• Publications of The Korean Astronomical Society
• /
• v.15 no.spc2
• /
• pp.27-35
• /
• 2000

The investigation of the space environment requires the use of experimental and theoretical tools and resources in order to perform the research task. Understanding of these research tools is imperative for proper interpretation of the results. In this paper, we discuss on research tools that are widely used in the field of aeronomy; Fabry-Perot interferometer and Michelson interferometer. These instruments have been used extensively as passive optical devices, spectrally monitoring the natural atmospheric emissions (airglow). This function has made both instruments valuable tools in upper atmospheric studies since they provide the ability to determine the dynamic and thermodynamic properties of the upper atmosphere by monitoring naturally-occuring emission.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.563-566
• /
• 2003

Quality measures play an important role in the field of image processing. Such measures are commonly used to assess the performance of different algorithms that are designed to perform a specific image processing task. In this paper we propose two novel measures for image quality assessment based on the notion of correlation between fuzzy sets. Two different definitions fur the correlation between fuzzy sets have been used. In order to calculate the proposed quality measures two approaches were evaluated, one with direct application of the measures to the image′s pixels and the other using the fuzzy set corresponding to the normalized histogram of the image. A comparative study of the proposed measures is performed by investigating their behavior using images with different types of distortions, such as impulsive "salt at pepper" noise, additive white Gaussian noise, multiplicative speckle noise, blurring, gamma distortion, and JPEG compression.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.2
• /
• pp.119-124
• /
• 2016

According to the expansion of smartphone penetration and development of wearable device, personal context information can be easily collected. To use this information, the context aware recommender system has been actively studied. The key issue in this field is how to deal with the context information, as users are influenced by different contexts while rating items. But measuring the similarity among contexts is not a trivial task. To solve this problem, we propose context aware post-filtering to apply the context compensation. To be specific, we calculate the compensation for different context information by measuring their average. After reflecting the compensation of the rating data, the mechanism recommends the items to the user. Based on the item recommendation list, we recover the rating score considering the context information. To verify the effectiveness of the proposed method, we use the real movie rating dataset. Experimental evaluation shows that our proposed method outperforms several state-of-the-art approaches.

• Electronics and Telecommunications Trends
• /
• v.35 no.3
• /
• pp.9-19
• /
• 2020

Recently, a technique for applying a deep learning language model pretrained from a large corpus to fine-tuning for each application task has been widely used as a language processing technology. The pretrained language model shows higher performance and satisfactory generalization performance than existing methods. This paper introduces the major research trends related to deep learning pretrained language models in the field of language processing. We describe in detail the motivations, models, learning methods, and results of the BERT language model that had significant influence on subsequent studies. Subsequently, we introduce the results of language model studies after BERT, focusing on SpanBERT, RoBERTa, ALBERT, BART, and ELECTRA. Finally, we introduce the KorBERT pretrained language model, which shows satisfactory performance in Korean language. In addition, we introduce techniques on how to apply the pretrained language model to Korean (agglutinative) language, which consists of a combination of content and functional morphemes, unlike English (refractive) language whose endings change depending on the application.

• Electronics and Telecommunications Trends
• /
• v.35 no.3
• /
• pp.20-33
• /
• 2020

Temporal action detection (TAD) in untrimmed videos is an important but a challenging problem in the field of computer vision and has gathered increasing interest recently. Although most studies on action in videos have addressed action recognition in trimmed videos, TAD methods are required to understand real-world untrimmed videos, including mostly background and some meaningful action instances belonging to multiple action classes. TAD is mainly composed of temporal action localization that generates temporal action proposals, such as single action and action recognition, which classifies action proposals into action classes. However, the task of generating temporal action proposals with accurate temporal boundaries is challenging in TAD. In this paper, we discuss TAD technologies that are considered high performance in terms of representative TAD studies based on deep learning. Further, we investigate evaluation methodologies for TAD, such as benchmark datasets and performance measures, and subsequently compare the performance of the discussed TAD models.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2001.05a
• /
• pp.20-25
• /
• 2001

In recent years, the concern about a user center design in increasing, and it's needed to task a user's visual cognitive characteristics for information presentation. Then this study aims to grasp user's cognitive characteristics about the information presentation by analyzing the fixation points. In the experiment, actually subject operated a copy machine. Recorded the fixation point movement of the operation panel by the eye mark recorder. Analysis examined the screen interface of the operation panel from the field of a fixation point trace. The top down type fixation oder by experience or the context became clear as a result. Furthermore, the difference of the fixation order by skill level was also examined. In this study, it was assumed that to grasp the visual cognitive characteristics becomes the key of efficient information.

• Journal of the Ergonomics Society of Korea
• /
• v.23 no.3
• /
• pp.111-119
• /
• 2004

In this study, we analyzed the old`s characteristics for depth perception in comparison with the young`s as a basic study for universal design in field of products or facilities. Twenty three of the old and twenty two of the young had participated and the depth perception apparatus was used in this experiment. Gender, viewing distance, and age were considered as factors and the differences of depth perception were analyzed for each experimental condition. In the result, a significant difference was not detected on gender, but significant differences were detected on age and viewing distance. That is, we can see that the old is remarkably worse than the young on depth perception task. Therefore, it means that these characteristics have to be absolutely considered in user interface design to improve the old`s accessibility for products or facilities.

• Journal of Korean Institute of Industrial Engineers
• /
• v.38 no.1
• /
• pp.67-73
• /
• 2012

Identification of meaningful patterns and trends in large volumes of text data is an important task in various research areas. In the present study we crawled the keywords from the abstracts in IIE Transactions, one of the representative journals in the field of Industrial Engineering from 1969 to 2011. We applied low-dimensional embedding method, clustering analysis, association rule, and social network analysis to find meaningful associative patterns of key words frequently appeared in the paper.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.04a
• /
• pp.709-712
• /
• 1996

Generating a project network of a specific construction project is very time consuming and difficult task in the field. To effectiviely automate and support the planning process, we design a case-based project planning expert system inspired by the fact a human expert project planner uses previous cases for planning a new project. A construction project case consist of its specific characteristics and the corresponding project network (i.e. project plan). Using frame based representation. we represent the project features affecting the progress network and the entities composing the project plan such as the buildings, construction methods, WBS (work breakdown structure), activities, and resources. The project planning process runs through most similar case retrieval, case adaptation, and user requirement satisfaction. We represent the construction domain knowledge for each procedure using constraints and rules. We develop the methodology for constraint-based case adaption. Case adaptation process mainly consist of activity generation/deletion and predecence constraint satisfaction, for which we develop the dynamic constraint generation method and connect user-level requirement representation the system-level network modification knowledge. The methodology is being applied to the prototype for apartment construction project planning.

• Journal of Korean Society for Atmospheric Environment
• /
• v.18 no.1
• /
• pp.59-65
• /
• 2002

The application of local air circulation models in the field of air pollution research has become more and more popular with increasing demands of detailed wind data for obtaining precise information on spatial and temporal variations. However the prediction of air circulation near the surface is generally not a simple task because of intricate interactions between surface and air. Particularly in Korea, many areas are mountainous with a complicated shoreline. Because considerable errors could be introduced into the model predictions, it is necessary to confirm their feasibility by comparing model predictions with observations. In this paper, the results from the evaluation of model predictions in selected publications in Korea as well as their procedures were reviewed. Various aspects of errors in the model predictions. such as possible sources, vulnerable conditions, and reduction methods, were discussed.