• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.872-875
• /
• 2009

In a bankruptcy prediction model, the accuracy is one of crucial performance measures due to its significant economic impacts. Ensemble is one of widely used methods for improving the performance of classification and prediction models. Two popular ensemble methods, Bagging and Boosting, have been applied with great success to various machine learning problems using mostly decision trees as base classifiers. In this paper, we analyze the performance of boosted neural networks for improving the performance of traditional neural networks on bankruptcy prediction tasks. Experimental results on Korean firms indicated that the boosted neural networks showed the improved performance over traditional neural networks.

• The Journal of Korea Robotics Society
• /
• v.16 no.2
• /
• pp.130-136
• /
• 2021

In recent years, much study has been conducted in robotic grasping. The grasping algorithms based on deep learning have shown better grasping performance than the traditional ones. However, deep learning-based algorithms require a lot of data and time for training. In this study, a grasping algorithm using an artificial neural network-based graspability estimator is proposed. This graspability estimator can be trained with a small number of data by using a neural network based on the residual blocks and point clouds containing the shapes of objects, not RGB images containing various features. The trained graspability estimator can measures graspability of objects and choose the best one to grasp. It was experimentally shown that the proposed algorithm has a success rate of 90% and a cycle time of 12 sec for one grasp, which indicates that it is an efficient grasping algorithm.

• Korean Journal of Applied Biomechanics
• /
• v.31 no.1
• /
• pp.44-49
• /
• 2021

Objective: The purpose of this study was to analyze kinematic variables according to ground slope angle during golf putting. Method: 26 collegiate golfers (age: 22.54±2.15 kg, height: 174.64±6.07 cm, weight: 71.35±9.27 kg, handicap: 5.11±4.50) were participated, and 8 motion capture cameras (250 Hz), Nexus, and Kwon3DXP software were used to collect data. It was performed repeated measures ANOVA and Bonferroni adjustment. Alpha set at .05. Results: Body alignments were not significantly different at address. Putter head trajectory and loft angle were significantly different, and AP direction of acceleration of putter head was significantly different. However, ML and SI direction of acceleration of putter head were not significantly different. Conclusion: Therefore, it was identified that ground slope angle was affected the kinematic variables during putting, and it will be performed that correlation analysis between putting success rate and kinematic variables according to ground slope angle during golf putting.

• The KIPS Transactions:PartD
• /
• v.13D no.1 s.104
• /
• pp.61-66
• /
• 2006

It is reported that the success ratio of software development projects has been only 30%. Many causes lower project's chance of success, particularly lack of systematic project management. Especially, moving on the next phase of project with unsatisfactory outputs can be very problematic because it can cause much waste of resource, time and even lead to the failure of the whole project. Peer review and inspection are some of the practices designed to prevent such waste and possible failure. When defects are identified through such progress, each developer has to work on the product component again and fix the problem. This process is called rework. In this paper, we propose a method for improving quality of reworked product component to prevent excessive cost and time consumed caused by moving on the next phase of a project with a problematic product component. More specifically, this paper suggests a rework indicator that measures the level of rework based on its complexity and severity and is used to choose appropriate checking method on reworked product component. The research also confirmed the method's usefulness and effectiveness by applying the suggested method on four projects.

• Knowledge Management Research
• /
• v.17 no.3
• /
• pp.65-91
• /
• 2016

Although the success of industrial clusters largely depends on whether clustering firms can achieve economic performance, there has been less attention on investigating factors and conditions contributing to the performance enhancement for clustering small and medium-sized enterprises (SMEs). Along this vein, we adopt the theories of social capital and organizational learning as those success factors for clustering SMEs. This study thus aims at examining what effect social capital accrued in the relationships among actors within clusters has on firm performance of clustering SMEs and what role organizational learning plays in the linkage between social capital and firm performance. For the empirical analysis, we operationalized the variables and their measures to develop questionnaires through the theoretical reviews on literatures. As a sample of 227 clustering SMEs, our collected data was analyzed by hierarchical regression analysis. The results confirmed that a high level of social capital, represented by network, trust, and norm, has positive effect on firm performance of clustering SMEs. We also found that clustering firms presenting high organizational learning, represented by absorptive and transformative capability, achieve better performance than those placing less value on organizational learning. Furthermore the significant relationship between social capital and firm performance is mediated partially through organizational learning. These findings imply not only that the territorial agglomeration of industrial cluster does not guarantee the performance creation of clustering SMEs but that they need to develop social capital among various actors within clusters, facilitating their knowledge diffusion. In order to absorb and mobilize the shared knowledge and information into strategic resources, the firms should improve their capability associated with organizational learning. These expand our understanding on the importance of social capital and organizational learning for the performance enhancement of clustering firms. Differentiating from major studies addressing benefits and advantages of industrial cluster, this study based on the perspective of firm-internal business process contributes to the literature advancement. Strategic and policy implications of this study are discussed in detail.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.3
• /
• pp.209-216
• /
• 2012

The purpose of this study is to find the UCC (User Created Contents) communication structure in the perspective of smart-phone technologies or SNS (Social Network Service). In developing the research model, we have focused on selecting the success factors appropriate for the UCC through reviewing past researches and on developing more accurate success measures. The model consists of relation each service (Facebook linked in Flickr and so on), relation of trust, transfer to Social Capital and so on . The result shows thar process of trust based in UCC is the most important determinants of structure and organization network. And collaboration relationship is the most important of SNS used in SSO and Open-API technologies. The practice characteristic of UCC has direct and indirect effect on SNS of improving social trust.

