• Journal of Internet Computing and Services
• /
• v.10 no.4
• /
• pp.55-70
• /
• 2009

Vision-based Human computer interaction is an emerging field of science and industry to provide natural way to communicate with human and computer. In that sense, inferring the emotional state of the person based on the facial expression recognition is an important issue. In this paper, we present a novel approach to recognize facial expression from a sequence of input images using emotional specific HMM (Hidden Markov Model) and facial motion tracking based on optical flow. Conventionally, in the HMM which consists of basic emotional states, it is considered natural that transitions between emotions are imposed to pass through neutral state. However, in this work we propose an enhanced transition framework model which consists of transitions between each emotional state without passing through neutral state in addition to a traditional transition model. For the localization of facial features from video sequence we exploit template matching and optical flow. The facial feature displacements traced by the optical flow are used for input parameters to HMM for facial expression recognition. From the experiment, we can prove that the proposed framework can effectively recognize the facial expression in real time.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.443-448
• /
• 2018

웹검색 결과의 품질 향상을 위해서는 질의의 정확한 매칭 뿐만이 아니라, 서로 같은 대상을 지칭하는 한글 문자열과 영문 문자열(예: 네이버-naver)의 매칭과 같은 유연한 매칭 또한 중요하다. 본 논문에서는 문장대문장 학습을 통해 영문 문자열을 한글 문자열로 음차변환하는 방법론을 제시한다. 또한 음차변환 결과로 얻어진 한글 문자열을 동일 영문 문자열의 다양한 음차변환 결과와 매칭시킬 수 있는 발음 유사성 기반 부분 매칭 방법론을 제시하고, 위키피디아의 리다이렉트 키워드를 활용하여 이들의 성능을 정량적으로 평가하였다. 이를 통해 본 논문은 문장대문장 학습 기반의 음차 변환 결과가 복잡한 문맥을 고려할 수 있으며, Damerau-Levenshtein 거리의 계산에 자모 유사도를 활용하여 기존에 비해 효과적으로 한글 키워드들 간의 부분매칭이 가능함을 보였다.

• Journal of ILASS-Korea
• /
• v.11 no.1
• /
• pp.1-6
• /
• 2006

The present study is focused on the small scale turbulent mixing processes in the scalar Held. In order to deal with molecular mixing in turbulent flow, the linear eddy model is addressed. In each realization, the molecular mixing term is implemented deterministically, and turbulent stirring is represented by a sequence of instantaneous, statistically independent rearrangement event called by triplet map. The LEM approach is applied with relatively simple conditions. The characteristics of scalar mixing and PDF profiles are addressed in detail.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.16 no.5 s.110
• /
• pp.495-502
• /
• 2006

A fault diagnosis method is developed in this study using automaton through quantization of vibration signals for normal and faulty conditions, respectively. Automaton is a kind of qualitative model which describes the system behaviour at the level of abstraction. The system behavior was extracted from the probability of the output sequence of vibration signals. The sequence was made as vibration levels by reconstructing the originally measured vibration signals. As an example, a fault diagnosis for the bearing of ATM machine was done, which detected the bearing fault with confident level compared to any other existing methods of kurtosis or spectrum analysis.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.49-59
• /
• 2022

In this paper, we designed a new enzyme function prediction model PSCREM based on a study that compared and evaluated CNN and LSTM/GRU models, which are the most widely used deep learning models in the field of predicting functions and structures using protein sequences in 2020, under the same conditions. Sequence evolution information was used to preserve detailed patterns which would miss in CNN convolution, and the relationship information between amino acids with functional significance was extracted through overlapping RNNs. It was referenced to feature map production. The RNN family of algorithms used in small CNN-RNN models are LSTM algorithms and GRU algorithms, which are usually stacked two to three times over 100 units, but in this paper, small RNNs consisting of 10 and 20 units are overlapped. The model used the PSSM profile, which is transformed from protein sequence data. The experiment proved 86.4% the performance for the problem of predicting the main classes of enzyme number, and it was confirmed that the performance was 84.4% accurate up to the sub-sub classes of enzyme number. Thus, PSCREM better identifies unique patterns related to protein function through overlapped RNN, and Overlapped RNN is proposed as a novel methodology for protein function and structure prediction extraction.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.5
• /
• pp.19-28
• /
• 2009

Prediction problem of the time-series data has been a research issue for a long time among many researchers and a number of methods have been proposed in the literatures. In this paper, a method is proposed that similarities among time-series data are examined by use of Hidden Markov Model and Likelihood and future direction of the data movement is determined. Query sequence is modeled by Hidden Markov Modeling and then the model is examined over the pre-recorded time-series to find the subsequence which has the greatest similarity between the model and the extracted subsequence. The similarity is evaluated by likelihood. When the best subsequence is chosen, the next portion of the subsequence is used to predict the next phase of the data movement. A number of experiments with different parameters have been conducted to confirm the validity of the method. We used KOSPI to verify suggested method.

