• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.635-639
• /
• 2004

In this paper, we present a novel approach for the structure of Fuzzy Neural Network(FNN) based on wavelet function and apply this network structure to the modeling of chaotic nonlinear systems. Generally, the wavelet fuzzy model(WFM) has the advantage of the wavelet transform by constituting the fuzzy basis function(FBF) and the conclusion part to equalize the linear combination of FBF with the linear combination of wavelet functions. However, it is very difficult to identify the fuzzy rules and to tune the membership functions of the fuzzy reasoning mechanism. Neural networks, on the other hand, utilize their learning capability for automatic identification and tuning. Therefore, we design a wavelet based FNN structure(WFNN) that merges these advantages of neural network, fuzzy model and wavelet transform. The basic idea of our wavelet based FNN is to realize the process of fuzzy reasoning of wavelet fuzzy system by the structure of a neural network and to make the parameters of fuzzy reasoning be expressed by the connection weights of a neural network. And our network can automatically identify the fuzzy rules by modifying the connection weights of the networks via the gradient descent scheme. To verify the efficiency of our network structure, we evaluate the modeling performance for chaotic nonlinear systems and compare it with those of the FNN and the WFM.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제4권1호
• /
• pp.111-118
• /
• 2004

In this paper, we present a novel approach for the structure of Fuzzy Neural Network(FNN) based on wavelet function and apply this network structure to the solution of the tracking problem for mobile robots. Generally, the wavelet fuzzy model(WFM) has the advantage of the wavelet transform by constituting the fuzzy basis function(FBF) and the conclusion part to equalize the linear combination of FBF with the linear combination of wavelet functions. However, it is very difficult to identify the fuzzy rules and to tune the membership functions of the fuzzy reasoning mechanism. Neural networks, on the other hand, utilize their learning capability for automatic identification and tuning. Therefore, we design a wavelet based FNN structure(WFNN) that merges these advantages of neural network, fuzzy model and wavelet transform. The basic idea of our wavelet based FNN is to realize the process of fuzzy reasoning of wavelet fuzzy system by the structure of a neural network and to make the parameters of fuzzy reasoning be expressed by the connection weights of a neural network. And our network can automatically identify the fuzzy rules by modifying the connection weights of the networks via the gradient descent scheme. To verify the efficiency of our network structure, we evaluate the tracking performance for mobile robot and compare it with those of the FNN and the WFM.

• 정보처리학회논문지C
• /
• 제15C권6호
• /
• pp.557-566
• /
• 2008

차세대네트워크(Next Generation Network, NGN)은 하부의 전송 매체와 상관없이 데이터 전송의 품질을 보장하는 광대역망으로 NGN에서 주요 서비스로 대두되고 있는 실시간 방송 서비스 등은 멀티캐스트 기법을 필요로 하고 있다. 그러나 기존의 IP 멀티캐스트는 실제로 적용되기에는 많은 제약점을 지니고 있다. 이를 해결하기 위한 오버레이 멀티캐스트는 IP 멀티캐스트를 대신해 유연성과 확장성을 제공하여 효과적인 멀티미디어 멀티캐스트 전송을 가능하게 하는 기술로 활발히 연구 중에 있는 가상 네트워크다. 본 연구에서는 각 수신자가 속해있는 목적지 네트워크에 에이전트를, 미디어 서버가 위치한 소스 네트워크에는 전체 오버레이 멀티캐스트 토폴로지를 관리하는 매니저를 설계하였다. 매니저와 에이전트는 서로 통신하면서 네트워크의 자원 상태를 기반으로 한 서비스 제공을 수행하는 역할을 담당한다. 이렇게 함으로써 NGN 환경에서 QoS를 보장하는 멀티캐스트 환경을 제공할 수 있으며 이는 NGN 구조의 품질관리 기능인 RACF(Resource and Admission Control Functions)를 기반으로 한다.

