• Journal of Information Processing Systems
• /
• v.16 no.6
• /
• pp.1250-1260
• /
• 2020

This study proposes a novel deep neural network model that can accurately detect objects and their relationships in an image and represent them as a scene graph. The proposed model utilizes several multimodal features, including linguistic features and visual context features, to accurately detect objects and relationships. In addition, in the proposed model, context features are embedded using graph neural networks to depict the dependencies between two related objects in the context feature vector. This study demonstrates the effectiveness of the proposed model through comparative experiments using the Visual Genome benchmark dataset.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.519-522
• /
• 2010

유비쿼터스 환경에서 서비스를 개발하는데 협업모델이 중요한 주제로 연구되어 왔다. 본 연구에서는 이를 위한 방법으로 커뮤니티 컴퓨팅 모델을 MDA(Model Driven Architecture)에 기반하여 개발하고 있다. MDA에 기반한 커뮤니티 컴퓨팅 모델을 PICM(Platform Independent Community Model)에서 PSCM(Platform Specific Community Model)을 거쳐 최종 프로그램으로 개발된다. 본 논문에서는 PICM에서 PSCM으로 변환되는 방법을 규칙에 기반하여 제안하고 이를 구현한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.8
• /
• pp.3656-3671
• /
• 2016

Most of the research in the area of wireless communications exclusively relies on simulations. Further, it is essential that the mobility management strategies and routing protocols should be validated under realistic conditions. Most appropriate mobility models play a pivotal role to determine, whether there is any subtle error or flaw in a proposed model. Simulators are the standard tool to evaluate the performance of mobility models however sometimes they suffer from numerous documented problems. To accomplish the widely acknowledged lack of formalization in this domain, a Coloured Petri nets (CPNs) based random direction mobility model for specification, analysis and validation is presented in this paper for wireless communications. The proposed model does not suffer from any border effect or speed decay issues. It is important to mention that capturing the mobility patterns through CPN is challenging task in this type of the research. Further, an appropriate formalism of CPNs supported to analyze the future system dynamic status. Finally the formal model is evaluated with the state space analysis to show how predefined behavioral properties can be applied. In addition, proposed model is evaluated based on generated simulations to track origins of errors during debugging.

• Journal of KIISE:Computer Systems and Theory
• /
• v.26 no.8
• /
• pp.863-874
• /
• 1999

세분화란 초기 원형 모델의 삼각형 메쉬를 여러 개의 작은 메쉬로 변환하는 기법으로, 간략화 된 모델을 다시 원상태로 표현하기 위해 사용된다. 기존의 보간에 의한 세분화는 전체 모델의 에지에 일률적으로 세분화를 적용하기 때문에, 효과가 적은 부분까지도 세분화가 수행하게 되어 효율이 떨어진다. 본 논문에서는 정점 변화율을 기반으로 에지를 선택하여 세분화를 수행한다. 따라서 원형 메쉬를 변환하여 세분화된 메쉬를 생성할 때, 모델의 각 부분들은 정점 변화율의 차이에 의해 서로 다른 세분화 정도를 가지게 된다. 이 과정을 통해 원형 모델의 곡률 특성이 반영된 세분화를 수행할 수 있게 되고, 전체 모델의 세분화 정도를 조정하는 것도 가능해진다. Abstract The subdivision is a mesh transformation, which makes an original triangle mesh to subdivided meshes. This method is used for recovering original model from simplified model. The existing subdivision based on interpolation is inefficient, because it is targeted for whole edges of mesh model. Therefore, this method applies to non-effective parts. In this paper the subdivision is executed by edge selection based on curvature. When original model is transformed to subdivided model by proposed method, the parts of model has different subdivision degrees by means of the averages of vertex curvature.Proposed method makes it enable subdivision, which deploy characteristics of curvatures of original model and adjusting a degree of subdivision in whole model.

• Proceedings of the KSME Conference
• /
• 2001.11b
• /
• pp.529-532
• /
• 2001

The purposes of the present study are to investigate hemodynamic characteristics and to define shear-sensitive remodeling in the stenosed coronary models. Two models for the compensatory remodelling used for this research are a pre-stenotic dilation and a post-stenotic dilation models for the computer simulation. The peak wall shear stress on the post-stenotic model is higher than that of the pre-stenotic model. Two recirculation zones are generated in the pre-stenotic model, and the zones in the pre-stenotic model are smaller than those in the post-stenotic model. Variation of the wall shear stress in the pre-stenotic model is lower than that in the post-stenotic model. In computer simulation with the post-stenotic model, higher temporal and spatial shear fluctuation and stress suggested shear-sensitive remodeling. Shear-sensitive remodeling may be associated with the increased risk of plaque rupture, the underlying cause of acute coronary syndromes, and sudden cardiac death.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.301-307
• /
• 2022

