• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.9
• /
• pp.820-827
• /
• 2014

One of the basic problems in Wireless Sensor Networks (WSNs) is the localization of the sensor nodes based on the known location of numerous anchor nodes. WSNs generally consist of a large number of sensor nodes and recording the location of each sensor nodes becomes a difficult task. On the other hand, based on the application environment, the nodes may be subject to mobility and their location changes with time. Therefore, a scheme that will autonomously estimate or calculate the position of the sensor nodes is desirable. This paper presents an intelligent localization scheme, which is an artificial neural network (ANN) based localization scheme used to estimate the position of the unknown nodes. In the proposed method, three anchors nodes are used. The mobile or deployed sensor nodes request a beacon from the anchor nodes and utilizes the received signal strength indicator (RSSI) of the beacons received. The RSSI values vary depending on the distance between the mobile and the anchor nodes. The three RSSI values are used as the input to the ANN in order to estimate the location of the sensor nodes. A feed-forward artificial neural network with back propagation method for training has been employed. An average Euclidian distance error of 0.70 m has been achieved using a ANN having 3 inputs, two hidden layers, and two outputs (x and y coordinates of the position).

• Smart Structures and Systems
• /
• v.12 no.5
• /
• pp.501-521
• /
• 2013

This paper is concerned with static and dynamic shape control of a laminated Bernoulli-Euler beam hosting a uniformly distributed array of resistively interconnected piezoelectric patches. We present an analytical one-dimensional model for a laminated piezoelectric beam with material discontinuities within the framework of Bernoulli-Euler and extent the model by a network of resistors which are connected to several piezoelectric patch actuators. The voltage of only one piezoelectric patch is prescribed: we answer the question how to design the interconnected resistive electric network in order to annihilate lateral vibrations of a cantilever. As a practical example, a cantilever with eight patch actuators under the influence of a tip-force is studied. It is found that the deflection at eight arbitrary points along the beam axis may be controlled independently, if the local action of the piezoelectric patches is equal in magnitude, but opposite in sign, to the external load. This is achieved by the proper design of the resistive network and a suitable choice of the input voltage signal. The validity of our method is exact in the static case for a Bernoulli-Euler beam, but it also gives satisfactory results at higher frequencies and for transient excitations. As long as a certain non-dimensional parameter, involving the number of the piezoelectric patches, the sum of the resistances in the electric network and the excitation frequency, is small, the proposed shape control method is approximately fulfilled for dynamic load excitations. We evaluate the feasibility of the proposed shape control method with a more refined model, by comparing the results of our one-dimensional calculations based on the extended Bernoulli-Euler equations to three-dimensional electromechanically coupled finite element results in ANSYS 12.0. The results with the simple Bernoulli-Euler model agree well with the three-dimensional finite element results.

• Steel and Composite Structures
• /
• v.27 no.4
• /
• pp.427-438
• /
• 2018

In this paper, the single and multi-objective optimization of thin-walled conical tubes with different types of indentations under axial impact has been investigated using surrogate models called metamodels. The geometry of tapered thin-walled tubes has been studied in order to achieve maximum specific energy absorption (SEA) and minimum peak crushing force (PCF). The height, radius, thickness, tapered angle of the tube, and the radius of indentation have been considered as design variables. Based on the design of experiments (DOE) method, the generated sample points are computed using the explicit finite element code. Different surrogate models including Kriging, Feed Forward Neural Network (FNN), Radial Basis Neural Network (RNN), and Response Surface Modelling (RSM) comprised to evaluate the appropriation of such models. The comparison study between surrogate models and the exploration of indentation shapes have been provided. The obtained results show that the RNN method has the minimum mean squared error (MSE) in training points compared to the other methods. Meanwhile, optimization based on surrogate models with lower values of MSE does not provide optimum results. The RNN method demonstrates a lower crashworthiness performance (with a lower value of 125.7% for SEA and a higher value of 56.8% for PCF) in comparison to RSM with an error order of $10^{-3}$. The SEA values can be increased by 17.6% and PCF values can be decreased by 24.63% by different types of indentation. In a specific geometry, higher SEA and lower PCF require triangular and circular shapes of indentation, respectively.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.49 no.4
• /
• pp.9-17
• /
• 2012

In this paper, we show the memory effect of the high-power amplifiers for wied-band signals, present a compensation method for the nonlinearity combined with memory effect, and analyze its performance. For the modeling and the compensation of the nonlinear high-power amplifier with memory effect, we investigate the Volterra series model, the Wiener model, and the Hammerstein model. As a compensator scheme, we propose a digital feedforward technique. Compared to analog feed-forward scheme, the proposed scheme has better stability and adaptability to the environmental changes. It has a simpler structure than the conventional digital nonlinear compensation schemes. The result of computer simulations using ADS of the Agilent shows that spectral re-growth is suppressed by more than 20 dB, which amounts to at least 10 dB back-off. Considering the compensation performance, implementation complexity, and convergence rate, we could conclude the Wiener model is most suitable for the proposed scheme.

