• 한국멀티미디어학회논문지
• /
• 제23권12호
• /
• pp.1447-1453
• /
• 2020

In this paper, we propose a method for no-reference quality assessment of sports videos using 3D shearlet transform and deep residual neural networks. In the proposed method, 3D shearlet transform-based spatiotemporal features are extracted from the overlapped video blocks and applied to logistic regression concatenated with a deep residual neural network based on a conditional video block-wise constraint to learn the spatiotemporal correlation and predict the quality score. Our evaluation reveals that the proposed method predicts the video quality with higher accuracy than the conventional no-reference video quality assessment methods.

• Journal of Information Processing Systems
• /
• 제18권1호
• /
• pp.12-25
• /
• 2022

In recent years, deep convolutional neural networks have made significant progress in the research of single image super-resolution. However, it is difficult to be applied in practical computing terminals or embedded devices due to a large number of parameters and computational effort. To balance these problems, we propose CSRNet, a lightweight neural network based on channel split residual learning structure, to reconstruct highresolution images from low-resolution images. Lightweight refers to designing a neural network with fewer parameters and a simplified structure for lower memory consumption and faster inference speed. At the same time, it is ensured that the performance of recovering high-resolution images is not degraded. In CSRNet, we reduce the parameters and computation by channel split residual learning. Simultaneously, we propose a double-upsampling network structure to improve the performance of the lightweight super-resolution network and make it easy to train. Finally, we propose a new evaluation metric for the lightweight approaches named 100_FPS. Experiments show that our proposed CSRNet not only speeds up the inference of the neural network and reduces memory consumption, but also performs well on single image super-resolution.

• 인터넷정보학회논문지
• /
• 제10권3호
• /
• pp.61-69
• /
• 2009

무선 센서 네트워크에서 클러스터 기반의 계층적 라우팅 프로토콜들은 모든 노드들의 수명을 균등하게 유지하여, 센서 네트워크의 수명을 최대로 연장하는 것을 목표로 하고 있다. 본 논문에서는 임계값 기반의 클러스터 헤드 교체 전략을 보인다. 이라우팅 프로토콜은 센서 노드가 클러스터 헤드의 역할을 수행하지 않으면서 최대한 오랜 시간 동안 네트워크에 참여하기 위해 필요한 에너지의 양을 임계값으로 정의하고, 한 번 클러스터 헤드로 선출된 노드는 이 값에 도달할 때 까지 클러스터 헤드의 역할을 유지하여 빈번한 헤드 교체를 방지하도록 함으로써 전체 네트워크의 에너지 효율은 물론 네트워크의 균형이 최대한 유지되도록 한다. 또한 시뮬레이션을 통해 대표적 계층적 라우팅 프로토콜인 LEACH와 네트워크의 균형 및 에너지 소모 정도를 비교하여 본 논문이 제시하는 알고리즘의 효용성을 입증한다.

• 한국컴퓨터정보학회논문지
• /
• 제22권3호
• /
• pp.115-122
• /
• 2017

In this paper, we propose an adaptive data aggregation and compression scheme for wireless sensor networks with energy-harvesting nodes, which increases the amount of data arrived at the sink node by efficient use of the harvested energy. In energy-harvesting wireless sensor networks, sensor nodes can have more than necessary energy because they harvest energy from environments continuously. In the proposed scheme, when a node judges that there is surplus energy by estimating its residual energy, the node compresses and transmits the aggregated data so far. Conversely, if the residual energy is estimated to be depleted, the node turns off its transceiver and collects only its own sensory data to reduce its energy consumption. As a result, this scheme increases the amount of data collected at the sink node by preventing the blackout of relay nodes and facilitating data transmission. Through simulation, we show that the proposed scheme suppresses the occurrence of blackout nodes and collect the largest amount of data at the sink node compared to previous schemes.

• Journal of Information Processing Systems
• /
• 제16권5호
• /
• pp.1145-1157
• /
• 2020

A convolution neural networks (CNNs) has demonstrated outstanding performance compared to other algorithms in the field of face recognition. Regarding the over-fitting problem of CNN, researchers have proposed a residual network to ease the training for recognition accuracy improvement. In this study, a novel face recognition model based on game theory for call-over in the classroom was proposed. In the proposed scheme, an image with multiple faces was used as input, and the residual network identified each face with a confidence score to form a list of student identities. Face tracking of the same identity or low confidence were determined to be the optimisation objective, with the game participants set formed from the student identity list. Game theory optimises the authentication strategy according to the confidence value and identity set to improve recognition accuracy. We observed that there exists an optimal mapping relation between face and identity to avoid multiple faces associated with one identity in the proposed scheme and that the proposed game-based scheme can reduce the error rate, as compared to the existing schemes with deeper neural network.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.4026-4040
• /
• 2019

