• Annual Conference of KIPS
• /
• 2011.11a
• /
• pp.535-538
• /
• 2011

기반 네트워크 (substrate network)의 자원 여분이 새로 삽입(embed)하고자 하는 가상 네트워크의 자원 요구량을 수용할 수 없을 때, 삽입하고자 하는 가상 네트워크의 요구 자원량을 분할하여 분산 수용함으로써 삽입을 가능케 할 수 있다. 그러나 이러한 작업을 위해서는 각 가상 네트워크의 자원간 상관관계를 꼭 알아야 한다. 이 논문에서 각 가상 네트워크의 명세에 자원 사용 패턴에 있어서의 상관관계를 입력 받음으로써 기반 네트워크의 사용률(utilization)과 가상 네트워크 수용률(acceptance ratio)을 높일 수 있음을 보인다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.91-94
• /
• 2021

As deep learning technologies becoming developed, realistic fake videos synthesized by deep learning models called "Deepfake" videos became even more difficult to distinguish from original videos. As fake news or Deepfake blackmailing are causing confusion and serious problems, this paper suggests a novel model detecting Deepfake videos. We chose Residual Convolutional Neural Network (Resnet50) as an extraction model and Long Short-Term Memory (LSTM) which is a form of Recurrent Neural Network (RNN) as a classification model. We adopted cosine similarity with hinge loss to train our extraction model in embedding the features of Deepfake and original video. The result in this paper demonstrates that temporal features in the videos are essential for detecting Deepfake videos.

• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.468-469
• /
• 2023

실세계 네트워크 데이터에서 노드들 간의 관계는 종종 친구/적 혹은 지지/반대와 같이 대조적인 부호를 갖는다. 이러한 네트워크를 분석하기 위해, 부호가 있는 네트워크 임베딩 (signed network embedding, 이하 SNE) 문제에 대한 관심이 급증하고 있다. 특히, 최근 들어 그래프 합성곱 네트워크 기술을 기반으로 하는 SNE 방법들에 대한 연구가 활발히 수행되어 오고 있다. 본 논문에서는, 부호가 있는 네트워크의 희소성 정도가 기존 SNE 방법들의 성능에 어떻게 영향을 미치는 지에 대해 분석하고자 한다. 4 개의 실세계 데이터 집합들을 이용한 실험을 통해, 우리는 기존 방법들의 부호 예측 정확도가 희소한 네트워크들에서는 상당히 감소하는 것을 확인하였다.

• The Journal of Korea Robotics Society
• /
• v.19 no.2
• /
• pp.196-202
• /
• 2024

The ability to understand given environments and plan a sequence of actions leading to goal state is crucial for personal service robots. With recent advancements in deep learning, numerous studies have proposed methods for state representation in planning. However, previous works lack explicit information about relationships between objects when the state observation is converted to a single visual embedding containing all state information. In this paper, we introduce graph-based state representation that incorporates both object and relationship features. To leverage these advantages in addressing the task planning problem, we propose a Graph Neural Network (GNN)-based subgoal prediction model. This model can extract rich information about object and their interconnected relationships from given state graph. Moreover, a search-based algorithm is integrated with pre-trained subgoal prediction model and state transition module to explore diverse states and find proper sequence of subgoals. The proposed method is trained with synthetic task dataset collected in simulation environment, demonstrating a higher success rate with fewer additional searches compared to baseline methods.

• Annual Conference of KIPS
• /
• 2007.11a
• /
• pp.659-662
• /
• 2007

알고리즘의 설계에 있어서 주어진 연결망을 다른 연결망으로 임베딩하는 것은 알고리즘을 활용하는 중용한 방법중의 하나이다. 본 논문에서는 하이퍼큐브보다 망비용이 개선된 이븐 연결망과 오드 연결망 사이의 임베딩을 분석하고, 이븐 연결망이 이분할 연결망임을 보인다. 이븐 연결망을 오드 연결망에 연장율 2, 밀집율 1에 임베딩 가능함을 보이고, 오드 연결망을 이븐 연결망에 연장율 2, 밀집율 1에 임베딩 가능함을 보인다.

• Annual Conference of KIPS
• /
• 2007.11a
• /
• pp.663-666
• /
• 2007

본 논문에서는 하이퍼큐브보다 망비용이 개선된 Folded 하이퍼큐브 연결망과 오드 연결망 사이의 임베딩을 분석한다. Folded 하이퍼큐브 $FQ_n$을 오드 연결망 $O_{2n+1}$에 연장율 2, 밀집율 1에 임베딩 가능함을 보이고, 오드 연결망 $O_d$을 Folded 하이퍼큐브 $FQ_{2d-1}$에 연장율 2, 밀집율 1에 임베딩 가능함을 보인다.

• Annual Conference of KIPS
• /
• 2007.11a
• /
• pp.667-670
• /
• 2007

알고리즘의 설계에 있어서 주어진 연결망을 다른 연결망으로 임베딩하는 것은 알고리즘을 활용하는 중용한 방법중의 하나이다. 본 논문에서는 하이퍼큐브보다 망비용이 개선된 이븐 연결망과 오드 연결망 사이의 임베딩을 분석하고, 이븐 연결망이 이분할 연결망임을 보인다. 이븐 연결망을 오드 연결망에 연장율 2, 밀집율 1에 임베딩 가능함을 보이고, 오드 연결망을 이븐 연결망에 연장율 2, 밀집율 1에 임베딩 가능함을 보인다.

• Journal of Information Processing Systems
• /
• v.20 no.3
• /
• pp.360-374
• /
• 2024

A personalized course recommendation algorithm based on deep learning in an online education cloud platform is proposed to address the challenges associated with effective information extraction and insufficient feature extraction. First, the user potential preferences are obtained through the course summary, course review information, user course history, and other data. Second, by embedding, the word vector is turned into a low-dimensional and dense real-valued vector, which is then fed into the compressed interaction network-deep neural network model. Finally, considering that learners and different interactive courses play different roles in the final recommendation and prediction results, an attention mechanism is introduced. The accuracy, recall rate, and F1 value of the proposed method are 0.851, 0.856, and 0.853, respectively, when the length of the recommendation list K is 35. Consequently, the proposed strategy outperforms the comparison model in terms of recommending customized course resources.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.2
• /
• pp.55-60
• /
• 2002

This paper presents a controller for the multiple DC motors using the CAN(Controller Area Network). The controller has a benefit of reducing the cable connections and making the controller boards compact through the network including expansibility. CAN, among the field buses, is a serial communication methodology which has the physical layer and the data link layer in the ISO's OSI (Open System Interconnect) 7 layered reference model. It provides the user with many powerful features including multi-master functionality and the ability to broadcast / multicast telegrams. When we use a microprocessor chip embedding the CAN function, the system becomes more economical and reliable to react shortly in the data transmission. The controller, we proposed, is composed of two main controllers and a sub controller, which have built with a one-chip microprocessor having CAN function. The sub controller is plugged into the Pentium PC to perform a CAN communication, and connected to the main controllers via the CAN. Main controllers are responsible for controlling two motors respectively. Totally four motors, actuators for the biped robot in our laboratory, are controlled in the experiment. We show that the four motors are controlled properly to actuate the biped robot through the network in real time.

• 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.