• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.275-282
• /
• 2006

For the efficient image retrieval, the method has studied that uses color distribution and relations between pixels. This paper presents the color descriptor that stands high above the others in image retrieval capacity. It is based on color co-occurrence histogram that the diagonal part and the non-diagonal part are attached the weight and modified to energy of color co-occurrence histogram, and the number of bins with petty worth have little influence is curtailed. It's verified by analysis that the diagonal part carries size information of homogeneous color region and the non-diagonal part does information about the coherence of it, Moreover the non-diagonal part is more influential than diagonal part in survey of similarity between images. So, the non-diagonal part is attached more weight than the diagonal part as a result of the research. The experiments validate that the proposed descriptor shows better image retrieval performance when the weight for non-diagonal part is set to the value between 0.7 and 0.9.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.2
• /
• pp.379-386
• /
• 2014

As the use of mobile device is increasing rapidly, the number of users is also increasing. However, most of the app stores are using recommendation of simple ranking method, so the accuracy of recommendation is lower. To recommend an item that is more appropriate to the user, this paper proposes a technique that reflects the weight of user information and recent preference degree of item. The proposed technique classifies the data set by categories and then derives a predicted value by applying the user's information weight to the collaborative filtering technique. To reflect the recent preference degree of item by categories, the average of items' rating values in the designated period is computed. An item is recommended by combining the two result values. The experiment result indicated that the proposed method has been more enhanced the accuracy, appropriacy, compared to item-based, user-based method.

• Land and Housing Review
• /
• v.11 no.1
• /
• pp.109-116
• /
• 2020

This study aims to establish an approach to assess urban flood vulnerability by identifying social characteristics such as the road transportation and the vulnerable groups. Assessment procedures comprise three steps as: (1) composing the assessment criteria to reflect the urban characteristics; (2) calculating the weight; and (3) evaluating the vulnerability. The criteria were adopted by Delphi survey technique. Four criteria as land cover, residents, vulnerable areas, and disaster response were adopted in the current study. To determine the weight set of criteria, subjective and objective methods were combined. The weight set was determined using the combined method which reflects the Delphi method and Entropy analysis. In the process of data-based construction, GIS tools wwere used to extract administrative unit materials such as land cover, road status, and slope. Data on population and other social criteria were collected through the National Statistical Office and the Seoul Metropolitan statistical data. TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution) technique, which uses materials from cell units in order to rank the closest distance to the best case and the farthest distance from the worst case by calculating the distances to the area of assessment, was applied to assess. The study area was the Dorimcheon basin, a flood special treatment area of Seoul city. The results from the current study indicates that the established urban flood vulnerability assessment approach is able to predict the inherent vulnerable factors in urban regions and to propose the area of priority control.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.8 no.1
• /
• pp.21-29
• /
• 2006

When apples are picked or selected by grader, the rate of wound occurrence on the skin by apple stalk is remarkably high if the apple was bigger than 3 size during the harvest time. Except this case, the other sizes showed very little similarity. The crop of apple per 1 minute was 2.9kg without cutting fruit stalk, whereas only 1.1kg of the apples were obtained due to cutting the fruit stalk. Thereby, the harvesting without cutting fruit stalk is highly effective in terms of productivity rather than cutting the fruit stalk. As far as the wound occurrence rate on apple skin by apple stalk of distance between grader's dish and accumulated board is concerned, the grader which has no distance showed quite low rate of wound occurrence compared with those grader with 3cm or 8cm distance. When the apple was being stored, there was no difference in firmness between the cut stalk apple and the uncut stalked apple, however there was slightly more weight loss in the cut stalk apple than uncut stalk apple.

• IE interfaces
• /
• v.21 no.4
• /
• pp.411-417
• /
• 2008

An impeller is a type of high-speed rotor that is used to compress or transfer fluid under high-speed and pressure at high temperatures. The impeller is composed of an axial hub and several blades attached along the hub. The weight and shape of an impeller must be balanced, because their imbalances can cause noise and vibration, which can lead to the breakage of the impeller blades during operation. Thus, the hub and blades of an impeller are commonly machined in a 5-axis NC machine to obtain qualified surfaces. The impeller machining strategy or process plan can not be easily obtained due to the complex, overlapped and twisted shapes of impeller blades. Skillful machining process planners may generate appropriate machining strategies based on their experiences and floor data. However, in practice most shop floor data for the impeller machining is not well-structured such that it does not effectively provide a process planner with information for machining strategies and/or process plans. This paper reports the development of a case-based machining strategy support system (CBMS) that employs case-based reasoning to obtain the machining strategy of an impeller by using the existing machining strategies of the shop floor. The CBMS generates impeller machining strategies through a stepwise reasoning process considering the similarity features between the blade shapes and machining regions. A case study is provided to demonstrate that CBMS can generate useful machining strategies facilitating process planners. The developed system can simulate the tool paths of impeller machining and runs on the web.

