• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.161-168
• /
• 2021

In this study, we propose a cardiovascular disease prediction model using machine learning. First, a multidimensional analysis of various differences between the two groups is performed and the results are visualized. In particular, we propose a predictive model using cost-sensitive learning that can improve the sensitivity for cases where there is a high class imbalance between the normal and patient groups, such as diseases. In this study, a predictive model is developed using CART and XGBoost, which are representative machine learning technologies, and prediction and performance are compared for cardiovascular disease patient data. According to the study results, CART showed higher accuracy and specificity than XGBoost, and the accuracy was about 70% to 74%.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.802-809
• /
• 2021

To cope with the increasing maintenance costs due to aging, the maintenance cost was evaluated from the perspective of asset management. The maintenance cost can be predicted based on the condition of the bridge, and the life cycle cost is used as an index. In general, the condition of a bridge has a wide distribution characteristic depending on the deterioration, load, and material characteristics. In this paper, to evaluate the effect of the bridge conditions on the life cycle cost, condition prediction models were constructed considering the service life, deterioration rate, and inspection error, which are the main variables of the bridge condition and life cycle cost calculation. In addition, condition prediction models were constructed based on the distribution of the health index to estimate the upper and lower bounds of the life cycle costs that can occur in individual bridges. Life cycle cost analysis showed that the life cycle cost differed significantly according to the condition of the bridge. Accordingly, research will be needed to increase the reliability of predicting the life cycle cost of individual bridges.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2006.06a
• /
• pp.55-60
• /
• 2006

Draw-bead is applied to control the material flow in a stamping process and improve the product quality by controlling the draw-bead restraining force (DBRF). Actual die design depends mostly on the trial-and-error method without calculating the optimum DBRF. Die design with the predicted value of DBRF can be utilized at the tryout stage effectively reducing the cost of the product development. For the prediction of DBRF, a simulation-based prediction model of the circular draw-bead is developed using the Box-Behnken design with selected shape parameters such as the bead height, the shoulder radius and the sheet thickness. The value of DBRF obtained from each design case by analysis is approximated by a second order regression equation. This equation can be utilized to the calculation of the restraining force and the determination of the draw-bead shape as a prediction model. For the evaluation of the prediction model, the optimum design of DBRF in sheet metal forming is carried out using response surface methodology. The suitable type of the draw-bead is suggested based on the optimum values of DBRF. The prediction model of the circular draw-bead proposes the design method of the draw-bead shape. The present procedure provides a guideline in the tool design stage for sheet metal forming to reduce the cost of the product development.

• Journal of Convergence for Information Technology
• /
• v.11 no.11
• /
• pp.44-50
• /
• 2021

Recently, enterprise storage systems that require large-capacity storage devices to accommodate big data have used large-capacity flash memory-based storage devices with high density compared to cost and size. This paper proposes a high-efficiency life prediction method with slope descent to maximize the life of flash memory media that directly affects the reliability and usability of large enterprise storage devices. To this end, this paper proposes the structure of a matrix for storing metadata for learning the frequency of defects and proposes a cost model using metadata. It also proposes a life expectancy prediction policy in exceptional situations when defects outside the learned range occur. Lastly, it was verified through simulation that a method proposed by this paper can maximize its life compared to a life prediction method based on the fixed number of times and the life prediction method based on the remaining ratio of spare blocks, which has been used to predict the life of flash memory.

• Journal of the Korean Statistical Society
• /
• v.13 no.2
• /
• pp.107-113
• /
• 1984

In a linear regression model the idependent variables are frequently subject to measurement errors. For this case, the problem of estimating unknown parameters has been extensively discussed in the literature while very few has been concerned with the effect of measurement errors on prediction. This paper investigates the behavior of the predicted values of the dependent variable in terms of the average mean square error of prediction (AMSEP). AMSEP may be used as a criterion for selecting an appropriate estimation method, for designing an estimation experiment, and for developing cost-effective future sampling schemes.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.35 no.5
• /
• pp.1165-1171
• /
• 2015

