• Journal of the Korean Institute of Intelligent Systems
• /
• 제18권2호
• /
• pp.157-162
• /
• 2008

This paper presents a learning method of tagging ontology using large tagging data such as a folksonomy, which stands for classification structure informally created by the people. There is no common agreement about the semantics of a tagging, and most social web sites internally use different methods to represent tagging information, obstructing interoperability between sites and the automated processing by software agents. To solve this problem, we need a tagging ontology, defined by analyzing intrinsic attributes of a tagging. Through several machine learning for tagging data, tag groups and similar user groups are extracted, and then used to learn the tagging ontology. A recommender system adopting the tagging ontology is also suggested as an applying field.

• Journal of Periodontal and Implant Science
• /
• 제38권2호
• /
• pp.199-206
• /
• 2008

Purpose: Variation in the morphology of gingival papilla may be determined by the shape and position of anatomic crown as well as contact area and embrasure form of individual teeth. However, periodontal biotype classification is regarded to be subjective because of the lack of definite criteria. In this study, we defined the objective parameters which constitute the periodontal biotype and measured their relationship. Materials and Methods: 109 of dental casts were prepared using three dimensional scanner and specialized reconstruction software, then acquiredvirtual models were sent to the 20 professional dentists to define the specific periodontal biotypes. Several parameters around periodontal structures were measured from the virtual models; facial surface area of the anterior tooth (AT), anterior papillary area (AP), proportion of the dento-papillary complex, clinical papillary length (PL), and clinical papillary angle (PA). Statistical analysis was performed to confirm the relationship among parameters. Results: Coincidence rate of periodontal biotype within observers was $63.77{\pm}16.05%$. Coincidence rate between observers was $76.15{\pm}16.43%$. Among the parameters measured, PL showed the most positive correlations and PA presented the most negative correlations. The parameter of the AP and PL of six maxillary anterior teeth showed significant correlation coefficient. Conclusion: Anterior papillary area and clinical papillary length would be objective parameters for determining the consistent periodontal biotypes.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• 제31권3B호
• /
• pp.239-253
• /
• 2006

For guaranteeing the international competitive power of SW industry that is the core industry for the future, the training of SW technical manpower as an architect is needed. They must confront the change of worldwide technology and also lead the design and analysis of SW industry for the future. However, SW technical manpower based on regular career tends to change his employment as a general manager in current status. For solve this situation and reconsider the quality level of SW technical manpower, we need to propose the systematic and effective growth direction for them. Therefore, we propose the systematic and effective growth direction for domestic SW technical manpower and a plan to be realized by suggesting the carrier path of high level SW analysis/design manpower in this paper.

• KIPS Transactions on Software and Data Engineering
• /
• 제3권9호
• /
• pp.381-388
• /
• 2014

In this paper, we deal with implementation issues of an unknown word classifier for middle-school level English writing test. We define the type of unknown words occurred in English text and discuss the detection process for unknown words. Also, we define the type of swear words occurred in students's English writings, and suggest how to handle this type of words. We implement an unknown word classifier with a swear detection module for developing an automatic English writing scoring system. By experiments with actual test data, we evaluate the accuracy of the unknown word classifier as well as the swear detection module.

• The Journal of Information Systems
• /
• 제18권2호
• /
• pp.35-59
• /
• 2009

The study of Information Systems(IS) is a relatively new discipline area, thus an analysis of the latest research literature could be useful to identify what the researchers are doing and what can be done to improve our discipline. With that purpose in mind, this study analyzes the total 208 articles published in "The Journal of Information Systems~ between 2001 and 2008. The classification system that comprises three key characteristics of diversity (research topic, research method, and reference discipline) was developed based on a review of prior literature. The results of this study were also compared with Kim et al.(2005)'s and Vessey et al.(2002)'s results to identify issues in current Information Systems research and 10 suggest some recommendations for future In formation Systems research. The findings identify popular research topic:s, the dominant research method, and reference discipline. The popular research topics consists of organizational concepts, problem domain-specific concepts, and systems/software management concepts. Field study was characterized as the dominant research method in the papers included in the study. Information Systems itself represents the major theoretical reference of the studies. However, many papers in this study relied on a number of reference disciplines., none of which was dominant, or they did not rely on a specific reference discipline. Finally, this study suggests more research on the disciplinary issues, more training on the research method, more accurate and specific reference discipline, and controlled diversity.

