• 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 KIISE:Computer Systems and Theory
• /
• v.27 no.8
• /
• pp.741-751
• /
• 2000

To achieve high performance by exploiting instruction level parallelism aggressively in superscalar processors, it is necessary to overcome the limitation imposed by control dependences and data dependences which prevent instructions from executing parallel. Value prediction is a technique that breaks data dependences by predicting the outcome of an instruction and executes speculatively its data dependent instruction based on the predicted outcome. In this paper, a hybrid value prediction scheme with dynamic classification mechanism is proposed. We design a hybrid predictor by combining the last predictor, a stride predictor and a two-level predictor. The choice of a predictor for each instruction is determined by a dynamic classification mechanism. This makes each predictor utilized more efficiently than the hybrid predictor without dynamic classification mechanism. To show performance improvements of our scheme, we simulate the SPECint95 benchmark set by using execution-driven simulator. The results show that our scheme effect reduce of 45% hardware cost and 16% prediction accuracy improvements comparing with the conventional hybrid prediction scheme and two-level value prediction scheme.

• Soft Computing and Machine Intelligence
• /
• v.1 no.1
• /
• pp.11-23
• /
• 2021

House price prediction is a significant financial decision for individuals working in the housing market as well as for potential buyers. From investment to buying a house for residence, a person investing in the housing market is interested in the potential gain. This paper presents machine learning algorithms to develop intelligent regressions models for House price prediction. The proposed research methodology consists of four stages, namely Data Collection, Pre Processing the data collected and transforming it to the best format, developing intelligent models using machine learning algorithms, training, testing, and validating the model on house prices of the housing market in the Capital, Islamabad. The data used for model validation and testing is the asking price from online property stores, which provide a reasonable estimate of the city housing market. The prediction model can significantly assist in the prediction of future housing prices in Pakistan. The regression results are encouraging and give promising directions for future prediction work on the collected dataset.

• The Journal of Information Systems
• /
• v.14 no.2
• /
• pp.277-292
• /
• 2005

This paper uses a data mining approach to develop bankruptcy prediction models suitable for traditional (off-line) companies and electronic (on-line) companies. It observes the differences in the composition prediction models between these two types of companies and provides interpretation of bankruptcy classifications. The bankruptcy prediction models revealed the major variables in predicting bankruptcy to be 'cash flow to total assets' and 'gross value-added to net sales' for traditional off-line companies while 'cash flow to liabilities','gross value-added to net sales', and 'current ratio' for electronic companies. The accuracy rates of final prediction models for traditional off-line and electronic companies were found to be $84.7\%\;and\;82.4\%$, respectively. When the model for traditional off-line companies was applied for electronic companies, prediction accuracy dropped significantly in the case of bankruptcy classification (from $70.4\%\;to\;45.2\%$) at the level of a blind guess ($41.30\%$). Therefore, the need for different models for traditional off-line and electronic companies is justified.

• The Journal of Information Systems
• /
• v.31 no.3
• /
• pp.197-220
• /
• 2022

Purpose The purpose of this study is to identifies the demand pattern categorization of repair parts of Automotive After-sales Service(A/S) and proposes a demand prediction model for Auto repair parts using Long Short-Term Memory (LSTM) of artificial neural networks (ANN). The optimal parts inventory quantity prediction model is implemented by applying daily, weekly, and monthly the parts demand data to the LSTM model for the Lumpy demand which is irregularly in a specific period among repair parts of the Automotive A/S service. Design/methodology/approach This study classified the four demand pattern categorization with 2 years demand time-series data of repair parts according to the Average demand interval(ADI) and coefficient of variation (CV²) of demand size. Of the 16,295 parts in the A/S service shop studied, 96.5% had a Lumpy demand pattern that large quantities occurred at a specific period. lumpy demand pattern's repair parts in the last three years is predicted by applying them to the LSTM for daily, weekly, and monthly time-series data. as the model prediction performance evaluation index, MAPE, RMSE, and RMSLE that can measure the error between the predicted value and the actual value were used. Findings As a result of this study, Daily time-series data were excellently predicted as indicators with the lowest MAPE, RMSE, and RMSLE values, followed by Weekly and Monthly time-series data. This is due to the decrease in training data for Weekly and Monthly. even if the demand period is extended to get the training data, the prediction performance is still low due to the discontinuation of current vehicle models and the use of alternative parts that they are contributed to no more demand. Therefore, sufficient training data is important, but the selection of the prediction demand period is also a critical factor.

• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1508-1520
• /
• 2018

In this paper, we propose an improved model to provide users with a better long-term prediction of waterworks operation data. The existing prediction models have been studied in various types of models such as multiple linear regression model while considering time, days and seasonal characteristics. But the existing model shows the rate of prediction for demand fluctuation and long-term prediction is insufficient. Particularly in the deep running model, the long-short-term memory (LSTM) model has been applied to predict data of water purification plant because its time series prediction is highly reliable. However, it is necessary to reflect the correlation among various related factors, and a supplementary model is needed to improve the long-term predictability. In this paper, convolutional neural network (CNN) model is introduced to select various input variables that have a necessary correlation and to improve long term prediction rate, thus increasing the prediction rate through the LSTM predictive value and the combined structure. In addition, a multiple linear regression model is applied to compile the predicted data of CNN and LSTM, which then confirms the data as the final predicted outcome.

• Atmosphere
• /
• v.32 no.4
• /
• pp.263-276
• /
• 2022

The observation error of satellite radiation data that assimilated into the Korean Integrated Model (KIM) was diagnosed by applying the Hollingsworth and Lönnberg and Desrozier techniques commonly used. The magnitude and correlation of the observation error, and the degree of contribution for the satellite radiance data were calculated. The observation errors of the similar device, such as Advanced Technology Microwave Sounder (ATMS) and Advanced Microwave Sounding Unit-A shows different characteristics. The model resolution accounts for only 1% of the observation error, and seasonal variation is not significant factor, either. The observation error used in the KIM is amplified by 3-8 times compared to the diagnosed value or standard deviation of first-guess departures. The new inflation value was calculated based on the correlation between channels and the ratio of background error and observation error. As a result of performing the model sensitivity evaluation by applying the newly inflated observation error of ATMS, the error of temperature and water vapor analysis field were decreased. And temperature and water vapor forecast field have been significantly improved, so the accuracy of precipitation prediction has also been increased by 1.7% on average in Asia especially.

• The Journal of Information Systems
• /
• v.32 no.1
• /
• pp.179-199
• /
• 2023

Purpose This study builds a prediction model to find stocks that can reach intrinsic value among KOSPI and KOSDAQ-listed companies to improve the stability and profitability of the stock investment. And investment simulations are conducted to verify whether stock investment performance is improved by comparing the prediction model, random stock selection, and the market indexes. Design/methodology/approach Value investment theory and machine learning techniques are applied to build the model. Various experiments find conditions such as the algorithm with the best predictive performance, learning period, and intrinsic value-reaching period. This study selects stocks through the prediction model learned with inventive variables, does not limit the holding period after buying to reach the intrinsic value of the stocks, and targets all KOSPI and KOSDAQ companies. The stock and financial data are collected for 21 years (2001-2021). Findings As a result of the experiment, using the random forest technique, the prediction model's performance was the best with one year of learning period and within one year of the intrinsic value reaching period. As a result of the investment simulation, the cumulative return of the prediction model was up to 1.68 times higher than the random stock selection and 17 times higher than the KOSPI index. The usefulness of the prediction model was confirmed in that the number of intrinsic values reaching the predicted stock was up to 70% higher than the random selection.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.15 no.4
• /
• pp.287-293
• /
• 2003

This study examined the temperature-dependent regression model of energy consumption based on various measuring period. The methodology employed was to construct temperature-dependent linear regression model of daily energy consumption from one day to three months data-sets and to compare the annual heating energy consumption predicted by these models with actual annual heating energy consumption. Heating energy consumption from a building in Daejon was examined experimentally. From the results, predicted value based on one day experimental data can have error over 100%. But predicted value based on one week experimental data showed error over 30%. And predicted value based on over three months experimental data provides accurate prediction within 6% but it will be required very expensive.

• 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.