• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1998.06b
• /
• pp.165-170
• /
• 1998

This paper presents a new prediction method RBP region-based prediction model where the context used for prediction contains regions instead of individual pixels. There is a meaningful property that RBP can partition a cartoon image into two distinctive types of regions, one containing full-color backgrounds and the other containing boundaries, edges and home-chromatic areas. With the development of computer techniques, synthetic images created with CG (computer graphics) becomes attactive. Like the demand on data compression, it is imperative to efficiently compress synthetic images such as cartoon animation generated with CG for storage of finite capacity and transmission of narrow bandwidth. This paper a lossy compression method to full-color regions and a lossless compression method to homo-chromatic and boundaries regions. Two criteria for partitioning are described, constant criterion and variable criterion. The latter criterion, in form of a linear function, gives the different threshold for classification in terms of contents of the image of interest. We carry out experiments by applying our method to a sequence of cartoon animation. We carry out experiments by applying our method to a sequence of cartoon animation. Compared with the available image compression standard MPEG-1, our method gives the superior results in both compression ratio and complexity.

• Computers and Concrete
• /
• v.13 no.4
• /
• pp.531-545
• /
• 2014

The purpose of this paper is to develop a prediction model for the compressive strength of waste LCD glass applied in concrete by analyzing a series of laboratory test results, which were obtained in our previous study. The hyperbolic function was used to perform the nonlinear-multivariate regression analysis of the compressive strength prediction model with the following parameters: water-binder ratio w/b, curing age t, and waste glass content G. According to the relative regression analysis, the compressive strength prediction model is developed. The calculated results are in accord with the laboratory measured data, which are the concrete compressive strengths of different mix proportions. In addition, a coefficient of determination $R^2$ value between 0.93 and 0.96 and a mean absolute percentage error MAPE between 5.4% and 8.4% were obtained by regression analysis using the predicted compressive analysis value, and the test results are also excellent. Therefore, the predicted results for compressive strength are highly accurate for waste LCD glass applied in concrete. Additionally, this predicted model exhibits a good predictive capacity when employed to calculate the compressive strength of washed glass sand concrete.

• Journal of the Korean Solar Energy Society
• /
• v.31 no.2
• /
• pp.72-81
• /
• 2011

The wind data obtained from an AWS(Automated Weather Station) was used to predict the AEP(annual energy production) of Gangwon wind farm having a total capacity of 98 MWin Korea. A wind energy prediction program based on the Reynolds averaged Navier-Stokes equation was used. Predictions were made for three consecutive years starting from 2007 and the results were compared with the actual AEPs presented in the CDM (Clean Development Mechanism) monitoring report of the wind farm. The results from the prediction program were close to the actual AEPs and the errors were within 7.8%.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.2
• /
• pp.329-338
• /
• 2021

This study predicts the amount of wind power generation for rational operation plan of wind power generation and capacity calculation of ESS. For forecasting, we present a method of predicting wind power generation by combining a physical approach and a statistical approach. The factors of wind power generation are analyzed and variables are selected. By collecting historical data of the selected variables, the amount of wind power generation is predicted using deep learning. The model used is a hybrid model that combines a bidirectional long short term memory (LSTM) and a convolution neural network (CNN) algorithm. To compare the prediction performance, this model is compared with the model and the error which consist of the MLP(:Multi Layer Perceptron) algorithm, The results is presented to evaluate the prediction performance.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.75-87
• /
• 2023

We designed to employ an Artificial Intelligence learning model to predict real estate prices and determine the reasons behind their changes, with the goal of using the results as a guide for policy. Numerous studies have already been conducted in an effort to develop a real estate price prediction model. The price prediction power of conventional time series analysis techniques (such as the widely-used ARIMA and VAR models for univariate time series analysis) and the more recently-discussed LSTM techniques is compared and analyzed in this study in order to forecast real estate prices. There is currently a period of rising volatility in the real estate market as a result of both internal and external factors. Predicting the movement of real estate values during times of heightened volatility is more challenging than it is during times of persistent general trends. According to the real estate market cycle, this study focuses on the three times of extreme volatility. It was established that the LSTM, VAR, and ARIMA models have strong predictive capacity by successfully forecasting the trading price index during a period of unusually high volatility. We explores potential synergies between the hybrid artificial intelligence learning model and the conventional statistical prediction model.

