• 디지털산업정보학회논문지
• /
• 제10권3호
• /
• pp.1-9
• /
• 2014

The inverse Rayleigh model distribution and Rayleigh distribution model were widely used in the field of reliability station. In this paper applied using the finite failure NHPP models in order to growth model. In other words, a large change in the course of the software is modified, and the occurrence of defects is almost inevitable reality. Finite failure NHPP software reliability models can have, in the literature, exhibit either constant, monotonic increasing or monotonic decreasing failure occurrence rates per fault. In this paper, proposes the inverse Rayleigh and Rayleigh software reliability growth model, which made out efficiency application for software reliability. Algorithm to estimate the parameters used to maximum likelihood estimator and bisection method, model selection based on mean square error (MSE) and coefficient of determination($R^2$), for the sake of efficient model, were employed. In order to insurance for the reliability of data, Laplace trend test was employed. In many aspects, Rayleigh distribution model is more efficient than the reverse-Rayleigh distribution model was proved. From this paper, software developers have to consider the growth model by prior knowledge of the software to identify failure modes which can helped.

• International Journal of Quality Innovation
• /
• 제1권1호
• /
• pp.89-96
• /
• 2000

Evolutionary operation (EVOP) is a continuous improvement system which explores a region of process operating conditions by deliberately creating some systematic changes to the process variable levels without jeopardizing the product. It is aimed at securing a satisfactory operating condition in full-scale manufacturing processes, which is generally different from that obtained in laboratory or pilot plant experiments. Information on how to improve the process is generated from a simple experimental design. Traditional EVOP procedures are established on the assumption that the variance of the response variable should be small and stable in the region of the process operation. However, it is often the case that process noises have an influence on the stability of the process. This process instability is due to many factors such as raw materials, ambient temperature, and equipment wear. Therefore, process variables should be optimized continuously not only to meet the target value but also to keep the variance of the response variables as low as possible. We propose a scheme to achieve robust process improvement. As a process performance measure, we adopted the mean square error (MSE) of the replicate response values on a specific operating condition, and used the Kruskal-Wallis test to identify significant differences between the process operating conditions.

• 대한산업공학회지
• /
• 제40권3호
• /
• pp.283-290
• /
• 2014

In the flat panel display industry, to meet production target quantities and the deadline of production, the scheduler and dispatching systems are major production management systems which control the order of facility production and the distribution of WIP (Work In Process). Especially the delivery time is a key factor of the dispatching system for the time when a lot can be supplied to the facility. In this paper, we use survival analysis methods to identify main factors of the delivery time and to build the delivery time forecasting model. To select important explanatory variables, the cox proportional hazard model is used to. To make a prediction model, the accelerated failure time (AFT) model was used. Performance comparisons were conducted with two other models, which are the technical statistics model based on transfer history and the linear regression model using same explanatory variables with AFT model. As a result, the mean square error (MSE) criteria, the AFT model decreased by 33.8% compared to the statistics prediction model, decreased by 5.3% compared to the linear regression model. This survival analysis approach is applicable to implementing the delivery time estimator in display manufacturing. And it can contribute to improve the productivity and reliability of production management system.

• Earthquakes and Structures
• /
• 제14권2호
• /
• pp.129-142
• /
• 2018

The current paper introduces a new approach for development of damage index to obtain the maximum damage in the reinforced concrete frames caused by as-recorded single and consecutive earthquakes. To do so, two sets of strong ground motions are selected based on maximum and approximately maximum peak ground acceleration (PGA) from "PEER" and "USGS" centers. Consecutive earthquakes in the first and second groups, not only occurred in similar directions and same stations, but also their real time gaps between successive shocks are less than 10 minutes and 10 days, respectively. In the following, a suite of six concrete moment resisting frames, including 3, 5, 7, 10, 12 and 15 stories, are designed in OpenSees software and analyzed for more than 850 times under two groups of as-recorded strong ground motion records with/without seismic sequences phenomena. The idealized multilayer artificial neural networks, with the least value of Mean Square Error (MSE) and maximum value of regression (R) between outputs and targets were then employed to generate the empirical charts and several correction equations for design utilization. To investigate the effectiveness of the proposed damage index, calibration of the new approach to existing real data (the result of Park-Ang damage index 1985), were conducted. The obtained results show good precision of the developed ANNs-based model in predicting the maximum damage of regular reinforced concrete frames.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권9호
• /
• pp.3559-3571
• /
• 2015

This paper addresses the problem of signal acquisition with a sparse representation in a given orthonormal basis using fewer noisy measurements. The authors formulate the problem statement for randomly measuring with strong signal noise. The impact of white Gaussian signals noise on the recovery performance is analyzed to provide a theoretical basis for the reasonable design of the measurement matrix. With the idea that the measurement matrix can be adapted for noise suppression in the adaptive CS system, an adapted selective compressive sensing (ASCS) scheme is proposed whose measurement matrix can be updated according to the noise information fed back by the processing center. In terms of objective recovery quality, failure rate and mean-square error (MSE), a comparison is made with some nonadaptive methods and existing CS measurement approaches. Extensive numerical experiments show that the proposed scheme has better noise suppression performance and improves the support recovery of sparse signal. The proposed scheme should have a great potential and bright prospect of broadband signals such as biological signal measurement and radar signal detection.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권8호
• /
• pp.3589-3605
• /
• 2018