• The Journal of Korean Medicine
• /
• v.35 no.2
• /
• pp.1-11
• /
• 2014

Objectives: To evaluate the effect of acupuncture as an adjunct treatment to increase the success rate of in vitro fertilisation (IVF). Methods: A review of the English and Korean literature was conducted to identify studies on acupuncture as an adjunct treatment to IVF. The main outcome measures were the biochemical pregnancy rate (BPR), the implantation rate (IR), the clinical pregnancy rate (CPR), the miscarriage rate (MR), the on-going pregnancy rate (OPR) and the live birth rate (LBR). Results: Nine meta-analyses of 11 systematic reviews (SRs) were included in this review. In four SRs, the overall IVF outcomes regardless of the procedural steps were documented; two of these SRs reported a significant effect on the CPR. One SR reported that acupuncture at the time of controlled ovarian hyperstimulation had a significant effect on the BPR. Seven SRs reported that acupuncture had no significant impact on transvaginal oocyte retrieval (TVOR). In eight SRs, significant impacts on the CPR, LIBR and OPR were reported when acupuncture was performed around the time of embryo transfer (ET). The results of repeated acupuncture after ET were included in two SRs, which included the same primary studies. The results of the SRs showed that acupuncture had a positive effect on the CPR. Conclusions: When the complete IVF procedure is analysed, there is conflicting evidence in that some reviews have found that acupuncture leads to an increased CPR but others have not. In addition, the reviews presented no evidence to suggest that acupuncture has any specific risks.

• Asia pacific journal of information systems
• /
• v.14 no.1
• /
• pp.101-123
• /
• 2004

User satisfaction has been widely used by information system(IS) researchers as the most appropriate surrogate variable for the systems success since Bailey and Pearson(1983) provided their user satisfaction measurement. Because user satisfaction is a perceived performance measure by users, not a real or objective measure for systems success, however, perceived user satisfaction by users may not be exactly identical with the real systems performance. In this regard, if the user's ultimately perceived satisfaction is different from the real systems performance, we need to investigate why these two measures are different and which factors may cause the difference. From the perspective of disconfirmation of user expecations, this study examined why user satisfaction and real systems performance may not be identical each other. Expectaion-disconfirmation theory which has had a central role in marketing in explaining the effects of expectation and disconfirmation on consumer satisfaction was similarly adopted in this study to explain the role of expectation and disconfirmation in user satisfaction in the IS environment. Based on the expectation-disconfirmation theory, the current study developed a research model to examine the effects of expectation, system performance, and disconfirmation on user satisfaction in particular. Six research hypotheses derived from the research model were empirically tested using the partial least squares(PLS) method. The results of the statistical analysis indicate that the effects of system performance and disconfirmation were fairly strong on user satisfaction, while the user's expectation has shown insignificant influences on user satisfaction.

• Journal of Agricultural Extension & Community Development
• /
• v.19 no.3
• /
• pp.699-727
• /
• 2012

Conditions of farm crop switching are affected by several important external factors such as agricultural products import opening, policy support, and climate change. Farming environment is always changing; barriers to imports are becoming lower and lower because of FTA and others, and climate change affects a boundary line of cultivation. Those situations give farmers motivation to change crops in order to cope with them. In addition, crop switching has been done in response to the local government measures about purchase of local agricultural products according to the local food and the expansion of organic agricultural products in school meal. Even though the favorable environment toward crop switching has been created, there are not many researches or outcomes regarding crop switching. Only few studies focus on the list of decision-making in crop switching, and locally suitable crop selection is not treated. In order to utilize crop switching as a farm management strategy, the proper frame should be studied and practical researches on application possibility also need. Therefore, study on crop switching is in a timely, proactive manner because farms catch the chance of expansion of school meal by changing crops. This paper applies HERO model used for venture foundation process to crop switching process. Success factors of HERO model are comprised of Habitate, Entrepreneurship, Resource, and Opportunity, and these phased application factors are applied to crop switching process. By doing so, each phase success factor of crop switching can be uncovered. Three farm organizations supplying organic agricultural products to schools are studied in Gyeonggi province. As a result, the stabilization stage cannot be achieved because of the habitate conditions and social conditions with low risk bearing of crop switching and current school meal systems are the main problems to block the diversification of risks. In order to succeed in crop switching, constructing the habitate in local districts or in systems of school meal is more effective than supporting each farm.

• Asia pacific journal of information systems
• /
• v.5 no.1
• /
• pp.236-257
• /
• 1995

Not much attention has been paid to the characteristics of successful MIS in small business in Korea. This study compares the characteristics of successful MIS with those of less successful MIS of manufacturing industry in Korea in terms of micro level, macro level, and personal level. The micro level consists of those variables relating to the system development and maintenance while the macro level consists of the environmental variables relating to the information systems. The personal level measures a personal EDP experience. A mail survey was sent to small manufacturing companies to collect the data for the hypothesis tests. And 81 usable questionnaires were returned for data analysis. This study performs the validity of the categorization of variables in terms of three levels. The results shows that this categorization is appropriate but the personal level. As the personal experiences of EDP in Korea used to come up with those of the organization, the variables in the personal level have high correlations with those in the macro level in empirical testing. As the personal level, however, is different dimension from the macro level in theoretical aspect, the level is maintained separately throughout the study. The data were analyzed with MANOVA and two group discriminant analysis. The analyses reveal that the characteristics of successful MIS are different from those of less successful MIS in terms of three levels. And the micro level is more important than the macro level to develop successful MIS. That is because the organizations have relatively few experience in dealing with information systems, they have not developed unique information systems which are adjusted to their organizational characteristics. Those findings seems to be important determinants of success for the MIS in a firm.