• The Journal of Korea Robotics Society
• /
• v.4 no.3
• /
• pp.185-191
• /
• 2009

This paper presents a new shape-based algorithm using affine category shape model for object category recognition and model learning. Affine category shape model is a graph of interconnected nodes whose geometric interactions are modeled using pairwise potentials. In its learning phase, it can efficiently handle large pose variations of objects in training images by estimating 2-D homography transformation between the model and the training images. Since the pairwise potentials are defined on only relative geometric relationship betweenfeatures, the proposed matching algorithm is translation and in-plane rotation invariant and robust to affine transformation. We apply spectral matching algorithm to find feature correspondences, which are then used as initial correspondences for RANSAC algorithm. The 2-D homography transformation and the inlier correspondences which are consistent with this estimate can be efficiently estimated through RANSAC, and new correspondences also can be detected by using the estimated 2-D homography transformation. Experimental results on object category database show that the proposed algorithm is robust to pose variation of objects and provides good recognition performance.

• Journal of information and communication convergence engineering
• /
• v.11 no.4
• /
• pp.268-273
• /
• 2013

In this paper, we propose a document classification model using Web documents as a part of the training corpus in order to resolve the imbalance of the training corpus size per category. For the purpose of retrieving the Web documents closely related to each category, the proposed document classification model calculates the matching score between word features and each category, and generates a Web search query by combining the higher-ranked word features and the category title. Then, the proposed document classification model sends each combined query to the open application programming interface of the Web search engine, and receives the snippet results retrieved from the Web search engine. Finally, the proposed document classification model adds these snippet results as Web documents to the training corpus. Experimental results show that the method that considers the balance of the training corpus size per category exhibits better performance in some categories with small training sets.

• Journal of the Korean Institute of Rural Architecture
• /
• v.17 no.1
• /
• pp.9-18
• /
• 2015

The purpose of this study is to analyze the usage of eco-friendly elements in Korean traditional architecture to evaluate Hanok(Unjoru and Jinwondang) according to Green Building Certification Criteria(G-SEED). The results of this study were as follows; Unjoru and Jinwondang was not enough to obtain certification points. From Site usage and Traffic category, Jinwondang gets more points than Unjoru. It's because Jinwondang is located in downtown Seoul, so it gets more points of traffic and neighborhood facility. From Energy and Environmental Pollution category, Jinwondang gets more points of energy performance than Unjoru, too. It's because Jinwondang secured insulation performance of wall and windows using insulator and glass. From Resources category, Unjoru gets more points than Jinwondang. It shows that modern Hanok was limited using natural resources. From Ecological Environments category, Jinwondang is located urban area, it's difficult to secure the open space, so Unjoru gets more points than Jinwondang. If Modern Honok installs a system that can getting point and secure insulation performance, it will be certificated according to G-SEED.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.11a
• /
• pp.204-209
• /
• 1999

In general, neural networks are widely used for the category classification. But when low contrast images, such as multispectral images, are used as the input of neural networks, neural networks converge very slowly and are of bad performance. To overcome this problem, we propose a new image enhancement method which consists of smoothing process, finding the main valley and enhancement process. And the enhanced images by the proposed method are used as the input of neural networks for the category classification. When the new category classification method is applied to multispectral LANDSAT TM images, we verified that neural networks converge very fast and overall category classification performance is improved.

• Journal of the Korean Home Economics Association
• /
• v.37 no.2
• /
• pp.55-72
• /
• 1999

The purpose of this study was to investigate developmental trends in organization strategy for taxonomic and slot-fiber lists and category typicality, use of organization strategy in relation to developmental changes in category knowledge structure, emergent organization capacity and effects in category typicality on children's recall. Moreover, the influences of children's age, use of organization strategy, list types and category typicality on children's recap were figured out. The major results were as follows. 1. Children's recall use of organization strategy increased with age. That is, the older children performed better recap and used organization strategy on both list types than the younger children. 2. AU children performed recall and used organization strategy better for the slot-filler than taxonomic list. The 4-year-olds, however, demonstrated better recap and use of organization strategy for the slot-filler than taxonomic list. While the 6-year-olds and 8-year-olds showed no such differences. These findings were supported the view that script-based slot-filler categories have a strong influence on young children's memory performance. 3. At each age level, children showed higher level of recall and use of organization strategy for category typical than category atypical list. AU children received higher scores for the typical than atypical items on recap and use of organization strategy. 4. Children's age, use of organization strategy, list types, and category typicality of lists significantly predicted children's recap.58% of the variance of children's recap was explained by four variables.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.1-25
• /
• 2020

