• 대한기계학회논문집A
• /
• 제33권8호
• /
• pp.753-759
• /
• 2009

Feed-forward neural networks have been widely used as function approximation tools in the context of global approximate optimization. In the present study, a wavelet neural network (WNN) which is based on wavelet transform theory is suggested as an alternative to a traditional back-propagation neural network (BPN). The basic theory of wavelet neural network is briefly described, and approximation performance is tested using a nonlinear multimodal function and a composite rotor blade analysis problem. Laplacian of Gaussian function, Mexican function, and Morlet function are considered during the construction of WNN architectures. In addition, approximation results from WNN are compared with those from BPN.

• Journal of information and communication convergence engineering
• /
• 제5권3호
• /
• pp.209-214
• /
• 2007

In this paper, we proposed a new MANET (Mobile Ad hoc Networks) technology of routing protocol. The MANET has a mobility formation of mobile nodes in the wireless networks. Wireless network have two types architecture: the Tree based multicast and shared tree based. The two kind's architecture of general wireless networks have difficult to solve the problems existing in the network, such as connectivity, safety, and reliability. For this purpose, as using that ADDMRP (Ad hoc network Doppler effect-based for Dynamic Multicast Routing Protocol), this study gives the following suggestion for new topology through network durability and Omni-directional information. The proposed architectures have considered the mobility location, mobility time, density, velocity and simultaneous using node by Doppler effects and improved the performance.

• Journal of Information Processing Systems
• /
• 제15권5호
• /
• pp.1119-1130
• /
• 2019

With the wide spread of Social Network Services (SNS), fake news-which is a way of disguising false information as legitimate media-has become a big social issue. This paper proposes a deep learning architecture for detecting fake news that is written in Korean. Previous works proposed appropriate fake news detection models for English, but Korean has two issues that cannot apply existing models: Korean can be expressed in shorter sentences than English even with the same meaning; therefore, it is difficult to operate a deep neural network because of the feature scarcity for deep learning. Difficulty in semantic analysis due to morpheme ambiguity. We worked to resolve these issues by implementing a system using various convolutional neural network-based deep learning architectures and "Fasttext" which is a word-embedding model learned by syllable unit. After training and testing its implementation, we could achieve meaningful accuracy for classification of the body and context discrepancies, but the accuracy was low for classification of the headline and body discrepancies.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 춘계학술발표대회
• /
• pp.652-654
• /
• 2023

The accurate prediction of User Equipment (UE) paths in wireless networks is crucial for improving handover mechanisms and optimizing network performance, particularly in the context of Beyond 5G and 6G networks. This paper presents a comprehensive evaluation of unidirectional and bidirectional recurrent neural network (RNN) architectures for UE path prediction. The study employs a sequence-to-sequence model designed to forecast user paths in a wireless network environment, comparing the performance of unidirectional and bidirectional RNNs. Through extensive experimentation, the paper highlights the strengths and weaknesses of each RNN architecture in terms of prediction accuracy and computational efficiency. These insights contribute to the development of more effective predictive path-based mobility management strategies, capable of addressing the challenges posed by ultra-dense cell deployments and complex network dynamics.

• International journal of advanced smart convergence
• /
• 제13권2호
• /
• pp.195-204
• /
• 2024

In this paper, we investigate the comparative performance of two leading object detection architectures, YOLOv7 and Detection Transformer (DETR), across varying levels of data augmentation using CycleGAN. Our experiments focus on chest scan images within the context of biomedical informatics, specifically targeting the detection of abnormalities. The study reveals that YOLOv7 consistently outperforms DETR across all levels of augmented data, maintaining better performance even with 75% augmented data. Additionally, YOLOv7 demonstrates significantly faster convergence, requiring approximately 30 epochs compared to DETR's 300 epochs. These findings underscore the superiority of YOLOv7 for object detection tasks, especially in scenarios with limited data and when rapid convergence is essential. Our results provide valuable insights for researchers and practitioners in the field of computer vision, highlighting the effectiveness of YOLOv7 and the importance of data augmentation in improving model performance and efficiency.