• Journal of the Korea Society of Computer and Information
• /
• v.4 no.3
• /
• pp.67-72
• /
• 1999

The neural network is a static network that consists of a number of layer: input layer, output layer and one or more hidden layer connected in a feed forward way. The popularity of neural network appear to be its ability of learning and approximation capability. The Elman Neural Network proposed the J. Elman. is a type of recurrent network. Is has the feedback links from hidden layer to context layer. So Elman Neural Network is the better performance than the neural network. In this paper. we propose the Modified Elman Neural Network. The structure of a MENN is based on the basic ENN. The recurrency of the network is due to the feedback links from the output layer and the hidden layer to the context layer. In order to certify the usefulness or the proposed method. the MENN apply to the multi target system. Simulation shows that the proposed MENN method is better performance than the multi layer neural network and ENN.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.2
• /
• pp.15-22
• /
• 2006

This paper presents a novel signal tracking algorithm for GNSS receivers using a MLE technique. In order to perform a robust signal tracking in severe signal environments, e.g., high dynamics for navigation vehicles or weak signals for indoor positioning, the MLE based signal tracking approach is adopted in the paper. With assuming white Gaussian additive noise, the cost function of MLE is expanded to the cost function of NLSE. Efficient and practical approach for Doppler frequency tracking by the MLE is derived based on the assumption of code-free signals, i.e., the cost function of the MLE for carrier Doppler tracking is used to derive a discriminator function to create error signals from incoming and reference signals. The use of the MLE method for carrier tracking makes it possible to generalize the MLE equation for arbitrary codes and modulation schemes. This is ideally suited for various GNSS signals with same structure of tracking module. This paper proposes two different types of MLE based tracking method, i.e., an iterative batch processing method and a non-iterative feed-forward processing method. The first method is derived without any limitation on time consumption, while the second method is proposed for a time limited case by using a 1st derivative of cost function, which is proportional to error signal from discriminators of conventional tracking methods. The second method can be implemented by a block diagram approach for tracking carrier phase, Doppler frequency and code phase with assuming no correlation of signal parameters. Finally, a state space form of FLL/PLL/DLL is adopted to the designed MLE based tracking algorithm for reducing noise on the estimated signal parameters.

• Journal of Power Electronics
• /
• v.16 no.1
• /
• pp.297-309
• /
• 2016

Grid-connected inverters (GCIs) with an LCL output filter have the ability of attenuating high-frequency (HF) switching ripples. However, by using only grid-current control, the system is prone to resonances if it is not properly damped, and the current distortion is amplified significantly under highly distorted grid conditions. This paper proposes a synchronous reference frame equivalent proportional-integral (SRF-EPI) controller in the αβ stationary frame using the parallel virtual resistance-based active damping (PVR-AD) strategy for grid-interfaced distributed generation (DG) systems to suppress LCL resonance. Although both a proportional-resonant (PR) controller in the αβ stationary frame and a PI controller in the dq synchronous frame achieve zero steady-state error, the amplitude- and phase-frequency characteristics differ greatly from each other except for the reference tracking at the fundamental frequency. Therefore, an accurate SRF-EPI controller in the αβ stationary frame is established to achieve precise tracking accuracy. Moreover, the robustness, the harmonic rejection capability, and the influence of the control delay are investigated by the Nyquist stability criterion when the PVR-based AD method is adopted. Furthermore, grid voltage feed-forward and multiple PR controllers are integrated into the current loop to mitigate the current distortion introduced by the grid background distortion. In addition, the parameters design guidelines are presented to show the effectiveness of the proposed strategy. Finally, simulation and experimental results are provided to validate the feasibility of the proposed control approach.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.11
• /
• pp.2162-2166
• /
• 2016

This paper describes the implementation of AUSV system for sonar image acquisition to survey the seabed. The system is controlled by Feed Forward PID algorithm on the vessel for bearing of the thrusters composed of motion sensor and DGPS which calculates the differences between the current location and the destination location for longitude and latitude based on GPS coordinates. As experimental results, the bearing control performance is good that the error distance from the destination positions are under 6m in total survey track of 1km. And the sonar image deviation of a object is under 12 pixels from the manned survey method, which the comparison with the total image quality is almost the same as the manned survey one. Thus the proposed AUSV system is a new method of system can be utilized at the limited survey areas as the surveyor should not be able to approach on sea surface by onboard vessel.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.5
• /
• pp.3434-3439
• /
• 2015

As a criterion of information theoretic learning, the Euclidean distance (ED) of two error probability distribution functions (minimum ED of error, MEDE) has been adopted in nonlinear (decision feedback, DF) supervised equalizer algorithms and has shown significantly improved performance in severe channel distortion and impulsive noise environments. However, the MEDE-DF algorithm has the problem of heavy computational complexity. In this paper, the recursive ED for MEDE-DF algorithm is derived first, and then the feed-forward and feedback section gradients for weight update are estimated recursively. To prove the effectiveness of the recursive gradient estimation for the MEDE-DF algorithm, the number of multiplications are compared and MSE performance in impulsive noise and underwater communication environments is compared through computer simulation. The ratio of the number of multiplications between the proposed DF and the conventional MEDE-DF algorithm is revealed to be $2(9N+4):2(3N^2+3N)$ for the sample size N with the same MSE learning performance in the impulsive noise and underwater channel environment.

• KIISE Transactions on Computing Practices
• /
• v.21 no.4
• /
• pp.338-342
• /
• 2015

Recurrent Neural Network (RNN), a machine learning model which can handle time-series data, can possess more varied structures than a feed-forward neural network, since a RNN allows hidden-to-hidden connections. This research focuses on the network structure among hidden neurons, and discusses the information processing capability of RNN. Time-series learning potential and dynamics of RNNs are investigated upon several well-established network structure models. Hidden neuron network structure is found to have significant impact on the performance of a model, and the performance variations are generally correlated with the criticality of the network dynamics. Especially Preferential Attachment Network model showed an interesting behavior. These findings provide clues for performance improvement of the RNN.