• 한국IT서비스학회지
• /
• 제10권2호
• /
• 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.

• 물과 미래
• /
• 제8권2호
• /
• 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.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 2000년도 가을 학술발표회논문집(I)
• /
• 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.

• 대한안전경영과학회지
• /
• 제4권2호
• /
• 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
• /
• 제41권2호
• /
• pp.111-119
• /
• 1994

배경 및 목적: 폐암 환자의 다수가 흡연력이 있고 만성 폐쇄성 폐질환이 병발되어 있으므로 수술후 폐기능의 변화를 정확히 예측하는 것은 수술후 합병증을 예방하는데 중요하다. 폐 절제술 후 잔여 폐기능을 예측함에 있어 현재까지 99mTc-MAA를 이용한 폐관류 스캔이 많이 이용되어 왔지만 이론적으로 폐환기와 폐관류의 불일치가 있는 경우 오차가 있을 수 있어 $^{99m}Tc$-DTPA 연무흡입 환기 스캔을 이용해 잔류 폐기능을 예측하여 관류 스캔을 비교하여 보았다. 방법: 수술전 연무 흡입스캔과 관류 스캔을 시행하고 수술전에 폐기능을 실시하여 잔여 폐기능을 예측하고 수술후 2개월 뒤에 폐기능을 실시하여 상관관계를 비교하여 보았다. 전 폐절제술인 경우: 수술전 폐기능$\times$전체 폐에 대한 잔류폐의 비 폐엽 절제술인 경우: 수술전 폐기능$\times$(1-침범된 폐의 전체폐에 대한 비$\times$절제될 폐의 분절 수/침범된 폐의 총 분절 수) 결과: 1) $FEV_1$에서 연무 흡입스캔을 이용하여 예측한 값과 실측치 간의 상관 계수는 0.94(p<0.0001), 폐관류 스캔을 이용한 경우는 0.86(p<0.0001)이었으며 두 군간에 통계학적으로 유의한 차이는 없었다. 2) FVC에 흡입스캔을 이용한 경우 상관 계수가 0.91(p<0.0001)이었고 폐관류 스캔에서는 0.72(p=0.0005)로 연무 흡입스캔으로 예측한 군에서 상관 관계가 좋았다. 3) $FEF_{25-75%}$에서의 결과는 연무 흡입스캔을 이용한 경우 상관 계수가 0.87(p=0.0001), 폐관류 스캔에서는 상관 계수가 0.87(p<0.0001)로 두 군간에 유의한 차이는 없었다. 4) 두 스캔을 동시에 시행한 군에서 비교한 결과를 보면 연무 흡입 스캔에서 상관 계수는 $FEV_1$ 0.97(p<0.0001), FVC 0.95(p<0.0001), $FEF_{25-75%}$ 0.85(p<0.001)이었고 폐관류 스캔에서는 $FEV_1$ 0.97(p<0.0001), FVC 0.96(p<0.0001), $FEF_{25-75%}$ 0.83(p<0.002)로 두 군간에 유의한 차이는 없었다. 결론: 수술후 잔여 폐기능을 예측함에 있어 연무 흡입스캔 및 관류 스캔사이에 큰 차이가 없었으며 비교적 정확했고 폐기능중에서는 $FEV_1$이 가장 상관 관계가 좋았다.

• 미생물학회지
• /
• 제39권2호
• /
• pp.67-75
• /
• 2003

비교유전체학의 주요 주제 중 유전자서열을 분류하고 단백질기능을 예측하는 연구가 있으며, 이를 위해 단백질 구조, 공통서열 및 바인딩 위치 예측등의 방법과 함께, 전유전체 서열에서 구해지는 유사도 그래프를 분석해 상동유전자를 검색하는 계산학적인 접근방법이 있다. 유사도그래프를 사용한 방법은 서열에 대한 기존 지식에 의존하지 않는 장점이 있지만 유사도 하한값과 같은 주관적인 임계값이 필요한 단점이 있다. 본 논문에서는 반복적으로 그래프를 분해하는 이전의 방법을 일반화시켜, 유사도 그래프에 기반한 유전자 서열군집분석 방법론과 객관적이고 안정적인 파라미터 임계값 계산 방법을 제안한다. 제시된 방법으로 알려진 미생물 유전체 서 열을 분석하여 이전의 방법인 BAG 알고리즘 결과와 비교했다.

• International Journal of Control, Automation, and Systems
• /
• 제2권2호
• /
• 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
• /
• 제17권5호
• /
• 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.

• 전기학회논문지
• /
• 제64권12호
• /
• 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.

• 응용통계연구
• /
• 제27권3호
• /
• pp.419-430
• /
• 2014

전력수급의 정확한 예측은 국민들의 일상적 생활 유지, 산업활동, 그리고 국가경영을 위하여 매우 중요하다. 본 연구에서는 시계열모형화에 의해 전력판매량을 예측한다. 실제 자료분석을 통하여 입력시계열로서 냉난방도일과 개입변수로 펄스함수를 사용한 전이함수모형이 다른 시계열모형에 비해서 제곱근평균제곱오차 및 평균절대오차의 의미에서 더 우수하였다.