• 건축역사연구
• /
• 제14권4호
• /
• pp.7-28
• /
• 2005

We are so used to the concept of the term 'space' that we do not question its conceptual validity. However, this paper argues that the notion of space prevailing all over the world, is not a universal concept that can be applicable to all architectures of the world, but is a particular concept that is generated from the Western way of thinking. This paper alms to identify the conceptual structure of the idea of space as it is originated in the tradition of the West, and, as an alternative view of space, tries to identify the nature of the view of space perceived in the tradition of the Eastern architecture. Comparison of the two views, that of the East and the West, and their meaning in the future of architecture, is another task to discuss in this paper. To be able to clarify the meaning of space in East Asian tradition, a set of new perspective of understanding of space was invited. They are ; 1. sky-earth(天地); insisting that the notion of space should be replaced within the context of sky, which is one half of sky-earth totality 2. energy of the air (空氣), space is not empty part inside of a building, but is a dynamic condition of air that is a part of the sky which always exist in form of energy 3. place(자리): instead of space, which, basically. is a man-made concept, idea of place is necessary, which include not only space but also earth Such concept of space which is different from the notion of space of the West, is meaningful not only to identify the idea of space in the East, but also to be able to contribute for more dynamic, varied, and balanced understanding of space.

• Smart Structures and Systems
• /
• 제31권4호
• /
• pp.335-349
• /
• 2023

Bridges constantly undergo deterioration and damage, the most common ones being concrete damage and exposed rebar. Periodic inspection of bridges to identify damages can aid in their quick remediation. Likewise, identifying components can provide context for damage assessment and help gauge a bridge's state of interaction with its surroundings. Current inspection techniques rely on manual site visits, which can be time-consuming and costly. More recently, robotic inspection assisted by autonomous data analytics based on Computer Vision (CV) and Artificial Intelligence (AI) has been viewed as a suitable alternative to manual inspection because of its efficiency and accuracy. To aid research in this avenue, this study performs a comparative assessment of different architectures, loss functions, and ensembling strategies for the autonomous segmentation of bridge components and damages. The experiments lead to several interesting discoveries. Nested Reg-UNet architecture is found to outperform five other state-of-the-art architectures in both damage and component segmentation tasks. The architecture is built by combining a Nested UNet style dense configuration with a pretrained RegNet encoder. In terms of the mean Intersection over Union (mIoU) metric, the Nested Reg-UNet architecture provides an improvement of 2.86% on the damage segmentation task and 1.66% on the component segmentation task compared to the state-of-the-art UNet architecture. Furthermore, it is demonstrated that incorporating the Lovasz-Softmax loss function to counter class imbalance can boost performance by 3.44% in the component segmentation task over the most employed alternative, weighted Cross Entropy (wCE). Finally, weighted softmax ensembling is found to be quite effective when used synchronously with the Nested Reg-UNet architecture by providing mIoU improvement of 0.74% in the component segmentation task and 1.14% in the damage segmentation task over a single-architecture baseline. Overall, the best mIoU of 92.50% for the component segmentation task and 84.19% for the damage segmentation task validate the feasibility of these techniques for autonomous bridge component and damage segmentation using RGB images.

