• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.335-338
• /
• 2017

Currently Artificial Inteligence and Deep Learning are social issues, and These technologies are applied to various fields. A good method among the various algorithms in Artificial Inteligence is Convolutional Neural Network. Convolutional Neural Network is a form that adds convolution layers that extracts features by convolution operation on a general neural network method. If you use Convolutional Neural Network as small amount of data, or if the structure of layers is not complicated, you don't have to pay attention to speed. But the learning time is long as the size of the learning data is large and the structure of layers is complicated. So, GPU-based parallel processing is a lot. In this paper, we developed Convolutional Neural Network using CUDA and Learning speed is faster and more efficient than the method using the CPU.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.4
• /
• pp.357-362
• /
• 2010

This paper proposes the speech and noise recognition system by using a neural network in order to detect the speech and noise sections at each frame. The proposed neural network consists of a layered neural network training by back-propagation algorithm. First, a power spectrum obtained by fast Fourier transform and linear predictive coefficients are used as the input to the neural network for each frame, then the neural network is trained using these power spectrum and linear predictive coefficients. Therefore, the proposed neural network can train using clean speech and noise. The performance of the proposed recognition system was evaluated based on the recognition rate using various speeches and white, printer, road, and car noises. In this experiment, the recognition rates were 92% or more for such speech and noise when training data and evaluation data were the different.

• Advances in environmental research
• /
• v.4 no.4
• /
• pp.219-231
• /
• 2015

In recent years, raising air pollutants has become as a big concern, especially in metropolitan cities such as Tehran. Therefore, forecasting the level of pollutants plays a significant role in air quality management. One of the forecasting tools that can be used is an artificial neural network which is able to model the complicated process of air pollution. In this study, we applied two different methods of artificial neural networks, the Multilayer Perceptron (MLP) and Radial Basis Function (RBF), to predict the hourly air concentrations of toluene in Tehran. Hourly temperature, wind speed, humidity and $NO_x$ were selected as inputs. Both methods had acceptable results; however, the RBF neural network produced better results. The coefficient of determination ($R^2$) between the observed and predicted data was 0.9642 and 0.99 for MLP and RBF neural networks, respectively. The results of the mean bias errors (MBE) were 0.00 and -0.014 for RBF and MLP, respectively which indicate the adequacy of the models. The index of agreement (IA) between the observed and predicted data was 0.999 and 0.994 in the RBF and the MLP, respectively which indicates the efficiency of the models. Finally, sensitivity analysis related to the MLP neural network determined that temperature was the most significant factor in air concentration of toluene in Tehran which may be due to the volatile nature of toluene.

• Journal of Digital Contents Society
• /
• v.18 no.3
• /
• pp.559-565
• /
• 2017

A lot of studies have been conducted to recognize the motion state or behavior of the user using the acceleration sensor built in the smartphone. In this paper, we applied the neural networks to the 3-axis acceleration information of smartphone to study human behavior. There are performance issues in applying time series data to neural networks. We proposed a multi-temporal neural networks which have trained three neural networks with different time windows for feature extraction and uses the output of these neural networks as input to the new neural network. The proposed method showed better performance than other methods like SVM, AdaBoot and IBk classifier for real acceleration data.

• Journal of the Korean Data and Information Science Society
• /
• v.12 no.2
• /
• pp.1-10
• /
• 2001

Neural networks we increasingly being seen as an addition to the statistics toolkit which should be considered alongside both classical and modern statistical methods. Neural networks are usually useful for classification and function estimation. In this paper we concentrate on function estimation using neural networks with weight decay factor The use of weight decay seems both to help the optimization process and to avoid overfitting. In this type of neural networks, the problem to decide the number of hidden nodes, weight decay parameter and iteration number of learning is very important. It is called the optimization of weight decay neural networks. In this paper we propose a automatic optimization based on genetic algorithms. Moreover, we compare the weight decay neural network automatically learned according to automatic optimization with ordinary neural network, projection pursuit regression and support vector machines.