• Korean Journal of Construction Engineering and Management
• /
• v.14 no.4
• /
• pp.140-151
• /
• 2013

In 2011 and 2012, Korean construction firms awarded around $ 64.5. Billion each year from the overseas market in 2011. This contract value accounted for overwhelming portion of total overseas construction contract values, and this growth is expected to continue for the next decade. However, contract scopes awarded to the Korean construction firms mainly involve detailed design and construction phases due to their competitiveness for the construction techniques. In other words, front-end-engineering-design and construction project management are not considered part of core business due to the lack of project management skills and experience. The researchers focused on development of construction sequence model required to improve construction planning and scheduling skills for the Korean construction firms. The model identifies critical work items and the sequence throughout project execution process. In addition, the researchers developed a risk evaluation method by applying fuzzy theory to the critical construction activities for the industrial plant construction projects. Developed methodology will help project practitioners to develop project schedule in a timely and effe ctive manner and evaluate project risks associated with scheduling process for the industrial plant construction projects.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.775-778
• /
• 2008

Augmented Reality is a growing area in virtual reality research, The world environment around us provides a wealth of information that is difficult to duplicate in a computer. This evidenced by the worlds used in virtual environments. An augmented reality system generates a composite view for the user. It is a combination of the real scene viewed by the user and a virtual scene generated by the computer that augments the scene with addition information. The registration method represent to the user enhances that person's performance in and perception of the world. It decide the direction and location between real world and 3D graphic objects. The registration method devide two method, Model based tracking and Move-Matching. This paper researched at to generate a commerce correlation using a tracking object method, using at a color distribution and information, in the sequence scene.

• The KIPS Transactions:PartB
• /
• v.9B no.5
• /
• pp.563-570
• /
• 2002

Robust extraction of 3D facial features and global motion information from 2D image sequence for the MPEG-4 SNHC face model encoding is described. The facial regions are detected from image sequence using multi-modal fusion technique that combines range, color and motion information. 23 facial features among the MPEG-4 FDP (Face Definition Parameters) are extracted automatically inside the facial region using color transform (GSCD, BWCD) and morphological processing. The extracted facial features are used to recover the 3D shape and global motion of the object using paraperspective camera model and SVD (Singular Value Decomposition) factorization method. A 3D synthetic object is designed and tested to show the performance of proposed algorithm. The recovered 3D motion information is transformed into global motion parameters of FAP (Face Animation Parameters) of the MPEG-4 to synchronize a generic face model with a real face.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.178-185
• /
• 2021

Sequence to sequence(S2S) 기반 음성인식 후처리기를 훈련하기 위한 학습 데이터 구축을 위해 (음성인식 결과(speech recognition sentence), 전사자(phonetic transcriptor)가 수정한 문장(Human post edit sentence))의 병렬 말뭉치가 필요하며 이를 위해 많은 노동력(human-labor)이 소요된다. BackTranScription (BTS)이란 기존 S2S기반 음성인식 후처리기의 한계점을 완화하기 위해 제안된 데이터 구축 방법론이며 Text-To-Speech(TTS)와 Speech-To-Text(STT) 기술을 결합하여 pseudo 병렬 말뭉치를 생성하는 기술을 의미한다. 해당 방법론은 전사자의 역할을 없애고 방대한 양의 학습 데이터를 자동으로 생성할 수 있기에 데이터 구축에 있어서 시간과 비용을 단축 할 수 있다. 본 논문은 BTS를 바탕으로 제주어 도메인에 특화된 음성인식 후처리기의 성능을 향상시키기 위하여 모델 수정(model modification)을 통해 성능을 향상시키는 모델 중심 접근(model-centric) 방법론과 모델 수정 없이 데이터의 양과 질을 고려하여 성능을 향상시키는 데이터 중심 접근(data-centric) 방법론에 대한 비교 분석을 진행하였다. 실험결과 모델 교정없이 데이터 중심 접근 방법론을 적용하는 것이 성능 향상에 더 도움이 됨을 알 수 있었으며 모델 중심 접근 방법론의 부정적 측면 (negative result)에 대해서 분석을 진행하였다.