• Journal of Internet Computing and Services
• /
• v.21 no.1
• /
• pp.33-43
• /
• 2020

Retrieving a 3D model from a 3D database and augmenting the retrieved model in the Augmented Reality system simultaneously became an issue in developing the plausible AR environments in a convenient fashion. It is considered that the sketch-based 3D object retrieval is an intuitive way for searching 3D objects based on human-drawn sketches as query. In this paper, we propose a novel deep learning based approach of retrieving a sketch-based 3D object as for an Augmented Reality Model. For this work, we introduce a new method which uses Sketch CNN, Wasserstein CNN and Wasserstein center loss for retrieving a sketch-based 3D object. Especially, Wasserstein center loss is used for learning the center of each object category and reducing the Wasserstein distance between center and features of the same category. The proposed 3D object retrieval and augmentation consist of three major steps as follows. Firstly, Wasserstein CNN extracts 2D images taken from various directions of 3D object using CNN, and extracts features of 3D data by computing the Wasserstein barycenters of features of each image. Secondly, the features of the sketch are extracted using a separate Sketch CNN. Finally, we adopt sketch-based object matching method to localize the natural marker of the images to register a 3D virtual object in AR system. Using the detected marker, the retrieved 3D virtual object is augmented in AR system automatically. By the experiments, we prove that the proposed method is efficiency for retrieving and augmenting objects.

• Clinical Psychopharmacology and Neuroscience
• /
• v.16 no.4
• /
• pp.449-460
• /
• 2018

Objective: Prior functional magnetic resonance imaging (fMRI) work has revealed that children/adolescents with disruptive behavior disorders (DBDs) show dysfunctional reward/non-reward processing of non-social reinforcements in the context of instrumental learning tasks. Neural responsiveness to social reinforcements during instrumental learning, despite the importance of this for socialization, has not yet been previously investigated. Methods: Twenty-nine healthy children/adolescents and 19 children/adolescents with DBDs performed the fMRI social/non-social reinforcement learning task. Participants responded to random fractal image stimuli and received social and non-social rewards/non-rewards according to their accuracy. Results: Children/adolescents with DBDs showed significantly reduced responses within the caudate and posterior cingulate cortex (PCC) to non-social (financial) rewards and social non-rewards (the distress of others). Connectivity analyses revealed that children/adolescents with DBDs have decreased positive functional connectivity between the ventral striatum (VST) and the ventromedial prefrontal cortex (vmPFC) seeds and the lateral frontal cortex in response to reward relative to non-reward, irrespective of its sociality. In addition, they showed decreased positive connectivity between the vmPFC seed and the amygdala in response to non-reward relative to reward. Conclusion: These data indicate compromised reinforcement processing of both non-social rewards and social non-rewards in children/adolescents with DBDs within core regions for instrumental learning and reinforcement-based decision-making (caudate and PCC). In addition, children/adolescents with DBDs show dysfunctional interactions between the VST, vmPFC, and lateral frontal cortex in response to rewarded instrumental actions potentially reflecting disruptions in attention to rewarded stimuli.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1653-1661
• /
• 2022

In this study, the classification of cold water and normal water based on Geo-Kompsat 2A images was performed. Daily mean surface temperature products provided by the National Meteorological Satellite Center (NMSC) were used, and convolution neural network (CNN) deep learning technique was applied as a classification algorithm. From 2019 to 2022, the cold water occurrence data provided by the National Institute of Fisheries Science (NIFS) were used as the cold water class. As a result of learning, the probability of detection was 82.5% and the false alarm ratio was 54.4%. Through misclassification analysis, it was confirmed that cloud area should be considered and accurate learning data should be considered in the future.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.31 no.6
• /
• pp.258-263
• /
• 2021

ZnO varistor is a semiconductor device which can serve to protect the circuit from surge voltage because its non-linear I-V characteristics by controlling the microstructure of grain and grain boundaries. In order to obtain desired electrical properties, it is important to control microstructure evolution during the sintering process. In this research, we defined a dataset composed of process conditions of sintering and relative permittivity of sintered body, and collected experimental dataset with DOE. Meta-models can predict permittivity were developed by learning the collected experimental dataset on various machine learning algorithms. By utilizing the meta-model, we can derive optimized sintering conditions that could show the maximum permittivity from the numerical-based HMA (Hybrid Metaheuristic Algorithm) optimization algorithm. It is possible to search the optimal process conditions with minimum number of experiments if meta-model-based optimization is applied to ceramic processing.

