• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.1
• /
• pp.85-92
• /
• 2020

Deep learning shows outstanding performance in image and video analysis, such as object classification, object detection and semantic segmentation. In this paper, it is analyzed that the performances of deep learning models can be affected by characteristics of train dataset. It is proposed as a method for selecting activation function and optimization algorithm of deep learning to classify facial expression. Classification performances are compared and analyzed by applying various algorithms of each component of deep learning model for CK+, MMI, and KDEF datasets. As results of simulation, it is shown that genetic algorithm can be an effective solution for optimizing components of deep learning model.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.44 no.4
• /
• pp.691-707
• /
• 2020

This study used big data analysis as informatics that identified keywords related to new-tro fashion; in addition, it conducted differences and types of classification according to demographic characteristics. First, it has been shown that two different generations, the Millennials and the older generation, coexist as important keywords in the context of new-tro fashion. Second, according to age, it has been shown that the keywords that appear in new-tro fashion are taken differently. In most regional keywords that differed in the classification, respondents in their 20s, 30s and 40s were classified as emotional, while those in their 50s or older perceived as factual phenomena. The results of eliciting keywords in new-tro fashion through big data analysis, keywords that reflect phenomena, design details and considerations, fashion styles, fashion brands, fashion items, social media, influence, and emotional adjectives. This study confirmed the meaning of new-tro fashion based on past that can give enjoyment to the new generation and memories to the older generation.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.1150-1155
• /
• 2009

In the information society, the amount of information have been increased by technological development. It is not easy to deal with information for fast data processing because of increasing of the complexity and diversity of data. So this paper will confirm the fact that the color plays the role of the classification of complex information and can make data processing fast. Experiment 1 shows that the searching time of target(line name) is more faster when the color of a subway line is equal to the color of station`s name. Experiment 2 using the task for classification of word mixed in various categories shows that color category processing is more faster rather than semantic category processing and the effect of this task is far better when color difference is more clear.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2008.10b
• /
• pp.292-297
• /
• 2008

복잡한 시맨틱을 포함한 웹 문서를 정확히 범주화하고 이 과정을 자동화하기 위해서는 인간의 지식체계를 수용할 수 있는 표준화, 지능화, 자동화된 문서표현 및 분류기술이 필요하다. 이를 위해 키워드 빈도수, 문서내 키워드들의 관련성, 시소러스의 활용, 확률기법 적용 등에 사용자의도(intention) 정보를 활용한 범주화와 조정 프로세스를 도입하였다. 웹 문서 분류과정에서 시소러스 등을 사용하는 지식베이스 문서분류와 비 감독 학습을 하는 사전 지식체계(a priori)가 없는 유사성 문서분류 방법에 의도정보를 사용할 수 있도록 기반체계를 설계하였고 다시 이 두 방법의 차이는 Hybrid조정프로세스에서 조정하였다. 본 연구에서 설계된 HDCI(Hybrid Document Classification with Intention) 모델은 위의 웹 문서 분류과정과 이를 제어 및 보조하는 사용자 의도 분석과정으로 구성되어 있다. 의도분석과정에 키워드와 함께 제공된 사용자 의도는 도메인 지식(domain Knowledge)을 이용하여 의도간 계층트리(intention hierarchy tree)를 구성하고 이는 문서 분류시 제약(constraint) 또는 가이드의 역할로 사용자 의도 프로파일(profile) 또는 문서 특성 대표 키워드를 추출하게 된다. HDCI는 문서간 유사성에 근거한 상향식(bottom-up)의 확률적인 접근에서 통제 및 안내의 역할을 수행하고 지식베이스(시소러스) 접근 방식에서 다양성에 한계가 있는 키워들 간 관계설정의 정확도를 높인다.

• Annual Conference on Human and Language Technology
• /
• 2010.10a
• /
• pp.166-171
• /
• 2010

본 논문은 한국어 온라인 리뷰 문서의 오피니언 분류(Opinion Classification)에 있어 그 핵심 키워드가 형용사 (Adjective) 범주라는 점을 고려하여, 한국어 형용사를 <문맥에 의존하지 않는 절대 극성>과, <문맥에 의존하여 극성이 바뀌는 상대극성>으로 대분류한 뒤 그 각각의 의미 극성을 하위 분류하는 작업을 수행하였다. 기존의 연구에서 특징적인 오피니언 어휘 수십개에 의존하여 자동 분류를 시도하고자 하였던 문제점을 극복하기 위해서는 한국어 형용사 전체 범주에 대한 체계적인 극성 분류가 이루어져야 할 필요가 있으며, 여기서 특히 상세히 주목받지 못했던 상대 극성 어휘에 대한 본격적인 의미 분류가 요구된다. 본 연구에서 제시하는 형용사의 극성 분류는 기존의 이론 언어학적 형용사 의미 분류와 달리 온라인 오피니언 문서에서 도메인에 따라 나타나는 특징적 의미 유형을 결정하고, 이를 기준으로 온라인 오피니언 문서의 극성 판별에 효과적으로 적용할 수 있는 사전을 구축하였다는 점에서 의의를 가진다.