• 대한전자공학회논문지SD
• /
• 제45권7호
• /
• pp.61-68
• /
• 2008

본 논문에서는 최신 동영상 압축 기술인 H.264/AVC (Advanced Video Coding)에서 엔트로피 코딩 방법 중 하나로 사용되는 CABAC (Context Adaptive Binary Arithmetic Coding)의 하드웨어 구현과 부호화 처리율을 높이기 위한 알고리즘 및 구조를 제안한다. CABAC는 CAVLC에 비해 쳐대 15%까지 더 나은 압축효율을 낼 수 있는 장점을 가지고 있지만 연산의 복잡도는 훨씬 높아진다. 특히 부호화 과정 중 데이터 사이의 의존도가 높기 때문에 연산과정의 복잡도가 더욱 증가하게 된다. 따라서 연산양을 줄이기 위한 다양한 구조가 제안되었으나, 여전히 데이터의 의존도에 의한 부호화에 latency가 존재하게 된다. 본 논문에서는 이진 산술 부호화의 첫 단계인 확률 값을 계산하는데 필요한 range의 7, 8번째 비트를 빠르게 계산하는 구조와 부호화할 심벌이 MPS인 경우 부호화 단계를 한 단계 줄일 수 있는 구조를 제안하였다. 제안된 구조를 적용하여, 6가지 시퀀스에 대하여 실험한 결과 기존의 구조에 비해 약 27-29%의 수행시간을 줄일 수 있었다. 또한 제안된 구조를 하드웨어로 구현한 결과 0.18um standard library에서 19K gate를 사용하였다.

• 한국통신학회논문지
• /
• 제42권5호
• /
• pp.1009-1019
• /
• 2017

모바일 엣지 컴퓨팅은 폭증하는 모바일 트래픽에 대응하고 다양한 요구사항을 만족시키는 서비스를 제공하기 위해 모바일 엣지 노드에서 다양한 기능을 직접 제공하는 기술이다. 예를 들어 모바일 트래픽 경감을 위한 캐싱이나, 위험감지 서비스 제공을 위한 비디오 분석 등이 모바일 엣지 노드에서 수행될 수 있다. 지금까지 개인화된 서비스를 추천하는 방법이나 구조 등에 대한 많은 연구가 있었지만, 모바일 엣지 컴퓨팅의 특성을 고려한 연구는 없었다. 개인화된 서비스를 제공하기 위해서는 사용자의 컨텍스트 정보를 획득하는 것이 중요하다. 기존 서버단 중심의 개인화된 서비스 모델은 모바일 엣지 컴퓨팅에 적용될 경우 컨텍스트 고립 문제와 프라이버시 이슈를 더욱 심화시킬 수 있다. 모바일 엣지 노드는 컨텍스트 수집이 용이하다는 이점을 가진다. 모바일 엣지 컴퓨팅 환경에서의 또 하나의 주목할 만한 특징은 사용자와 어플리케이션의 상호 연동이 매우 유동적이라는 점이다. 본 논문에서는 모바일 엣지 컴퓨팅의 특징을 반영한 로컬 서비스 추천 플랫폼 구조를 제시하고 컨텍스트 고립 문제와 프라이버시 이슈를 완화할 수 있는 개인화된 서비스 제공 방법을 제시한다.

• 전기학회논문지
• /
• 제59권2호
• /
• pp.436-444
• /
• 2010

In this study, we introduce and discuss a concept of a granular-oriented radial basis function neural networks (GRBF NNs). In contrast to the typical architectures encountered in radial basis function neural networks(RBF NNs), our main objective is to develop a design strategy of GRBF NNs as follows : (a) The architecture of the network is fully reflective of the structure encountered in the training data which are granulated with the aid of clustering techniques. More specifically, the output space is granulated with use of K-Means clustering while the information granules in the multidimensional input space are formed by using a so-called context-based Fuzzy C-Means which takes into account the structure being already formed in the output space, (b) The innovative development facet of the network involves a dynamic reduction of dimensionality of the input space in which the information granules are formed in the subspace of the overall input space which is formed by selecting a suitable subset of input variables so that the this subspace retains the structure of the entire space. As this search is of combinatorial character, we use the technique of genetic optimization to determine the optimal input subspaces. A series of numeric studies exploiting some nonlinear process data and a dataset coming from the machine learning repository provide a detailed insight into the nature of the algorithm and its parameters as well as offer some comparative analysis.