• Journal of Intelligence and Information Systems
• /
• v.13 no.3
• /
• pp.31-45
• /
• 2007

Large data handling is one of critical issues that the data mining community faces. This is particularly true for computationally intense tasks such as data clustering. Random sampling of instances is one possible means of achieving large data handling, but a pervasive problem with this approach is how to deal with the noise in the evaluation of the learning algorithm. This paper develops a new optimization based clustering approach using an algorithm specifically designed for noisy performance. Numerical results show this algorithm better than the other algorithms such as PAM and CLARA. Also with this algorithm substantial benefits can be achieved in terms of computational time without sacrificing solution quality using partial data.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2005.11a
• /
• pp.365-368
• /
• 2005

While the goal of new IT adoption in small and medium sized firms is to choose an optimal system to fit with their own environments and conditions, that of IT post-adoption usage is to fully implement new IT and maximize their benefits from it. Therefore, the decision-making environments of new IT adoption is definitely different from those of post-adoption. Also, The direct experience of IT usage can provide some learning effect and the change of users' beliefs on new IT. From this point of view, this study attempts to figure out the differences of influencing factors on IOS usage intention between adopters and non-adopters. The results show that there are clear differences of influencing factors between two groups. Non-adopter group shows that perceived financial cost and ability of use have significant influences on IOS usage intention, while relative advantage and perceived risk in adopter group have statistically significant influences on post-adoption usage of IOS.

• Nutrition Research and Practice
• /
• v.5 no.6
• /
• pp.578-584
• /
• 2011

Compliance with food group and nutrient recommendations, and self-efficacy, stage of change, perceived barriers and benefits for healthy eating were assessed among a convenience sample of college students majoring in health-related disciplines. Dietary and psychosocial data were collected using three-day food records and scales, respectively. Means (SD), frequencies, and percents were calculated on all data, and logistic regressions were used to determine whether any of the psychosocial correlates predicted the stage of change for healthy eating. Noncompliance with food group recommendations ranged from 53% for the meat/meat alternates group to 93% for the vegetables/juice group, whereas noncompliance with nutrient recommendations ranged from 26% for cholesterol to 99% for potassium. A majority of students (57%) self-classified in the preaction and 40% in the action stages of change for eating healthy. The students' self-efficacy to eat healthy was highest in positive/social situations and lowest when experiencing emotional upset. The most important perceived barrier to healthy eating was that friends/roommates do not like to eat healthy foods, and the most important perceived benefit was that eating healthy foods provides the body with adequate nutrients. The difficult/inconvenient self-efficacy subscale predicted the stage of change for healthy eating. These students would benefit from interactive learning opportunities that teach how to purchase and prepare more whole grain foods, fruits, and vegetables, enhance their self-efficacy for making healthy food choices when experiencing negative emotions, and overcome perceived barriers to healthy eating.

• The KIPS Transactions:PartB
• /
• v.9B no.4
• /
• pp.407-414
• /
• 2002

Being recently increased interests of our healthcare, a host of symptoms-diagnostic sites has been introduced on the World Wide Web. But conventional healthcare sites provide users with only a very restricted functions. In this paper, we propose the use of Artificial Neural Networks (ANNs) as a flexible symptoms-diagnostic tool that enables learning effects of ANNs (not expert's knowledge) to be incorporated into the diagnostic process. We develop a novel algorithm for predicting patient\`s disease that satisfy user (or expert)-specified symptoms on WWW. Our algorithm provides two important benefits : 1) enables users (patients) to be taken early diagnostic, and 2) enables experts to perform confidently diagnostic by referencing the predicted diseases-list with its respective possibility.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37B no.11
• /
• pp.1082-1089
• /
• 2012

Recent malicious attempts in Cyber space are intended to emerge national threats such as Suxnet as well as to get financial benefits through a large pool of comprised botnets. The evolved botnets use the Domain Name System(DNS) to communicate with the C&C server and zombies. DNS is one of the core and most important components of the Internet and DNS traffic are continually increased by the popular wireless Internet service. On the other hand, domain names are popular for malicious use. This paper studies on DNS-based cyber threats domain detection by data classification based on supervised learning. Furthermore, the developed cyber threats domain detection system using DNS traffic analysis provides collection, analysis, and normal/abnormal domain classification of huge amounts of DNS data.

