• Journal of Electrical Engineering and Technology
• /
• v.9 no.5
• /
• pp.1739-1745
• /
• 2014

Prediction of fault-prone modules continues to attract researcher's interest due to its significant impact on software development cost. The most important goal of such techniques is to correctly identify the modules where faults are most likely to present in early phases of software development lifecycle. Various software metrics related to modules level fault data have been successfully used for prediction of fault-prone modules. Goal of this research is to predict the faulty modules at design phase using design metrics of modules and faults related to modules. We have analyzed the effect of pre-processing and different machine learning schemes on eleven projects from NASA Metrics Data Program which offers design metrics and its related faults. Using seven machine learning and four preprocessing techniques we confirmed that models built from design metrics are surprisingly good at fault proneness prediction. The result shows that we should choose Naïve Bayes or Voting feature intervals with discretization for different data sets as they outperformed out of 28 schemes. Naive Bayes and Voting feature intervals has performed AUC > 0.7 on average of eleven projects. Our proposed framework is effective and can predict an acceptable level of fault at design phases.

• The Korean Journal of Applied Statistics
• /
• v.26 no.6
• /
• pp.943-952
• /
• 2013

Wald, Agresti-Coull, Jeffreys, and Bayes-Laplace methods are commonly used for confidence interval of binomial proportion are applied for prediction intervals. We used coverage probability, mean coverage probability, root mean squared error, and mean expected width for numerical comparisons. From the comparisons, we found that Wald is not proper as for confidence interval and Agresti-Coull is too conservative to differ from confidence interval. However, Jeffrey and Bayes-Laplace are good for prediction interval and Jeffrey is especially desirable as for confidence interval.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.10
• /
• pp.3851-3866
• /
• 2015

The dynamic nature of opportunistic networks results in long delays, low rates of success for deliveries, etc. As such user experience is limited, and the further development of opportunistic networks is constrained. This paper proposes a prediction-based routing method for opportunistic networks (PB-OppNet). Firstly, using an ARIMA model, PB-OppNet describes the historical contact information between a node pair as a time series to predict the average encounter time interval of the node pair. Secondly, using an optimal stopping rule, PB-OppNet obtains a threshold for encounter time intervals as forwarding utility. Based on this threshold, a node can easily make decisions of stopping observing, or delivering messages when potential forwarding nodes enter its communication range. It can also report different encounter time intervals to the destination node. With the threshold, PB-OppNet can achieve a better compromise of forwarding utility and waiting delay, so that delivery delay is minimized. The simulation experiment result presented here shows that PB-OppNet is better than existing methods in prediction accuracy for links, delivery delays, delivery success rates, etc.

• The Korean Journal of Applied Statistics
• /
• v.34 no.4
• /
• pp.579-588
• /
• 2021

Wald, Agresti-Coull, Jeffreys, and Bayes-Laplace methods are commonly used for confidence interval of binomial proportion are applied for prediction intervals. We used coverage probability, mean coverage probability, root mean squared error, and mean expected width for numerical comparisons. From the comparisons, we found that Wald is not proper as for confidence interval and Agresti-Coull is too conservative to differ from confidence interval. However, Jeffrey and Bayes-Laplace are good for prediction interval and Jeffrey is especially desirable as for confidence interval.

• Journal of Auto-vehicle Safety Association
• /
• v.12 no.4
• /
• pp.31-38
• /
• 2020

This study is to develop the prediction model for the HIC15 in frontal vehicle crash tests. The 28 frontal impact test results of the MY2019 and MY2020 USNCAP are utilized. The metrics for evaluating the crash pulse severity such as moving average acceleration, Restraint Quotient (RQ) and ride-down efficiency are reviewed to find out whether the metrics can predict the HIC15. It is observed that the R² values based on the linear regression of all pairs between the existing metrics and the occupant injuries such as the HIC15, 3 ms chest g's and chest deflection are very low. In this study, using the vehicle crash pulses, the linear regression model for estimating the HIC15 is developed. The vehicle crash pulse is splitted seven 10 ms intervals in 70 ms after impact for extracting the average accelerations in each intervals. The prediction model can predict effectively not only the HIC15 but also the maximum head g's, chest deflection and 3 ms chest g's of 13 vehicles out of 28 vehicles.

