• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.5
• /
• pp.552-559
• /
• 2005

Recurrent neural networks(RNNs) trained with gradient based such as real time recurrent learning(RTRL) has a drawback of slor convergence rate. This algorithm also needs the derivative calculation which is not trivialized in error back propagation process. In this paper a derivative free Kalman filter, so called the unscented Kalman filter(UKF), for training a fully connected RNN is presented in a state space formulation of the system. A derivative free Kalman filler learning algorithm makes the RNN have fast convergence speed and good tracking performance without the derivative computation. Through experiments of nonlinear channel equalization, performance of the RNNs with a derivative free Kalman filter teaming algorithm is evaluated.

• 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.

• Current Optics and Photonics
• /
• v.8 no.2
• /
• pp.127-137
• /
• 2024

The distribution of tags is an important factor that affects the performance of radio-frequency identification (RFID). To study RFID performance, it is necessary to obtain RFID tags' coordinates. However, the positioning method of RFID technology has large errors, and is easily affected by the environment. Therefore, a new method using optical measurement is proposed to achieve RFID performance analysis. First, due to the possibility of blurring during image acquisition, the paper derives a new image prior to removing blurring. A nonlocal means-based method for image deconvolution is proposed. Experimental results show that the PSNR and SSIM indicators of our algorithm are better than those of a learning deep convolutional neural network and fast total variation. Second, an RFID dynamic testing system based on photoelectric sensing technology is designed. The reading distance of RFID and the three-dimensional coordinates of the tags are obtained. Finally, deep learning is used to model the RFID reading distance and tag distribution. The error is 3.02%, which is better than other algorithms such as a particle-swarm optimization back-propagation neural network, an extreme learning machine, and a deep neural network. The paper proposes the use of optical methods to measure and collect RFID data, and to analyze and predict RFID performance. This provides a new method for testing RFID performance.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.22 no.1
• /
• pp.40-49
• /
• 2008

Interior permanent magnet synchronous motor(IPMSM) has become a popular choice in electric vehicle applications and so of due to their excellent power to weight ratio. To obtain maximum efficiency in these applications, this paper proposes the neural network control method. The controllable electrical loss which consists of the copper loss and the iron loss can be minimized by the error back propagation algorithm(EBPA) of neural network. The minimization of loss is possible to realize eHciency optimization control for the IPMSM drive. This paper proposes high performance and robust control through a real time calculation of parameter variation such as variation of back emf constant, armature resistance and d-axis inductance about the motor operation. Proposed algorithm is applied IPMSM drive system, prove validity through analysis operating characteristics con011ed by efficiency optimization control.

• Bulletin of the Korean Chemical Society
• /
• v.26 no.12
• /
• pp.2007-2016
• /
• 2005

An artificial neural network (ANN) is successfully presented for prediction acidity constant (pKa) of various benzoic acids and phenols with diverse chemical structures using a nonlinear quantitative structure-property relationship. A three-layered feed forward ANN with back-propagation of error was generated using six molecular descriptors appearing in the multi-parameter linear regression (MLR) model. The polarizability term $(\pi_1)$, most positive charge of acidic hydrogen atom $(q^+)$, molecular weight (MW), most negative charge of the acidic oxygen atom $(q^-)$, the hydrogen-bond accepting ability $(\epsilon_B)$ and partial charge weighted topological electronic (PCWTE) descriptors are inputs and its output is pKa. It was found that properly selected and trained neural network with 205 compounds could fairly represent dependence of the acidity constant on molecular descriptors. For evaluation of the predictive power of the generated ANN, an optimized network was applied for prediction pKa values of 37 compounds in the prediction set, which were not used in the optimization procedure. Squared correlation coefficient $(R^2)$ and root mean square error (RMSE) of 0.9147 and 0.9388 for prediction set by the MLR model should be compared with the values of 0.9939 and 0.2575 by the ANN model. These improvements are due to the fact that acidity constant of benzoic acids and phenols in water shows nonlinear correlations with the molecular descriptors.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.8
• /
• pp.137-146
• /
• 2011

In order to support increased consumer awareness regarding energy consumption, we present new ways of monitoring and predicting with energy in electric appliances. The proposed system is a design of a common electrical power outlet called smart plug that measures the amount of current passing through current sensor at 0.5 second. To acquire data for training and testing the proposed neural network, weather parameters used include average temperature of day, min and max temperature, humidity, and sunshine hour as input data, and power consumption as target data from smart plug. Using the experimental data for training, the neural network model based on Back-Propagation algorithm was developed. Multi layer perception network was used for nonlinear mapping between the input and the output data. It was observed that the proposed neural network model can predict the power consumption quite well with correlation coefficient was 0.9965, and prediction mean square error was 0.02033.

