• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3823-3840
• /
• 2020

Recently, auto-encoder has emerged as the most popular method in convolutional neural network (CNN) based image compression and has achieved impressive performance. In the traditional auto-encoder based image compression model, the encoder simply sends the features of last layer to the decoder, which cannot allocate bits over different spatial regions in an efficient way. Besides, these methods do not fully exploit the contextual information under different receptive fields for better reconstruction performance. In this paper, to solve these issues, a novel auto-encoder model is designed for image compression, which can effectively transmit the hierarchical features of the encoder to the decoder. Specifically, we first propose an adaptive bit-allocation strategy, which can adaptively select an importance channel. Then, we conduct the multiply operation on the generated importance mask and the features of the last layer in our proposed encoder to achieve efficient bit allocation. Moreover, we present an additional novel perceptual loss function for more accurate image details. Extensive experiments demonstrated that the proposed model can achieve significant superiority compared with JPEG and JPEG2000 both in both subjective and objective quality. Besides, our model shows better performance than the state-of-the-art convolutional neural network (CNN)-based image compression methods in terms of PSNR.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.3
• /
• pp.341-357
• /
• 2010

Forward Error Correction (FEC) techniques have been adopted to overcome packet losses and to improve the quality of video delivery. The efficiency of the FEC has been significantly compromised, however, due to the characteristics of the wireless channel such as burst packet loss, channel fluctuation and lack of Quality of Service (QoS) support. We propose herein an Adaptive Cross-layer FEC mechanism (ACFEC) to enhance the quality of video streaming over 802.11 WLANs. Under the conventional approaches, FEC functions are implemented on the application layer, and required feedback information to calculate redundancy rates. Our proposed ACFEC mechanism, however, leverages the functionalities of different network layers. The Automatic Repeat reQuest (ARQ) function on the Media Access Control (MAC) layer can detect packet losses. Through cooperation with the User Datagram Protocol (UDP), the redundancy rates are adaptively controlled based on the packet loss information. The experiment results demonstrate that the ACFEC mechanism is able to adaptively adjust and control the redundancy rates and, thereby, to overcome both of temporary and persistent channel fluctuations. Consequently, the proposed mechanism, under various network conditions, performs better in recovery than the conventional methods, while generating a much less volume of redundant traffic.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.8
• /
• pp.2796-2813
• /
• 2014

This paper presents a new algorithm called the adaptive logarithmic increase and adaptive decrease algorithm (A-LIAD), which mainly addresses the Round-Trip Time (RTT) fairness problem in satellite networks with a very high propagation delay as an alternative to the current TCP congestion control algorithm. We defined a new increasing function in the fashion of a logarithm depending on the increasing factor ${\alpha}$, which is different from the other logarithmic increase algorithm adopting a fixed value of ${\alpha}$ = 2 leading to a binary increase. In A-LIAD, the ${\alpha}$ value is derived in the RTT function through the analysis. With the modification of the increasing function applied for the congestion avoidance phase, a hybrid scheme is also presented for the slow start phase. From this hybrid scheme, we can avoid an overshooting problem during a slow start phase even without a SACK option. To verify the feasibility of the algorithm for deployment in a high-speed and long-distance network, several aspects are evaluated through an NS-2 simulation. We performed simulations for intra- and interfairness as well as utilization in different conditions of varying RTT, bandwidth, and PER. From these simulations, we showed that although A-LIAD is not the best in all aspects, it provides a competitive performance in almost all aspects, especially in the start-up and packet loss impact, and thus can be an alternative TCP congestion control algorithm for high BDP networks including a satellite network.

• Journal of Wind Energy
• /
• v.14 no.1
• /
• pp.44-51
• /
• 2023

Some controllers have been introduced in various studies to mitigate the negative effects of renewable sources. These have been modified to fit a formed solution in various ways. This paper deals with the voltage regulation of wind farms in voltage dip situations where communication failures occur. The aim is to discuss the modification of the online wind farm management system. To discuss modifications of the online wind farm management system, we focus on voltage regulation of wind farms when communication failures occur. The structure has been designed to respond to a voltage drop when the outer reference is absent due to communication errors. Since the loss reduction effect has been maintained in the designed case studies, it can be derived that the proposed method can respond to voltage drops, along with a used objective function.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.10
• /
• pp.1852-1859
• /
• 2016

The effectiveness of a binarization algorithm in image processing depends on how to eliminate the uncertainty of determining threshold in a reasonable way and on minimizing information loss due to the binarization effect. Fuzzy binarization technique was proposed to handle that uncertainty with fuzzy logic. However, that method is known to be inefficient when the given image has low intensity contrast. In this paper, we propose an improved fuzzy binarization method to overcome such known drawbacks. Our method proposes a trapezoid type fuzzy membership function instead of most-frequently used triangle type one. We also propose an adaptive ${\alpha}$_cut determination policy. Our proposed method has less information loss than other algorithms since we do not use any stretching based preprocessing for enhancing the intensity contrast. In experiment, our proposed method is verified to be more effective in binarization with less information loss for many different types of images with low intensity contrast such as night scenery, lumber scoliosis, and lipoma images.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.305-312
• /
• 2023

