• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.4
• /
• pp.219-226
• /
• 2013

Feature selection is the one of important issues in the field of machine learning and pattern recognition. It is the technique to find a subset from the source data and can give the best classification performance. Ie, it is the technique to extract the subset closely related to the purpose of the classification. In this paper, we experimented to select the best feature subset for improving classification accuracy when classify success and failure factors in software reuse. And we compared with existing studies. As a result, we found that a feature subset was selected in this study showed the better classification accuracy.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2007.11a
• /
• pp.463-468
• /
• 2007

The disputes in construction projects are very important issue for stakeholders. However, many of presented claims have not received the compensation money required, and frequently turned down. The most cause is that the claims are not managed systemically on construction. Therefore, it is important to identify which management works are conducted on construction and how significantly do they relevant to construction claim. This research derives key claim management factors through analyzing causes for claim success and failure, and then presents management works relevant to them. This research also proposes the method for effective claim management and its expected effect through expert interview.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4725-4747
• /
• 2020

Software defined networking (SDN) is considered to be one of the most promising paradigms in the future. To solve the scalability and performance problem that a single and centralized controller suffers from, the distributed multi-controller architecture is adopted, thus forms multi-domain SDN. In a multi-domain SDN network, it is of great importance to ensure a reliable control plane. In this paper, we focus on the reliability problem of multi-domain SDN against controller failure from perspectives of backup controller deployment and controller replication. We firstly propose a placement algorithm for backup controllers, which considers both the reliability and the cost factors. Then a controller replication mechanism based on shared data storage is proposed to solve the inconsistency between the active and standby controllers. We also propose a shared data storage layout method that considers both reliability and performance. Besides, a fault recovery and repair process is designed based on the controller backup and shared data storage mechanism. Simulations show that our approach can recover and repair controller failure. Evaluation results also show that the proposed backup controller placement approach is more effective than other methods.

• Geomechanics and Engineering
• /
• v.15 no.2
• /
• pp.721-728
• /
• 2018

The surrounding rock mass contains cracks and joints which are distributed randomly around tunnels, and in the process of tunnel blasting excavation, radial cracks could also be induced in the surrounding rock mass. In order to clearly understand the impact of radial cracks on tunnel stability, tunnel model tests and finite element numerical analysis were implemented in this paper. Two kinds of materials: cement mortar and sandstone, were used to make tunnel models, which were loaded vertically and confined horizontally. The tunnel failure pattern was simulated by using RFPA2D code, and the Tresca stresses and the stress intensity factors were calculated by using ABAQUS code, which were applied to the analysis of tunnel model test results. The numerical results generally agree with the model test results, and the mode II stress intensity factors calculated by ABAQUS code can well explain the model test results. It can be seen that for tunnels with a radial crack emanating from three points on tunnel edge, i.e., the middle point between tunnel spandrel and its top with a dip angle $45^{\circ}$, the tunnel foot with a dip angle $127^{\circ}$, and the tunnel spandrel with $135^{\circ}$ with tunnel wall, the tunnel model strength is about a half of the regular tunnel model strength, and the corresponding tunnel stability decreases largely.

• Journal of Digital Convergence
• /
• v.13 no.12
• /
• pp.143-149
• /
• 2015

This study aims to analyze the predict capability of some of the popular software NHPP reliability models(Goel-Okumo model, delayed S-shaped reliability model and Rayleigh distribution model). The predict capability analysis will be on two key factors, one pertaining to the degree of fitment on available failure data and the other for its prediction capability. Estimation of parameters for each model was used maximum likelihood estimation using first 80% of the failure data. Comparison of predict capability of models selected by validating against the last 20% of the available failure data. Through this study, findings can be used as priori information for the administrator to analyze the failure of software.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.65-75
• /
• 2021

This study explores multiple variables of an OTT service for discovering hidden relationship between rating and the other variables of each successful and failed content, respectively. In order to extract key variables that are strongly correlated to the rating across the contents, this work analyzes 170 Netflix original dramas and 419 movies. These contents are classified as success and failure by using the rating site IMDb, respectively. The correlation between the contents, which are classified via rating, and variables such as violence, lewdness and running time are analyzed to determine whether a certain variable appears or not in each successful and failure content. This study employs a regression analysis to discover correlations across the variables as a main analysis method. Since the correlation between independent variables should be low, check multicollinearity and select the variable. Cook's distance is used to detect and remove outliers. To improve the accuracy of the model, a variable selection based on AIC(Akaike Information Criterion) is performed. Finally, the basic assumptions of regression analysis are identified by residual diagnosis and Dubin Watson test. According to the whole analysis process, it is concluded that the more director awards exist and the less immatatable tend to be successful in movies. On the contrary, lower fear tend to be failure in movies. In case of dramas, there are close correlations between failure dramas and lower violence, higher fear, higher drugs.