In this paper, we investigate an individual channel estimation problem for multiple-input multiple-output (MIMO) two-way amplify-and-forward (AF) relay networks. To avoid self-interference during the estimation of the individual MIMO channels, a novel blind interference cancellation (BIC) approach is proposed based on an orthogonal preceding framework, where a pair of orthogonal precoding matrices is utilized at the source nodes. By designing an optimal decoding scheme, we propose to decompose the bidirectional transmission into a pair of unidirectional transmissions. Unlike most existing approaches, we make the practical assumption that the nonreciprocal MIMO channel and the mutual interference of multiple antennas are both taken into consideration. Under the precoding framework, we employ an orthogonal superimposed training strategy to obtain the individual MIMO channels. However, the AF strategy causes the noise at the terminal to be the sum of the local noise and the relay-propagated noise. To remove the relay-propagated noise during the estimation of the second-hop channel, a partial noise-nulling method is designed. We also derive a closed-form expression for the total mean square error (MSE) of the MIMO channel from which we compute the optimal power allocation. The simulation results demonstrate that the analytical and simulated curves match fully.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2007년도 정기 학술대회 논문집
• /
• pp.565-570
• /
• 2007

Fiber reinforced polymer(FRP) composite decks are new to bridge applications and hence not much literature exists on their structural mechanical behavior. As there are many differences between numerical displacements through static analysis of the primary model and experimental displacements through static load tests, system identification (SI)techniques such as Neural Networks (NN) and support vector machines (SVM) utilized in the optimization of the FE model. During the process of identification, displacements were used as input while stiffness as outputs. Through the comparison of numerical displacements after SI and experimental displacements, it can note that NN and SVM would be effective SI methods in modeling an FRP deck. Moreover, two methods such as response surface method and iteration were proposed to optimize the estimated stiffness. Finally, the results were compared through the mean square error (MSE) of the differences between numerical displacements and experimental displacements at 6 points.

• 전기학회논문지
• /
• 제56권11호
• /
• pp.2040-2050
• /
• 2007

In this study, we present a novel method for estimating the information of MU(motor unit) which is the basic element of human muscle by using surface EMG. Some of the method developed in this field could only estimate the numbers of MU that is activated. However, in our study the MU-simulator based on the line source model was designed to estimate the MU information including the numbers of MU and muscle fiber, conduction velocity, MU diameter, fiber diameter, and end plate position. The SMUAP(single motor unit action potential) detector was designed and CMAP(compound muscle action potential) by electrical stimulus was recorded. With these data, the MU-simulator can estimate the MU information by varying muscle paramater settings through MSE(mean square error) method. Our results shows that the proposed method can be comparable with the method of anatomical studies. Moreover, our system can be utilized to build a tool for diagnosis and treatment assessment of neuromuscular patients.

• Bulletin of the Korean Chemical Society
• /
• 제26권1호
• /
• pp.139-145
• /
• 2005

Artificial neural networks (ANNs), for a first time, were successfully developed for the modeling and prediction of solvent effects on rate constant of [2+2] cycloaddition reaction of diethyl azodicarboxylate with ethyl vinyl ether in various solvents with diverse chemical structures using quantitative structure-activity relationship. The most positive charge of hydrogen atom (q$^+$), dipole moment ($\mu$), the Hildebrand solubility parameter (${\delta}_H^2$) and total charges in molecule (q$_t$) are inputs and output of ANN is log k$_2$ . For evaluation of the predictive power of the generated ANN, the optimized network with 68 various solvents as training set was used to predict log k$_2$ of the reaction in 16 solvents in the prediction set. The results obtained using ANN was compared with the experimental values as well as with those obtained using multi-parameter linear regression (MLR) model and showed superiority of the ANN model over the regression model. Mean square error (MSE) of 0.0806 for the prediction set by MLR model should be compared with the value of 0.0275 for ANN model. These improvements are due to the fact that the reaction rate constant shows non-linear correlations with the descriptors.

• 산업경영시스템학회지
• /
• 제33권1호
• /
• pp.1-9
• /
• 2010

Quality design methodologies have received constituent attention from a number of researchers and practitioners for more than twenty years. Specially, the quality design for drug products must be carefully considered because of the hazards involved in the pharmaceutical industry. Conventional pharmaceutical formulation design problems with mixture experiments have been typically studied under the assumption of an unconstrained experimental region with a single quality characteristic. However, real-world pharmaceutical industrial situations have many physical limitations. We are often faced with multiple quality characteristics with constrained experimental regions. ln order to address these issues, the main objective of this paper is to propose a robust desirability function (RDF) model using a desirability function (DF) and mean square error (MSE) to simultaneously consider a number of multiple quality characteristics. This paper then present L-pseudocomponents and U-pseudocomponents to handle physical constraints. Finally, a numerical example shows that the proposed RDF can efficiently be applied to a pharmaceutical process design.