• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.6
• /
• pp.2310-2332
• /
• 2020

In recent years, deep learning techniques have achieved tremendous successes in natural language processing, speech recognition and image processing. Collaborative filtering(CF) recommendation is one of widely used methods and has significant effects in implementing the new recommendation function, but it also has limitations in dealing with the problem of poor scalability, cold start and data sparsity, etc. Combining the traditional recommendation algorithm with the deep learning model has brought great opportunity for the construction of a new recommender system. In this paper, we propose a novel collaborative recommendation model based on auxiliary stacked denoising autoencoder(ASDAE), the model learns effective the preferences of users from auxiliary information. Firstly, we integrate auxiliary information with rating information. Then, we design a stacked denoising autoencoder based collaborative recommendation model to learn the preferences of users from auxiliary information and rating information. Finally, we conduct comprehensive experiments on three real datasets to compare our proposed model with state-of-the-art methods. Experimental results demonstrate that our proposed model is superior to other recommendation methods.

• International journal of advanced smart convergence
• /
• v.5 no.3
• /
• pp.40-46
• /
• 2016

The internet allows the information to flow at anywhere in anytime easily. Unfortunately, the network also becomes a great tool for the criminals to operate cybercrimes such as identity theft. To prevent the issue, using a very complex password is not a very encouraging method. Alternatively, keystroke dynamics helps the user to solve the problem. Keystroke dynamics is the information of timing details when a user presses a key or releases a key. A machine can learn a user typing behavior from the information integrate with a proper machine learning algorithm. In this paper, we have proposed mini-batch ensemble (MIBE) method which does the preprocessing on the original dataset and then produces multiple mini batches in the end. The mini batches are then trained by a machine learning algorithm. From the experimental result, we have shown the improvement of the performance for each base algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.236-242
• /
• 1992

Multi-layered neural networks are applied to the identification and control of nonlinear dynamical system. Traditional adaptive control techniques can only deal with linear systems or some special nonlinear systems. A scheme for combining multi-layered neural networks with model reference network techniques has the capability to learn the nonlinearity and shows the great potential for adaptive control. In many interesting cases the system can be described by a nonlinear model in which the control input appears linearly. In this paper the identification of linear and nonlinear part are performed simultaneously. The projection algorithm and the new estimation method which uses the delta rule of neural network are compared throughout the simulation. The simulation results show that the identification and adaptive control schemes suggested are practically feasible and effective.

• Proceedings of the KSR Conference
• /
• 2010.06a
• /
• pp.2154-2165
• /
• 2010

Successful opening and operating of High Speed Rail in South Korea make the Korean railway industry the world's five great powers. It provides an opportunity to enter overseas rail industry to the related companies actively. Lastly developing countries want to learn about Korea's development experience and apply to there country. Also development cooperation needs are increasing. The State Brand Committee is promoting the 'Hangeul advocacy and globalization' which is expanding technology to the overseas that can be grafted in the Korean railway system as well as contributing to the globalization policies. Korea Railroad Corporation can enhance the national brand and rise of the Name value simultaneously by disseminating of operation technology. It would be a worthy project. In this study, effective support for developing strategic partnerships with the developing countries can build a future of growth. And let me introduce strategic model for overseas business expansion that is combined the railway industry and the Korean.

• Preventive Nutrition and Food Science
• /
• v.22 no.2
• /
• pp.67-80
• /
• 2017

Cholesterol is a vital component of the human body. It stabilizes cell membranes and is the precursor of bile acids, vitamin D and steroid hormones. However, cholesterol accumulation in the bloodstream (hypercholesterolemia) can cause atherosclerotic plaques within artery walls, leading to heart attacks and strokes. The efficiency of cholesterol absorption in the small intestine is of great interest because human and animal studies have linked cholesterol absorption with plasma concentration of total and low density lipoprotein cholesterol. Cholesterol absorption is highly regulated and influenced by particular compounds in the food supply. Therefore, it is desirable to learn more about natural food components that inhibit cholesterol absorption so that food ingredients and dietary supplements can be developed for consumers who wish to manage their plasma cholesterol levels by non-pharmacological means. Food components thus far identified as inhibitors of cholesterol absorption include phytosterols, soluble fibers, phospholipids, and stearic acid.