Sentiment Analysis (SA) is a Natural Language Processing (NLP) task that analyzes the sentiments consumers or the public feel about an arbitrary object from written texts. Furthermore, Aspect-Based Sentiment Analysis (ABSA) is a fine-grained analysis of the sentiments towards each aspect of an object. Since having a more practical value in terms of business, ABSA is drawing attention from both academic and industrial organizations. When there is a review that says "The restaurant is expensive but the food is really fantastic", for example, the general SA evaluates the overall sentiment towards the 'restaurant' as 'positive', while ABSA identifies the restaurant's aspect 'price' as 'negative' and 'food' aspect as 'positive'. Thus, ABSA enables a more specific and effective marketing strategy. In order to perform ABSA, it is necessary to identify what are the aspect terms or aspect categories included in the text, and judge the sentiments towards them. Accordingly, there exist four main areas in ABSA; aspect term extraction, aspect category detection, Aspect Term Sentiment Classification (ATSC), and Aspect Category Sentiment Classification (ACSC). It is usually conducted by extracting aspect terms and then performing ATSC to analyze sentiments for the given aspect terms, or by extracting aspect categories and then performing ACSC to analyze sentiments for the given aspect category. Here, an aspect category is expressed in one or more aspect terms, or indirectly inferred by other words. In the preceding example sentence, 'price' and 'food' are both aspect categories, and the aspect category 'food' is expressed by the aspect term 'food' included in the review. If the review sentence includes 'pasta', 'steak', or 'grilled chicken special', these can all be aspect terms for the aspect category 'food'. As such, an aspect category referred to by one or more specific aspect terms is called an explicit aspect. On the other hand, the aspect category like 'price', which does not have any specific aspect terms but can be indirectly guessed with an emotional word 'expensive,' is called an implicit aspect. So far, the 'aspect category' has been used to avoid confusion about 'aspect term'. From now on, we will consider 'aspect category' and 'aspect' as the same concept and use the word 'aspect' more for convenience. And one thing to note is that ATSC analyzes the sentiment towards given aspect terms, so it deals only with explicit aspects, and ACSC treats not only explicit aspects but also implicit aspects. This study seeks to find answers to the following issues ignored in the previous studies when applying the BERT pre-trained language model to ACSC and derives superior ACSC models. First, is it more effective to reflect the output vector of tokens for aspect categories than to use only the final output vector of [CLS] token as a classification vector? Second, is there any performance difference between QA (Question Answering) and NLI (Natural Language Inference) types in the sentence-pair configuration of input data? Third, is there any performance difference according to the order of sentence including aspect category in the QA or NLI type sentence-pair configuration of input data? To achieve these research objectives, we implemented 12 ACSC models and conducted experiments on 4 English benchmark datasets. As a result, ACSC models that provide performance beyond the existing studies without expanding the training dataset were derived. In addition, it was found that it is more effective to reflect the output vector of the aspect category token than to use only the output vector for the [CLS] token as a classification vector. It was also found that QA type input generally provides better performance than NLI, and the order of the sentence with the aspect category in QA type is irrelevant with performance. There may be some differences depending on the characteristics of the dataset, but when using NLI type sentence-pair input, placing the sentence containing the aspect category second seems to provide better performance. The new methodology for designing the ACSC model used in this study could be similarly applied to other studies such as ATSC.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.6
• /
• pp.382-390
• /
• 2018