• Journal of Korean Library and Information Science Society
• /
• v.38 no.4
• /
• pp.187-213
• /
• 2007

The purpose of this study is to investigate application of information literacy education. Lifelong education program that accomplishes local information center lifelong education center assigned among public libraries is surveyed and analyzed by e-learning and off-line program. This study is surveyed and analyzed on information literacy lifelong education and examples and data of public library.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2006.05a
• /
• pp.241-248
• /
• 2006

Web is greatly contributing in providing a variety of information. Especially, as media for the purpose of development and education of human resources, the role of web is important. Furthermore, E-Learning through web plays an important role for each enterprise and an educational institution. Also, above all, fast and various searches are required in order to manage and search a great number of educational contents in web. Therefore, most of present information is composed in HTML, so there are lots of restrictions. As a solution to such restriction, XML a standard of Web document, and its various search functions is being extended and studied variously. This paper proposes a search system able to search XML in E-Learning or var ious contents of non-XML using mobile device PDA.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.804-806
• /
• 1995

This paper discusses Self-organized Distributed Networks(SODN) as identifier of nonlinear dynamical systems. The structure of system identification employs series-parallel model. The identification procedure is based on a discrete-time formulation. The learning with the proposed SODN is fast and precise. Such properties arc caused from the local learning mechanism. Each local networks learns only data in a subregion. Large number of memory requirements and low generalization capability for the untrained region, which are drawbacks of conventional local network learning, are overcomed in the SODN. Through extensive simulation, SODN is shown to be effective for identification of nonlinear dynamical systems.

• Clinical Endoscopy
• /
• v.51 no.6
• /
• pp.547-551
• /
• 2018

Unlike wired endoscopy, capsule endoscopy requires additional time for a clinical specialist to review the operation and examine the lesions. To reduce the tedious review time and increase the accuracy of medical examinations, various approaches have been reported based on artificial intelligence for computer-aided diagnosis. Recently, deep learning-based approaches have been applied to many possible areas, showing greatly improved performance, especially for image-based recognition and classification. By reviewing recent deep learning-based approaches for clinical applications, we present the current status and future direction of artificial intelligence for capsule endoscopy.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.458-461
• /
• 2021

유동인구 예측은 상권의 특성에 따른 점포의 입지 선정 및 고객 맞춤형 마케팅 등 민간 분야에서부터 교통망 등 사회 간접 자본 설계를 위한 공공 분야에 이르기까지 다양한 목적으로 연구되어 왔으며, 최근에는 Covid-19 의 확산에 따라 그 중요도가 더욱 높아지고 있다. 보다 정교한 예측을 위해서는 전체적인 유동 인구 뿐만 아니라 특성 별로 세분화된 하위 그룹에 대해서도 정확한 예측이 요구되나, 기존의 예측 모델들은 이러한 데이터의 계층 구조를 고려하지 않았다. 본 연구에서는 세분화된 하위 그룹 별 유동인구의 예측 정확도를 높이기 위해 전체 유동인구의 패턴을 동시에 활용하는 Global-Local 구조 기반의 Deep Learning 유동인구 분석 모델을 제안한다. 실험 결과 단일 시계열 데이터만을 사용하는 경우 대비 5.4%~52.6%의 예측 오류 감소 효과가 있음을 확인하였다.

• Architectural research
• /
• v.26 no.1
• /
• pp.1-12
• /
• 2024

This study introduces a deep reinforcement learning (DRL)-based methodology for optimizing apartment space arrangements, addressing the limitations of human capability in evaluating all potential spatial configurations. Leveraging computational power, the methodology facilitates the autonomous exploration and evaluation of innovative layout options, considering architectural principles, legal standards, and client re-quirements. Through comprehensive simulation tests across various apartment types, the research demonstrates the DRL approach's effec-tiveness in generating efficient spatial arrangements that align with current design trends and meet predefined performance objectives. The comparative analysis of AI-generated layouts with those designed by professionals validates the methodology's applicability and potential in enhancing architectural design practices by offering novel, optimized spatial configuration solutions.