Due to the increasing trend of operation and maintenance cost (O&M cost) of infrastructure, the accurate estimation of O&M cost is crucial part to the government. Recent literatures pointed out that gradual climate changes such as average temperature changes, average precipitation changes, and etc. have significant impact on infrastructure O&M cost. This research is intended to develop a long-term O&M cost prediction model of road facilities by considering the impacts of average temperature changes. For this end, the climate change scenarios of Intergovernmental Panel on Climate Change (IPCC)'s $5^{th}$ report are adopted to structure the impact of average temperature changes by using binomial lattice model. The proposed framework is expected to regional government in supporting decisions for road O&M cost.

• Journal of Information Technology Applications and Management
• /
• v.11 no.1
• /
• pp.39-51
• /
• 2004

Application systems outsourcing is an important part of IT outsourcing services. Application systems outsourcing costs is determined by service levels of outsourcers. Recent researches show there is a strong need to build industry-specific cost estimation models. In this study, an industry-specific application systems operation cost estimation model is suggested. We reviewed operation cost models of previous researches, and proposed a cost estimation model for security industry. Industry-specific service factors are defined and service levels are determined by Interviews with experts. The proposed model is tested and adjusted with empirical data. The new model shows more accurate prediction than previous general models. Future research will be needed to develop outsourcing cost estimation models for other industries and to refine cost models developed in this study.

• Asia pacific journal of information systems
• /
• v.8 no.3
• /
• pp.101-118
• /
• 1998

The purpose of this study is to construct a value-oriented sizing and cost estimation model for system integration projects. In particular, this study is to build a system architecture design and integration cost model, and a network design and implementation cost model. Unlike software development projects, system integration projects include knowledge-intensive professional services on system architecture and network design areas. Because of these work's high invisibility, the cost of these services is hard to estimate and measure. Therefore, we need to develop value-oriented cost models. This study presents 6 value-oriented cost models, and tests statistical significance of these models with real system integration project data. The results show that cost factors on these models are valid, and models are statistically significant. Future work is needed to integrate various cost models and apply the whole model to field projects to increase model's prediction accuracy.

• The KIPS Transactions:PartB
• /
• v.18B no.5
• /
• pp.271-278
• /
• 2011

Storm and flood such as torrential rains and major typhoons has often caused damages on a large scale in Korea and damages from storm and flood have been increasing by climate change and warming. Therefore, it is an essential work to maneuver preemptively against risks and damages from storm and flood by predicting the possibility and scale of the disaster. Generally the research on numerical model based on statistical methods, the KDF model of TCDIS developed by NIDP, for analyzing and predicting disaster risks and damages has been mainstreamed. In this paper, we introduced the model for prediction of damage cost from storm and flood by the neural network algorithm which outstandingly implements the pattern recognition. Also, we compared the performance of the neural network model with that of KDF model of TCDIS. We come to the conclusion that the robustness and accuracy of prediction of damage cost on TCDIS will increase by adapting the neural network model rather than the KDF model.

• Journal of Internet of Things and Convergence
• /
• v.7 no.4
• /
• pp.9-14
• /
• 2021

In computing systems that require high reliability, the method of predicting the lifetime of a storage device is one of the important factors for system management because it can maximize usability as well as data protection. The life of a solid state drive (SSD) that has recently been used as a storage device in several storage systems is linked to the life of the NAND flash memory that constitutes it. Therefore, in a storage system configured using an SSD, a method of accurately and efficiently predicting the lifespan of a NAND flash memory is required. In this paper, a method for optimizing the lifetime prediction of a flash memory-based storage device using the frequency of NAND flash memory failure is proposed. For this, we design a cost matrix to collect the frequency of defects that occur when processing data in units of Drive Writes Per Day (DWPD). In addition, a method of predicting the remaining cost to the slope where the life-long finish occurs using the Gradient Descent method is proposed. Finally, we proved the excellence of the proposed idea when any defect occurs with simulation.