Physics-Informed Neural Network (PINN) is used to invert bubble size distributions from attenuation losses. By considering a linear system for the bubble population inversion, Adaptive Learned Iterative Shrinkage Thresholding Algorithm (Ada-LISTA), which has been solved linear systems in image processing, is used as a neural network architecture in PINN. Furthermore, a regularization based on the linear system is added to a loss function of PINN and it makes a PINN have better generalization by a solution satisfying the bubble physics. To evaluate an uncertainty of bubble estimation, deep ensemble is adopted. 20 Ada-LISTAs with different initial values are trained using the same training dataset. During test with attenuation losses different from those in the training dataset, the bubble size distribution and corresponding uncertainty are indicated by average and variance of 20 estimations, respectively. Deep ensemble Ada-LISTA demonstrate superior performance in inverting bubble size distributions than the conventional convex optimization solver of CVX.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.6
• /
• pp.485-492
• /
• 2016

A role of the binarization is very important in separating the foreground and the background in the field of the computer vision. In this study, an adaptive fuzzy binarization is proposed. An ${\alpha}$-cut control ratio is obtained by the distribution of grey level of pixels in a sliding window, and binarization is performed using the value. To obtain the ${\alpha}$-cut, existing thresholding methods which execution speed is fast are used. The threshold values are set as the center of each membership function and the fuzzy intervals of the functions are specified with the distribution of grey level of the pixel. Then ${\alpha}$-control ratio is calculated using the specified function and binarization is performed according to the membership degree of the pixels. The experimental results show the proposed method can segment the foreground and the background well than existing binarization methods and decrease loss of the foreground.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.606-609
• /
• 2015

본 연구에서는 support vector regression (SVR) 및 매개변수 최적화 알고리즘을 이용한 하천수위 예측모델을 구축하고 이를 실제 유역에 적용하여 모델 효율성을 평가하였다. 여기서, SVR은 하천수위를 예측하기 위한 예측모델로서 채택되었으며, 커널함수 (Kernel function)로서는 radial basis function (RBF)을 선택하였다. 최적화 알고리즘은 SVR의 최적 매개변수 (C?, cost parameter or regularization parameter; ${\gamma}$, RBF parameter; ${\epsilon}$, insensitive loss function parameter)를 탐색하기 위하여 적용되었다. 매개변수 최적화 알고리즘으로는 grid search (GS), genetic algorithm (GA), particle swarm optimization (PSO), artificial bee colony (ABC) 알고리즘을 채택하였으며, 비교분석을 통해 최적화 알고리즘의 적용성을 평가하였다. 또한 SVR과 최적화 알고리즘을 결합한 모델 (SVR-GS, SVR-GA, SVR-PSO, SVR-ABC)은 기존에 수자원 분야에서 널리 적용되어온 신경망(Artificial neural network, ANN) 및 뉴로퍼지 (Adaptive neuro-fuzzy inference system, ANFIS) 모델과 비교하였다. 그 결과, 모델 효율성 측면에서 SVR-GS, SVR-GA, SVR-PSO 및 SVR-ABC는 ANN보다 우수한 결과를 나타내었으며, ANFIS와는 비슷한 결과를 나타내었다. 또한 SVR-GA, SVR-PSO 및 SVR-ABC는 SVR-GS보다 상대적으로 우수한 결과를 나타내었으며, 모델 효율성 측면에서 SVR-PSO 및 SVR-ABC는 가장 우수한 모델 성능을 나타내었다. 따라서 본 연구에서 적용한 매개변수 최적화 알고리즘은 SVR의 매개변수를 최적화하는데 효과적임을 확인할 수 있었다. SVR과 최적화 알고리즘을 이용한 하천수위 예측모델은 기존의 ANN 및 ANFIS 모델과 더불어 하천수위 예측을 위한 효과적인 도구로 사용될 수 있을 것으로 판단된다.

• Journal of the Optical Society of Korea
• /
• v.18 no.6
• /
• pp.809-817
• /
• 2014

The loss in contrast-discrimination ability of the human visual system under high ambient illumination level can cause image quality degradation in mobile phones. In this paper, we propose a perceived contrast compensation method by processing the original displayed image. With consideration that the perceived contrast significantly varies across the image, this method extracts the local band contrast from the original image; it then compensates these contrast components to counteract the perceived contrast degradation. Experimental results demonstrate that this method can maintain most contrast details even in high ambient illumination levels.

• Journal of Microbiology and Biotechnology
• /
• v.32 no.8
• /
• pp.1047-1053
• /
• 2022

When ptsG, a glucose-specific phosphotransferase system (PTS) component, is deleted in Escherichia coli, growth can be severely poor because of the lack of efficient glucose transport. We discovered a new PTS transport system that could transport glucose through the growth-coupled experimental evolution of ptsG-deficient E. coli C strain under anaerobic conditions. Genome sequencing revealed mutations in agaR, which encodes a repressor of N-acetylgalactosamine (Aga) PTS expression in evolved progeny strains. RT-qPCR analysis showed that the expression of Aga PTS gene increased because of the loss-of-function of agaR. We confirmed the efficient Aga PTS-mediated glucose uptake by genetic complementation and anaerobic fermentation. We discussed the discovery of new glucose transporter in terms of different genetic backgrounds of E. coli strains, and the relationship between the pattern of mixed-acids fermentation and glucose transport rate.