• Journal of the Korea Society of Computer and Information
• /
• v.12 no.3
• /
• pp.75-84
• /
• 2007

Due to the increasing complexity and shorter life cycle of web applications, web applications need to be restructured to improve flexibility and extensibility. These days approaches are being used where systems are understood and restructured through clustering techniques. In this paper, the coupling metrics are proposed for clustering web pages more effectively. To achieve this, web application models are defined, where the relationship between web pages and the numbers of parameters are included. Considering direct and indirect coupling strength based on these models, coupling metrics are defined. The more direct relations between two pages and the more parameters they have, the stronger direct coupling is. The higher indirect connectivity strength between two pages is, the more similar the patterns of relationships among other web pages are. We verify the suggested metrics according to the well known verification framework and provide a case study to show that our metrics complements some existing metrics.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.30 no.3 s.246
• /
• pp.219-230
• /
• 2006

Digital CAD models are one of the most important assets the manufacturer holds. The trend toward concurrent engineering and outsourcing in the distributed development and manufacturing environment has elevated the importance of high quality CAD model and its efficient exchange. But designers have spent a great deal of their time repairing CAD model errors. Most of those poor quality models may be due to designer errors caused by poor or incorrect CAD data generation practices. In this paper, we propose a rule-based approach for healing CAD model errors. The proposed approach focuses on the design history data representation from a commercial CAD model, and the procedural method for building knowledge base to heal CAD model. Through the use of rule-based approach, a CAD model healing system can be implemented, and experiments are carried out on automobile part models.

• 한국정보통신설비학회:학술대회논문집
• /
• 2007.08a
• /
• pp.155-158
• /
• 2007

In this paper, we solved the underestimation problem of PSNR, which is caused by repeated frames, by easily synchronizing original and decoded frames using the proposed marks. Also we propose full-reference system which can be applied for measuring the quality of various kinds of video communication systems, e.g. wireless handsets, mobile phones and applications for PC. In addition, we propose a new video quality assessment metric using video communication parameters, i.e. frame rate and delay. According to the experiments, the proposed metric is not only appropriate for real-time video communication systems but also shows better correlation with the subjective video quality assessment than PSNR. The proposed measuring system and metric can be effectively used for measuring and standardizing the video quality of future communications.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.10
• /
• pp.407-420
• /
• 2021

Deep neural networks are widely used to solve various problems. However, the deep neural network with a deep hidden layer frequently has a vanishing gradient or exploding gradient problem, which is a major obstacle to learning the deep neural network. In this paper, we propose a parametric activation function to alleviate the vanishing gradient problem that can be caused by nonlinear activation function. The proposed parametric activation function can be obtained by applying a parameter that can convert the scale and location of the activation function according to the characteristics of the input data, and the loss function can be minimized without limiting the derivative of the activation function through the backpropagation process. Through the XOR problem with 10 hidden layers and the MNIST classification problem with 8 hidden layers, the performance of the original nonlinear and parametric activation functions was compared, and it was confirmed that the proposed parametric activation function has superior performance in alleviating the vanishing gradient.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.12
• /
• pp.72-81
• /
• 2009

In this paper, we investigate a spectrum sharing scheme based on the interference temperature (IT), that is a recently introduced receiver-centric metric by FCC. We extend the existing frequency sharing procedure for single CR to the one for multiple CRs (or secondary users, SUs). In the proposed interference model, we consider the practical operating characteristics of primary users (PUs), stochastically activated (ON)/deactivated (OFF) at the time axis, and analyze quantitatively the CR user capacity based on the model. We define the instantaneous capacity for idle time-slot channel allocation and the mean capacity averaging this instantaneous capacity and use them for a proper frequency sharing. Apart from existing schemes, the proposed frequency sharing scheme changes the frequency parameters adaptively depending on the channel characteristics and does not need any sensing information from PUs. Through computer simulation, we verify the proposed model.

• The KIPS Transactions:PartA
• /
• v.12A no.5 s.95
• /
• pp.451-460
• /
• 2005

We present a methodology to design energy-efficient data paths using FPGAs. Our methodology integrates domain specific modeling, coarse-grained performance evaluation, design space exploration, and low-level simulation to understand the tradeoffs between energy, latency, and area. The domain specific modeling technique defines a high-level model by identifying various components and parameters specific to a domain that affect the system-wide energy dissipation. A domain is a family of architectures and corresponding algorithms for a given application kernel. The high-level model also consists of functions for estimating energy, latency, and area that facilitate tradeoff analysis. Design space exploration(DSE) analyzes the design space defined by the domain and selects a set of designs. Low-level simulations are used for accurate performance estimation for the designs selected by the DSE and also for final design selection We illustrate our methodology using a family of architectures and algorithms for matrix multiplication. The designs identified by our methodology demonstrate tradeoffs among energy, latency, and area. We compare our designs with a vendor specified matrix multiplication kernel to demonstrate the effectiveness of our methodology. To illustrate the effectiveness of our methodology, we used average power density(E/AT), energy/(area x latency), as themetric for comparison. For various problem sizes, designs obtained using our methodology are on average $25\%$ superior with respect to the E/AT performance metric, compared with the state-of-the-art designs by Xilinx. We also discuss the implementation of our methodology using the MILAN framework.