Energy consumption has grown alongside dramatic population increases. Statistics show that buildings in particular utilize a significant amount of energy, worldwide. Because of this, building energy prediction is crucial to best optimize utilities' energy plans and also create a predictive model for consumers. To improve energy prediction performance, this paper proposes a ResNet-LSTM model that combines residual networks (ResNets) and long short-term memory (LSTM) for energy consumption prediction. ResNets are utilized to extract complex and rich features, while LSTM has the ability to learn temporal correlation; the dense layer is used as a regression to forecast energy consumption. To make our model more robust, we employed Huber loss during the optimization process. Huber loss obtains high efficiency by handling minor errors quadratically. It also takes the absolute error for large errors to increase robustness. This makes our model less sensitive to outlier data. Our proposed system was trained on historical data to forecast energy consumption for different time series. To evaluate our proposed model, we compared our model's performance with several popular machine learning and deep learning methods such as linear regression, neural networks, decision tree, and convolutional neural networks, etc. The results show that our proposed model predicted energy consumption most accurately.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.1044-1049
• /
• 2006

얼굴 추적은 Vision base HCI의 핵심인 얼굴인식, 표정인식 그리고 Gesture recognition등의 다른 여러 기술을 지원하는 중요한 기술이다. 이런 얼굴 추적기술에는 영상(Image)의 Color또는 Contour등의 불변하는 특징들을 사용 하거나 템플릿(template)또는 형태(appearance)를 사용하는 방법 등이 있는데 이런 방법들은 조명환경이나 주위 배경등의 외부 환경에 민감하게 반응함으로 해서 다양한 환경에 사용할 수 없을 뿐더러 얼굴영상만을 정확하게 추출하기도 쉽지 않은 실정이다. 이에 본 논문에서는 deformable한 model을 사용하여 model과 유사한 shape과 appearance를 찾아 내는 AAM(Active Appearance Model)을 사용하는 얼굴 추적 시스템을 제안하고자 한다. 제안된 시스템에는 기존의 Combined AAM이 아닌 Independent AAM을 사용하였고 또한 Fitting Algorithm에 Inverse Compositional Image Alignment를 사용하여 Fitting 속도를 향상 시켰다. AAM Model을 만들기 위한 Train set은 150장의 4가지 형태에 얼굴을 담고 있는 Gray-scale 영상을 사용 하였다. Shape Model은 각 영상마다 직접 표기한 47개의 Vertex를 Trianglize함으로서 생성되는 71개의 Triangles을 하나의 Mesh로 구성하여 생성 하였고, Appearance Model은 Shape 안쪽의 모든 픽셀을 사용해서 생성하였다. 시스템의 성능 평가는 Fitting후 Shape 좌표의 정확도를 측정 함으로서 평가 하였다.

• Smart Media Journal
• /
• v.5 no.1
• /
• pp.137-142
• /
• 2016

In this paper, a multi-scale model is applied to the simulation of thrombus growth. This model includes macroscale model and microscale model. The former is used to model the plasma flow with Navier-Stokes equations, and the latter is used to model the platelets adhesion and aggregation, thrombus motion, and the surface expansion of thrombus. The force acting on platelets and thrombus from plasma is modeled by the drag force, and the forces from biochemical reactions are modeled by the adhesion force and the aggregation force. As more platelets are merged into the thrombus, the thrombus surface expands. We proposed a thrombus growth model for simulating the expansion of thrombus surface and tracking the surface by Level Set Methods. We implemented the computational model. The model performs well, and the experimental results show that the shape of thrombus in level set expansion form is similar with the thrombus in clinical test.

• The Journal of Korean Association of Computer Education
• /
• v.4 no.1
• /
• pp.11-18
• /
• 2001

As the usage of computer and internet is growing, ICT-based teaching is required in education. So far almost web-based coursewares are learner-based individual teaching. Current learning theories and learning model in WBI are too focusing on courseware or too general to apply in education directly. In this view, learning model with subject-specific search engine might be a solution. In this thesis, we developed systematic concept learning model, promoting traditional concept learning to suitable model in education field and also, we developed CEhunt(Computer Education Hunter), that is computer education search engine providing the teaching materials and supporting the design of teaching and effective concept learning environment to learners. Also, we verified that this model could have a positive effect in systematic concept forming process of learners for subject concerned.

• International Journal of Computer Science & Network Security
• /
• v.22 no.8
• /
• pp.328-342
• /
• 2022

The Internet of Things (IoT) is a technology that offers lucrative services in various industries to facilitate human communities. Important information on people and their surroundings has been gathered to ensure the availability of these services. This data is vulnerable to cybersecurity since it is sent over the internet and kept in third-party databases. Implementation of data encryption is an integral approach for IoT device designers to protect IoT data. For a variety of reasons, IoT device designers have been unable to discover appropriate encryption to use. The static support provided by research and concerned organizations to assist designers in picking appropriate encryption costs a significant amount of time and effort. IoTES is a web app that uses machine language to address a lack of support from researchers and organizations, as ML has been shown to improve data-driven human decision-making. IoTES still has some weaknesses, which are highlighted in this research. To improve the support, these shortcomings must be addressed. This study proposes the "IoTES with Security" model by adding support for the security level provided by the encryption algorithm to the traditional IoTES model. We evaluated our technique for encryption algorithms with available security levels and compared the accuracy of our model with traditional IoTES. Our model improves IoTES by helping users make security-oriented decisions while choosing the appropriate algorithm for their IoT data.