• 한국컴퓨터그래픽스학회논문지
• /
• 제17권4호
• /
• pp.23-30
• /
• 2011

본 논문에서는 시내 상황을 반영한 교통 시뮬레이션을 위한 띠(ribbon)형 도로 네트워크를 형성하고, 에너지 함수를 이용하여 대용량의 차량 객체들의 움직임을 사실적으로 재현하는 실시간 시뮬레이션 방법을 제안한다. 본 연구에서 제안하는 방법으로 GIS (Geographic Information System)의 지도정보 혹은 임의 생성된 지도 모델을 이용하여 도로 네트워크 모델을 기존의 연구보다 적은 오차로 효율적으로 구성할 수 있다. 차량 객체들의 움직임을 사실적으로 재현하기 위하여, 본 논문은 새로운 객체-환경 상호작용 에너지 함수와 객체-객체 상호작용 에너지 함수를 제안한다. 본 논문에서 제안하는 상호작용 에너지와 효율적인 도로 네트워크 구성법으로 교차로 및 진입로 등과 같은 대부분의 교통 상황을 사실적으로 실시간 시뮬레이션 할 수 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권8호
• /
• pp.4043-4060
• /
• 2017

Network Intrusion Detection (NID), an important topic in the field of information security, can be viewed as a pattern recognition problem. The existing pattern recognition methods can achieve a good performance when the number of training samples is large enough. However, modern network attacks are diverse and constantly updated, and the training samples have much smaller size. Furthermore, to improve the learning ability of SVM, the research of kernel functions mainly focus on the selection, construction and improvement of kernel functions. Nonetheless, in practice, there are no theories to solve the problem of the construction of kernel functions perfectly. In this paper, we effectively integrate the advantages of the radial basis function kernel and the polynomial kernel on the notion of the game theory and propose a novel kernel SVM algorithm with game theory for NID, called GTNID-SVM. The basic idea is to exploit the game theory in NID to get a SVM classifier with better learning ability and generalization performance. To the best of our knowledge, GTNID-SVM is the first algorithm that studies ensemble kernel function with game theory in NID. We conduct empirical studies on the DARPA dataset, and the results demonstrate that the proposed approach is feasible and more effective.

• 인터넷정보학회논문지
• /
• 제22권5호
• /
• pp.27-33
• /
• 2021

With the broad adoption of the Internet of Things (IoT) in a variety of scenarios and application services, management and orchestration entities require upgrading the traditional architecture and develop intelligent models with ultra-reliable methods. In a heterogeneous network environment, mission-critical IoT applications are significant to consider. With erroneous priorities and high failure rates, catastrophic losses in terms of human lives, great business assets, and privacy leakage will occur in emergent scenarios. In this paper, an efficient resource slicing scheme for optimizing federated learning in software-defined IoT (SDIoT) is proposed. The decentralized support vector regression (SVR) based controllers predict the IoT slices via packet inspection data during peak hour central congestion to achieve a time-sensitive condition. In off-peak hour intervals, a centralized deep neural networks (DNN) model is used within computation-intensive aspects on fine-grained slicing and remodified decentralized controller outputs. With known slice and prioritization, federated learning communications iteratively process through the adjusted resources by virtual network functions forwarding graph (VNFFG) descriptor set up in software-defined networking (SDN) and network functions virtualization (NFV) enabled architecture. To demonstrate the theoretical approach, Mininet emulator was conducted to evaluate between reference and proposed schemes by capturing the key Quality of Service (QoS) performance metrics.

• Journal of Multimedia Information System
• /
• 제9권1호
• /
• pp.21-32
• /
• 2022

Early-stage diagnosis of Alzheimer's Disease (AD) from Cognitively Normal (CN) patients is crucial because treatment at an early stage of AD can prevent further progress in the AD's severity in the future. Recently, computer-aided diagnosis using magnetic resonance image (MRI) has shown better performance in the classification of AD. However, these methods use a traditional machine learning algorithm that requires supervision and uses a combination of many complicated processes. In recent research, the performance of deep neural networks has outperformed the traditional machine learning algorithms. The ability to learn from the data and extract features on its own makes the neural networks less prone to errors. In this paper, a dense neural network is designed for binary classification of Alzheimer's disease. To create a classifier with better results, we studied result of different activation functions in the prediction. We obtained results from 5-folds validations with combinations of different activation functions and compared with each other, and the one with the best validation score is used to classify the test data. In this experiment, features used to train the model are obtained from the ADNI database after processing them using FreeSurfer software. For 5-folds validation, two groups: AD and CN are classified. The proposed DNN obtained better accuracy than the traditional machine learning algorithms and the compared previous studies for AD vs. CN, AD vs. Mild Cognitive Impairment (MCI), and MCI vs. CN classifications, respectively. This neural network is robust and better.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1586-1589
• /
• 2005

