiences under the direction of a preceptor in U.S.A. In RN-BSN program, total mean credits through lecture and clinical practice for earn the degree of BSN is 35.5(lecture : 27.7, practice ; 7.8)in U.S.A., whereas,48.1 (lecture;42.1, practice;6.0) in Korea. RN-BSN program can be taken on a full-or-part time basis in U.S.A., whereas didn't in Korea. Especially, emphasis is place on the advanced nursing practicum that focus on the role of the professional nurse in providing health care to individuals, families, and groups in community setting in U.S.A. 27.7 of mean credits was earned through lecture in U.S.A., whereas 42.1 of mean credits in Korea. It means that RN-BSN program in Korea is the lesser development in teaching method and appraisal method than in U.S.A. Students of RN-BSN program in U.S.A. can earns credit through CLEP, NLN achievement test, portfolio review session etc as well as lecture. Therefore, the authors suggests some recommendations for the development of curriculum of RN-BSN program in Korea based on comparative analysis of RN-BSN curricula in U.S.A. and Korea. 1. The curriculum of RN-BSN Program in nursing was required to do some alterations. Nursing care, today, is complex and ever changing. According to change of public need, RN-BSN curriculum intensified primary care program in community setting, geriatric nursing, marketing skill, computer language. 2. The various and new methods of earning credit should be developed. That is, the students will earn credits through the transfer of previous nursing college credits, accredited examination of university, advanced placement examination, portfolio review session, case study, report, self-directed learning and so on. Flexible teaching place should ile offered. 3. Flexible teaching place should be offered. The RN-BSN curriculum should accommodate each RN student's geographical needs and school/work schedule. Therefore, the university should search a variety of teaching places and the RN students can obtain their degrees comfortably throughout the teaching place such as lecture room inside the health care agency and establishment of the branch school in each student's residence area. 4. The RN-BSN program should offer a long distance education to place-bound RN student in many parts of Korea. That is, from the main office of university, the RN-BSN courses are delivered to many areas by Internet, EdNet (satellite telecommunication) and other non-traditional methods. 5. For allowing RN student to take nursing courses, program length should be various, depending upon the student's study/work schedule. That is, the various term systems such as semester, three terms, quarter systems and the student's status like full time or part time should be considered. Therefore, the student can take advantage of the many other educational and professional opportunities, making them available during the school year.

  • PDF

The Effect of Marketing Mix elements on brand Equity (마케팅 믹스 요소가 브랜드 자산에 미치는 영향에 관한 연구)

