• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.1
• /
• pp.95-99
• /
• 2018

In this paper, we propose an efficient pixel value prediction algorithm that can accurately predict pixel value using neighboring pixel values scanned in reverse s-order in the image. Generally, image has similarity with similar values between adjacent pixel values, and may have directional edge characteristics. In this paper, we proposed a method to improve pixel value prediction accuracy by improving GAP(Gradient Adjacent Pixel) algorithm for predicting pixel value by using similarity between adjacent pixels and edge characteristics. The proposed method increases the accuracy of the predicted pixel value by precisely predicting the pixel value using the positional weights of the neighboring pixels. Experiments on real images confirmed the superiority of the proposed algorithm. The proposed algorithm is useful for applications such as reversible data hiding, reversible watermarking, and data compression applications.

• Journal of the Korean Solar Energy Society
• /
• v.36 no.3
• /
• pp.33-43
• /
• 2016

Daylight is an important factor which influences building energy efficiency and visual comfort for occupants. It is important to predict precise sky luminance at the early stages of design to reduce light energy in the building. This study predicted sky luminance distributions of standard sky model(CIE overcast sky, CIE clear sky) that was provided from the CIE(Commission internationale de $l^{\prime}{\acute{e}}clairage$). Afterward, result of sky luminance was compared and verified with simulation value of Radiance program. From the CIE overcast sky, zenith and horizon ratio is about 3:1. From the CIE clear sky, luminance value gets most high value around the sun. On the other hand, luminance value is the lowest in the opposite direction of the sun when angle is $90^{\circ}$ between the sun and sky element. As a result of comparing the calculation results with Radiance program, sky luminance prediction error rate is 0.4~1.3% when it is CIE overcast sky. Also, sky luminance prediction error rate is 0.3~1.5% when it is CIE clear sky. When compared with the results of radiance simulation, it was evaluated as fairly accurate.

• Computers and Concrete
• /
• v.19 no.5
• /
• pp.467-475
• /
• 2017

The purpose of this study is to establish a prediction model for the electrical resistivity ($E_r$) of self-consolidating concrete by using waste LCD (liquid crystal display) glass as part of the fine aggregate and then, to analyze the results obtained from a series of laboratory tests. A hyperbolic function is used to perform nonlinear multivariate regression analysis of the electrical resistivity prediction model, with parameters such as water-binder ratio (w/b), curing age (t) and waste glass content (G). Furthermore, the relationship of compressive strength and electrical resistivity of waste LCD glass concrete is also found by a logarithm function, while compressive strength is evaluated by the electrical resistivity of non-destructive testing (NDT). According to relative regression analysis, the electrical resistivity and compressive strength prediction models are developed, and the results show that a good agreement is obtained using the proposed prediction models. From the comparison between the predicted analysis values and test results, the MAPE value of electrical resistivity is 17.0-18.2% and less than 20%, the MAPE value of compressive strength evaluated by $E_r$ is 5.9-10.6% and nearly less than 10%. Therefore, the prediction models established in this study have good predictive ability for electrical resistivity and compressive strength of waste LCD glass concrete. However, further study is needed in regard to applying the proposed prediction models to other ranges of mixture parameters.

• Genomics & Informatics
• /
• v.14 no.4
• /
• pp.149-159
• /
• 2016

With the success of the genome-wide association studies (GWASs), many candidate loci for complex human diseases have been reported in the GWAS catalog. Recently, many disease prediction models based on penalized regression or statistical learning methods were proposed using candidate causal variants from significant single-nucleotide polymorphisms of GWASs. However, there have been only a few systematic studies comparing existing methods. In this study, we first constructed risk prediction models, such as stepwise linear regression (SLR), least absolute shrinkage and selection operator (LASSO), and Elastic-Net (EN), using a GWAS chip and GWAS catalog. We then compared the prediction accuracy by calculating the mean square error (MSE) value on data from the Korea Association Resource (KARE) with body mass index. Our results show that SLR provides a smaller MSE value than the other methods, while the numbers of selected variables in each model were similar.

• Nuclear Engineering and Technology
• /
• v.53 no.8
• /
• pp.2610-2615
• /
• 2021

The prediction of irradiation-induced transition temperature shift for RPV steels is an important method for long term operation of nuclear power plant. Based on the irradiation embrittlement data, an irradiation-induced transition temperature shift prediction model is developed with machine learning method XGBoost. Then the residual, standard deviation and predicted value vs. measured value analysis are conducted to analyze the accuracy of this model. At last, Cu content threshold and saturation values analysis, temperature dependence, Ni/Cu dependence and flux effect are given to verify the reliability. Those results show that the prediction model developed with XGBoost has high accuracy for predicting the irradiation embrittlement trend of RPV steel. The prediction results are consistent with the current understanding of RPV embrittlement mechanism.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.10
• /
• pp.569-578
• /
• 2003

