• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2003.10a
• /
• pp.53-60
• /
• 2003

생명과학 관련 문서에서의 이벤트 추출은 관련 연구자들의 연구에 많은 도움을 줄 수 있다. 기존의 연구에서는 주로 이벤트 동사에 대해 패턴을 정의한 후에 정의된 패턴에 의해서만 이벤트를 추출하고자하였다. 그러나 모든 패턴을 수동으로 정의하는 것은 너무 많은 비용이 들기 때문에 패턴을 자동 추출 또는 확장하는 방법이 필요하다. 또한 학습을 하기 위해서는 상당수의 학습 말뭉치가 있어야 하는데 그것 또한 충분하지 않은 실정이다. 본 논문에서는 초기 패턴에 의해 생성된 소량의 정답 이벤트로부터 학습한 후 공기정보와 패턴정보를 이용한 Co-training방법으로 패턴 확장 및 이벤트 추출을 시도하였다. 실험 결과, 이벤트 동사의 패턴 정보가 유용한 정보라는 것을 확인할 수 있었고, 후보 이벤트 내의 개체간 공기정보와 문법관계정보 또한 매우 중요한 정보라는 것을 새롭게 보일 수 있었다. GENIA 말뭉치에서 162개의 이벤트 동사에 대해 실험한 결과, 88.02%의 정확률, 79.25%의 재현율을 얻었다.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.1E
• /
• pp.64-74
• /
• 1997

In many decision making systems, rule-based approaches are used to solve complex problems in the areas of pattern analysis and computer vision. In this paper, we present methods for generating fuzzy IF-THEN rules automatically from training data for pattern classification and high-level computer vision. The rules are generated by construction minimal approximate fuzzy aggregation networks and then training the networks using gradient descent methods. The training data that represent features are treated as linguistic variables that appear in the antecedent clauses of the rules. Methods to generate the corresponding linguistic labels(values) and their membership functions are presented. In addition, an inference procedure is employed to deduce conclusions from information presented to our rule-base. Two experimental results involving synthetic and real are given.

• Proceedings of the Korea Database Society Conference
• /
• 1997.10a
• /
• pp.24-48
• /
• 1997

. Supported byㆍDARPA′s image Understanding (IU) program under "Video Retrieval Based on Language and image Analysis" project.DARPA′s Computer Assisted Education and Training Initiative program (CAETI)ㆍObjective: Develop practical systems for automatic understanding and indexing of video sequences using both audio and video tracks(omitted)

• Journal of Korea Game Society
• /
• v.11 no.6
• /
• pp.23-31
• /
• 2011

The cognitive abilities are functions in human brain. They are closely with the real life. The cognitive abilities are likely to be decreased when human gets older and older. Fortunately, due to the plasticity of human brain, it is possible to help recover and rehabilitate brain function. Those efforts are called brain training and cognitive ability training. The cognitive ability training needs continuous trials and efforts. But many users feel boring because of simple repetitive works. This paper proposes a cognitive training system implemented in a smart device. The proposed system is designed to make users to focus on the repetitive training by using game-based tasks on the smart device. It shows that the proposed system is effective to attention and flexible on cognitive training game.

• Korean Journal of Computational Design and Engineering
• /
• v.20 no.4
• /
• pp.420-430
• /
• 2015

Operator Training Simulators (OTSs) provide macroscopic training environment for plant operation. They are equipped with simulation systems for the emulation of remote monitoring and controlling operations. OTSs typically provide 2D block diagram-based graphic user interface (GUI) and connect to process simulation tools. However, process modeling for OTSs is a difficult task. Furthermore, conventional OTSs do not provide real plant field information since they are based on 2D human machine interface (HMI). In order to overcome the limitation of OTSs, we propose a new type of plant training system. This system has the capability required for collaborative training between operators and field workers. In addition, the system provides 3D virtual training environment such that field workers feel like they are in real plant site. For this, we designed system architecture and developed essential functions for the system. For the verification of the proposed system design, we implemented a prototype training system and performed experiments of collaborative training between one operator and two field workers with the prototype system.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.549-551
• /
• 2003