  • Ryu, Jang-Mu
    • Journal of Industrial Convergence
    • /
    • v.1 no.1
    • /
    • pp.41-70
    • /
    • 2003
  • Many researches on brand equity have been focused in definition about it, factors of it, and the process of formation. Most of them have been used by voluntary production category, as is durable goods or nondurable goods. But this study, using the model is developed by Foote, Cone & Be1ding(FCB) Company, classified four fields, high-low involvement, rationality(rational or sensitive) involvement. The selected goods is a sensitive high involvement(casual wear). This study investigate the effects of brand equity and search the influences of brand equity formation according to factors of marketing mix. To this goals, this study kept a literature survey and a demonstrative research. In literature survey, there are several definitions of brand and brand equity. The research model is derived from selected factors of marketing mix and former study. This study used the regression analysis to verify effects from brand equity through the selected marketing mix. The research data is collected from the capital area. The focus of this study is effects of brand equity according to marketing mix. The followings are results and suggestions of this study. First, in the price factors, the affirmative effects are revealed the perceived quality and the brand awareness in a rational high involvement goods, the perceived quality and the brand associations in a sensitive high involvement goods, all factors of brand equity in a rational low involvement goods, and the perceived quality in a sensitive low involvement goods. As summary, the important characteristics is the price factors to consumers, and consumers recognize that a high price means a high quality. Second, in the store image factors, the affirmative effects are revealed all brand equity factors in a rational high involvement and a sensitive high-low involvement. A good store image incites more interest, contact, and visit from potential consumer. And such store offers more consumer satisfaction, simulates more active and positive conversation to consumers. Third, in advertising spending factors, the affirmative effects are revealed the brand awareness and associations in a rational high involvement and a sensitive high involvement, all brand equity factors in a rational low involvement and a sensitive low involvement. An advertisement increases not only a brand awareness but also strong brand associations. Forth, in price promotion factors, the affirmative effects are revealed the brand associations in a rational high involvement, the negative effects are revealed all brand equity in sensitive high involvement. According the result about the effects of brand royalty through the brand equity factors, a perceived quality and brand associations have positive effects to brand royalty in all factors. Consumers choice a deep perceived quality than other competitive brand. So, brand equity will increase according to a qualitative grade of a perceived brand by consumers. Brand associations represent a quality and a degree of involvement. In conclusion, brand associations and equity have a positive relation each other. According to the analysis results about a brand royalty of selected marketing mix factors, the affirmative effects are revealed the store image and price promotion factors in a rational high involvement, the price and store image in a sensitive high involvement, and the price and advertising spending in a rational low involvement. The results about the affect of selected marketing mix factors according to brand equity, are the perceived quality in a high involvement, and all brand equity factors in a low involvement. The affirmative effects about a store image are revealed all equity factors in high-low involvement. In advertising spending factors, the affirmative effects are revealed the brand awareness and associations in a high involvement goods, and the perceived quality and the brand awareness in a low involvement goods. In price promotion factors, the affirmative effects are revealed the brand awareness in a low involvement goods, and the negative effects are revealed the brand awareness in a high involvement goods. According to a degree of involvement, the results of a brand royalty through a brand equity factors are following. The affirmative effects are revealed the perceived quality and the brand royalty in a high involvement goods, and the brand awareness are revealed a negative effect. The affirmative effects are revealed the perceived Quality and the brand associations in a low involvement goods. So, in a high involvement goods, the brand royalty is built by strong brand associations, but, in a low involvement goods, the brand royalty is built also by a perceived Quality and a brand awareness. This study have some concept of limitation. So, this study presents a future direction of research. First, a future study has to have more deep analysis for this study analyzed through a limited marketing mix factors. Second, a future research has to get mutual effects about brand equity of marketing mix factors for this study has an individual marketing decision factors. Third, for the future, a brand equity needs a research about a several goods such as services, profit or nonprofit, industrial products, culture, and so on. Forth, the research have to diversify a various data for population.

  • PDF

A Ethnographic Field Study for a Model Development of the Chronic Bed-ridden Patient s Home-ward (만성 재가 기동장애자의 가정병실 모델 개발을 위한 현장 연구)

