• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1031-1033
• /
• 2005

This paper presents a system of handwritten numerals recognition, which is based on Ant-miner algorithm (data mining based on Ant colony optimization). At the beginning, three distinct fractures (also called attributes) of each numeral are extracted. The attributes are Loop zones, End points, and Feature codes. After these data are extracted, the attributes are in the form of attribute = value (eg. End point10 = true). The extraction is started by dividing the numeral into 12 zones. The numbers 1-12 are referenced for each zone. The possible values of Loop zone attribute in each zone are "true" and "false". The meaning of "true" is that the zone contains the loop of the numeral. The Endpoint attribute being "true" means that this zone contains the end point of the numeral. There are 24 attributes now. The Feature code attribute tells us how many lines of a numeral are passed by the referenced line. There are 7 referenced lines used in this experiment. The total attributes are 31. All attributes are used for construction of the classification rules by the Ant-miner algorithm in order to classify 10 numerals. The Ant-miner algorithm is adapted with a little change in this experiment for a better recognition rate. The results showed the system can recognize all of the training set (a thousand items of data from 50 people). When the unseen data is tested from 10 people, the recognition rate is 98 %.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.44 no.2
• /
• pp.354-368
• /
• 2020

Accurate and versatile image data-sets are essential for fashion AI research and AI-based fashion businesses based on a systematic attribute classification system. This study constructs a color and texture attribute hierarchical classification system by collecting fashion item images and analyzing the metadata of fashion items described by consumers. Essential dimensions to explain color and texture attributes were extracted; in addition, attribute values for each dimension were constructed based on metadata and previous studies. This hierarchical classification system satisfies consistency, exclusiveness, inclusiveness, and flexibility. The image tagging to confirm the usefulness of the proposed classification system indicated that the contents of attributes of the same image differ depending on the annotator that require a clear standard for distinguishing differences between the properties. This classification system will improve the reliability of the training data for machine learning, by providing standardized criteria for tasks such as tagging and annotating of fashion items.

• Journal of Korean Society for Geospatial Information Science
• /
• v.11 no.4 s.27
• /
• pp.45-51
• /
• 2003

This study intended to extract the spatial data and attribute data from the images of terrestrial photographs to compile the digital map from the images using photogrammetric analysis. In this study, the plane map of present objective area was made using the single terrestial photographs and graphical method, and the spatial or attribute data for the facilities in the area was extracted. Also, it is concluded that the efficient techniques for acquiring spatial and attribute data of the building and road facilities in proper time for the concerning area were suggested.

• Current Research on Agriculture and Life Sciences
• /
• v.26
• /
• pp.45-54
• /
• 2008

The purpose of this research is to develope street trees management program for more an effective street trees management. The principal point of this program is to relate spatial data and attribute data that is the main concept in GIS(Geographic Information System). To do this function, MapObjects which is ESRI's mapping and GIS components was used to process spatial data and Access which had been developed by MS was used to manipulate attribute data in this program. Visual Basic also was used to design and develop user interfaces and procedures, relate two sort of data, and lastly complete Application. Relational data model was adopted to design tables and their relation, Antenucci's GIS development model was selected to design and complete this program. The configuration of this application is composed of management data and reference data. The management data includes the location of street tree, a growth condition, a surrounding environment, the characters of tree, an equipments, a management records and etc. The reference data include general information about tree, blight and insects.

• East Asian Journal of Business Economics (EAJBE)
• /
• v.4 no.2
• /
• pp.48-60
• /
• 2016

This study analyzes what effects does restaurant's well-being attribute selection have on word-of-mouth intention. Based on the result, this study aims to provide basic data for establishing Korean restaurant's service strategy and marketing strategy. The researchers surveyed 350 customers who visited a Korean restaurant located in Kangbook, Seoul. We encoded gathered data and analyzed them using SPSS 17.0 statistics package program. Following are the analyzed results. First, under hypothesis 1 - Korean restaurant's well-being attribute selection will have a positive influence on re-visitation intention - it is shown that sufficiency, healthiness, and steadiness have similar influence on re-visitation intention. Second, under hypothesis 2 - Korean restaurant's well-being attribute selection will have a positive influence on word-of-mouth intention - it is shown that sufficiency, healthiness, environment, and steadiness have similar influence on word -of-mouth intention. Third, under hypothesis 3 - Korean restaurant's re-visitation intention will have a positive influence on word -of-mouth intention - it is considered that eliciting customer's re-visitation intention also has influence on word-of-mouth intention. We will be necessary to consult how to derive customer's re-visitation intention or word-of-mouth intention by considering factors which customers of traditional Korean restaurant value.

