• The Transactions of the Korea Information Processing Society
• /
• v.6 no.10
• /
• pp.2779-2789
• /
• 1999

In this paper, we propose a new neural Buffered Leaky Bucket algorithm for preventing the degradation of network performance caused by congestion and dealing with the traffic congestion in ATM networks. We networks. We justify the validity of the suggested method through performance comparison in aspects of cell loss rate and mean transfer delay under a variety of traffic conditions requiring the different QoS(Quality of Service). also, the cell scheduling algorithms such as DWRR and DWEDF used for multiplexing the incoming traffics are induced to get the delay time of the traffics fairly. The network congestion information from cell scheduler is used to control the predicted traffic loss rate of Neural Leaky Bucket, and token generation rate is changed by the predicted values. The prediction of traffic loss rate by neural networks can effectively reduce the cell loss rate and the cell transfer delay of next incoming cells and be applied to other traffic control systems. Computer simulation results performed for traffic prediction show that QoSs of the various kinds of traffics are increased.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.301-307
• /
• 2022

Energy consumption has grown alongside dramatic population increases. Statistics show that buildings in particular utilize a significant amount of energy, worldwide. Because of this, building energy prediction is crucial to best optimize utilities' energy plans and also create a predictive model for consumers. To improve energy prediction performance, this paper proposes a ResNet-LSTM model that combines residual networks (ResNets) and long short-term memory (LSTM) for energy consumption prediction. ResNets are utilized to extract complex and rich features, while LSTM has the ability to learn temporal correlation; the dense layer is used as a regression to forecast energy consumption. To make our model more robust, we employed Huber loss during the optimization process. Huber loss obtains high efficiency by handling minor errors quadratically. It also takes the absolute error for large errors to increase robustness. This makes our model less sensitive to outlier data. Our proposed system was trained on historical data to forecast energy consumption for different time series. To evaluate our proposed model, we compared our model's performance with several popular machine learning and deep learning methods such as linear regression, neural networks, decision tree, and convolutional neural networks, etc. The results show that our proposed model predicted energy consumption most accurately.

• Proceedings of the KIEE Conference
• /
• 1992.07a
• /
• pp.196-200
• /
• 1992

Transmission loss retains a complete set of system state information. If we could exploit its behavior, we could find various useful applications. This study is a such exploitation to find same possibilities of the loss application. It seems to have very prospective possibilities. It has been tried to establish some network indices to indicate operation margin. And further some prospective applications are suggested.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.315-315
• /
• 2000

In this paper, we perform the time series prediction using the SVM(Support Vector Machine). We make use of two different loss functions and two different kernel functions; i) Quadratic and $\varepsilon$-insensitive loss function are used; ii) GRBF(Gaussian Radial Basis Function) and ERBF(Exponential Radial Basis Function) are used. Mackey-Glass time series are used for prediction. For both cases, we compare the results by the SVM to those by ANN(Artificial Neural Network) and show the better performance by SVM than that by ANN.

• Convergence Security Journal
• /
• v.16 no.5
• /
• pp.41-48
• /
• 2016

In this paper we propose a new method of security visualization, VisFlow, using traffic flows to solve the problems of existing traffic flows based visualization techniques that were a loss of end-to-end semantics of communication, reflection problem by symmetrical address coordinates space, and intuitive loss problem in mass of traffic. VisFlow, a simple and effective security visualization interface, can do a real-time analysis and monitoring the situation in the managed network with visualizing a variety of network behavior not seen in the individual traffic data that can be shaped into patterns. This is a way to increase the intuitiveness and usability by identifying the role of nodes and by visualizing the highlighted or simplified information based on their importance in 2D/3D space. In addition, it monitor the network security situation as a way to increase the informational effectively using the asymmetrical connecting line based on IP addresses between pairs of nodes. Administrator can do a real-time analysis and monitoring the situation in the managed network using VisFlow, it makes to effectively investigate the massive traffic data and is easy to intuitively understand the entire network situation.

• Journal of Digital Contents Society
• /
• v.10 no.2
• /
• pp.233-238
• /
• 2009

The advances in the digital communication and network technology, Internet technology and the proliferation of smart appliances in home, have dramatically increased the need for a high speed/high quality home network. As consumer electronic devices and computing devices are increasing in the home network, it is obvious that the data traffic of home network increases as well. Various home network devices want to access Internet servers to get multimedia contents. Therefore, we introduce TLC(Telephone Line Carrier) system for networked digital consumer electronic appliances within a house using Ethernet or wire/wireless technology. In the future home network environment, the primary purposes of the smart home network based TLC are to create low-cost, easily deployable, high performance, and wide coverage throughout the home. In this paper, the channel capacity of telephone line communication system is evaluated and compared as a function of transmission power, number of OFDM carrier, channel loss, and noise loss for smart home network.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.9
• /
• pp.1357-1366
• /
• 2022

It is important to quickly and accurately build a disaster network or tactical mobile communication network adapting to the field. In configuring the traditional wireless communication systems, the parameters of the base station are set through cell planning. However, for cell planning, information on the environment must be established in advance. If parameters which are not appropriate for the field are used, because they are not reflected in cell planning, additional optimization must be carried out to solve problems and improve performance after network construction. In this paper, we present a rapid mobile communication network construction and optimization method using artificial intelligence and SON technologies in mobile communication base stations. After automatically setting the base station parameters using the CNN model that classifies the terrain with path loss prediction through the DNN model from the location of the base station and the measurement information, the path loss model enables continuous overage/capacity optimization.

• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.3 s.180
• /
• pp.61-68
• /
• 2006

This paper is to investigate the influence of the endface quality on the loss characteristics of a plastic optical fiber(POF) connector and the stability of new designed sleeve for in-car network service. Using the parameters of the surface roughness and applied load, insertion loss of connector is measured. Endface condition for optimizing the connection is presented by the surface roughness satisfying loss criteria and the stress for minimizing the loss, $R_{rms}=8nm$ and 19 MPa, respectively. By vibration test and dynamic loss measurement, we show the stability of the new designed sleeve.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.72-74
• /
• 2021

The deep learning process currently utilized in various fields consists of data preparation, data preprocessing, model generation, model learning, and model evaluation. In the process of model learning, the loss function compares the value of the model with the actual value and outputs the difference. In this paper, we analyze various loss functions used in the deep learning model for biomarker extraction, which measure the degree of loss of neural network output values, and try to find the best loss function through experiments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.11
• /
• pp.2553-2562
• /
• 2013

It is difficult for TCP congestion control algorithm to ensure the bandwidth and delay bound required for media streaming services in broadband wireless network environments. In this paper, we propose the COIN TCP (COncave INcrease TCP) scheme for providing a high-quality media streaming services. The COIN TCP concavely increases the congestion window size by adjusting the increment rate of congestion window, that is inversely proportional to the amount of data accumulated in the router queue. As a result, our scheme can quickly occupy the available bandwidth and prevent the heavy congestion. It also improves the link utilization by adjusting the decrement rate of congestion window according to the packet loss rate with the random loss. Through the simulation results, we prove that our scheme improves the total throughput in broadband wireless network.