  • 김태연;정연강
    • Journal of Korean Academy of Nursing
    • /
    • v.24 no.4
    • /
    • pp.597-615
    • /
    • 1994
  • This study is designed to facilitate the creation of home environment conducive to the family taking care of chronic bed-ridden patients with more effective method. The need for this study has emerged against the background of marked changes in the structure of ailments and causes of death, resulting in the number and plights of chronic bed-ridden patients as well as of a rapid increase in demand for medical care and resulting premature discharge. Keeping these in mind, this study focused on home-wards where the majority of chronic bed-ridden patients are being cared for. Despite. their overriding importance, home-words are less than efficient in caring (or chronic bed-ridden patients. These circumstances require the designing of home-wards that can offer greater comfort to patients and at the same time make things easier for caregivers, on the basis of an overall analysis of patients' life and home - ward situation. According1y this study adopted a Participant Observation Method derived cultural anthropology, Toward this end, 3 patients were chosen as subjects of this study for intensive interviewing and participant observation. In the process of this field re-search efforts were made to collect emprical data, that is, to faithfully record the words of the subjects and their caregivers for analysis and interpretation. The findings of these analyses are as follows. Firstly, the chronic bed-ridden patients are mostly being taken care by close family members. Secondly, a room for the exclusive use of the patient, floor, kitchen, bathroom and multipurpose space were found to be necessary for proper caring of the patient. These spaces were respectively used with a view to 1) accomodating the patient as well as caregivers' activities, 2) keeping general and medical supplies and other appliances for patient's care and drying the patient's washing, 3) preparing and keeping the patient's foods and beverages, 4) keeping the supplies necessary for cleaning the patient's body and treating the patient's eliminations, 5) washing the patient's clothes, underwears and bedclothes. The patient's room in turn is subdivided into six portions in terms of uses : specifically the places for accomodating 1) the patient, 2) medical supplies, 3) medicines, 4) linens St clothes, 5) bedclothes and, 6) diapers. Thirdly, the activities of the caregiver are subdivided into seven key areas : hygiene, exercise, diet, elimination, therapeutic nursing, prevention of sore, and other activities. Each area is further classified into several different activities of caring. These activities we mainly carried out in the patient's room. Fourthly, the supplies for caring the chronic bed-ridden patient is divided into two large domains : medical and general supplies. Finally, three main problems areas were found in this study on the part of caregivers, that is, sore prevention, hygiene problem related frequent urination / defecation, the caregiver's physical, psych ological and emotional burden. In consideration of the aforesaid problem areas, a model home-ward was developed in this study. The newly-developed model has been found to have the following six advantages. Firstly, the time and effort required for maintaining the patient's hygiene are reduced, thus relievins the caregiver's physical and psychological bur-den. Secondly, the patient's hygiene can be maintained in satisfactory conditions, because the patient's eliminations are more easily removed. Thirdly, skin irritations caused by the patient's eliminations were remarkably reduced and so were the patient's sores due to moisture and bacteria. Fourthly, the home-ward have a tilt-table ef-fect thanks to the inclining room floor. This improves the patient's cardiovascular function as well as constantly changes pressed skin areas and thus prevents sores. Fifthly, improved shelf arrangements help make the best use of patient's supplies. Sixthly, the trouble of continuously changing clothes, underwears, diapers & bedclothes is remarkably reduced simply by covering the patient with cotton sheets when laid in bed. This is espected to cut down expenses by reducing the comsumptions of diapers and other disposable supplies.

  • PDF

A Study for Factors Influencing the Usage Increase and Decrease of Mobile Data Service: Based on The Two Factor Theory (모바일 데이터 서비스 사용량 증감에 영향을 미치는 요인들에 관한 연구: 이요인 이론(Two Factor Theory)을 바탕으로)