• Journal of Animal Science and Technology
• /
• v.55 no.6
• /
• pp.489-500
• /
• 2013

Daily milk yields on test days were estimated using morning or afternoon partial milk yields collected by official agencies and the accuracy of the estimates was determined. Test-day data for milk yields consisted of 3,156,734 records of AM/PM partial milking measurements of 255,437 milking Holstein cows from 3,708 farms collected from December 2008 to April 2013. A linear regression model (LRM) was applied to estimate daily milk yields using alternate AM/PM milk yield records within lactation stages, milking intervals, and parities on every daily milk yield. The alternate statistical approach was a non-linear hierarchical model (NHM) in which Brody's growth function was implemented by reflecting an animal's physiological milk production cycle. When compared with LRM, daily milk yields predicted by the NHM were assumed to be functionally related to day in milk (or lactation) stage, milking intervals, and partial milk yields. Since the results were in terms of accuracies based on comparisons of different statistical models, accuracies of estimates of daily milk yields by NHM were close to those determined by the LRM. The average of these accuracies was 0.94 for AM partial milk yields and 0.93 for PM partial milk yields for first calving cows. However, the accuracies of AM/PM milk yield estimations from cows under a calving stage higher than the first parity were 0.96 and 0.95, respectively. Correlations between the estimated daily milk yields and the actual daily milk yields ranged from 0.96~0.98. These accuracies were lower for unbalanced AM/PM milking intervals and the first calving cows. Overall, prediction of daily milk yields by NHM would be more appropriate than by LRM due to its flexibility under different milk yield-related circumstances, which provides an idea of the functional relationship between milking intervals and days in milk with daily milk yields from statistical viewpoints.

• Journal of the Korean Data and Information Science Society
• /
• v.13 no.1
• /
• pp.139-145
• /
• 2002

This paper deals with the problem of obtaining the Bayesian predictive density function and the prediction intervals for a future observation and the p-th order statistics of n future observations for the exponential model under the censored sampling with incomplete information.

• Journal of the Korean Data and Information Science Society
• /
• v.10 no.1
• /
• pp.147-154
• /
• 1999

Using a noninformative prior and an inverted gamma prior, the Bayesian predictive density and the prediction intervals for a future observation or the p - th order statistic of n' future observations from the censord Pareto model have been obtained. In additions, numerical examples are given in order to illustrate the proposed predictive procedure.

• Journal of KIISE:Software and Applications
• /
• v.37 no.7
• /
• pp.558-567
• /
• 2010

There is a large body of ongoing research to develop efficient prediction methods for data streams. These methods provide single prediction with a fixed time interval. It is necessary to develop a method for multi-interval prediction (MIP) because different prediction results may be obtained based on different intervals in many cases. In this paper, we propose a solution for MIP based on the Hierarchical Temporal Memory (HTM) model. In order to solve the problem of MIP with HTM, we present an Integrated Hierarchical Temporal Memory (IHTM) network by introducing a new node type Zeta1LastNode to the original HTM network. Using the hierarchical characteristic of the IHTM network, different levels in the network learn and model the features of a data stream with different intervals and generate prediction results for different intervals. Performance evaluation shows that the IHTM is efficient in the memory and time consumption compared with the original HTM network in MIP.

• Journal of Korea Multimedia Society
• /
• v.14 no.9
• /
• pp.1152-1164
• /
• 2011

Stock price is stream data to change continuously. The characteristics of these data, stock trends according to flow of time intervals may differ. therefore, stock price should be continuously prediction when the price is updated. In this paper, we propose the new prediction system that continuously predicts the stock price according to the predefined time intervals for the selected stock item using HTM model. We first present a preprocessor which normalizes the stock data and passes its result to the stream sensor. We next present a stream sensor which efficiently processes the continuous input. In addition, we devise a storage node which stores the prediction results for each level and passes it to next upper level and present the HTM network for prediction using these nodes. We show experimented our system using the actual stock price and shows its performance.