• ETRI Journal
• /
• v.46 no.3
• /
• pp.461-472
• /
• 2024

We propose a network traffic prediction model based on linear and nonlinear model combination. Network traffic is modeled by an autoregressive moving average model, and the error between the measured and predicted network traffic values is obtained. Then, an echo state network is used to fit the prediction error with nonlinear components. In addition, an improved slime mold algorithm is proposed for reservoir parameter optimization of the echo state network, further improving the regression performance. The predictions of the linear (autoregressive moving average) and nonlinear (echo state network) models are added to obtain the final prediction. Compared with other prediction models, test results on two network traffic datasets from mobile and fixed networks show that the proposed prediction model has a smaller error and difference measures. In addition, the coefficient of determination and index of agreement is close to 1, indicating a better data fitting performance. Although the proposed prediction model has a slight increase in time complexity for training and prediction compared with some models, it shows practical applicability.

• 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 KIPS Transactions:PartD
• /
• v.16D no.3
• /
• pp.407-416
• /
• 2009

To support an efficient management of software verification and validation activities, much research has been conducted to predict defects in early phase. And defect prediction models have been proposed to predict defects. But the generality of the models has not been experimentally studied for other software system. In other words, most of prediction models were applied only to the same system that had been used to build the prediction models themselves. Therefore, we performed an experiment to explore generality of major prediction models. In the experiment, we applied three defects prediction models to three different systems. As a result, we cannot find their generality of defect prediction capability. The cause is analyzed to result from a different metric distribution between the systems.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.6
• /
• pp.1-16
• /
• 2023

Accurate traffic information prediction is considered to be one of the most important aspects of intelligent transport systems(ITS), as it can be used to guide users of transportation facilities to avoid congested routes. Various deep learning models have been developed for accurate traffic prediction. Recently, ensemble techniques have been utilized to combine the strengths and weaknesses of various models in various ways to improve prediction accuracy and stability. Therefore, in this study, we developed and evaluated a traffic information prediction model using various deep learning models, and evaluated the performance of the developed deep learning models as a stacking ensemble. The individual models showed error rates within 10% for traffic volume prediction and 3% for speed prediction. The ensemble model showed higher accuracy compared to other models when no cross-validation was performed, and when cross-validation was performed, it showed a uniform error rate in long-term forecasting.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.1
• /
• pp.203-209
• /
• 2009

Frailty models are useful for the analysis of correlated and/or heterogeneous survival data. However, the inferences of fixed parameters, rather than random effects, have been mainly studied. The prediction (or estimation) of random effects is also practically useful to investigate the heterogeneity of the hospital or patient effects. In this paper we propose how to extend the prediction method for random effects in HGLMs (hierarchical generalized linear models) to log-normal semiparametric frailty models with nonparametric baseline hazard. The proposed method is demonstrated by a simulation study.

• Speech Sciences
• /
• v.10 no.4
• /
• pp.7-21
• /
• 2003

Sums-of-Products models were built for segment duration prediction of spoken Korean. An experiment for the modelling was carried out to apply the results to Korean text-to-speech synthesis systems. 670 read sentences were analyzed. trained and tested for the construction of the duration models. Traditional sequential rule systems were extended to simple additive, multiplicative and additive-multiplicative models based on Sums-of-Products modelling. The parameters used in the modelling include the properties of the target segment and its neighbors and the target segment's position in the prosodic structure. Two optimisation strategies were used: the downhill simplex method and the simulated annealing method. The performance of the models was measured by the correlation coefficient and the root mean squared prediction error (RMSE) between actual and predicted duration in the test data. The best performance was obtained when the data was trained and tested by ' additive-multiplicative models. ' The correlation for the vowel duration prediction was 0.69 and the RMSE. 31.80 ms. while the correlation for the consonant duration prediction was 0.54 and the RMSE. 29.02 ms. The results were not good enough to be applied to the real-time text-to-speech systems. Further investigation of feature interactions is required for the better performance of the Sums-of-Products models.

• Coupled systems mechanics
• /
• v.12 no.6
• /
• pp.539-555
• /
• 2023

Although some prediction models have successfully developed for ultra-high performance concrete (UHPC), they do not provide insights and explicit relations between all constituents and its consistency, and compressive strength. In the present study, based on the experimental results, several mathematical models have been evaluated to predict the consistency and the 28-day compressive strength of UHPC. The models used were Linear, Logarithmic, Inverse, Power, Compound, Quadratic, Cubic, Mixed, Sinusoidal and Cosine equations. The applicability and accuracy of these models were investigated using experimental data, which were collected from literature. The comparisons between the models and the experimental results confirm that the majority of models give acceptable prediction with a high accuracy and trivial error rates, except Linear, Mixed, Sinusoidal and Cosine equations. The assessment of the models using numerical methods revealed that the Quadratic and Inverse equations based models provide the highest predictability of the compressive strength at 28 days and consistency, respectively. Hence, they can be used as a reliable tool in mixture design of the UHPC.

• International Journal of Highway Engineering
• /
• v.14 no.5
• /
• pp.133-143
• /
• 2012

PURPOSES: Using the collected data for crash, traffic volume, and design elements on ramps between 2007 and 2009, this research effort was initiated to develop traffic crash prediction models for expressway ramps. METHODS: Three negative binomial regression models and three zero-inflated negative binomial regression models were developed for individual ramp types, including direct, semi-direct and loop, respectively. For validating the developed models, authors compared the estimated crash frequencies with actual crash frequencies of twelve randomly selected interchanges, the ramps of which have not been used for model developing. RESULTS: The results show that the negative binomial regression models for direct, semi-direct and loop ramps showed 60.3%, 63.8% and 48.7% error rates on average whereas the zero-inflated negative binomial regression models showed 82.1%, 120.4% and 57.3%, respectively. CONCLUSIONS: Conclusively, the negative binomial regression models worked better in traffic crash prediction than the zero-inflated negative binomial regression models for estimating the frequency of traffic accidents on expressway ramps.

• 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.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.14 no.3
• /
• pp.175-184
• /
• 2004

Ground-borne noise and vibration generated by underground transit system has been recognized as an important environmental problem. This study reviews several of the procedures that have been used to predict ground-borne vibration. The vibration responses are measured at three sites that have different soil qualities. The measured vibration levels are compared with the predicted results by previously used vibration level prediction models. There are some drawbacks to apply these prediction models to selected sites because most of the existing prediction models are primarily based on empirical data and all of them lack of analytical models for the mechanism of ground-borne vibration generation. radiation, and propagation. In this study a numerical method, which is based on explicit differential method, is used to compensate for the shortcomings of existing prediction models. Although numerically computed results are not quantitatively in good agreement with the measured results, the trends are comparable in the sense that vibration level does not decrease monotonically with distance. Also, the site with the deepest tunnel gives the highest vibration level.