  • Lee, Sang-Hoon;Kim, Il-Kyung;Lee, Ho-Geun;Park, Hyun-Jee
    • Asia pacific journal of information systems
    • /
    • v.17 no.2
    • /
    • pp.97-122
    • /
    • 2007
  • Conventional networking and telecommunications infrastructure characterized by wires, fixed location, and inflexibility is giving way to mobile technologies. Numerous research reports point to the ultimate domination of wireless communication. With the increasing prevalence of advanced cell-phones, various mobile data services (hereafter MDS) are gaining popularity. Although cellular networks were originally introduced for voice communications, statistics indicate that data services are replacing the matured voice service as the growth engine for telecom service providers. For example, SK Telecom, the Korea's largest mobile service provider, reported that 25.6% of revenue and 28.5% of profit came from MDS in 2006 and the share is growing. Statistics also indicate that, in 2006, the average revenue per user (ARPU) for voice didn't change but MDS grew seven percents from the previous year, further highlighting its growth potential. MDS is defined "as an assortment of digital data services that can be accessed using a mobile device over a wide geographic area." A variety of MDS have been deployed, with a few reaching the status of killer applications. Many of them need to access the Internet through the cellular-phone infrastructure. In the past, when the cellular network didn't have acceptable bandwidth for data services, SMS (short messaging service) dominated MDS. Now, Internet-ready, next-generation cell-phones are driving rich digital data services into the fabric of everyday life, These include news on various topics, Internet search, mapping and location-based information, mobile banking and gaming, downloading (i.e., screen savers), multimedia streaming, and various communication services (i.e., email, short messaging, messenger, and chaffing). The huge economic stake MDS has on its stakeholders warrants focused research to understand associated dynamics behind its adoption. Lyytinen and Yoo(2002) pointed out the limitation of traditional adoption models in explaining the rapid diffusion of innovations such as P2P or mobile services. Also, despite the increasing popularity of MDS, unexpected drop in its usage is observed among some people. Intrigued by these observations, an exploratory study was conducted to examine decision factors of MDS usage. Data analysis revealed that the increase and decrease of MDS use was influenced by different forces. The findings of the exploratory study triggered our confirmatory research effort to validate the uni-directionality of studied factors in affecting MDS usage. This differs from extant studies of IS/IT adoption that are largely grounded on the assumption of bi-directionality of explanatory variables in determining the level of dependent variables (i.e., user satisfaction, service usage). The research goal is, therefore, to examine if increase and decrease in the usage of MDS are explained by two separate groups of variables pertaining to information quality and system quality. For this, we investigate following research questions: (1) Does the information quality of MDS increase service usage?; (2) Does the system quality of MDS decrease service usage?; and (3) Does user motivation for subscribing MDS moderate the effect information and system quality have on service usage? The research questions and subsequent analysis are grounded on the two factor theory pioneered by Hertzberg et al(1959). To answer the research questions, in the first, an exploratory study based on 378 survey responses was conducted to learn about important decision factors of MDS usage. It revealed discrepancy between the influencing forces of usage increase and those of usage decrease. Based on the findings from the exploratory study and the two-factor theory, we postulated information quality as the motivator and system quality as the de-motivator (or hygiene) of MDS. Then, a confirmative study was undertaken on their respective role in encouraging and discouraging the usage of mobile data service.

The Structural Relationship between Entrepreneurial Competency, Entrepreneurial Opportunity Recognition on and Entrepreneurial Intentions of Middle-aged Eldery Office Workers (중·장년 직장인의 창업역량과 창업기회인식 및 창업의지의 구조적 관계)

  • Choi, In Woo
    • Asia-Pacific Journal of Business Venturing and Entrepreneurship
    • /
    • v.17 no.5
    • /
    • pp.169-185
    • /
    • 2022
  • This study analyzed the effect of entrepreneurial competency on entrepreneurial intentions by using the entrepreneurial opportunity recognition as a mediator for middle and middle-aged office workers. The sub-variables of entrepreneurial competency are classified into management competency, technology competency, business competency and funding competency. 222 copies of questionnaires collected from middle-aged and elderly office workers residing across the country centered on the metropolitan area were used for empirical analysis. Based on a simple mediating model with singular mediator using SPSS v22.0 and PROCESS macro v4.0. was analyzed. As a result of the analysis, first, among entrepreneurial competencies, business competency and funding capacity were found to have a positive (+) significant effect on the entrepreneurial intentions, but management and technical competency did not have a significant effect. The higher the business competency and funding competency. Second, it was found that all of the sub-variables of entrepreneurial competency had a significant effect in the positive (+) direction on the recognition of entrepreneurial opportunities. It was confirmed that management competency has the greatest influence on the entrepreneurial opportunity recognition and technology competence has the smallest effect. Third, it was found that the entrepreneurial opportunity recognition had a significant effect on entrepreneurial intentions. The discovery of an opportunity recognizing opportunities for start-up is a prerequisite for entrepreneur. Fourth, it was found that the entrepreneurial opportunity recognition mediates between the management competency, technological competency, business competency, funding competency, and entrepreneurial intention. It suggests that opportunity discovery by recognizing opportunities for entrepreneurship is a prerequisite for start-up. As implications of this study, it suggests that in order to inspire middle-aged and elderly office workers to start their own business, it is necessary to have indirect experience with education and to establish and promote a government support system for financing.. Second, It suggests that education on leadership and organizational management is particularly necessary to strengthen the opportunity recognition. Third, it suggests that the discovery of opportunities to recognize opportunities for start-up is a prerequisite for entrepreneur. Therefore, it is necessary to prepare a manual and conduct training on opportunity search, recognition, evaluation, and utilization according to the stage of opportunity development. Fourth, it suggests that in order to strengthen the intention to start a business, ALso, it is necessary to manage both the entrepreneurial competency and entrepreneurial opportunities recognition at the same time. By presenting the practical directions that can be given differentially, we intend to contribute to the provision of practical directions and policy establishment for the promotion of entrepreneurial activities of office workers who can give vitality to the ecosystem.