GUMF (Global User Management Framework) that is proposed in this research can be applied to next generation network such as BcN (Broadband convergence Network), it is QoS guaranteed security framework for user that can solve present Internet's security vulnerability. GUMF offers anonymity for user of service and use the user's real-name or ID for management of service and it is technology that can realize secure QoS. GUMF needs management framework, UMS (User Management System), VNC (Virtual Network Controller) etc. UMS consists of root UMS in country dimension and Local UMS in each site dimension. VNC is network security equipment including VPN, QoS and security functions etc., and it achieves the QoSS (Quality of Security Service) and CLS(Communication Level Switching) functions. GUMF can offer safety in bandwidth consumption attacks such as worm propagation and DoS/DDoS, IP spoofing attack, and current most attack such as abusing of private information because it can offer the different QoS guaranteed network according to user's grades. User's grades are divided by 4 levels from Level 0 to Level 3, and user's security service level is decided according to level of the private information. Level 3 users that offer bio-information can receive secure network service that privacy is guaranteed. Therefore, GUMF that is proposed in this research can offer profit model to ISP and NSP, and can be utilized by strategy for secure u-Korea realization.

• International Journal of Computer Science & Network Security
• /
• 제23권12호
• /
• pp.13-26
• /
• 2023

Recently, the development of wireless network technologies has been advancing in several directions: increasing data transmission speed, enhancing user mobility, expanding the range of services offered, improving the utilization of the radio frequency spectrum, and enhancing the intelligence of network and subscriber equipment. In this research, a series of contradictions has emerged in the field of wireless network technologies, with the most acute being the contradiction between the growing demand for wireless communication services (on operational frequencies) and natural limitations of frequency resources, in addition to the contradiction between the expansions of the spectrum of services offered by wireless networks, increased quality requirements, and the use of traditional (outdated) management technologies. One effective method for resolving these contradictions is the application of artificial intelligence elements in wireless telecommunication systems. Thus, the development of technologies for building intelligent (cognitive) radio and cognitive wireless networks is a technological imperative of our time. The functions of artificial intelligence in prospective wireless systems and networks can be implemented in various ways. One of the modern approaches to implementing artificial intelligence functions in cognitive wireless network systems is the application of fuzzy logic and fuzzy processors. In this regard, the work focused on exploring the application of fuzzy logic in prospective cognitive wireless systems is considered relevant.

• 한국농공학회논문집
• /
• 제63권1호
• /
• pp.103-116
• /
• 2021

Analysis of runoff is substantial for effective water management in the watershed. Runoff occurs by reaction of a watershed to the rainfall and has non-linearity and uncertainty due to the complex relation of weather and watershed factors. ANN (Artificial Neural Network), which learns from the data, is one of the machine learning technique known as a proper model to interpret non-linear data. The performance of ANN is affected by the ANN's structure, the number of hidden layer nodes, learning rate, and activation function. Especially, the activation function has a role to deliver the information entered and decides the way of making output. Therefore, It is important to apply appropriate activation functions according to the problem to solve. In this paper, ANN models were constructed to estimate runoff with different activation functions and each model was compared and evaluated. Sigmoid, Hyperbolic tangent, ReLU (Rectified Linear Unit), ELU (Exponential Linear Unit) functions were applied to the hidden layer, and Identity, ReLU, Softplus functions applied to the output layer. The statistical parameters including coefficient of determination, NSE (Nash and Sutcliffe Efficiency), NSEln (modified NSE), and PBIAS (Percent BIAS) were utilized to evaluate the ANN models. From the result, applications of Hyperbolic tangent function and ELU function to the hidden layer and Identity function to the output layer show competent performance rather than other functions which demonstrated the function selection in the ANN structure can affect the performance of ANN.