본 논문은 점점 증가되고 있는 SPAM 메일 문제를 해결하기 위한 방법으로써, 특정 속성에 기반을 둔 학습 알고리즘의 co-training을 통한 전자메일 분류 기법을 제안한다. 전자메일 분류는 결국 문서 분류 기술과 다르지 않다. 이미 많은 연구에서 학습 알고리즘을 이용한 문서 분류 기법은 많이 제안되고 검증되었다. 본 논문에서는 이러한 학습 알고리즘들을 co-training을 통하여 해당 메일이 SPAM인지 아닌지 구분하며, 학습의 효율성을 높이기 위하여 전자메일의 특정한 속성들, 예를 들면, 핵심문구나 기타 특정한 문구 및 전자메일의 헤더 정보 등을 학습 기반으로 이용하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.123-124
• /
• 2019

This paper proposes an improved deep learning method based on small data sets for animal image classification. Firstly, we use a CNN to build a training model for small data sets, and use data augmentation to expand the data samples of the training set. Secondly, using the pre-trained network on large-scale datasets, such as VGG16, the bottleneck features in the small dataset are extracted and to be stored in two NumPy files as new training datasets and test datasets. Finally, training a fully connected network with the new datasets. In this paper, we use Kaggle famous Dogs vs Cats dataset as the experimental dataset, which is a two-category classification dataset.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.11-20
• /
• 2024

While artificial neural networks are adept at identifying patterns, they can struggle to distinguish between actual correlations and false associations between extracted facial features and criminal behavior within the training data. These associations may not indicate causal connections. Socioeconomic factors, ethnicity, or even chance occurrences in the data can influence both facial features and criminal activity. Consequently, the artificial neural network might identify linked features without understanding the underlying cause. This raises concerns about incorrect linkages and potential misclassification of individuals based on features unrelated to criminal tendencies. To address this challenge, we propose a novel region-based training approach for artificial neural networks focused on criminal propensity detection. Instead of solely relying on overall facial recognition, the network would systematically analyze each facial feature in isolation. This fine-grained approach would enable the network to identify which specific features hold the strongest correlations with criminal activity within the training data. By focusing on these key features, the network can be optimized for more accurate and reliable criminal propensity prediction. This study examines the effectiveness of various algorithms for criminal propensity classification. We evaluate YOLO versions YOLOv5 and YOLOv8 alongside VGG-16. Our findings indicate that YOLO achieved the highest accuracy 0.93 in classifying criminal and non-criminal facial features. While these results are promising, we acknowledge the need for further research on bias and misclassification in criminal justice applications

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.665-667
• /
• 2014

Wellness is IT fused with the user manage and maintain the health of a service can help you. If you are using an existing Fitness Center to yourself by choosing appliances that fit with the risk of injury in order to learn how the efficient movement had existed for a long time was needed. To resolve, use the personal training but more expensive cost of people's problems, and shown again in the habit of exercising alone will have difficulty. This paper provides a variety of smart phones based on a hybrid app with compatibility with the platform and personalized training market system. Users of the Fitness Center is built into smart phones in the history of their movement sensors or transmits to the Web by typing directly. This is based on exercise programs tailored to users via the training market. Personal training marketplace has a variety of users, check the history of this movement he can recommend an exercise program for themselves can be applied by selecting the. This provides users with the right exercise program can do long-term exercise habits can be proactive and goal setting.

• Journal of Information Processing Systems
• /
• v.16 no.4
• /
• pp.809-819
• /
• 2020

Gender prediction accuracy increases as convolutional neural network (CNN) architecture evolves. This paper compares voting and ensemble schemes to utilize the already trained five CNN models to further improve gender prediction accuracy. The majority voting usually requires odd-numbered models while the proposed softmax-based voting can utilize any number of models to improve accuracy. The ensemble of CNN models combined with one more fully-connected layer requires further tuning or training of the models combined. With experiments, it is observed that the voting or ensemble of CNN models leads to further improvement of gender prediction accuracy and that especially softmax-based voters always show better gender prediction accuracy than majority voters. Also, compared with softmax-based voters, ensemble models show a slightly better or similar accuracy with added training of the combined CNN models. Softmax-based voting can be a fast and efficient way to get better accuracy without further training since the selection of the top accuracy models among available CNN pre-trained models usually leads to similar accuracy to that of the corresponding ensemble models.