• Journal of Electrical Engineering and Technology
• /
• v.12 no.6
• /
• pp.2388-2398
• /
• 2017

In this study, we propose a robust face recognition system to pose variations based on automatic pose estimation. Radial basis function neural network is applied as one of the functional components of the overall face recognition system. The proposed system consists of preprocessing and recognition modules to provide a solution to pose variation and high-dimensional pattern recognition problems. In the preprocessing part, principal component analysis (PCA) and 2-dimensional 2-directional PCA ($(2D)^2$ PCA) are applied. These functional modules are useful in reducing dimensionality of the feature space. The proposed RBFNNs architecture consists of three functional modules such as condition, conclusion and inference phase realized in terms of fuzzy "if-then" rules. In the condition phase of fuzzy rules, the input space is partitioned with the use of fuzzy clustering realized by the Fuzzy C-Means (FCM) algorithm. In conclusion phase of rules, the connections (weights) are realized through four types of polynomials such as constant, linear, quadratic and modified quadratic. The coefficients of the RBFNNs model are obtained by fuzzy inference method constituting the inference phase of fuzzy rules. The essential design parameters (such as the number of nodes, and fuzzification coefficient) of the networks are optimized with the aid of Particle Swarm Optimization (PSO). Experimental results completed on standard face database -Honda/UCSD, Cambridge Head pose, and IC&CI databases demonstrate the effectiveness and efficiency of face recognition system compared with other studies.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.2
• /
• pp.399-406
• /
• 2009

In this study, Polynomial Radial Basis Function Neural Network(pRBFNN) based on Fuzzy Inference System is designed and its parameters such as learning rate, momentum coefficient, and distributed weight (width of RBF) are optimized by means of Particle Swarm Optimization. The proposed model can be expressed as three functional module that consists of condition part, conclusion part, and inference part in the viewpoint of fuzzy rule formed in 'If-then'. In the condition part of pRBFNN as a fuzzy rule, input space is partitioned by defining kernel functions (RBFs). Here, the structure of kernel functions, namely, RBF is generated from HCM clustering algorithm. We use Gaussian type and Inverse multiquadratic type as a RBF. Besides these types of RBF, Conic RBF is also proposed and used as a kernel function. Also, in order to reflect the characteristic of dataset when partitioning input space, we consider the width of RBF defined by standard deviation of dataset. In the conclusion part, the connection weights of pRBFNN are represented as a polynomial which is the extended structure of the general RBF neural network with constant as a connection weights. Finally, the output of model is decided by the fuzzy inference of the inference part of pRBFNN. In order to evaluate the proposed model, nonlinear function with 2 inputs, waster water dataset and gas furnace time series dataset are used and the results of pRBFNN are compared with some previous models. Approximation as well as generalization abilities are discussed with these results.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.56 no.4
• /
• pp.9-19
• /
• 2014

The objective of this study was to evaluate of the Tank model in simulating runoff discharge from rural watershed in comparison to the SWAT (Soil and Water Assessment Tool) model. The model parameters of SWAT was calibrated by the shuffled complex evolution-university Arizona (SCE-UA) method while Tank model was calibrated by genetic algorithm (GA) and validated. Four dam watersheds were selected as the study areas. Hydrological data of the Water Management Information System (WAMIS) and geological data were used as an input data for the model simulation. Runoff data were used for the model calibration and validation. The determination coefficient ($R^2$), root mean square error (RMSE), Nash-Sutcliffe efficiency index (NSE) were used to evaluate the model performances. The result indicated that both SWAT model and Tank model simulated runoff reasonably during calibration and validation period. For annual runoff, the Tank model tended to overestimate, especially for small runoff (< 0.2 mm) whereas SWAT model underestimate runoff as compared to observed data. The statistics indicated that the Tank model simulated runoff more accurately than the SWAT model. Therefore the Tank model could be a good tool for runoff simulation considering its ease of use.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.10 s.181
• /
• pp.2487-2495
• /
• 2000

The acoustic characteristics of expansion chamber will be changed with the variation of inlet/outlet location due to the higher order acoustic mode in a high frequency in which the plane wave theory is not available. In this paper, the acoustic performance of reactive type expansion chamber with circular cross-section is analyzed by using the modified mode matching theory. The sensitivity analysis of four-pole parameters with respect to the location of inlet and outlet is also suggested to increase the acoustic performance. The acoustic power transmission coefficient is used as cost function, and the location of inlet and outlet is used as design variables. The steepest descent method and SUMT algorithm are used for optimization technique. Several results showed that the expansion chamber with optimally located inlet/outlet had better acoustic performance than concentric expansion chamber.

• Advances in aircraft and spacecraft science
• /
• v.2 no.3
• /
• pp.329-343
• /
• 2015

This study aimed to observe the effect of a novel concept (referred to as the flap extension) implemented on the leading edge of the flap of a three element high lift device. The high lift device, consisting of a flap, main element and slat is designed around an Airbus research profile for sufficient take off and landing performance of a large commercial aircraft. The concept is realised on the profile and numerically optimised to achieve an optimum geometry. Two different optimisation approaches based on Genetic Algorithm optimisations are used: a zero order approach which makes simplifying assumptions to achieve an optimised solution: as well as a direct approach which employs an optimisation in ANSYS DesignXplorer using RANS calculations. Both methods converge to different optimised solutions due to simplifying assumptions. The solution to the zero order optimisation showed a decreased stall angle and decreased maximum lift coefficient against angle of attack due to early stall onset at the flap. The DesignXplorer optimised solution matched that of the baseline solution very closely. The concept was seen to increase lift locally at the flap for both optimisation methods.