• Journal of Mechanical Science and Technology
• /
• v.17 no.12
• /
• pp.1969-1976
• /
• 2003

In the early phases of the product life cycle, Life Cycle Assessment (LCA) is recently used to support the decision-making for the product concepts, and the best alternative can be selected based on its estimated LCA and benefits. Both the lack of detailed information and time for a full LCA for a various range of design concepts need a new approach for the environmental analysis. This paper explores a new approximate LCA methodology for the product concepts by grouping products according to their environmental characteristics and by mapping product attributes into environmental impact driver (EID) index. The relationship is statistically verified by exploring the correlation between total impact indicator and energy impact category. Then, a neural network approach is developed to predict an approximate LCA of grouping products in conceptual design. Trained learning algorithms for the known characteristics of existing products will quickly give the result of LCA for newly designed products. The training is generalized by using product attributes for an EID in a group as well as another product attributes for the other EIDs in other groups. The neural network model with back propagation algorithm is used, and the results are compared with those of multiple regression analysis. The proposed approach does not replace the full LCA but it would give some useful guidelines for the design of environmentally conscious products in conceptual design phase.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.10
• /
• pp.4930-4951
• /
• 2018

The deep learning based speech enhancement has shown considerable success. However, it still suffers performance degradation under mismatch conditions. In this paper, an adaptation method is proposed to improve the performance under noise mismatch conditions. Firstly, we advise a noise aware training by supplying identity vectors (i-vectors) as parallel input features to adapt deep neural network (DNN) acoustic models with the target noise. Secondly, given a small amount of adaptation data, the noise-dependent DNN is obtained by using $L_2$ regularization from a noise-independent DNN, and forcing the estimated masks to be close to the unadapted condition. Finally, experiments were carried out on different noise and SNR conditions, and the proposed method has achieved significantly 0.1%-9.6% benefits of STOI, and provided consistent improvement in PESQ and segSNR against the baseline systems.

• English Language & Literature Teaching
• /
• v.17 no.4
• /
• pp.293-312
• /
• 2011

Many immersion programs have been established and managed throughout Korea in recent years in schools, English villages and camps. Research on the effects of various programs has been reported with focus on the program types or the benefits and learning outcomes for the participants. The purpose of this study is to find out the effects of participation at English camp as a teaching assistant by comparing some factors such as competence, English abilities, and connection to current studies/career before and after camp experience. The results show that all 17 competence rates rose with 'crisis management' showing prominent change. Also, the camp experience provides opportunity for improving English Test scores, conversational skills, teaching skills, and mostly language confidence. Lastly, the camp helped in setting career goals and was helpful in the preparation process of job seeking. Most of the subjects, the teaching assistants at camp, replied that the impact of camp experience is useful in current studies/career. In conclusion, the experience as camp teaching assistant is valuable in many aspects.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.1
• /
• pp.109-112
• /
• 2014

Korean informationization technology development speed is growing fastly and IT technology become world-class. Especially, by grafting IT technology to war commanding system, built an network center operational environment. However, conscription administration and the barracks informationization have inadequate points, to provide the people who have a duty of military service and parents with benefits and develop conscription administration and the barracks informationization base system conformed to IT age include using online system to guarantee military personnel's studying environment, writer proposed an improvement plan.

• Fashion, Industry and Education
• /
• v.14 no.1
• /
• pp.40-49
• /
• 2016

This study examined students' perceived importance of the benefits derived from an international multi-course collaborative (IMCC) project and how these perceptions impact students' extrinsic and intrinsic motivations for using the project Facebook (i.e., perceived usefulness and enjoyment), attitude toward the project, and intent to participate in future IMCC projects. The data were collected from 96 students who participated in the IMCC project and were enrolled in four different fashion merchandising courses in two different countries, the U.S. and South Korea. This study found that perceived enjoyment of the project Facebook influenced attitude toward the project and intent to participate in future IMCC projects. Perceived usefulness and enjoyment were predicted by the perceived importance of cultural understanding and feedback exchange among international group members. Attitude was influenced by the perceived importance of networking through the IMCC project, while intent to participate in future IMCC projects was predicted by perceived importance of cultural understanding and networking through the IMCC project. This study provides educators in the related disciplines insights about how to incorporate social network sites into course curricula to motivate students' project participation and learning.