• The KIPS Transactions:PartB
• /
• v.15B no.5
• /
• pp.457-464
• /
• 2008

In the real-world operational environment, most of text classification systems have the problems of insufficient training documents and no prior knowledge of feature space. In this regard, $Na{\ddot{i}ve$ Bayes is known to be an appropriate algorithm of operational text classification since the classification model can be evolved easily by incrementally updating its pre-learned classification model and feature space. This paper proposes the improving technique of $Na{\ddot{i}ve$ Bayes classifier through feature weighting strategy. The basic idea is that parameter estimation of $Na{\ddot{i}ve$ Bayes considers the degree of feature importance as well as feature distribution. We can develop a more accurate classification model by incorporating feature weights into Naive Bayes learning algorithm, not performing a learning process with a reduced feature set. In addition, we have extended a conventional feature update algorithm for incremental feature weighting in a dynamic operational environment. To evaluate the proposed method, we perform the experiments using the various document collections, and show that the traditional $Na{\ddot{i}ve$ Bayes classifier can be significantly improved by the proposed technique.

• Journal of the Korea Convergence Society
• /
• v.10 no.9
• /
• pp.1-9
• /
• 2019

In this paper, we propose an evaluation model to evaluate the usability of locomotion technologies in a virtual environment (VE; Virtual Environment) and try to verify them through a case study. The order of this study firstly, the factors for analysis are derived through theoretical approach to locomotion technology on VR. Second, the definition and concept of mobile technology and usability evaluation in VR are established theoretically and the elements for analysis are derived through the literature survey through the theoretical approach to VE. Third, based on this, a usability evaluation model is proposed to evaluate locomotion technologies in the VE. Finally, the results are derived by experimenting and analyzing the existing VR games applied with the three locomotion technologies derived from the literature survey. Through this paper, the locomotion technology in VR is not used separately, but can propose mobile technology that conforms to VR game content characteristics by assessing its usability and analyzing it, and it is considered to be a significant data that can suggest criteria for identifying problems in locomotion technology.

• The Journal of Society for e-Business Studies
• /
• v.12 no.3
• /
• pp.1-17
• /
• 2007

A virtual enterprise (VE) can be mapped into a multi-agent system (MAS) that consists of various agents with specific role(s), communicating with each other to accomplish common goal(s). However, a MAS for enacting VE requires more advanced mechanism such as context that can guarantee autonomy and dynamism of VE members considering heterogeneity and complex structure of them. This paper is to suggest a context-based MAS as a platform for constructing and managing virtual enterprises. In the Context-based MAS a VE is a collection of Actor, Interaction (among Actors), Actor Context, and Interaction Context. It can raise the speed and correctness of decision-making and operation of VE enactment using context, i.e., information about the situation (e.g., goal, role, task, time, location, media) of Actors and Interactions, as well as simple data of their properties. The Context-based MAS for VE we proposed('VECoM') may consists of Context Ontology, Context Model, Context Analyzer, and Context Reasoner. The suggested approach and system is validated through an example where a VE tries to find a partner that could join co-development of new technology.

• Journal of Korea Multimedia Society
• /
• v.17 no.2
• /
• pp.232-239
• /
• 2014

As online texts have been rapidly growing, their automatic classification gains more interest with machine learning methods. Nevertheless, comparatively few research could be found, aiming for Korean texts. Evaluating them with statistical methods are also rare. This study took a sample of tweets and used machine learning methods to classify emotions with features of morphemes and n-grams. As a result, about 76% of emotions contained in tweets was correctly classified. Of the two methods compared in this study, Support Vector Machines were found more accurate than Na$\ddot{i}$ve Bayes. The linear model of SVM was not inferior to the non-linear one. Morphological features did not contribute to accuracy more than did the n-grams.

• Korean Journal of Construction Engineering and Management
• /
• v.12 no.3
• /
• pp.131-139
• /
• 2011

In this Study, the Cost of Public Facility Construction in the VE Cost Model, and the Progress of the Construction Site Management, and Cost due to the Lack of Cpatial Information in Dispute Cost Work Type Recognize the limits of Historical Information, and to Overcome the Perception of Cost and Space Systems Unit In the Process of Transition that Began Seeking Ways to Improve Through this Study, Different Parts of the Proposed Area of Construction Work Unit System, the Core of Calculating Hourly and Detailed Engineering Information and Cost Information Generated Extension to Configure the Construction Unit in Every Space, Every Work Unit System, All Materials That Make Up Work Unit System, Unit Labor Costs, And All of the Configuration Items Enables Precise And Multidimensional Understanding is That.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.5
• /
• pp.345-349
• /
• 2009

