• 한국경영과학회지
• /
• 제25권2호
• /
• pp.87-100
• /
• 2000

As a result of rapid advances in communication technology, fiber optics have begun to be adopted in most telecommunication systems 3s an economic choice Due to the trend of evolution toward broadband communication network with fiber optics and electronic devices. the network design problem for broadband communication has been received a great deal of research attention recently. In this paper, we address a topological design problem for broadband local access network with uncertain demands, which has received surprisingly little attention so far. in our problem, we select a set of hubs and links for constructing network expected penalty cost for the amount of undersupplied In addition to the usual cost terms of the fixed demand problem Our problem can be approximated as a mixed 0-1 integer programming problem by using Szwarc’s linear approximation technique. Then the problem is transformed successfully into a version of classical network design model. Some computational experiments for the model and concluding remarks are described.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 춘계학술발표대회
• /
• pp.358-361
• /
• 2021

In order to improve the accuracy of small target detection more effectively, this paper proposes an improved single shot detector (SSD) target detection and recognition method based on cspdarknet53, which introduces lightweight ECA attention mechanism and Feature Pyramid Network (FPN). First, the original SSD backbone network is replaced with cspdarknet53 to enhance the learning ability of the network. Then, a lightweight ECA attention mechanism is added to the basic convolution block to optimize the network. Finally, FPN is used to gradually fuse the multi-scale feature maps used for detection in the SSD from the deep to the shallow layers of the network to improve the positioning accuracy and classification accuracy of the network. Experiments show that the proposed target detection algorithm has better detection accuracy, and it improves the detection accuracy especially for small targets.

• 전자공학회논문지C
• /
• 제34C권4호
• /
• pp.36-44
• /
• 1997

An efficient context-free multiple-object segmentation using attention operator based on modified generalized symmetry transform is proposed and implemented by modifying a radial basis function network. By using the difference of intensity gradient, instead of te intensity gradient itself, in generalized symmetry tranform so as to make the attention operator to preserve the edges of the objects shape, an efficient context-free multiple-object segementation is proposed in which no a priori shape informtion on the objects is requried. The attention operator is implemented by using a modified radial basis function network which can reflect symmetry, and by using te edge pyramid of the input image, both of the local and the global symmetry of the objects are reflected simultaneously to make the multiple-object with different sizes be segmented with a singel fixed-size $n\timesm$ can be done with O(n) complexity. The simulaton results show that the proposed algorithm can efficiently be used in context-free multiple-object segmentation even for the low contrast IR images as well as for the images from the camera.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.242-252
• /
• 2021

Following the intuition that the local information in time instances is hardly incorporated into the posterior sequence in long short-term memory (LSTM), this paper proposes an attention augmented mechanism for fault diagnosis of the complex chemical process data. Unlike conventional fault diagnosis and classification methods, an attention mechanism layer architecture is introduced to detect and focus on local temporal information. The augmented deep network results preserve each local instance's importance and contribution and allow the interpretable feature representation and classification simultaneously. The comprehensive comparative analyses demonstrate that the developed model has a high-quality fault classification rate of 95.49%, on average. The results are comparable to those obtained using various other techniques for the Tennessee Eastman benchmark process.

• Journal of Information Processing Systems
• /
• 제17권4호
• /
• pp.754-771
• /
• 2021

In the task of continuous dimension emotion recognition, the parts that highlight the emotional expression are not the same in each mode, and the influences of different modes on the emotional state is also different. Therefore, this paper studies the fusion of the two most important modes in emotional recognition (voice and visual expression), and proposes a two-mode dual-modal emotion recognition method combined with the attention mechanism of the improved AlexNet network. After a simple preprocessing of the audio signal and the video signal, respectively, the first step is to use the prior knowledge to realize the extraction of audio characteristics. Then, facial expression features are extracted by the improved AlexNet network. Finally, the multimodal attention mechanism is used to fuse facial expression features and audio features, and the improved loss function is used to optimize the modal missing problem, so as to improve the robustness of the model and the performance of emotion recognition. The experimental results show that the concordance coefficient of the proposed model in the two dimensions of arousal and valence (concordance correlation coefficient) were 0.729 and 0.718, respectively, which are superior to several comparative algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권9호
• /
• pp.2458-2482
• /
• 2023

Medical image segmentation techniques based on convolution neural networks indulge in feature extraction triggering redundancy of parameters and unsatisfactory target localization, which outcomes in less accurate segmentation results to assist doctors in diagnosis. In this paper, we propose a multi-level semantic-rich encoding-decoding network, which consists of a Pooling-Conv-Former (PCFormer) module and a Cbam-Dilated-Transformer (CDT) module. In the PCFormer module, it is used to tackle the issue of parameter explosion in the conservative transformer and to compensate for the feature loss in the down-sampling process. In the CDT module, the Cbam attention module is adopted to highlight the feature regions by blending the intersection of attention mechanisms implicitly, and the Dilated convolution-Concat (DCC) module is designed as a parallel concatenation of multiple atrous convolution blocks to display the expanded perceptual field explicitly. In addition, MultiHead Attention-DwConv-Transformer (MDTransformer) module is utilized to evidently distinguish the target region from the background region. Extensive experiments on medical image segmentation from Glas, SIIM-ACR, ISIC and LGG demonstrated that our proposed network outperforms existing advanced methods in terms of both objective evaluation and subjective visual performance.

