• Journal of Information Technology Services
• /
• v.10 no.2
• /
• pp.235-245
• /
• 2011

Early criticality prediction models that determine whether a design entity is fault-prone or not are becoming more and more important as software development projects are getting larger. Effective predictions can reduce the system development cost and improve software quality by identifying trouble-spots at early phases and proper allocation of effort and resources. Many prediction models have been proposed using statistical and machine learning methods. This paper builds a prediction model using Support Vector Machine(SVM) which is one of the most popular modern classification methods and compares its prediction performance with a well-known prediction model, BackPropagation neural network Model(BPM). SVM is known to generalize well even in high dimensional spaces under small training data conditions. In prediction performance evaluation experiments, dimensionality reduction techniques for data set are not used because the dimension of input data is too small. Experimental results show that the prediction performance of SVM model is slightly better than that of BPM and polynomial kernel function achieves better performance than other SVM kernel functions.

• Water for future
• /
• v.8 no.2
• /
• pp.93-99
• /
• 1975

A linear and optimum linear systems have been reviewed in some detail. The procedure of the solution of the Wiener-Hopf equation analytically in time domain is given and the prediction of downstream outflow for given upstream inflow are made. The predicted results are fairly satisfaotory. The intended physical interpretation of the analytical solution could be descriptable but it was found that the evaluation of the parameters of the response function is rather difficult due to complicacy and a great deal of works.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2000.10a
• /
• pp.173-178
• /
• 2000

New prediction model is investigated estimating splitting tensile strength and modulus of elasticity with curing temperature and aging. New prediction model is based on the model which was proposed to predict compressive strength, and splitting tensile strength and modulus of elasticity calculated by this model are compared with experimental values. New prediction model well estimated splittinge tensile strength and elastic modulus as well as compressive strength.

• Journal of the Korea Safety Management & Science
• /
• v.4 no.2
• /
• pp.11-22
• /
• 2002

In this study, an asymmetric lifting posture prediction model was developed, which was a three-dimensional model with 12 links and 23 degrees of freedom open kinematic chains. Although previous researchers have proposed biomechanical, psychophysical, or physiological measures as cost functions, for solving redundancy, they lack in accuracy in predicting actual lifting postures and most of them are confined to the two-dimensional model. To develop an asymmetric lifting posture prediction model, we used the resolved motion method for accurately simulating the lifting motion in a reasonable time. Furthermore, in solving the redundant problem of the human posture prediction, a moment weighted Joint Range Availability (JRA) was used as a cost function in order to consider dynamic lifting. However, it is known that the moment weighted JRA as a cost function predicted the lower extremity and L5/S1 joint motions better than the upper extremities, while the constant weighted JRA as a cost function predicted the latter better than the former. To compensate for this, we proposed a hybrid moment weighted JRA as a new cost function with moment weighted for only the lower extremity. In order to validate the proposed cost function, the predicted and real lifting postures for various lifting conditions were compared by using the root mean square(RMS) error. This hybrid JRA reduced RMS more than the previous cost functions. Therefore, it is concluded that the cost function of a hybrid moment weighted JRA can be used to predict three-dimensional lifting postures. To compare with the predicted trajectories and the real lifting movements, graphical validations were performed. The results also showed that the hybrid moment weighted cost function model was found to have generated the postures more similar to the real movements.

• Tuberculosis and Respiratory Diseases
• /
• v.41 no.2
• /
• pp.111-119
• /
• 1994

Background: Because of the common etiologic factor, such as smoking, lung cancer and chronic obstructive pulmonary disease are often present in the same patient. The preoperative prediction of remaining pulmonary function after the resectional surgery is very important to prevent serious complication and postoperative respiratory failure. $^{99m}Tc$-MAA perfusion scan has been used for the prediction of postoperative pulmonary function, but it may be inaccurate in case of large V/Q mismatching. We compared $^{99m}Tc$-DTPA radioaerosol inhalation scan with $^{99m}Tc$-MAA perfusion scan in predicting postoperative lung function. Method: Preoperative inhalation scan and/or perfusion scan were performed and pulmonary function test were performed preoperatively and 2 month after operation. We predicted the postoperative pulmonary functions using the following equations. Postpneurnonectomy $FEV_1$=Preop $FEV_1x%$ of total function of lung to remain Postlobectomy $FEV_1$=Preop $FEV_1{\times}$(% of total 1-function of affected lung${\times}$$\frac{Number\;of\;segments\;to\;be\;resected}{Number\;of\;segments\;of\;affected\;lung})$ Results: 1) The inhalation scan showed good correlations between measured and predicted $FEV_1$, FVC and $FEF_{25-75%}$. (correlation coefficiency; 0.94, 0.91, 0.87 respectively). 2) The perfusion scan also showed good correlations between measured and predicted $FEV_1$, FVC and $FEF_{25-75%}$. (correlation coefficiency; 0.86, 0.72, 0.87 respectively). 3) Among three parameters, $FEV_1$ showed the best correlations in the prediction by lung scans. 4) Comparison between inhalation scan and perfusion scan in predicting pulmonary function did not show any significant differneces except FVC. Conclusion: The inhalation scan and perfusion scan are very useful in the prediction of postoperative lung function and don't make a difference in the prediction of pulmonary function a1though the former showed a better correlation in FVC.