• Journal of Forest and Environmental Science
• /
• 제29권2호
• /
• pp.131-137
• /
• 2013

This study attempts to classify forest species using hyperspectral data for supporting resources management. The primary dataset used was AISA sensor. The sensor was mounted onboard the NOMAD GAF-27 aircraft at 2,000 m altitude creating a 2 m spatial resolution on the ground. Pre-processing was carried out with CALIGEO software, which automatically corrects for both geometric and radiometric distortions of the raw image data. The radiance data set was then converted to at-sensor reflectance derived from the FODIS sensor. Spectral Angle Mapper (SAM) technique was used for image classification. The spectra libraries for tree species were established after confirming the appropriate match between field spectra and pixel spectra. Results showed that the highest spectral signature in NIR range were Kembang Semangkok (Scaphium macropodum), followed by Meranti Sarang Punai (Shorea parvifolia) and Chengal (Neobalanocarpus hemii). Meanwhile, the lowest spectral response were Kasai (Pometia pinnata), Kelat (Eugenia spp.) and Merawan (Hopea beccariana), respectively. The overall accuracy obtained was 79%. Although the accuracy of SAM techniques is below the expectation level, SAM classifier was able to classify tropical tree species. In future it is believe that the most effective way of ground data collection is to use the ground object that has the strongest response to sensor for more significant tree signatures.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• 제11권4호
• /
• pp.99-104
• /
• 2011

In this paper the approach of neural network was proposed which detects a variety of defects in the molded parts. In an attempt to improve the response of the system, It is designed to minimize the use of memory via LookUp table in software. The goal of these methods was to extract the features of samples in learning of neural networks, overcoming the algorithms of defects detection and classification. Through the learning of 500 sample patterns of molded parts, defects of 3% molded parts was detected and classified as the incorrect diameter parts. We expect that proposed approach is an effective alternative to save test time and cost for defect detection of a fine pattern within the molded parts.

• Journal of Digital Contents Society
• /
• 제8권4호
• /
• pp.587-592
• /
• 2007

This paper explains the design and implementation of the EC_NH. EC_NH is a system that is suitable for detecting, sharing and recovering software error based on multimedia CSCW(Computer Supportes Cooperated Work). With error sharing system, a group cooperating users can share error applications. From the perspective of multimedia collaborative environment, an error application becomes another interactive presentation error is shared with participants engaged in a cooperative work. Our Digital Carousel enables user to share media objects through media synchronization mechanism. We implemented the Digital Carousel so that the users participated in collaborative work may refer shared media or error objects as the same view to others.

• International Journal of Ocean System Engineering
• /
• 제3권2호
• /
• pp.61-67
• /
• 2013

In this study, wave spectrum based fatigue analyses are studied for Turkey's adjacent coastal seas by using Maestro finite element analyzing software. Palmgren-Miner's method is used to obtain the fatigue safe life time. Palmgren-Miner's method was selected for the fatigue analyses because of its good acceptance of data from almost all classification societies such as Germanischer Lloyd, the American Bureau of Shipping, Det Norske Veritas, etc. The maximum stress regions of the structures are obtained by using finite element analyses, and the results are compared with the endurance limit of the W$\ddot{o}$hler diagram of AA5059 H321 aluminum alloy. The wave characteristics table given in this article is used to obtain the number of cycles for each sea condition. By using the wave characteristics table, the wave lengths, wave speeds, and cycles are obtained. This study is performed to estimate the lifetimes of a semi-swath type coast guard boat and/or commercial yacht projects, which are produced by using AA5059 H321 aluminum alloy, under different sea environment conditions. Fatigue examinations are performed for both head seas and oblique seas.

• Journal of the Korea Convergence Society
• /
• 제11권9호
• /
• pp.45-50
• /
• 2020

This study used data from the 15th (2019) Youth Health Behavior Online Survey. A study was conducted to investigate the relationship between oral health behaviors and drink intake and oral symptoms in adolescents. The collected data was analyzed using SPSS/WIN 25.0 program, a software for statistical analysis. Logistic regression analysis using oral symptoms as a dependent variable revealed that gender, school classification, academic performance, dental treatment experience, carbonated beverages, energy drinks, and sweet drink intake were associated with oral symptoms. Based on the above results, consumption of carbonated beverages, energy drinks, and sweet beverages was found to have a negative effect on oral symptoms. In the future, it is thought that oral health education related to drinking intake will be needed by setting guidelines for sugar intake.