In this paper, we present an approach for detecting slide transitions in lecture videos by introducing the spatio-temporal residual networks. Given a lecture video which records the digital slides, the speaker, and the audience by multiple cameras, our goal is to find keyframes where slide content changes. Since temporal dependency among video frames is important for detecting slide changes, 3D Convolutional Networks has been regarded as an efficient approach to learn the spatio-temporal features in videos. However, 3D ConvNet will cost much training time and need lots of memory. Hence, we utilize ResNet to ease the training of network, which is easy to optimize. Consequently, we present a novel ConvNet architecture based on 3D ConvNet and ResNet for slide transition detection in lecture videos. Experimental results show that the proposed novel ConvNet architecture achieves the better accuracy than other slide progression detection approaches.

• International Journal of Computer Science & Network Security
• /
• 제23권7호
• /
• pp.39-48
• /
• 2023

Breast cancer screening makes extensive utilization of mammography. Even so, there has been a lot of debate with regards to this application's starting age as well as screening interval. The deep learning technique of transfer learning is employed for transferring the knowledge learnt from the source tasks to the target tasks. For the resolution of real-world problems, deep neural networks have demonstrated superior performance in comparison with the standard machine learning algorithms. The architecture of the deep neural networks has to be defined by taking into account the problem domain knowledge. Normally, this technique will consume a lot of time as well as computational resources. This work evaluated the efficacy of the deep learning neural network like Visual Geometry Group Network (VGG Net) Residual Network (Res Net), as well as inception network for classifying the mammograms. This work proposed optimization of ResNet with Teaching Learning Based Optimization (TLBO) algorithm's in order to predict breast cancers by means of mammogram images. The proposed TLBO-ResNet, an optimized ResNet with faster convergence ability when compared with other evolutionary methods for mammogram classification.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2019년도 추계학술대회
• /
• pp.119-121
• /
• 2019

부가적 백색 잡음 모델(additive white Gaussian noise, AWGN에서 학습된 깊은 신경만 (deep neural networks)을 이용한 잡음 제거기는 제거하려는 잡음이 AWGN인 경우에는 뛰어난 성능을 보이지만 실제 카메라 잡음에 대해서 잡음 제거를 시도하였을 때는 성능이 크게 저하된다. 본 논문은 U-Net 구조의 깊은 인공신경망 모델에 residual block을 결합함으로서 실제 카메라 영상에서 기존 알고리즘보다 뛰어난 성능을 지니는 신경망을 제안하다. 제안한 방법을 통해 Darmstadt Noise Dataset에서 PSNR과 SSIM 모두 CBDNet 대비 향상됨을 확인하였다.

• Journal of Communications and Networks
• /
• 제15권3호
• /
• pp.258-265
• /
• 2013

In this study, we investigate the multi-carrier spread spectrum (MCSS) communication system which adopts the self-encoded spread spectrum in a downlink synchronous channel. It is very difficult to completely eliminate the frequency offset in practical channel scenarios. We demonstrate that the self-encoded MCSS (SE-MCSS) with iterative despreading manifests a remarkable immunity to residual frequency offset. The SE-MCSS can be an excellent candidate for the future generation of wireless services.

• International Journal of Concrete Structures and Materials
• /
• 제9권2호
• /
• pp.159-172
• /
• 2015

Estimation of the residual strength of corroded reinforced concrete beams has been studied from experimental and theoretical perspectives. The former is arduous as it involves casting beams of various sizes, which are then subjected to various degrees of corrosion damage. The latter are static; hence cannot be generalized as new coefficients need to be re-generated for new cases. This calls for dynamic models that are adaptive to new cases and offer efficient generalization capability. Computational intelligence techniques have been applied in Construction Engineering modeling problems. However, these techniques have not been adequately applied to the problem addressed in this paper. This study extends the empirical model proposed by Azad et al. (Mag Concr Res 62(6):405-414, 2010), which considered all the adverse effects of corrosion on steel. We proposed four artificial neural networks (ANN) models to predict the residual flexural strength of corroded RC beams using the same data from Azad et al. (2010). We employed two modes of prediction: through the correction factor ($C_f$) and through the residual strength ($M_{res}$). For each mode, we studied the effect of fixed and random data stratification on the performance of the models. The results of the ANN models were found to be in good agreement with experimental values. When compared with the results of Azad et al. (2010), the ANN model with randomized data stratification gave a $C_f$-based prediction with up to 49 % improvement in correlation coefficient and 92 % error reduction. This confirms the reliability of ANN over the empirical models.