• The KIPS Transactions:PartC
• /
• v.19C no.1
• /
• pp.63-70
• /
• 2012

To ensure privacy of individual information in remote healthcare service, health data should be protected through a secure technology such as encryption scheme. Only user who delegated decryption right can access to sensitive health data and delegator needs capability for revocating access privilege. Recently, in ubiquitous environment, CP-ABTD(Ciphertext-Policy Attribute-Based Threshold Decryption with Flexible Delegation and Revocation of User Attributes) which extends CP-ABE(Ciphertext-Policy Attribute-Based Encryption) has been proposed for these requirements. In this paper, we construct remote healthcare monitoring system with delegation and revocation capability for attribute in CP-ABTD. Finally, we analyze collusion attack between users in our system.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.31 no.2 s.161
• /
• pp.236-246
• /
• 2007

The purpose of the current study is to investigate the underlying reasons of fashion brand repurchase intention formation based on means-end chain theory and to identify whether the price level moderates the relationships between attribute evaluation and re-purchase intention. Questionnaire data from 291 consumers who had purchase experience of casual wear during the last 6 month period through off-line retail shops were analyzed. The results showed that hedonic shopping value had a positive impact on aesthetic attribute and utilitarian shopping value also had a positive impact on physical attribute of fashion product. While aesthetic attribute had a positive influence on brand repurchase intention, physical attribute had no effect on brand repurchase intention. In addition, there was no moderating effect of price level between the links from shopping value to fashion product attribute evaluation. When casual wear companies have to devise price related strategies, they need to pay attention to diverse promotion factors except for product attributes to realize price-based differentiation.

• Korean Journal of Clinical Pharmacy
• /
• v.25 no.4
• /
• pp.286-295
• /
• 2015

Objective: This experiment is to study how elderly group and their various lifestyles interact with health functional foods, according to their selection behavior. Different lifestyles will be observed closely, as well as how different health conditions and consumer involvements will affect critical decision making in selecting health functional foods. Method: Theories and discoveries from original advanced research were compared parallel to the new study. Results: First, cluster analysis and exploratory analysis were performed amongst different elder lifestyles. Lifestyle exploratory analysis was used for healthy, unique, leisure, and economical-style elders. Cluster analysis was used for material trend oriented, health oriented, complacent oriented-style elders. Health Functional Foods' selection trait Exploratory Factor Analysis showed that product's originality (function, uniqueness, specialty, compatibility, distributor, expiration date), quality (amount, daily dose, visual representation, accessibility, portability, natural ingredients), and popularity (product container, brand image, taste and smell, advertised product, domestic or import, well-known function) were the three main causes. Secondly, the amount of benefits for the elderly group health lifestyle were affected by 'Interest in health', 'Notability of the health functional food', and 'Functionality approved mark'. Specifically, the importance of, 'Interest in health', 'Notability of health functional food', and 'Functionality approved mark' were noticeably high within health oriented elders. Lastly, after examining the data from elder lifestyle's relationship with health functional food selection trait, all three different results showed equal importance. If you closely examine material trend oriented elderly group, selection trait showed distinctively high regards in 'Fundamental Attribute', 'Typical Attribute', and 'Cognitive Attribute'. Health oriented elders showed their distinctively high regards in 'Natural Attribute', and less consideration in 'Typical Attribute' and 'Cognitive Attribute'. Complacent oriented-style elderly group showed less focus on 'Fundamental Attribute', and even less in 'Typical Attribute', and 'Cognitive Attribute'. Health oriented elderly group concluded with above data from the fact that they showed most importance and involvement in health beneficial products that are scientifically proven. Material trend oriented elderly group showed balanced traits in their concluded data, showing that they prefer function, safety, as well as the brand image and their reputation. Also, they consider the products' outer elements, such as design and product name, in order to sense inner functions. Conclusion: So, Silver Business corporations must develop products to fulfill the market demands, and strategize marketing plans to better target the correct audience.

• Proceedings of the Safety Management and Science Conference
• /
• 2011.11a
• /
• pp.695-716
• /
• 2011

In the future, smartphone convergences are not only based on the on/offline integration, but also with the integration between mobile communications and broadcasts. Therefore, there is a need to search for new direction of mobile device that enables variety user applications that are different from the existing size and application issue. The aim of this reserch is to improve user interface of smartphone's functional attribute. The survey results in this paper showed that the most preferable attribute of smartphone among the 8 was the wireless internet 25.3%, followed by messaging 20% and application 19.8%, which totaled to 62.5%. But the samples used were mostly limited to those aged 20 through 30. So the results are not considered as a representative preference of all smartphone users, and should be considered otherwise before materializing them to a product. Therefore, for the more liable results the further research should be conducted to gather data from a variety of users of all ages, and the functional attribute should be analysed through QFD.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.86-88
• /
• 2014

Naive Bayes (NB) assumption has some harmful effects in classification to the real world data. To relax this assumption, we now propose approach called Naive Bayes Mutual Information Attribute Weighting with Smooth Kernel Density Estimation (NBMIKDE) that combine the smooth kernel for attribute and attribute weighting method based on mutual information measure.