• Korean Journal of Food Science and Technology
• /
• v.27 no.4
• /
• pp.525-531
• /
• 1995

Three quality factors of bread during baking process were measured to develop neural network models for bread baking process. Firstly, volume and browning changes during bread baking process were measured using image processing technique and temperature changes inside the bread during process were measured by K-type thermocouples. Relationships among them showed nonlinearity. Secondly, multilayer perception structure with error back propagation learning was used to construct neural network models. Three neural network models for volume, browning, and bread temperature were developed respectively. Developed models showed good performance with predictive error of 4.62% for volume and browning changes after 30 seconds, 7.38% for volume and browning changes after 2 minutes, and 1.09% for temperature change inside the bread respectively.

• Journal of Ocean Engineering and Technology
• /
• v.18 no.6 s.61
• /
• pp.79-83
• /
• 2004

The curved blocks which compose the bow and stem of a ship contain many skewed joints that are inclined horizontally and vertically. Most of these joints have a large fitness error and are continuously changing their form and are not easily accessible. The welding position and parameter values should be appropriately set in correspondence to the shape and the inclination of the joints. The welding parameters such as current, voltage, travel speed, and melting rate, are related to each other and their values must be in a specific limited range for the sound welding. These correlations and the ranges are dependent up on the kind and size of wire, shielding gas, joint shape and fitness. To determine these relationships, extensive welding experiments were performed. The experimental data were processed using several information processing technologies. The regression method was used to determine the relationship between current voltage, and deposition rate. When a joint is inclined, the weld bead should be confined to a the limited size, inorder to avoid undercut as well as overlap due to flowing down of molten metal by gravity. The dependency of the limited weld size which is defined as the critical deposited area on various factors such as the horizontally and vertically inclined angle of the joint, skewed angle of the joint, up or down welding direction and weaving was investigated through a number of welding experiments. On the basis of this result, an ANN system was developed to estimate the critical deposited area. The ANN system consists of a 4 layer structure and uses an error back propagation learning algorithm. The estimated values of the ANN were validated using experimental values.

• Industry Promotion Research
• /
• v.6 no.1
• /
• pp.1-7
• /
• 2021

We investigated multi-layer perceptrons and supervised learning algorithms, and also examined how to model functional relationships between covariates and response variables using a package called neuralnet. The algorithm applied in this paper is characterized by continuous adjustment of the weights, which are parameters to minimize the error function based on the comparison between the actual and predicted values of the response variable. In the neuralnet package, the activation and error functions can be appropriately selected according to the given situation, and the remaining parameters can be set as default values. As a result of using the neuralnet package for the infertility data, we found that age has little influence on infertility among the four independent variables. In addition, the weight of the neural network takes various values from -751.6 to 7.25, and the intercepts of the first hidden layer are -92.6 and 7.25, and the weights for the covariates age, parity, induced, and spontaneous to the first hidden neuron are identified as 3.17, -5.20, -36.82, and -751.6.

• Advances in concrete construction
• /
• v.10 no.6
• /
• pp.479-488
• /
• 2020

The experimental and numerical works were carried out on high performance fiber reinforced concrete (HPFRC) with w/cm ratios ranging from 0.25 to 0.40, fiber volume fraction (Vf)=0-1.5% and 10% silica fume replacement. Improvements in compressive and flexural strengths obtained for HPFRC are moderate and significant, respectively, Empirical equations developed for the compressive strength and flexural strength of HPFRC as a function of fiber volume fraction. A relation between flexural strength and compressive strength of HPFRC with R=0.78 was developed. Due to the complex mix proportions and non-linear relationship between the mix proportions and properties, models with reliable predictive capabilities are not developed and also research on HPFRC was empirical. In this paper due to the inadequacy of present method, a back propagation-neural network (BP-NN) was employed to estimate the 28-day compressive strength of HPFRC mixes. BP-NN model was built to implement the highly non-linear relationship between the mix proportions and their properties. This paper describes the data sets collected, training of ANNs and comparison of the experimental results obtained for various mixtures. On statistical analyses of collected data, a multiple linear regression (MLR) model with R2=0.78 was developed for the prediction of compressive strength of HPFRC mixes, and average absolute error (AAE) obtained is 6.5%. On validation of the data sets by NNs, the error range was within 2% of the actual values. ANN model has given the significant degree of accuracy and reliability compared to the MLR model. ANN approach can be effectively used to estimate the 28-day compressive strength of fibrous concrete mixes and is practical.