• The Korean Journal of Applied Statistics
• /
• v.33 no.4
• /
• pp.511-526
• /
• 2020

Single-cell RNA-sequencing (scRNA-seq) data consists of each cell's RNA expression extracted from large populations of cells. One main purpose of using scRNA-seq data is to identify inter-cellular heterogeneity. However, scRNA-seq data pose statistical challenges when applying traditional clustering methods because they have many missing values and high level of noise due to technical and sampling issues. In this paper, motivated by analyzing scRNA-seq data, we propose a novel spectral-based clustering method by imposing different weights on genes when computing a similarity between cells. Assigning weights on genes and clustering cells are performed simultaneously in the proposed clustering framework. We solve the proposed non-convex optimization using an iterative algorithm. Both real data application and simulation study suggest that the proposed clustering method better identifies underlying clusters compared with existing clustering methods.

• Korean Journal of Veterinary Research
• /
• v.54 no.2
• /
• pp.107-112
• /
• 2014

Four viruses showing cytopathic effects in MDBK cells were isolated from brains of cattle showing downer cattle syndrome in 2012. The isolates were confirmed to belong to the genus Rubulavirus of the subfamily Paramyxovirinae. Isolate QIA-B1201 had the ability to hemagglutinate red blood cells from several species of animals and was capable of adsorbing guinea pig erythrocytes on the surface of infected Vero cells. Nucleotide sequence analysis showed that two isolates (QIA-B1201 and QIA-B1204) had high similarity with other human and animal PIV5 isolates ranging from 98.1 to 99.8%. The highest sequence similarity of the two isolates corresponded to strain KNU-11 (99.8% at the nucleotide and amino acid level) isolated from suckling piglets in Korea in 2012. To evaluate the virulence of strain QIA-B1201, we inoculated bPIV5 into 5 week-old mice via both the intraperitoneal and intracranial route. Body weight was not significantly altered in mice inoculated with QIA-B1201. In this study, we isolated and characterized novel bPIV5s from brain samples showing downer cattle syndrome, but were not able to elucidate the pathogenicity of the bPIV5s in mice.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.11-14
• /
• 2009

In this paper, we propose the method configuring social networks among users based on users' context and profile. Recently, many researchers are concerned about social networks related with collaborative systems. In case of the existing researches, however, it is difficult to configure social networks dynamically because they are based on static data types, such as log and profile of users. The proposed method uses not only user profiles but also context reflecting users' behavior dynamically. It computes the similarity among users' behavior contexts using hierarchical structure of context domain knowledge model. And it calculates relationships between contexts by given weight factors of category of context model. In order to verify usefulness of the method, we conduct an experiment on configuring social network according to change of user context. We expect that it makes dynamic analysis of relationship of users possible.

• Journal of the Korea Convergence Society
• /
• v.11 no.10
• /
• pp.89-96
• /
• 2020

Linked Data allows structured data to be published in a standard way that datasets from various domains can be interlinked. With the rapid evolution of Linked Open Data(LOD), researchers are exploiting it to solve particular problems such as semantic similarity assessment. In this paper, we propose a method, on top of the basic concept of Linked Data Semantic Distance (LDSD), for calculating the Linked Data semantic distance between resources that can be used in the LOD-based recommender system. The semantic distance measurement model proposed in this paper is based on a similarity measurement that combines the LOD-based semantic distance and a new link weight using TF-IDF, which is well known in the field of information retrieval. In order to verify the effectiveness of this paper's approach, performance was evaluated in the context of an LOD-based recommendation system using mixed data of DBpedia and MovieLens. Experimental results show that the proposed method shows higher accuracy compared to other similar methods. In addition, it contributed to the improvement of the accuracy of the recommender system by expanding the range of semantic distance calculation.

• Archives of design research
• /
• v.14 no.4
• /
• pp.5-14
• /
• 2001

Among Human Sensibility-oriented products a gap between the images that designers try to express through that product and users emotional evaluation becomes an issue. The data on the correlation between image words used for design evaluation and images used in the design process are especially significant. This study based on these correlations suggests a Fuzzy retrieval system supporting styling design with images and image words. In the system, the relational data are demonstrated by Fuzzy thesaurus as correlation coefficient from the degree of similarity among image words. And the degree of similarity is produced based on image evaluation. Image retrieval is conducted by the algorithm of Fuzzy thesaurus development, 1) among image words, 2) images to image words, 3) image words to images and 4) among images: 4 different modes are provided as retrieval modes. Also transfer between modes is carried by direct operating interface, therefore divergent thinking and convergent thinking is supported well. The system consists of operation for the gap and the measurement unit of emotional evaluation, and visualization units. Under unified interface environments are set in order for consistency of the operation.