• 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.

• 한국정보전자통신기술학회논문지
• /
• 제6권4호
• /
• pp.243-248
• /
• 2013

In this thesis, we have designed the indirect adaptive controller using Dynamic Neural Units(DNU) for unknown nonlinear systems. Proposed indirect adaptive controller using Dynamic Neural Unit based upon the topology of a reverberating circuit in a neuronal pool of the central nervous system. In this thesis, we present a genetic DNU-control scheme for unknown nonlinear systems. Our method is different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its training.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 추계학술대회 논문집
• /
• pp.538-541
• /
• 1995

Joint flexibilities and frictional uncertainties are known to be a major cause of performance degration in motion control systems. This paper investigates the modeling and compensation of these undesired effects. A hybrid controller, which consists of a predictive controller and a neural network controller, is designed to overcome these undesired effects. Also learning scheme for friction uncertainies, which don't interfere with feedback controller dynamics, is discussed. Through simulation works with two inetia-torsional spring system having Coulomb friction, the effectiveness of the proposed hybrid controller was tested. The proposed predictive & neural network hybrid controller shows better performance over one when only predictive controller used.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2006년도 춘계학술발표논문집
• /
• pp.311-315
• /
• 2006

"Dynamic Neural Unit"(DNU) based upon the topology of a reverberating circuit in a neuronal pool of the central nervous system. In this thesis, we present a genetic DNU-control scheme for unknown nonlinear systems. Our methodis different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its trainin

• 대한전기학회논문지
• /
• 제43권6호
• /
• pp.1027-1035
• /
• 1994

This paper aims to make an artificial arm control strategy. For this, we propose a new feature extraction method and design artificial neural network for the functional classification of myoelectric signal(MES). We first transform the two channel myoelectric signals (MES) for biceps and triceps into frequency domain using fast Fourier transform (FFT). And features were obtained by comparing the magnitudes of ensemble spectrum data and used as inputs to the three-layer neural network for the learning. By changing the number of units in hidden layer of neural network we observed the improvement of classification performance. To observe the effeciency of the proposed scheme we performed experiments for classification of six arm functions to the three subjects. And we obtained on average 94[%] the ratio of classification.

• 한국정밀공학회지
• /
• 제21권5호
• /
• pp.55-63
• /
• 2004

This paper presents neural network based controller using the feedback error loaming technique for a heavy load pointing system. Also the mathematical model was developed to analyze heavy load pointing system. The control scheme consists of a feedforward neural network controller and a fixed-gain feedback controller. This neural network controller is trained so as to make the output of the feedback controller zero. The proposed controller is compared with the conventional PI controller through simulations, and the results show that the pointing accuracy of the proposed control system are improved against the disturbance induced by vehicle running on the bump course.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2007년도 추계학술발표논문집
• /
• pp.81-84
• /
• 2007

In this thesis, we have designed the indirect adaptive controller using Dynamic Neural Units(DNU) for unknown nonlinear systems. Proposed indirect adaptive controller using Dynamic Neural Unit based upon the topology of a reverberating circuit in a neuronal pool of the central nervous system. In this thesis, we present a genetic DNU-control scheme for unknown nonlinear systems. Our method is different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its training.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.492-495
• /
• 2003

Fuzzy Min-Max Neural Network(FMMNN) is a powerful classifier, It has, however, some problems. Learning result depends on the presentation order of input data and the training parameter that limits the size of hyperbox. The latter problem affects the result seriously. In this paper, the new approach to alleviate that without loss of on-line learning ability is proposed. The committee machine is used to achieve the multi-resolution FMMNN. Each expert is a FMMNN with fixed training parameter. The advantages of small and large training parameters are used at the same time. The parameters are selected by performance and independence measures. The Decision of each expert is guided by the gating network. Therefore the regional and parametric divide and conquer scheme are used. Simulation shows that the proposed method has better classification performance.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1995년도 추계학술대회 논문집 학회본부
• /
• pp.161-164
• /
• 1995

This paper introduces an identification model called the Dynamic Neural Network(DNN) with a multilayer neural network in the forward path and a linear dynamical system in the feedback path, and defines Dynamic BackPropagation(DBP) as a learning algorithm for it. This identification model uses the feedback of its own output as a learning signal, which is not affected by a noise added to the output terminal of the plant so, it can be considered as a parallel identification model, and when compared with a series-parallel model which does not use the concept of the feedback, the proposed identification scheme exhibits more robust performance.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 하계학술대회 논문집 C
• /
• pp.1876-1878
• /
• 2003

The recognition of PD(Partial Discharge) phenomenon is useful for classification of defects. The distribution of stochastic parameters which consisted of those PD pulses data and pulses train can show discriminable characteristics of PD sources. But it is not sufficient to discriminate among to PD sources. In this paper, we suggests that classification method of PD source by NN(Neural Networks) are good tools for differentiate of those. The learning scheme of NN is (Back Propagation learning algorithm(BP).