Resolving the 'Gray sheep' Problem Using Social Network Analysis (SNA) in Collaborative Filtering (CF) Recommender Systems (소셜 네트워크 분석 기법을 활용한 협업필터링의 특이취향 사용자(Gray Sheep) 문제 해결)

  • Kim, Minsung;Im, Il
    • Journal of Intelligence and Information Systems
    • /
    • v.20 no.2
    • /
    • pp.137-148
    • /
    • 2014
  • Recommender system has become one of the most important technologies in e-commerce in these days. The ultimate reason to shop online, for many consumers, is to reduce the efforts for information search and purchase. Recommender system is a key technology to serve these needs. Many of the past studies about recommender systems have been devoted to developing and improving recommendation algorithms and collaborative filtering (CF) is known to be the most successful one. Despite its success, however, CF has several shortcomings such as cold-start, sparsity, gray sheep problems. In order to be able to generate recommendations, ordinary CF algorithms require evaluations or preference information directly from users. For new users who do not have any evaluations or preference information, therefore, CF cannot come up with recommendations (Cold-star problem). As the numbers of products and customers increase, the scale of the data increases exponentially and most of the data cells are empty. This sparse dataset makes computation for recommendation extremely hard (Sparsity problem). Since CF is based on the assumption that there are groups of users sharing common preferences or tastes, CF becomes inaccurate if there are many users with rare and unique tastes (Gray sheep problem). This study proposes a new algorithm that utilizes Social Network Analysis (SNA) techniques to resolve the gray sheep problem. We utilize 'degree centrality' in SNA to identify users with unique preferences (gray sheep). Degree centrality in SNA refers to the number of direct links to and from a node. In a network of users who are connected through common preferences or tastes, those with unique tastes have fewer links to other users (nodes) and they are isolated from other users. Therefore, gray sheep can be identified by calculating degree centrality of each node. We divide the dataset into two, gray sheep and others, based on the degree centrality of the users. Then, different similarity measures and recommendation methods are applied to these two datasets. More detail algorithm is as follows: Step 1: Convert the initial data which is a two-mode network (user to item) into an one-mode network (user to user). Step 2: Calculate degree centrality of each node and separate those nodes having degree centrality values lower than the pre-set threshold. The threshold value is determined by simulations such that the accuracy of CF for the remaining dataset is maximized. Step 3: Ordinary CF algorithm is applied to the remaining dataset. Step 4: Since the separated dataset consist of users with unique tastes, an ordinary CF algorithm cannot generate recommendations for them. A 'popular item' method is used to generate recommendations for these users. The F measures of the two datasets are weighted by the numbers of nodes and summed to be used as the final performance metric. In order to test performance improvement by this new algorithm, an empirical study was conducted using a publically available dataset - the MovieLens data by GroupLens research team. We used 100,000 evaluations by 943 users on 1,682 movies. The proposed algorithm was compared with an ordinary CF algorithm utilizing 'Best-N-neighbors' and 'Cosine' similarity method. The empirical results show that F measure was improved about 11% on average when the proposed algorithm was used

