• Wind and Structures
• /
• v.38 no.1
• /
• pp.75-91
• /
• 2024

Reliable wind signal reconstruction can be beneficial to the operational safety of long-span bridges. Non-Gaussian characteristics of wind signals make the reconstruction process challenging. In this paper, non-Gaussian wind signals are converted into a combined prediction of two kinds of features, actual wind speeds and wind angles of attack. First, two decomposition techniques, empirical mode decomposition (EMD) and variational mode decomposition (VMD), are introduced to decompose wind signals into intrinsic mode functions (IMFs) to reduce the randomness of wind signals. Their principles and applicability are also discussed. Then, four artificial intelligence (AI) algorithms are utilized for wind signal reconstruction by combining the particle swarm optimization (PSO) algorithm with back propagation neural network (BPNN), support vector regression (SVR), long short-term memory (LSTM) and bidirectional long short-term memory (Bi-LSTM), respectively. Measured wind signals from a bridge site in a deep-cutting gorge are taken as experimental subjects. The results showed that the reconstruction error of high-frequency components of EMD is too large. On the contrary, VMD fully extracts the multiscale rules of the signal, reduces the component complexity. The combination of VMD-PSO-Bi-LSTM is demonstrated to be the most effective among all hybrid models.

• ETRI Journal
• /
• v.44 no.5
• /
• pp.805-815
• /
• 2022

The model-based evolutionary algorithms are divided into three groups: estimation of distribution algorithms, inverse modeling, and surrogate modeling. Existing inverse modeling is mainly applied to solve multi-objective optimization problems and is not suitable for many-objective optimization problems. Some inversed-model techniques, such as the inversed-model of multi-objective evolutionary algorithm, constructed from the Pareto front (PF) to the Pareto solution on nondominated solutions using a random grouping method and Gaussian process, were introduced. However, some of the most efficient inverse models might be eliminated during this procedure. Also, there are challenges, such as the presence of many local PFs and developing poor solutions when the population has no evident regularity. This paper proposes inverse modeling using random forest regression and uniform reference points that map all nondominated solutions from the objective space to the decision space to solve many-objective optimization problems. The proposed algorithm is evaluated using the benchmark test suite for evolutionary algorithms. The results show an improvement in diversity and convergence performance (quality indicators).

• The Korean Journal of Applied Statistics
• /
• v.30 no.2
• /
• pp.243-257
• /
• 2017

In this paper, we compare several methods to approximate option prices: Edgeworth expansion, A-type and C-type Gram-Charlier expansions, a method using normal inverse gaussian (NIG) distribution, and an asymptotic method using nonlinear regression. We used two different types of approximation. The first (called the RNM method) approximates the risk neutral probability density function of the log return of the underlying asset and computes the option price. The second (called the OPTIM method) finds the approximate option pricing formula and then estimates parameters to compute the option price. For simulation experiments, we generated underlying asset data from the Heston model and NIG model, a well-known stochastic volatility model and a well-known Levy model, respectively. We also applied the above approximating methods to the KOSPI200 call option price as a real data application. We then found that the OPTIM method shows better performance on average than the RNM method. Among the OPTIM, A-type Gram-Charlier expansion and the asymptotic method that uses nonlinear regression showed relatively better performance; in addition, among RNM, the method of using NIG distribution was relatively better than others.

• The Korean Journal of Applied Statistics
• /
• v.29 no.1
• /
• pp.181-192
• /
• 2016

We consider several methods to approximate option prices with correction terms to the Black-Scholes option price. These methods are able to compute option prices from various risk-neutral distributions using relatively small data and simple computation. In this paper, we compare the performance of Edgeworth expansion, A-type and C-type Gram-Charlier expansions, a method of using Normal inverse gaussian distribution, and an asymptotic method of using nonlinear regression through simulation experiments and real KOSPI200 option data. We assume the variance gamma model in the simulation experiment, which has a closed-form solution for the option price among the pure jump $L{\acute{e}}vy$ processes. As a result, we found that methods to approximate an option price directly from the approximate price formula are better than methods to approximate option prices through the approximate risk-neutral density function. The method to approximate option prices by nonlinear regression showed relatively better performance among those compared.