• 한국인터넷방송통신학회논문지
• /
• 제23권6호
• /
• pp.89-95
• /
• 2023

인간 행동 인식 (Human action recognition, HAR) 기술은 스포츠 분석, 인간과 로봇 간의 상호작용, 대형 사이니지 콘텐츠 등의 애플리케이션에 활용되는 핵심 기술 중 하나이다. 본 논문에서는 몰입형 대형 사이니지 콘텐츠를 위한 STAGCN (Spatial temporal attention graph convolutional network) 기반 인간 행동 인식 시스템을 제안한다. STAGCN은 attention mechanism을 통해 스켈레톤 시퀀스의 시공간적 특징에 서로 다른 가중치를 부과하여, 동작 인식에 중요한 관절 및 시점을 고려할 수 있다. NTU RGB+D 데이터셋을 사용한 실험 결과, 제안된 시스템은 기존 딥러닝 모델들에 비해 높은 분류 정확도를 달성한 것을 확인했다.

• 한국전자통신학회논문지
• /
• 제15권3호
• /
• pp.465-472
• /
• 2020

최근 들어, 오디오 이벤트 검출을 위하여 다양한 딥뉴럴네트워크 기반의 방법들이 제안되어 왔다. 본 연구에서는 베이스라인 CRNN(Convolutional Recurrent Neural Network) 구조에 attention 방식을 도입함으로서 오디오 이벤트 검출의 성능을 향상시키고자 하였다. 베이스라인 CRNN의 입력단에 context gating을 적용하고 출력단에 attention layer을 추가하였다. 또한, 프레임(frame) 단위의 강전사 레이블(strong label)정보 뿐만 아니라 클립(clip) 단위의 약전사 레이블(weakly label) 오디오 데이터를 이용한 학습을 통하여 보다 나은 성능을 이루고자 하였다. DCASE 2018/2019 Challenge Task 4 데이터를 이용한 오디오 이벤트 검출 실험에서 제안된 attention 기반의 CRNN을 통하여 기존의 CRNN 방식에 비해서 최대 66%의 상대적 F-score 향상을 얻을 수 있었다.

• 한국군사과학기술학회지
• /
• 제24권2호
• /
• pp.175-186
• /
• 2021

In the field of automatic target recognition(ATR) with synthetic aperture radar(SAR) imagery, it is usually impractical to obtain SAR target images covering a full range of aspect views. When the database consists of SAR target images with limited angular diversity, it can lead to performance degradation of the SAR-ATR system. To address this problem, this paper proposes a deep learning-based method where channel attention modules(CAMs) are inserted to a convolutional neural network(CNN). Motivated by the idea of the squeeze-and-excitation(SE) network, the CAM is considered to help improve recognition performance by selectively emphasizing discriminative features and suppressing ones with less information. After testing various CAM types included in the ResNet18-type base network, the SE CAM and its modified forms are applied to SAR target recognition using MSTAR dataset with different reduction ratios in order to validate recognition performance improvement under the limited angular diversity condition.

• 한국컴퓨터정보학회논문지
• /
• 제29권7호
• /
• pp.11-20
• /
• 2024

본 논문에서는 생성 모델을 이용한 데이터 프리 양자화에서 발생할 수 있는 지식 격차를 줄이기 위하여 BAG (Bit-width Aware Generator)와 채널 어텐션 기반 중간 레이어 지식 증류를 제안한다. 생성 모델을 이용한 데이터 프리 양자화의 생성자는 오직 원본 네트워크의 피드백에만 의존하여 학습하기 때문에, 양자화된 네트워크의 낮은 bit-width로 인한 감소된 수용 능력 차이를 학습에 반영하지 못한다. 제안한 BAG는 양자화된 네트워크와 동일한 bit-width로 양자화하여, 양자화된 네트워크에 맞는 합성 이미지를 생성하여 이러한 문제를 완화한다. 또한, 양자화된 네트워크와 원본 모델 간의 지식 격차를 줄이는 것 역시 양자화에서 매우 중요한 문제이다. 이를 완화하기 위해 제안한 채널 어텐션 기반 중간 레이어 지식 증류는 학생 모델이 교사 모델로부터 어떤 채널에 더 집중해서 학습해야 하는지를 가르친다. 제안한 기법의 효율성을 보이기 위해, CIFAR-100에서 학습한 원본 네트워크를 가중치와 활성값을 각각 3-bit로 양자화하여 학습을 수행하였다. 그 결과 56.14%의 Top-1 Accuracy를 달성하였으며, 베이스라인 모델인 AdaDFQ 대비 3.4% 정확도를 향상했다.