    . Past studies to improve CF performance typically used additional information other than users' evaluations such as demographic data. Some studies applied SNA techniques as a new similarity metric. This study is novel in that it used SNA to separate dataset. This study shows that performance of CF can be improved, without any additional information, when SNA techniques are used as proposed. This study has several theoretical and practical implications. This study empirically shows that the characteristics of dataset can affect the performance of CF recommender systems. This helps researchers understand factors affecting performance of CF. This study also opens a door for future studies in the area of applying SNA to CF to analyze characteristics of dataset. In practice, this study provides guidelines to improve performance of CF recommender systems with a simple modification.

  • Application of Support Vector Regression for Improving the Performance of the Emotion Prediction Model (감정예측모형의 성과개선을 위한 Support Vector Regression 응용)

    • Kim, Seongjin;Ryoo, Eunchung;Jung, Min Kyu;Kim, Jae Kyeong;Ahn, Hyunchul
      • Journal of Intelligence and Information Systems
      • /
      • v.18 no.3
      • /
      • pp.185-202
      • /
      • 2012
    • .Since the value of information has been realized in the information society, the usage and collection of information has become important. A facial expression that contains thousands of information as an artistic painting can be described in thousands of words. Followed by the idea, there has recently been a number of attempts to provide customers and companies with an intelligent service, which enables the perception of human emotions through one's facial expressions. For example, MIT Media Lab, the leading organization in this research area, has developed the human emotion prediction model, and has applied their studies to the commercial business. In the academic area, a number of the conventional methods such as Multiple Regression Analysis (MRA) or Artificial Neural Networks (ANN) have been applied to predict human emotion in prior studies. However, MRA is generally criticized because of its low prediction accuracy. This is inevitable since MRA can only explain the linear relationship between the dependent variables and the independent variable. To mitigate the limitations of MRA, some studies like Jung and Kim (2012) have used ANN as the alternative, and they reported that ANN generated more accurate prediction than the statistical methods like MRA. However, it has also been criticized due to over fitting and the difficulty of the network design (e.g. setting the number of the layers and the number of the nodes in the hidden layers). Under this background, we propose a novel model using Support Vector Regression (SVR) in order to increase the prediction accuracy. SVR is an extensive version of Support Vector Machine (SVM) designated to solve the regression problems. The model produced by SVR only depends on a subset of the training data, because the cost function for building the model ignores any training data that is close (within a threshold ${\varepsilon}$) to the model prediction. Using SVR, we tried to build a model that can measure the level of arousal and valence from the facial features. To validate the usefulness of the proposed model, we collected the data of facial reactions when providing appropriate visual stimulating contents, and extracted the features from the data. Next, the steps of the preprocessing were taken to choose statistically significant variables. In total, 297 cases were used for the experiment. As the comparative models, we also applied MRA and ANN to the same data set. For SVR, we adopted '${\varepsilon}$-insensitive loss function', and 'grid search' technique to find the optimal values of the parameters like C, d, ${\sigma}^2$, and ${\varepsilon}$. In the case of ANN, we adopted a standard three-layer backpropagation network, which has a single hidden layer. The learning rate and momentum rate of ANN were set to 10%, and we used sigmoid function as the transfer function of hidden and output nodes. We performed the experiments repeatedly by varying the number of nodes in the hidden layer to n/2, n, 3n/2, and 2n, where n is the number of the input variables. The stopping condition for ANN was set to 50,000 learning events. And, we used MAE (Mean Absolute Error) as the measure for performance comparison. From the experiment, we found that SVR achieved the highest prediction accuracy for the hold-out data set compared to MRA and ANN. Regardless of the target variables (the level of arousal, or the level of positive / negative valence), SVR showed the best performance for the hold-out data set. ANN also outperformed MRA, however, it showed the considerably lower prediction accuracy than SVR for both target variables. The findings of our research are expected to be useful to the researchers or practitioners who are willing to build the models for recognizing human emotions.