• Research in Mathematical Education
• /
• v.10 no.2 s.26
• /
• pp.135-150
• /
• 2006

Although improper integrals constitute a concept of great utility for Mathematics students, it appears that students are unable to assimilate this concept within the wider system of concepts they learn in their first year of Mathematics studies. In this paper we describe a competence model used in a study about the kind of understanding students possess about improper integral calculus when two registers of representation come into play. Competence will be considered as the coherent articulation of different semiotic registers. After analysing the results of a questionnaire, six students were selected to be interviewed on the basis of their overall results and the significance of their answers. For the interview, five original questions from the questionnaire were used together with a new question. In this article we will analyse, from our theoretical point of view, the work carried out by one student who was interviewed to show how our competence model works and we will discuss this formal competence model used.

• Journal of the Korean Home Economics Association
• /
• v.36 no.1
• /
• pp.51-63
• /
• 1998

The purpose of this study was to relate confucian ideas in Chosun-Dynasty with ancestral rites in order to recover our traditional rules of propriety and morality which is disappeared in mordern society. For this object, this study reviewed ceremonies of traditional society in examining original literature such as $\ulcorner$Kyung-moon-yokyal$\lrcorner$ by Lee Yul Kok, $\ulcorner$Karae-geep-ram$\lrcorner$, $\ulcorner$Oee-rae-mun-hae$\lrcorner$y Kim Jang Saeng, $\ulcorner$Sarae-pyun-ram$\lrcorner$ by Lee Jae which is written in Chosun-Dynasty. By this literatures, the main idea of ancestral rites represented in literture is that filial piety is the most important thing and a true heart rather emphasized more than formality. From this study, I figured out that our traditional ancestral rites and its performance offered the mode군 good opportunities to learn how to respect other and made a great contribution to create better cultural life in modern home.

• Journal of Korean Neurosurgical Society
• /
• v.43 no.2
• /
• pp.69-78
• /
• 2008

Recently, due to the evolution of technology, the field of neurosurgery is receiving spotlight. In particular endovascular neurosurgery has gained a great interest along with the advancement of the modern neurosurgery. The most remarkable advances were made in embolization of the cerebral aneurysms, arteriovenous malformations and intracranial stenosis during the past 10 years. These advances will further change the role of neurosurgeons in treating cerebrovascular disease. Because interventional neuroradiologists have performed most of procedures in the past, neurosurgeons have been deprived of chances to learn endovascular procedure. This article discusses the development of technological aspect of endovascular neurosurgery in chronological order. By understanding the history and current status of the endovascular surgery, the future of neurosurgery will be promising.

• Journal of Korean language education
• /
• v.23 no.1
• /
• pp.101-122
• /
• 2012

To learn correctly how irregular verbs conjugate is one of the most important items which must be acquired by learners of Korean. Although a great deal of study has been made on irregular verbs, lots of problems seem to be remaining unsolved or even undescribed. The purpose of this paper is: (1) to give a definition of irregular conjugation of Korean from pedagogical point of view; (2) to describe an appearance of irregular verbs in the spoken and written context; (3) to show appropriate explanation how irregular verbs conjugate.

• Journal of Plant Biotechnology
• /
• v.48 no.4
• /
• pp.207-222
• /
• 2021

Coffee is the most frequently consumed functional beverage world wide. The average daily coffee consumption is increasing. This crop, which plays an important role in the global economy is under great threat from climate change. To with stand the current climate change, farmers have to learn crop cultivation techniques, strategies to protect crops from diseases, and understand which type of seed varieties to use to avoid crop loss. The present review briefly discusses the coffee cultivation techniques, impact of climate changes on coffee production, processing techniques of coffee, and the importance of coffee in our society, including its chemical composition and prevention against, major diseases. Furthermore, the importance and role of advanced nanotechnology along with molecular approaches for coffee crop improvement and facing challenges are explained.