• Journal of KIBIM
• /
• v.9 no.4
• /
• pp.31-40
• /
• 2019

With Building Information Modeling(BIM) becoming the de facto standard for data sharing in the AEC industry, additional needs have increased to ensure the data integrity of BIM models themselves. Although the Industry Foundation Classes provide an open and neutral data format, its generalized schema leaves it open to data loss and misclassifications This research applied deep learning to automatically classify BIM elements and thus check the integrity of BIM-to-IFC mappings. Multi-view CNN(MVCC) and PointNet, which are two deep learning models customized to learn and classify in 3 dimensional non-euclidean spaces, were used. The analysis was restricted to classifying subtypes of architectural walls. MVCNN resulted in the highest performance, with ACC and F1 score of 0.95 and 0.94. MVCNN unitizes images from multiple perspectives of an element, and was thus able to learn the nuanced differences of wall subtypes. PointNet, on the other hand, lost many of the detailed features as it uses a sample of the point clouds and perceived only the 'skeleton' of the given walls.

• Journal of the Korean Society of Visualization
• /
• v.20 no.2
• /
• pp.78-85
• /
• 2022

In these days, the rapid development in prediction technology using artificial intelligent is being applied in a variety of engineering fields. Especially, dimensionality reduction technologies such as autoencoder and convolutional neural network have enabled the classification and regression of high-dimensional data. In particular, pixel level prediction technology enables semantic segmentation (fine-grained classification), or physical value prediction for each pixel such as depth or surface normal estimation. In this study, the pressure distribution of the ship's surface was estimated at the pixel level based on the artificial neural network. First, a potential flow analysis was performed on the hull form data generated by transforming the baseline hull form data to construct 429 datasets for learning. Thereafter, a neural network with a U-shape structure was configured to learn the pressure value at the node position of the pretreated hull form. As a result, for the hull form included in training set, it was confirmed that the neural network can make a good prediction for pressure distribution. But in case of container ship, which is not included and have different characteristics, the network couldn't give a reasonable result.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.10
• /
• pp.3230-3255
• /
• 2022

Causality mining in NLP is a significant area of interest, which benefits in many daily life applications, including decision making, business risk management, question answering, future event prediction, scenario generation, and information retrieval. Mining those causalities was a challenging and open problem for the prior non-statistical and statistical techniques using web sources that required hand-crafted linguistics patterns for feature engineering, which were subject to domain knowledge and required much human effort. Those studies overlooked implicit, ambiguous, and heterogeneous causality and focused on explicit causality mining. In contrast to statistical and non-statistical approaches, we present Bidirectional Encoder Representations from Transformers (BERT) integrated with Multi-level Feature Networks (MFN) for causality recognition, called BERT+MFN for causality recognition in noisy and informal web datasets without human-designed features. In our model, MFN consists of a three-column knowledge-oriented network (TC-KN), bi-LSTM, and Relation Network (RN) that mine causality information at the segment level. BERT captures semantic features at the word level. We perform experiments on Alternative Lexicalization (AltLexes) datasets. The experimental outcomes show that our model outperforms baseline causality and text mining techniques.

• Journal of KIBIM
• /
• v.12 no.2
• /
• pp.12-25
• /
• 2022

To increase the usability of Building Information Modeling (BIM) in construction projects, it is critical to ensure the interoperability of data between heterogeneous BIM software. The Industry Foundation Classes (IFC), an international ISO format, has been established for this purpose, but due to its structural complexity, geometric information and properties are not always transmitted correctly. Recently, deep learning approaches have been used to learn the shapes of the BIM elements and thereby verify the mapping between BIM elements and IFC entities. These models performed well for elements with distinct shapes but were limited when their shapes were highly similar. This study proposed a method to improve the performance of the element type classification by using an Ensemble model that leverages not only shapes characteristics but also the relational information between individual BIM elements. The accuracy of the Ensemble model, which merges MVCNN and MLP, was improved 0.03 compared to the existing deep learning model that only learned shape information.

• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.535-548
• /
• 2022

Using a rich resource language to classify sentiments in a language with few resources is a popular subject of research in natural language processing. Burmese is a low-resource language. In light of the scarcity of labeled training data for sentiment classification in Burmese, in this study, we propose a method of transfer learning for sentiment analysis of a language that uses the feature transfer technique on sentiments in English. This method generates a cross-language word-embedding representation of Burmese vocabulary to map Burmese text to the semantic space of English text. A model to classify sentiments in English is then pre-trained using a convolutional neural network and an attention mechanism, where the network shares the model for sentiment analysis of English. The parameters of the network layer are used to learn the cross-language features of the sentiments, which are then transferred to the model to classify sentiments in Burmese. Finally, the model was tuned using the labeled Burmese data. The results of the experiments show that the proposed method can significantly improve the classification of sentiments in Burmese compared to a model trained using only a Burmese corpus.