• Computers and Concrete
• /
• v.30 no.3
• /
• pp.175-183
• /
• 2022

To study the working mechanism and size effect of an innovative dovetail UHPC joint originated from the 5th Nanjing Yangtze River Bridge, a large-scale testing subject to negative bending moment was conducted and compared with the previous scaled specimens. The static responses, i.e., the crack pattern, failure mode, ductility and stiffness degradation were analyzed. It was found that the scaled specimens presented similar working stages and working mechanism with the large-scale ones. However, the post-cracking ductility and relative stiffness degradation all decrease with the enlarged length/scale, apart from the relative stiffness after flexural cracking. The slab stiffness at the flexural cracking stage is 90% of the initial stiffness while only 24% of the initial stiffness reserved in the ultimate stage. Finite element model (FEM) was established and compared with the experiments to verify its effectiveness in exploring the working mechanism of the innovative joint. Based on this effective method, a series of FEMs were established to further study the influence of material strength, pre-stressing level and ratio of reinforcement on its deflection-load relationship. It is found that the ratio of reinforcement can significantly improve its load-carrying capacity among the three major-influenced factors.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2021.05a
• /
• pp.151-152
• /
• 2021

The sale price of apartment buildings is a key factor in the success or failure of apartment projects, and the factors that affect the sale price of apartments vary widely, including location, environmental factors, and economic conditions. Existing methods of predicting the sale price do not reflect the nonlinear characteristics of apartment prices, which are determined by the complex impact factors of reality, because statistical analysis is conducted under the assumption of a linear model. To improve these problems, a new analysis technique is needed to predict apartment sales prices by complex nonlinear influencing factors. Using machine learning techniques that have recently attracted attention in the field of engineering, it is possible to predict the sale price reflecting the complexity of various factors. Therefore, this study aims to conduct a basic study for the development of a machine learning-based prediction model for apartment sale prices.

• Geomechanics and Engineering
• /
• v.13 no.6
• /
• pp.1027-1044
• /
• 2017

Membrane penetration is the most important factor influencing the measurement of volume change for triaxial consolidated-drained shear test for coarse-grained soil. The effective pressure p, average particle size $d_{50}$, thickness $t_m$ and elastic modulus $E_m$ of membrane, contact area between membrane and soil $A_m$ as well as the initial void ratio e are the major factors influencing membrane penetration. According to the membrane deformation model given by Kramer and Sivaneswaran, an analytical solution of the membrane penetration considering the initial void ratio is deduced using the energy conservation law. The basic equations from theory of plates and shells and the elastic mechanics are employed during the derivation. To verify the presented solution, isotropic consolidation tests of a coarse-grained soil are performed by using the method of embedding different diameter of iron rods in the triaxial samples, and volume changes due to membrane penetration are obtained. The predictions from presented solution and previous analytical solutions are compared with the test results. It is found that the prediction from presented analytical solution agrees well with the test results.

• Journal of the Korea Safety Management & Science
• /
• v.15 no.1
• /
• pp.109-120
• /
• 2013

As information-oriented industry has been developed and electronic devices has come to be smaller, lighter, multifunctional, and high speed, the components used to the devices need to be much high density and should have find pattern due to high integration. Also, diverse reliability problems happen as user environment is getting harsher. For this reasons, establishing and securing products and components reliability comes to key factor in company's competitiveness. It makes accelerated test important to check product reliability in fast way. Out of fine pattern failure modes, failure of Electrochemical Migration(ECM) is kind of degradation of insulation resistance by electro-chemical reaction, which it comes to be accelerated by biased voltage in high temperature and high humidity environment. In this thesis, the accelerated life test for failure caused by ECM on fine pattern substrate, $20/20{\mu}m$ pattern width/space applied by Semi Additive Process, was performed, and through this test, the investigation of failure mechanism and the life-time prediction evaluation under actual user environment was implemented. The result of accelerated test has been compared and estimated with life distribution and life stress relatively by using Minitab software and its acceleration rate was also tested. Through estimated weibull distribution, B10 life has been estimated under 95% confidence level of failure data happened in each test conditions. And the life in actual usage environment has been predicted by using generalized Eyring model considering temperature and humidity by developing Arrhenius reaction rate theory, and acceleration factors by test conditions have been calculated.