• Journal of Intelligence and Information Systems
• /
• v.11 no.3
• /
• pp.69-81
• /
• 2005

As the competition in business becomes severe, companies are focusing their capacity on customer relationship management (CRM) for survival. One of the important issues in CRM is to build a purchase prediction model, which classifies customers into either purchasing or non-purchasing groups. Until now, various techniques for building purchase prediction models have been proposed. However, they have been criticized because their performances are generally low, or it requires much effort to build and maintain them. Thus, in this study, we propose the support vector machine (SVM) a tool for building a purchase prediction model. The SVM is known as the technique that not only produces accurate prediction results but also enables training with the small sample size. To validate the usefulness of SVM, we apply it and some of other comparative techniques to a real-world purchase prediction case. Experimental results show that SVM outperforms all the comparative models including logistic regression and artificial neural networks.

• Journal of Korean Society of Steel Construction
• /
• v.18 no.4
• /
• pp.481-490
• /
• 2006

The actual performance of a building during an earthquake depends on many factors. The prediction of the seismic performance of a new or existing structure is complex, due not only to the large number of factors that need to be considered and the complexity of the seismic response, but also due to the large inherent uncertainties and randomness associated with making these predictions. A central issue of this research is the proper treatment and incorporation of these uncertainties and randomness in the evaluation of structural capacity and response has been adopted in the seismic performance evaluation of steel tall buildings to account for the uncertainties and randomness in seismic demand and capacities in a consistent manner. The basic framework for reliability-based seismic performance evaluation and the key factors for statistical studies were summarized. A total of 36 target structures that represent typical tall steel buildings based on national building code (KBC-2005) were designed for the statistical studies of demand factor s and capacity factors. The incremental dynamic analysis (IDA) approach was examined through the simple steel moment frame building in determination of global drift capacity.

• Journal of Korea Multimedia Society
• /
• v.15 no.5
• /
• pp.639-650
• /
• 2012

In 2009, Tsai et al. proposed reversible image hiding scheme using linear prediction coding and histogram shifting. Tsai et al.'s scheme improved the hiding capacity of Ni et al.'s scheme by using the prediction coding and two histograms. However, Tsai et al.'s scheme has problems. In the prediction coding, the basic pixel is not used from embedding procedure. Many additional communication data are generated because two peak and zero point pairs are generated by each block. To solve the problems, this paper proposes a novel reversible data hiding scheme based on modulo operation and histogram shifting. In experimental results, the hiding capacity was increased by 28% than Tsai et al.'s scheme. However, the additional communication data was decreased by 71%.

• Structural Engineering and Mechanics
• /
• v.54 no.3
• /
• pp.501-520
• /
• 2015

Presence of torsional loadings can significantly affect the flow of internal forces and deformation capacity of reinforced concrete (RC) columns. It increases the possibility of brittle shear failure leading to catastrophic collapse of structural members. This necessitates accurate prediction of the torsional behaviour of RC members for their safe design. However, a review of previously published studies indicates that the torsional behaviour of RC members has not been studied in as much depth as the behaviour under flexure and shear in spite of its frequent occurrence in bridge columns. Very few analytical models are available to predict the response of RC members under torsional loads. Softened truss model (STM) developed in the University of Houston is one of them, which is widely used for this purpose. The present study shows that STM prediction is not sufficiently accurate particularly in the post cracking region when compared to test results. An improved analytical model for RC square columns subjected to torsion with and without axial compression is developed. Since concrete is weak in tension, its contribution to torsional capacity of RC members was neglected in the original STM. The present investigation revealed that, disregard to tensile strength of concrete is the main reason behind the discrepancies in the STM predictions. The existing STM is extended in this paper to include the effect of tension stiffening for better prediction of behaviour of square RC columns under torsion. Three different tension stiffening models comprising a linear, a quadratic and an exponential relationship have been considered in this study. The predictions of these models are validated through comparison with test data on local and global behaviour. It was observed that tension stiffening has significant influence on torsional behaviour of square RC members. The exponential and parabolic tension stiffening models were found to yield the most accurate predictions.

• Transactions of the KSME C: Technology and Education
• /
• v.3 no.1
• /
• pp.15-21
• /
• 2015

In this paper a prediction method of GHP performance is proposed for increasing design accuracy. Two compressors with different capacity and 2311cc gas engine are used for prediction and the target capacity of GHP is 25HP. For predicting GHP performance at first the operation points are randomly selected and then as compared with compressor performance date and heat exchanger characteristic, more accurate operating points are decided through recursive calculation. Lastly engine performance date is used for calculating gas consumption volume. Predicting heating mode performance of GHP, evaporator is separated to the two section of absorbing heat in outdoor air and in engine. From the experimental results, it was found that the simulation model is good for the predicting GHP efficiency and the difference of predicted and measured efficiency is less than 5%.