• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.4
• /
• pp.279-293
• /
• 2023

This study investigates network effects to measure how strongly the early adopters affect the brand choice of the potential consumer. By using the Gumbel-Hougaard (GH) copula, this study checks the magnitude of network effects varied from country to country. To consider consumer heterogeneity and network effects in the growth market, this study proposes the multi-brand Gamma/Shifted-Gompertz (m-G/SG) model based on the GH copula. Out of eighteen Western European cellular phone market data and South Korea smartphone data sets, the m-G/SG model provides an improvement in the estimation accuracy over the Libai, Muller, and Peres model. The results show that network effects enhance (i) the polarization of brand choice probabilities as time elapses; (ii) the dominance of the more preferred and the earlier entered brand; and (iii) the deceleration of category-level diffusion. Potential followers can analyze their relationship with earlier entrants through the m-G/SG model and also establish an optimal market entry strategy.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.38 no.1
• /
• pp.139-152
• /
• 2013

The purpose of this study is to claim the validity of tuning the architecture of neural network models for multi-class classification. A neural network model for multi-class classification is basically constructed by building a series of neural network models for binary classification. Building a neural network model, we are required to set the values of parameters such as number of hidden nodes and weight decay parameter in advance, which draws special attention as the performance of the model can be quite different by the values of the parameters. For better performance of the model, it is absolutely necessary to have a prior process of tuning the parameters every time the neural network model is built. Nonetheless, previous studies have not mentioned the necessity of the tuning process or proved its validity. In this study, we claim that we should tune the parameters every time we build the neural network model for multi-class classification. Through empirical analysis using wine data, we show that the performance of the model with the tuned parameters is superior to those of untuned models.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.4
• /
• pp.437-442
• /
• 2005

The forecasting of flood runoff in the river is essential for flood control. The purpose of this study is to test a development of system for flood runoff forecasting using neural network model. For the flood events the tested rainfall and runoff data were the input to the input layer and the flood runoff data were used in the output layer To choose the forecasting model which would make up of runoff forecasting system properly, real-time runoff in the river when flood periods were forecasted by using the neural network model and the state-space model. A comparison of the results obtained by the two forecasting models indicated the superiority and reliability of the neural network model over the state-space model. The neural network model was modified to work in the Web and developed to be the basic model of the forecasting system for the flood runoff.

• Journal of Information Processing Systems
• /
• v.20 no.3
• /
• pp.375-390
• /
• 2024

Edge computing architecture has effectively alleviated the computing pressure on cloud platforms, reduced network bandwidth consumption, and improved the quality of service for user experience; however, it has also introduced new security issues. Existing anomaly detection methods in big data scenarios with cloud-edge computing collaboration face several challenges, such as sample imbalance, difficulty in dealing with complex network traffic attacks, and difficulty in effectively training large-scale data or overly complex deep-learning network models. A lightweight deep-learning model was proposed to address these challenges. First, normalization on the user side was used to preprocess the traffic data. On the edge side, a trained Wasserstein generative adversarial network (WGAN) was used to supplement the data samples, which effectively alleviates the imbalance issue of a few types of samples while occupying a small amount of edge-computing resources. Finally, a trained lightweight deep learning network model is deployed on the edge side, and the preprocessed and expanded local data are used to fine-tune the trained model. This ensures that the data of each edge node are more consistent with the local characteristics, effectively improving the system's detection ability. In the designed lightweight deep learning network model, two sets of convolutional pooling layers of convolutional neural networks (CNN) were used to extract spatial features. The bidirectional long short-term memory network (BiLSTM) was used to collect time sequence features, and the weight of traffic features was adjusted through the attention mechanism, improving the model's ability to identify abnormal traffic features. The proposed model was experimentally demonstrated using the NSL-KDD, UNSW-NB15, and CIC-ISD2018 datasets. The accuracies of the proposed model on the three datasets were as high as 0.974, 0.925, and 0.953, respectively, showing superior accuracy to other comparative models. The proposed lightweight deep learning network model has good application prospects for anomaly traffic detection in cloud-edge collaborative computing architectures.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.39 no.1
• /
• pp.63-71
• /
• 2019

The two-fluid model proposed by Herman and Prigogine is useful for analyzing macroscopic traffic flow in a network. The two-fluid model is used for analyzing a network through the relationship between the ratio of stopped vehicles and the average moving speed of the network, and the two-fluid model has also been applied in the urban transportation network where many signalized or unsignalized intersections existed. In general, the average travel speed and moving speed of a network decrease, and the ratio of stopped vehicles and low speed vehicles in network increase as the traffic demand increases. This study proposed the two-fluid model considering congested and uncongested traffic situations. The critical velocity and the weight factor for congested situation are calibrated by minimizing the root mean square error (RMSE). The critical speed of the Seoul network was about 34 kph, and the weight factor of the congestion on the network was about 0.61. In the proposed model, $R^2$ increased from 0.78 to 0.99 when compared to the existing model, suggesting that the proposed model can be applied in evaluating network performances or traffic signal operations.

