• The KIPS Transactions:PartD
• /
• v.15D no.2
• /
• pp.207-212
• /
• 2008

This paper evaluates software cost estimation models, and presents the most suitable model. First, we transformed a relevant model into variables to make in linear. Second, we evaluated model's performance considering how much suitable the cost data of the actual development software was. In the stage of model performance evaluation criteria, we used MMRE which is the relative error concept rather than the absolute error. Existing software cost estimation model follows Weibull, Gamma, and Rayleigh function. In this paper, Gompertz function model is suggested which is a kind of growth curve. Additionally, we verify the compatability of other different growth curves. As a result of evaluation of model's performance, Gompertz function was considered to be the most suitable for the cost estimation model.

• Journal of Korea Multimedia Society
• /
• v.22 no.9
• /
• pp.1069-1079
• /
• 2019

In this study, we developed a $PM_{10}$ forecasting model using DNN and Membership Function, and improved the forecasting performance. The model predicts the $PM_{10}$ concentrations of the next 3 days in the Seoul area by using the weather and air quality observation data and forecast data. The best model(RM14)'s accuracy (82%, 76%, 69%) and false alarm rate(FAR:14%,33%,44%) are good. Probability of detection (POD: 79%, 50%, 53%), however, are not good performance. These are due to the lack of training data for high concentration $PM_{10}$ compared to low concentration. In addition, the model dose not reflect seasonal factors closely related to the generation of high concentration $PM_{10}$. To improve this, we propose Julian date membership function as inputs of the $PM_{10}$ forecasting model. The function express a given date in 12 factors to reflect seasonal characteristics closely related to high concentration $PM_{10}$. As a result, the accuracy (79%, 70%, 66%) and FAR (24%, 48%, 46%) are slightly reduced in performance, but the POD (79%, 75%, 71%) are up to 25% improved compared with those of the RM14 model. Hence, this shows that the proposed Julian forecast model is effective for high concentration $PM_{10}$ forecasts.

• Journal of the Korean Institute of Navigation
• /
• v.11 no.1
• /
• pp.67-91
• /
• 1987

In this paper, a synthetic method for evaluating the seakeeping performance of a ship in waves is studied. For the prediction and evaluation of irregular phenomena to be correlated each other, the multi-dimensional Rayleigh's joint probability density function and the cumulative distribution function are approximated. According to this approximated function, it is able to calculate easily the occurrence probability of the factors on seakeeping performance. We proposed an evaluation method and an index to be defined by the seakeeping performance reliability, that is considered as the dangerousness and the relative dangerousness of the factors on seakeeping performance in waves. The use of this method aid index will be effective to install the sensors which are necessary to evaluate the states of ships at sea. Some example of the calculations by this method for 175m length single screw container ship equipped with diesel engine are also presented.

• Journal of Korean Institute of Industrial Engineers
• /
• v.37 no.4
• /
• pp.271-278
• /
• 2011

This paper is to review and organize performance strategies, issues, and measures for the efficient operation of order picking function. Order picking is the process of retrieving items from storage to meet a specific customer order, which is known to be the most labor-intensive and costly function among all the warehouse functions. This function is also important in that it has a critical impact on downstream customer service. For understanding the background of order picking and related performance issues, we will briefly introduce warehousing functions. Then we will introduce material handling within a warehouse and order picking strategies. Lastly, we will discuss about performance issues and measures in the domain of order picking operations. Productive and quality measures will be reviewed in more detail.

• Proceedings of the IEEK Conference
• /
• 2003.11c
• /
• pp.15-19
• /
• 2003

In this paper, the bit error rate (BER) performance of the fast frequency hopping/M-ary frequency shift keying system using the clipper receiver is analyzed by using the characteristic function (CF) technique in the presence of n=1 band multitone jamming and additive white Gaussian noise environment. The CFs of the clipper receiver outputs are derived as a infinite series representation using Gamma function and Marcum's Q -function. The analytical results are validated with various simulation results. Performance comparisons with linear combining receiver are shown that the BER performance of the clipper receiver is much better than that of the linear combining receiver In addition, as the clipping level approaches to infinity, it is shown that the clipper receiver simply performs a linear combining without clipping and there exists an optimum value of diversity level (the number of hops per symbol) that maximizes the worst case BER performance of the clipper receiver.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2021.05a
• /
• pp.255-256
• /
• 2021

The performance measurement of construction projects has traditionally been evaluated as a prerequisite for successful project completion. Considering this importance, the UK and the US are operating quantitative performance measurement systems for construction projects. However, in the case of Korea, there is a limit to the use of existing methods due to the limitation of data collection. Recently, in consideration of the domestic situation, research is being conducted to measure the quantitative performance of a project by using big data including progress and project attribute information. Therefore, this study aims to present the design direction of a performance monitoring system using Quality Function Deployment.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.9
• /
• pp.371-380
• /
• 2022

Convolutional neural networks are widely used to manipulate data arranged in a grid, such as images. A general convolutional neural network consists of a convolutional layers and a fully connected layers, and each layer contains a nonlinear activation functions. This paper proposes a combined parametric activation function to improve the performance of convolutional neural networks. The combined parametric activation function is created by adding the parametric activation functions to which parameters that convert the scale and location of the activation function are applied. Various nonlinear intervals can be created according to parameters that convert multiple scales and locations, and parameters can be learned in the direction of minimizing the loss function calculated by the given input data. As a result of testing the performance of the convolutional neural network using the combined parametric activation function on the MNIST, Fashion MNIST, CIFAR10 and CIFAR100 classification problems, it was confirmed that it had better performance than other activation functions.

• Journal of Families and Better Life
• /
• v.32 no.1
• /
• pp.13-26
• /
• 2014

The purpose of this study was to explore the effects of parenting behaviors on preschoolers' executive function, focusing on methods of measuring executive function. The subjects of this study were 166 preschoolers who were 3 to 5 years of age, and their parents. Data were collected by various performance-based tests and their parents' reports and analyzed by descriptive statistics and hierarchical linear regression analysis using the SPSS 19.0 program. The major results were as follows: First, maternal autonomous and paternal affective parenting behaviors significantly affected preschoolers' performance-based executive function. Second, maternal affective parenting behaviors significantly affected preschoolers' parent-report executive function. The results suggest the importance of positive parenting practices in the development of preschoolers' executive function.

• 한국정보통신설비학회:학술대회논문집
• /
• 2009.08a
• /
• pp.382-386
• /
• 2009

Online or sequential learning is one of the most basic and powerful method to train neuron network, and it has been widely used in disease detection, weather prediction and other realistic classification problem. At present, there are many algorithms in this area, such as MRAN, GAP-RBFN, OS-ELM, SVM and SMC-RBF. Among them, SMC-RBF has the best performance; it has less number of hidden neurons, and best efficiency. However, all the existing algorithms use signal normal distribution as kernel function, which means the output of the kernel function is same at the different direction. In this paper, we use multi-variable normal distribution as kernel function, and derive EKF learning formulas for multi-variable normal distribution kernel function. From the result of the experience, we can deduct that the proposed method has better efficiency performance, and not sensitive to the data sequence.

• Communications for Statistical Applications and Methods
• /
• v.16 no.2
• /
• pp.383-388
• /
• 2009

In this paper we propose a variance function estimation method based on kernel trick for replicated data or data consisted of sample variances. Newton-Raphson method is used to obtain associated parameter vector. Furthermore, the generalized approximate cross validation function is introduced to select the hyper-parameters which affect the performance of the proposed variance function estimation method. Experimental results are then presented which illustrate the performance of the proposed procedure.