Social bookmarking systems are a typical web 2.0 service based on folksonomy, providing the platform for storing and sharing bookmarking information. Spammers in social bookmarking systems denote the users who abuse the system for their own interests in an improper way. They can make the entire resources in social bookmarking systems useless by posting lots of wrong information. Hence, it is important to detect spammers as early as possible and protect social bookmarking systems from their attack. In this paper, we applied a diverse set of machine learning approaches, i.e., decision tables, decision trees (ID3), $na{\ddot{i}}ve$ Bayes classifiers, TAN (tree-augment $na{\ddot{i}}ve$ Bayes) classifiers, and artificial neural networks to this task. In our experiments, $na{\ddot{i}}ve$ Bayes classifiers performed significantly better than other methods with respect to the AUC (area under the ROC curve) score as veil as the model building time. Plausible explanations for this result are as follows. First, $na{\ddot{i}}ve$> Bayes classifiers art known to usually perform better than decision trees in terms of the AUC score. Second, the spammer detection problem in our experiments is likely to be linearly separable.

• Korean Journal of Construction Engineering and Management
• /
• v.12 no.3
• /
• pp.42-52
• /
• 2011

As environmental issues are rising recently efforts to reduce environmental stress are emerging in all industry segments. Especially environmental impact of buildings occupy a critical portion, so each country is operating green building rating system for life cycle of buildings. Accordingly green building rating system for every facility is operating in Korea. And acquisition of grade I for building energy efficiency is mandatory for every new public buildings since 2010. To design green building efficiently and systematically eco-friendly elements should be considered and checked from the schematic design phase. But in many cases eco-friendly elements are checked at the end of constructed design phase. So applying eco-friendly elements at the value engineering process, which is performing through schematic and constructed design phase, could make a efficient and systematic green building design. Value engineering process is divided into pre workshop, workshop and post workshop stages. And subject selection in pre workshop stage is the step that finds out the subjects which has the great possibility to be improved to perform efficient value engineering workshop. So this study present the Green VE subject selection model to select the most considerable eco-friendly subjects in projects.

• The Korean Journal of Mycology
• /
• v.41 no.3
• /
• pp.192-196
• /
• 2013

Fungal development is largely affected by many environmental factors. In a model filamentous fungus Aspergillus nidulans, asexual development is promoted by exposure of light, presence of salt and non-fermentable sugars. In other hand, sexual development is largely induced by absence of light, fermentable sugars and hypoxic condition. Also, some important genes including veA and nsdD play positive roles in activating sexual development. Here, we reported that the effect of high concentration of $CO_2$ on developmental decision in A. nidulans. When wild-type $veA^+$ strain was cultured in normal condition, sexual and asexual development occurred in balanced manner. However, high concentration of $CO_2$ (~5%) strongly activated sexual development and inhibited asexual development. Furthermore, this $CO_2$ effect was controlled by the veA or nsdD gene. High $CO_2$ culture of $veA^-$ or $nsdD^-$ mutant didn't activate sexual development, suggesting that the activation of sexual development induced by high $CO_2$ cannot overcome the genetic requirement of sexual development such as veA or nsdD. Since 5% $CO_2$ is an important condition for human pathogenic fungi for surviving and adapting in human body, this developmental pattern of A. nidulans affected by $CO_2$ concentration may provide interesting clues for comparative study with human fungal pathogens including Aspergillus fumigatus.

• The Journal of Bigdata
• /
• v.5 no.1
• /
• pp.197-208
• /
• 2020

Lexical ambiguity means that a word can be interpreted as two or more meanings, such as homonym and polysemy, and there are many cases of word sense ambiguation in words expressing emotions. In terms of projecting human psychology, these words convey specific and rich contexts, resulting in lexical ambiguity. In this study, we propose an emotional classification model that disambiguate word sense using bidirectional LSTM. It is based on the assumption that if the information of the surrounding context is fully reflected, the problem of lexical ambiguity can be solved and the emotions that the sentence wants to express can be expressed as one. Bidirectional LSTM is an algorithm that is frequently used in the field of natural language processing research requiring contextual information and is also intended to be used in this study to learn context. GloVe embedding is used as the embedding layer of this research model, and the performance of this model was verified compared to the model applied with LSTM and RNN algorithms. Such a framework could contribute to various fields, including marketing, which could connect the emotions of SNS users to their desire for consumption.

• Journal of the Korean Society for Railway
• /
• v.7 no.3
• /
• pp.215-222
• /
• 2004

Optimal route selection of railway should take consideration of the function of the railway, topography, practicability of construction and management as well as the cost. This study performed the surveys for experts and surrounding industries and the review for the bid guidelines in order to develop the quality model with the AHP method and establish the weight for each factor. Six quality models were developed for such as the efficiency of railway operation, structure design and practicability, economic feasibility, correspondence with other plans, civil appeal and environmental sustainability, and correspondence with system. The detailed evaluation elements were also derived by each factors.