This study developed a model to evaluate the quality management system of a medical device manufacturing company, and applied it to medical device manufacturers to understand the impact on business performance in response to international regulations and industry's change. This study prepared preliminary items, defined four (4) major factors (Plan-Do-Check-Act) that consist of the evaluation layers and items per category according to prior research review and expert interview, and calculated the weight and importance using AHP. The study results showed that responsibility & authority and quality objective in Planning Category, product-related requirement and R&D in Doing Category, Measuring and monitoring in Check Category, and review of meeting Regulatory and regulation in Action Category are relatively more important factors. The evaluation model developed based on the calculated weight and importance to business performance was applied to medical device manufacturers to investigate and analyze the implementation level of QMS and its impact on business performance according to each category. Most medical device manufacturers to be studied showed a reasonable level of QMS and effective business performance. Almost all the evaluation layers and items in the four (4) factors had a significant influence on business performance. Although the medical device quality management system is aimed mainly at license acquisition, it is important that management environment factors not related directly to licensing and authorization are important to business performance, and it is effective when these factors are integrated and operated within and outside the manufacturer.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.06a
• /
• pp.354-356
• /
• 2013

ITU와 ISO/IEC가 공동으로 UHD급 영상 부호화를 위해 표준화를 진행하고 있는 HEVC 코덱은 H.264/AVC 대비 2배 이상의 압축 효율을 갖는 것을 목표로 정하고 있다. HEVC(High Efficiency Video Coding)는 In-Loop Filter 기술로 H.264/AVC에서 사용하고 있는 Deblocking Filter와 새롭게 추가 된 SAO(Sample Adaptive Offset)를 사용하고 있다. 본 논문에서는 HEVC의 In-Loop Filter 기술 중 하나인 SAO의 기술의 EO에서 Category를 조금 더 정확하게 판단하여 분류하는 방법을 제안을 한다.

• Journal of Korea Multimedia Society
• /
• v.14 no.6
• /
• pp.730-741
• /
• 2011

With the development of the internet and computer technology, the amount of information through the internet is increasing rapidly and it is managed in document form. For this reason, the research into the method to manage for a large amount of document in an effective way is necessary. The conventional document categorization method used only the keywords of related documents for document classification. However, this paper proposed keyword extraction method of based on association rule. This method extracts a set of related keywords which are involved in document's category and classifies representative keyword by using the classification rule proposed in this paper. In addition, this paper proposed the preprocessing method for efficient keywords creation and predicted the new document's category. We can design the classifier and measure the performance throughout the experiment to increase the profile's classification performance. When predicting the category, substituting all the classification rules one by one is the major reason to decrease the process performance in a profile. Finally, this paper suggested automatically categorizing plan which can be applied to hierarchical category architecture, extended from simple category architecture.

• Journal of Fashion Business
• /
• v.16 no.6
• /
• pp.21-35
• /
• 2012

In consideration of the injuries and deaths occurring at manufacturing sites due to the use of inappropriate work clothes or safety devices, this study aims to categorize manufacturing work processes to develop functional work clothes for heavy industries including the automobile, machine and shipbuilding industries in South Korea. Defining the features of the work environments and work postures of these industries provided for a categorization of the work processes which would enable the development of suitable work clothes for each work process' category. The results of the study based on a questionnaire survey are as follows: Work process category 1, including steel panel pressing and auto body assembly, final inspection (in automobile) and inspection (in machine), requires work clothes with upper body and arm mobility and performance to protect from the toxic fume factor. Work process category 2, consisting of welding (in automobile), cutting-and-forming (in machine) and attachment-and-construction (in shipbuilding), requires clothing elasticity, durability and heat and fire resistance. Work process category 3 comprising welding and grinding in the machine and shipbuilding industries, requires work clothes' tear resistance and elasticity, particularly for lateral bending mobility, and work clothes' sleeves' and pants' hemlines with sealed designs to defend against iron filing penetration, as well as incombustible and heat-resistant material performance. Finally, work process category 4, including painting in machine and shipbuilding, requires work clothes with waterproofing, air permeability, thermal performance, elasticity, durability and abrasion resistance.