• Earthquakes and Structures
• /
• v.16 no.4
• /
• pp.437-453
• /
• 2019

This study investigates a new optimal placement method for viscous dampers between structures in order to prevent pounding of adjacent structures with different dynamic characteristics under earthquake effects. A relative displacement spectrum is developed in two single degree of freedom system to reveal the critical period ratios for the most risky scenario of collision using El Centro earthquake record (NS). Three different types of viscous damper design, which are classical, stair and X-diagonal model, are considered to prevent pounding on two adjacent building models. The objective function is minimized under the upper and lower limits of the damping coefficient of the damper and a target modal damping ratio. A new algorithm including time history analyses and numerical optimization methods is proposed to find the optimal dampers placement. The proposed design method is tested on two 12-storey adjacent building models. The effects of the type of damper placement on structural models, the critical period ratios of adjacent structures, the permissible relative displacement limit, the mode behavior and the upper limit of damper are investigated in detail. The results of the analyzes show that the proposed method can be used as an effective means of finding the optimum amount and location of the dampers and eliminating the risk of pounding.

• Computers and Concrete
• /
• v.27 no.5
• /
• pp.489-512
• /
• 2021

In this study, two powerful techniques, namely particle swarm optimization (PSO) and imperialist competitive algorithm (ICA) were selected and combined with a pre-developed ANN model aiming at improving its performance prediction of the compressive strength of concrete modified with fly ash. To achieve this study's aims, a comprehensive database with 379 data samples was collected from the available literature. The output of the database is the compressive strength (CS) of concrete samples, which are influenced by 9 parameters as model inputs, namely those related to mix composition. The modeling steps related to ICA-ANN (or neuro-imperialism) and PSO-ANN (or neuro-swarm) were conducted through the use of several parametric studies to design the most influential parameters on these hybrid models. A comparison of the CS values predicted by hybrid intelligence techniques with the experimental CS values confirmed that the neuro-swarm model could provide a higher degree of accuracy than another proposed hybrid model (i.e., neuro-imperialism). The train and test correlation coefficient values of (0.9042 and 0.9137) and (0.8383 and 0.8777) for neuro-swarm and neuro-imperialism models, respectively revealed that although both techniques are capable enough in prediction tasks, the developed neuro-swarm model can be considered as a better alternative technique in mapping the concrete strength behavior.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.8
• /
• pp.2587-2605
• /
• 2022

In order to efficiently detect community structure in complex networks, community detection algorithms can be designed from the perspective of node similarity. However, the appropriate parameters should be chosen to achieve community division, furthermore, these existing algorithms based on the similarity of common neighbors have low discrimination between node pairs. To solve the above problems, a noval community detection algorithm using closeness similarity based on common neighbor node clustering entropy is proposed, shorted as CSCDA. Firstly, to improve detection accuracy, common neighbors and clustering coefficient are combined in the form of entropy, then a new closeness similarity measure is proposed. Through the designed similarity measure, the closeness similar node set of each node can be further accurately identified. Secondly, to reduce the randomness of the community detection result, based on the closeness similar node set, the node leadership is used to determine the most closeness similar first-order neighbor node for merging to create the initial communities. Thirdly, for the difficult problem of parameter selection in existing algorithms, the merging of two levels is used to iteratively detect the final communities with the idea of modularity optimization. Finally, experiments show that the normalized mutual information values are increased by an average of 8.06% and 5.94% on two scales of synthetic networks and real-world networks with real communities, and modularity is increased by an average of 0.80% on the real-world networks without real communities.

• Computers and Concrete
• /
• v.33 no.1
• /
• pp.1-11
• /
• 2024

Aggressive environmental conditions, and especially the acidic effects of sulfate ion penetration, have reduced the lifetime of concrete structures in some areas, especially coastal and marine areas. In this research, at first, samples made of type II and V cement were kept in a solution of magnesium sulfate (MgSO₄) for a period of 90 and 180 days, the change of appearance. Field Emission Scanning Electron Microscopy (FE-SEM) and X-Ray Diffraction (XRD), were used to analyze the microstructure and the complex mineral composition of the concrete after exposure to corrosive environments. Then solving the differential equation governing the sulfate ion penetration, which is based on the second Fick law, it has been tried to determine the concentration of sulfate ions inside the concrete. In the following, an attempt has been made to improve the prediction of sulfate ion concentration in concrete by using Crank's penetration equation. At the same time, the coefficient in the Crank's solution have been optimized by using the Particle Swarm Optimization (PSO algorithm). The comparison between the results shows that the values obtained from Crank's relation are closer to the experimental results than the equation obtained from Fick's second law and shows a more accurate prediction.

• Journal of Korean Association for Spatial Structures
• /
• v.24 no.2
• /
• pp.83-90
• /
• 2024

Machine learning is widely applied to various engineering fields. In structural engineering area, machine learning is generally used to predict structural responses of building structures. The aging deterioration of reinforced concrete structure affects its structural behavior. Therefore, the aging deterioration of R.C. structure should be consider to exactly predict seismic responses of the structure. In this study, the machine learning based seismic response prediction model was developed. To this end, four machine learning algorithms were employed and prediction performance of each algorithm was compared. A 3-story coupled shear wall structure was selected as an example structure for numerical simulation. Artificial ground motions were generated based on domestic site characteristics. Elastic modulus, damping ratio and density were changed to considering concrete degradation due to chloride penetration and carbonation, etc. Various intensity measures were used input parameters of the training database. Performance evaluation was performed using metrics like root mean square error, mean square error, mean absolute error, and coefficient of determination. The optimization of hyperparameters was achieved through k-fold cross-validation and grid search techniques. The analysis results show that neural networks and extreme gradient boosting algorithms present good prediction performance.