• Journal of Korea Water Resources Association
• /
• v.41 no.10
• /
• pp.1059-1065
• /
• 2008

Rainfall data is the most basic input data to analyze the hydrological phenomena and can be missing due to various reasons. In this research, a neural network based model to estimate missing rainfall data as approximate values was developed for 12 rainfall stations in the Soyang river basin to improve existing methods. This approach using neural network has shown to be useful in many applications to deal with complicated natural phenomena and displayed better results compared to the popular offline estimating methods, such as RDS(Reciprocal Distance Squared) method and AMM(Arithmetic Mean Method). Additionally, we proposed automated data reconciliation systems composed of a neural network learning processer to be capable of real-time reconciliation to transmit reliable hydrological data online.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.6 no.1
• /
• pp.27-33
• /
• 1997

A neural network approach has been developed to determine the depth of a surface breaking crack in a steel plate from ultrasonic backscattering data. The network is trained by the use of feedforward three-layered network together with a back-scattering algorithm for error correction. The signal used for crack insonification is a mode converted 70$^{\circ}$transverse wave. A numerical analysis of back scattered field is carried out based on elastic wave theory, by the use of the boundary element method. The numerical data are calibrated by comparison with experimental data. The numerical analysis provides synthetic data for the training of the network. The training data have been calculated for cracks with specified increments of the crack depth. The performance of the network has been tested on other synthetic data and experimental data which are different from the training data.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.1
• /
• pp.96-102
• /
• 2018

For efficient operating strategy of electric power system, forecasting of daily peak electric load is an important but difficult problem. Therefore a daily peak electric load forecasting system using a neural network and fuzzy system is presented in this paper. First, original peak load data is interpolated in order to overcome the shortage of data for effective prediction. Next, the prediction of peak load using these interpolated data as input is performed in parallel by a neural network predictor and a fuzzy predictor. The neural network predictor shows better performance at drastic change of peak load, while the fuzzy predictor yields better prediction results in gradual changes. Finally, the superior one of two predictors is selected by the rules based on rough sets at every prediction time. To verify the effectiveness of the proposed method, the computer simulation is performed on peak load data in 2015 provided by KPX.

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.149-151
• /
• 2005

In this paper, we propose the Optimal Polynomial Neural Networks(PNN) for nonlinear process. The PNN is based on Group Method of Data Handling(GMDH) method and its structure is similar to feedforward Neural Networks. But the structure of PNN is not fixed like in conventional Neural Networks and can be generated. The each node of PNN structure uses several types of high-order polynomial such as linear, quadratic and modified quadratic, and is connected as various kinds of multi-variable inputs. The conventional PNN depends on experience of a designer that select No. of input variable, input variable and polynomial type. Therefore it is very difficult a organizing of optimized network. The proposed algorithm identified and selected No. of input variable, input variable and polynomial type by using Genetic Algorithms(GAs). In the sequel the proposed model shows not only superior results to the existing models, but also pliability in organizing of optimal network. Medical Imaging System(MIS) data is simulated in order to confirm the efficiency and feasibility of the proposed approach in this paper.

• Journal of the Korea Institute of Building Construction
• /
• v.13 no.1
• /
• pp.66-74
• /
• 2013

In the early stages of a construction project, the most important thing is to predict construction costs in a rational way. For this reason, many studies have been performed on the estimation of construction costs for apartment housing and office buildings at early stage using artificial intelligence, statistics, and the like. In this study, cost data held by a provincial Office of Education on elementary schools constructed from 2004 to 2007 were used to compare the multiple regression model with an artificial neural network model. A total of 96 historical data were classified into 76 historical data for constructing models and 20 historical data for comparing the constructed regression model with the artificial neural network model. The results of an analysis of predicted construction costs were that the error rate of the artificial neural network model is lower than that of the multiple regression model.