Data dependencies are one of major hurdles to limit ILP(Instruction Level Parallelism), so several related works have suggested that the limit imposed by data dependencies can be overcome to some extent with use of the data value prediction. Hybrid value predictor can obtain the high prediction accuracy using advantages of various predictors, but it has a defect that same instruction has overlapping entries in all predictor. In this paper, we propose a new hybrid value predictor which achieves high performance by using the information of static and dynamic classification. The proposed predictor can enhance the prediction accuracy and efficiently decrease the prediction table size of predictor, because it allocates each instruction into single best-suited predictor during the fetch stage by using the information of static classification. Also, it can enhance the prediction accuracy because it selects a best- suited prediction method for the “Unknown”pattern instructions by using the dynamic classification mechanism. Simulation results based on the SimpleScalar/PISA tool set and the SPECint95 benchmarks show the average correct prediction rate of 85.1% by using the static classification mechanism. Also, we achieve the average correction prediction rate of 87.6% by using static and dynamic classification mechanism.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.1
• /
• pp.71-82
• /
• 2022

Most of the predictions using machine learning are neutral predictions considering the symmetrical situation where the predicted value is not smaller or larger than the actual value. However, in some situations, asymmetric prediction such as over-prediction or under-prediction may be better than neutral prediction, and it can induce better judgment by providing various predictions to decision makers. A method called Asymmetric Twin Support Vector Regression (ATSVR) using TSVR(Twin Support Vector Regression), which has a fast calculation time, was proposed by controlling the asymmetry of the upper and lower widths of the ε-tube and the asymmetry of the penalty with two parameters. In addition, by applying the existing GSVQR and the proposed ATSVR, prediction using the prediction propensities of over-prediction, under-prediction, and neutral prediction was performed. When two parameters were used for both GSVQR and ATSVR, it was possible to predict according to the prediction propensity, and ATSVR was found to be more than twice as fast in terms of calculation time. On the other hand, in terms of accuracy, there was no significant difference between ATSVR and GSVQR, but it was found that GSVQR reflected the prediction propensity better than ATSVR when checking the figures. The accuracy of under-prediction or over-prediction was lower than that of neutral prediction. It seems that using both parameters rather than using one of the two parameters (p_1,p_2) increases the change in the prediction tendency. However, depending on the situation, it may be better to use only one of the two parameters.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.9
• /
• pp.437-444
• /
• 2017

Although many studies tried to predict movie revenues in the last decade, the main focus is still to learn an efficient forecast model to fit the box-office revenues. However, the previous works lack the analysis about why the prediction errors occur, and no method is proposed to reduce the errors. In this paper, we consider the prediction error comes from the competition between the movies that are released in the same period. Our purpose is to analyze the competition value for a movie and to predict how much it will be affected by other competitors so as to improve the performance of movie box-office prediction. In order to predict the competition value, firstly, we classify its sign (positive/negative) and compute the probability of positive sign and the probability of negative sign. Secondly, we forecast the competition value by regression under the condition that its sign is positive and negative respectively. And finally, we calculate the expectation of competition value based on the probabilities and values. With the predicted competition, we can adjust the primal predicted box-office. Our experimental results show that predictive competition can help improve the performance of the forecast.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.12
• /
• pp.943-947
• /
• 2009

To support an efficient management of software verification and validation activities, many defect prediction models have been proposed based on object oriented metrics. In order to apply defect prediction models, we need to determine a threshold value. Because we cannot know actually where defects are, it is difficult to determine threshold. Therefore, we performed a series of experiments to explore the issue of determining a threshold. In the experiments, we applied defect prediction models to other systems different from the system used in building the prediction model. Specifically, we have applied three models - Olague model, Zhou model, and Gyimothy model - to four different systems. As a result, we found that the prediction capabilities varied considerably with a chosen threshold value. Therefore, we need to perform a study on the determination of an appropriate threshold value to improve the applicably of defect prediction models.

• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.215-229
• /
• 2020

The interest in machine learning is growing in all industries, but it is difficult to apply it to real-world tasks because of inexplicability. This paper introduces a case of developing a financial customer churn prediction model for a securities company, and introduces the research results on an attempt to develop a machine learning model that can be explained using the SHAP Value methodology and derivation of interpretability. In this study, a total of six customer churn models are compared and analyzed, and the cause of customer churn is inferred through the classification and data analysis of SHAP Value and the type of customer asset change. Based on the results of this study, it would be possible to use it as a basis for comprehensive judgment, such as using the Value of the deviation prediction result that can infer the cause of the marketing manager's actual customer marketing in the future and establishing a target marketing strategy for each customer.