• Structural Engineering and Mechanics
• /
• v.71 no.6
• /
• pp.739-749
• /
• 2019

This article deals with the application of reliability analysis for determining the safety of simply supported beam under the uniformly distributed load. The uncertainties of the existing methods were taken into account and hence reliability analysis has been adopted. To accomplish this aim, Generalized Regression Neural Network (GRNN), Extreme Learning Machine (ELM) and Gaussian Process Regression (GPR) models are developed. Reliability analysis is the probabilistic style to determine the possibility of failure free operation of a structure. The application of probabilistic mathematics into the quantitative aspects of a structure and improve the qualitative aspects of a structure. In order to construct the GRNN, ELM and GPR models, the dataset contains Modulus of Elasticity (E), Load intensity (w) and performance function (${\delta}$) in which E and w are inputs and ${\delta}$ is the output. The achievement of the developed models was weighed by various statistical parameters; one among the most primitive parameter is Coefficient of Determination ($R^2$) which has 0.998 for training and 0.989 for testing. The GRNN outperforms the other ELM and GPR models. Other different statistical computations have been carried out, which speaks out the errors and prediction performance in order to justify the capability of the developed models.

• Geomechanics and Engineering
• /
• v.31 no.3
• /
• pp.265-279
• /
• 2022

Tunnel convergence prediction is essential for the safe construction and design of tunnels. This study proposes five machine learning models of deep neural network (DNN), K-nearest neighbors (KNN), Gaussian process regression (GPR), support vector regression (SVR), and decision trees (DT) to predict the convergence phenomenon during or shortly after the excavation of tunnels. In this respect, a database including 650 datasets (440 for training, 110 for validation, and 100 for test) was gathered from the previously constructed tunnels. In the database, 12 effective parameters on the tunnel convergence and a target of tunnel wall convergence were considered. Both 5-fold and hold-out cross validation methods were used to analyze the predicted outcomes in the ML models. Finally, the DNN method was proposed as the most robust model. Also, to assess each parameter's contribution to the prediction problem, the backward selection method was used. The results showed that the highest and lowest impact parameters for tunnel convergence are tunnel depth and tunnel width, respectively.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.337-339
• /
• 2004

In this paper, we discuss optimal design of Fuzzy Polynomial Neural Networks by means of Genetic Algorithms(GAs). Proceeding the layer, this model creates the optimal network architecture through the selection and the elimination of nodes by itself. So, there is characteristic of flexibility. We use a triangle and a Gaussian-like membership function in premise part of rules and design the consequent structure by constant and regression polynomial (linear, quadratic and modified quadratic) function between input and output variables. GAs is applied to improve the performance with optimal input variables and number of input variables and order. To evaluate the performance of the GAs-based FPNNs, the models are experimented with the use of Medical Imaging System(MIS) data.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.15-15
• /
• 2000

In the past couple of years, there has been increasing interest in the fusion of neural networks and fuzzy logic. Most of the existing fused models have been proposed to implement different types of fuzzy reasoning mechanisms and inevitably they suffer from the dimensionality problem when dealing with complex real-world problem. To overcome the problem, we propose the self-organizing networks with activation nodes based on fuzzy inference and polynomial function. The proposed model consists of two parts, one is fuzzy nodes which each node is operated as a small fuzzy system with fuzzy implication rules, and its fuzzy system operates with Gaussian or triangular MF in Premise part and constant or regression polynomials in consequence part. the other is polynomial nodes which several types of high-order polynomials such as linear, quadratic, and cubic form are used and are connected as various kinds of multi-variable inputs. To demonstrate the effectiveness of the proposed method, time series data for gas furnace process has been applied.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.2977-2979
• /
• 2000

A Fuzzy Hybrid-Multilayer Perceptron (FH-MLP) Structure is proposed in this paper. proposed FH-MLP is not a fixed architecture. that is to say. the number of layers and the number of nodes in each layer of FH-MLP can be generated to adapt to the changing environment. FH-MLP consists of two parts. one is fuzzy nodes which each node is operated as a small fuzzy system with fuzzy implication rules. and its fuzzy system operates with Gaussian or Triangular membership functions in premise part and constants or regression polynomial equation in consequence part. the other is polynomial nodes which several types of high-order polynomial such as linear. quadratic. and cubic form are used and is connected as various kinds of multi-variable inputs. To demonstrate the effectiveness of the proposed method. time series data for gas furnace process has been applied.

• Proceedings of the KSPS conference
• /
• 2005.11a
• /
• pp.159-162
• /
• 2005

Identification is the process automatically identify who is speaking on the basis of information obtained from speech waves. In training phase, each speaker models are trained using each speaker's speech data. GMMs (Gaussian Mixture Models), which have been successfully applied to speaker modeling in text-independent speaker identification, are not efficient in insufficient training data environment. This paper proposes speaker modeling method using MLLR (Maximum Likelihood Linear Regression) method which is used for speaker adaptation in speech recognition. We make SD-like model using MLLR adaptation method instead of speaker dependent model (SD). Proposed system outperforms the GMMs in small training data environment.