    Color Analyses on Digital Photos Using Machine Learning and KSCA - Focusing on Korean Natural Daytime/nighttime Scenery - (머신러닝과 KSCA를 활용한 디지털 사진의 색 분석 -한국 자연 풍경 낮과 밤 사진을 중심으로-)

    • Gwon, Huieun;KOO, Ja Joon
      • Trans-
      • /
      • v.12
      • /
      • pp.51-79
      • /
      • 2022
    • This study investigates the methods for deriving colors which can serve as a reference to users such as designers and or contents creators who search for online images from the web portal sites using specific words for color planning and more. Two experiments were conducted in order to accomplish this. Digital scenery photos within the geographic scope of Korea were downloaded from web portal sites, and those photos were studied to find out what colors were used to describe daytime and nighttime. Machine learning was used as the study methodology to classify colors in daytime and nighttime, and KSCA was used to derive the color frequency of daytime and nighttime photos and to compare and analyze the two results. The results of classifying the colors of daytime and nighttime photos using machine learning show that, when classifying the colors by 51~100%, the area of daytime colors was approximately 2.45 times greater than that of nighttime colors. The colors of the daytime class were distributed by brightness with white as its center, while that of the nighttime class was distributed with black as its center. Colors that accounted for over 70% of the daytime class were 647, those over 70% of the nighttime class were 252, and the rest (31-69%) were 101. The number of colors in the middle area was low, while other colors were classified relatively clearly into day and night. The resulting color distributions in the daytime and nighttime classes were able to provide the borderline color values of the two classes that are classified by brightness. As a result of analyzing the frequency of digital photos using KSCA, colors around yellow were expressed in generally bright daytime photos, while colors around blue value were expressed in dark night photos. For frequency of daytime photos, colors on the upper 40% had low chroma, almost being achromatic. Also, colors that are close to white and black showed the highest frequency, indicating a large difference in brightness. Meanwhile, for colors with frequency from top 5 to 10, yellow green was expressed darkly, and navy blue was expressed brightly, partially composing a complex harmony. When examining the color band, various colors, brightness, and chroma including light blue, achromatic colors, and warm colors were shown, failing to compose a generally harmonious arrangement of colors. For the frequency of nighttime photos, colors in approximately the upper 50% are dark colors with a brightness value of 2 (Munsell signal). In comparison, the brightness of middle frequency (50-80%) is relatively higher (brightness values of 3-4), and the brightness difference of various colors was large in the lower 20%. Colors that are not cool colors could be found intermittently in the lower 8% of frequency. When examining the color band, there was a general harmonious arrangement of colors centered on navy blue. As the results of conducting the experiment using two methods in this study, machine learning could classify colors into two or more classes, and could evaluate how close an image was with certain colors to a certain class. This method cannot be used if an image cannot be classified into a certain class. The result of such color distribution would serve as a reference when determining how close a certain color is to one of the two classes when the color is used as a dominant color in the base or background color of a certain design. Also, when dividing the analyzed images into several classes, even colors that have not been used in the analyzed image can be determined to find out how close they are to a certain class according to the color distribution properties of each class. Nevertheless, the results cannot be used to find out whether a specific color was used in the class and by how much it was used. To investigate such an issue, frequency analysis was conducted using KSCA. The color frequency could be measured within the range of images used in the experiment. The resulting values of color distribution and frequency from this study would serve as references for color planning of digital design regarding natural scenery in the geographic scope of Korea. Also, the two experiments are meaningful attempts for searching the methods for deriving colors that can be a useful reference among numerous images for content creator users of the relevant field.


    (34141) Korea Institute of Science and Technology Information, 245, Daehak-ro, Yuseong-gu, Daejeon
    Copyright (C) KISTI. All Rights Reserved.