• Journal of Environmental Impact Assessment
• /
• v.14 no.2
• /
• pp.55-62
• /
• 2005

This study applied the Neural Network and Fuzzy theory to show water-purity control and preventive measure in water quality forecasting of the future river. This study picked out NAJU and HAMPYUNG as the subject of investigation and used monthly the water quality and the outflow data of KWANGJU2, NAJU, YOUNGSANNPO and HAMPYUNG from 1995 to 1999 to forecast BOD, COD, T-N, T-P water density. The datum from 1995 to 1999 are used for study and that of 2000 are used for verification. To develop model of water quality forecasting, firstly, this research formed Neural Network model and divided Neural Network model into two case - the case of considering lag and not considering. And this study selected optimal Neural Network model through changing the number of hidden layer based on input layer(n) from n to 3n. Through forecasting result, the case without considering lag showed more precise simulated result. Accordingly, this study intended to compare, analyse that Fuzzy model using the method without considering lag with Neural Network model. As a result, this study found that the model without considering lag in Neural Network Network shows the most excellent outcome. Thus this study examined a forecasting accuracy, analyzed result and verified propriety through appling the method of water quality forecasting using Neural Network and Fuzzy Algorithms to the actual case.

• International Journal of Computer Science & Network Security
• /
• v.23 no.1
• /
• pp.153-163
• /
• 2023

This study is situated in the context of intelligent transport systems, where in-vehicle devices assist drivers to avoid accidents and therefore improve road safety. The vehicles present in a given area form an ad' hoc network of vehicles called vehicular ad' hoc network. In this type of network, the nodes are mobile vehicles and the messages exchanged are messages to warn about obstacles that may hinder the correct driving. Node mobilities make it impossible for inter-node communication to be end-to-end. Recognizing this characteristic has led to delay-tolerant vehicular networks. Embedded devices have small buffers (memory) to hold messages that a node needs to transmit when no other node is within its visibility range for transmission. The performance of a vehicular delay-tolerant network is closely tied to the successful management of the nodes' transit buffer. In this paper, we propose a message transit buffer management model for nodes in vehicular delay tolerant networks. This model consists in setting up, on the one hand, a policy of dropping messages from the buffer when the buffer is full and must receive a new message. This drop policy is based on the concept of intermediate node to destination, queues and priority class of service. It is also based on the properties of the message (size, weight, number of hops, number of replications, remaining time-to-live, etc.). On the other hand, the model defines the policy for selecting the message to be transmitted. The proposed model was evaluated with the ONE opportunistic network simulator based on a 4000m x 4000m area of downtown Bouaké in Côte d'Ivoire. The map data were imported using the Open Street Map tool. The results obtained show that our model improves the delivery ratio of security alert messages, reduces their delivery delay and network overload compared to the existing model. This improvement in communication within a network of vehicles can contribute to the improvement of road safety.

• Proceedings of the Korean Society of Soil and Groundwater Environment Conference
• /
• 2003.09a
• /
• pp.543-547
• /
• 2003

We applied the modified invasion percolation (MIP) model to the migration of DNAPL within a two-dimensional random fracture network. The MIP model was verified against laboratory experiments, which was conducted using a two-dimensional random fracture network model. The results showed that the MIP needs modification. To remove TCE trapped in a random fracture network, the density-surfactant-motivated removal method was applied and found very effective to remove TCE from dead-end fractures.

• Journal of Environmental Science International
• /
• v.9 no.6
• /
• pp.455-462
• /
• 2000

This study aims at the development of the model for a forecasting of water quality in river basins using artificial neural network technique. Water quality by Artificial Neural Network Model forecasted and compared with observed values at the Sangju q and Dalsung stations in Nakdong river basin. For it, a multi-layer neural network was constructed to forecast river water quality. The neural network learns continuous-valued input and output data. Input data was selected as BOD, CO discharge and precipitation. As a result, it showed that method III of three methods was suitable more han other methods by statistical test(ME, MSE, Bias and VER). Therefore, it showed that Artificial Neural Network Model was suitable for forecasting river water quality.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.10
• /
• pp.1451-1457
• /
• 2013

Recently, new concept of energy systems such as microgrid, smart grid, supergrid, and energy network has been introducing. In this paper, the concept of the centralized micro-energy network, which is an energy community of a building group without district heating system, is introduced. In addition, a mathematical model for optimal operation of the micro-energy network as a main function of an energy management system (EMS) for the micro-energy network is proposed. In order to show the validation, the proposed model is tested through the simulation and analyzed.