• Korean Journal of Microbiology
• /
• v.39 no.2
• /
• pp.67-75
• /
• 2003

One large topic in comparative genomics is to predict functional annotation by classifying protein sequences. Computational approaches for function prediction include protein structure prediction, sequence alignment and domain prediction or binding site prediction. This paper is on another computational approach searching for sets of homologous sequences from sequence similarity graph. Methods based on similarity graph do not need previous knowledges about sequences, but largely depend on the researcher's subjective threshold settings. In this paper, we propose a genome sequence clustering method of iterative testing and graph decomposition, and a simple method to calculate a strict threshold having biochemical meaning. Proposed method was applied to known bacterial genome sequences and the result was shown with the BAG algorithm's. Result clusters are lacking some completeness, but the confidence level is very high and the method does not need user-defined thresholds.

• International Journal of Control, Automation, and Systems
• /
• v.2 no.2
• /
• pp.256-262
• /
• 2004

Conventionally, profile non-uniformity has been characterized by relying on approximated profile with angle or anisotropy. In this study, a new non-uniformity model for etch profile is presented by applying a discrete wavelet to the image obtained from a scanning electron microscopy (SEM). Prediction models for wavelet-transformed data are then constructed using a back-propagation neural network. The proposed method was applied to the data collected from the etching of tungsten material. Additionally, 7 experiments were conducted to obtain test data. Model performance was evaluated in terms of the average prediction accuracy (APA) and the best prediction accuracy (BPA). To take into account randomness in initial weights, two hundred models were generated for a given set of training factors. Behaviors of the APA and BPA were investigated as a function of training factors, including training tolerance, hidden neuron, initial weight distribution, and two slopes for bipolar sig-moid and linear function. For all variations in training factors, the APA was not consistent with the BPA. The prediction accuracy was optimized using three approaches, the best model based approach, the average model based approach and the combined model based approach. Despite the largest APA of the first approach, its BPA was smallest compared to the other two approaches.

• Journal of Power Electronics
• /
• v.17 no.5
• /
• pp.1288-1297
• /
• 2017

The estimation of the remaining useful life (RUL) of lithium-ion (Li-ion) batteries is important for intelligent battery management system (BMS). Data mining technology is becoming increasingly mature, and the RUL estimation of Li-ion batteries based on data-driven prognostics is more accurate with the arrival of the era of big data. However, the support vector machine (SVM), which is applied to predict the RUL of Li-ion batteries, uses the traditional single-radial basis kernel function. This type of classifier has weak generalization ability, and it easily shows the problem of data migration, which results in inaccurate prediction of the RUL of Li-ion batteries. In this study, a novel multi-kernel SVM (MSVM) based on polynomial kernel and radial basis kernel function is proposed. Moreover, the particle swarm optimization algorithm is used to search the kernel parameters, penalty factor, and weight coefficient of the MSVM model. Finally, this paper utilizes the NASA battery dataset to form the observed data sequence for regression prediction. Results show that the improved algorithm not only has better prediction accuracy and stronger generalization ability but also decreases training time and computational complexity.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.12
• /
• pp.1748-1755
• /
• 2015

A linear regression is widely used for prediction problem, but it is hard to manage an irregular nature of nonlinear system. Although nonlinear regression methods have been adopted, most of them are only fit to low and limited structure problem with small number of independent variables. However, real-world problem, such as weather prediction required complex nonlinear regression with large number of variables. GP(Genetic Programming) based evolutionary nonlinear regression method is an efficient approach to attach the challenging problem. This paper introduces the improvement of an GP based nonlinear regression method using ADF(Automatically Defined Function). It is believed ADFs allow the evolution of modular solutions and, consequently, improve the performance of the GP technique. The suggested ADF based GP nonlinear regression methods are compared with UM, MLR, and previous GP method for 3 days prediction of wind speed using MOS(Model Output Statistics) for partial South Korean regions. The UM and KLAPS data of 2007-2009, 2011-2013 years are used for experimentation.

• The Korean Journal of Applied Statistics
• /
• v.27 no.3
• /
• pp.419-430
• /
• 2014

An accurate prediction of electricity supply and demand is important for daily life, industrial activities, and national management. In this paper electricity sales is predicted by time series modelling. Real data analysis shows the transfer function model with cooling and heating days as an input time series and a pulse function as an intervention variable outperforms other time series models for the root mean square error and the mean absolute percentage error.