• Journal of the Korea Society of Computer and Information
• /
• v.25 no.9
• /
• pp.101-108
• /
• 2020

Recommender system is a must-have feature of e-commerce, since it provides customers with convenience in selecting products. Collaborative filtering is a widely-used and representative technique, where it gives recommendation lists of products preferred by other users or preferred by the current user in the past. Recently, researches on the recommendation system using deep learning artificial intelligence technologies are actively being conducted to achieve performance improvement. This study develops a collaborative filtering based recommender system using restricted Boltzmann machines of the deep learning technology by utilizing user ratings. Moreover, a learning parameter update algorithm is proposed for learning efficiency and performance. Performance evaluation of the proposed system is made through experimental analysis and comparison with conventional collaborative filtering methods. It is found that the proposed algorithm yields superior performance than the basic restricted Boltzmann machines.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.12
• /
• pp.2657-2664
• /
• 2012

Web-based learning receives much attention as an effective learning method because users can use the learning service at any time from any space. A learning management system(LMS) provides online educational environment among teachers and students, supporting various facilities to deliver educational contents. Since most of the existing LMSs support one-way or limited two-way teaching services among teachers and students, there are a lot of difficulties in performing collaboration among students and/or collaboration among teachers and students. In this paper, we describe the development of collaborative workspaces which provides effective collaborative educational environment on Moodle which is widely accepted as a typical LMS. Through the provided various types of collaborative workspaces, users can easily perform group activities, sharing educational with appropriate access control mechanism.

• The Journal of Korean Association of Computer Education
• /
• v.4 no.1
• /
• pp.43-52
• /
• 2001

The aim of this paper is to develop a network-based collaborative learning system based on cooperative learning, computer simulation, role playing, and web-based instruction, which is called NetClass. It is an educational system of hybrid-type, and supports three learning modes as a distributed network, a stand-alone system, or a web browser. To accomplish the purpose of this paper, we have studied on the following topics. First, we selected appropriate learning contents among dilemmas on information ethics. Second, a Collaborative Dilemma-solving Learning Model (CDLM) was designed, and this model means systematic procedures that leaners can notice others' feeling and thinking and predict the results of his actions by introducing interactions among learners on computer networks. Third, Collaborative Learning System Model based on standard architecture of an educational system was proposed. Fourth, we developed many components such as network components, database components, and interface components.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.173-178
• /
• 2022

Recently, a recommendation system using deep learning in social network services has been actively studied. However, in the case of a recommendation system using deep learning, the cold start problem and the increased learning time due to the complex computation exist as the disadvantage. In this paper, the user-tailored exercise routine recommendation algorithm is proposed using the user's metadata. Metadata (the user's height, weight, sex, etc.) set as the input of the model is applied to the designed model in the proposed algorithms. The exercise recommendation system model proposed in this paper is designed based on the neural collaborative filtering (NCF) algorithm using multi-layer perceptron and matrix factorization algorithm. The learning proceeds with proposed model by receiving user metadata and exercise information. The model where learning is completed provides recommendation score to the user when a specific exercise is set as the input of the model. As a result of the experiment, the proposed exercise recommendation system model showed 10% improvement in recommended performance and 50% reduction in learning time compared to the existing NCF model.

• The Journal of Korean Association of Computer Education
• /
• v.9 no.1
• /
• pp.41-48
• /
• 2006

The latest several studies show that Wiki is a very efficient tools for collaborative learning in the distributed environments. Even though Wiki supports efficient knowledge sharing between group members, there are still some problems to be solved for collaborative learning. Since the structure of group contents becomes more complex and the links between pages are dynamically changed, each member of group has difficulties to perceive the changed contents and links on group pages. We designed the adaptive navigation system to guide individual browsing paths of each member through the calculating of friendship and the state of pages. At first we developed the relation model between member and each pages by the historical log that stored the change of pages and the activity of members, and then we implemented the adaptive navigation system using the model. Experimental results show that this adaptive system is very effective to share the group knowledge and to promote collaborative learning activities.

• Journal of Information Technology Applications and Management
• /
• v.29 no.3
• /
• pp.43-55
• /
• 2022

In this study, with the goal of developing a deep learning-based product recommendation model for effective matching of influencers and products, a deep learning model with a collaborative filtering model combined with generalized matrix decomposition(GMF), a collaborative filtering model based on multi-layer perceptron (MLP), and neural collaborative filtering and generalized matrix Factorization (NeuMF), a hybrid model combining GMP and MLP was developed and tested. In particular, we utilize one-class problem free boosting (OCF-B) method to solve the one-class problem that occurs when training is performed only on positive cases using implicit feedback in the deep learning-based collaborative filtering recommendation model. In relation to model selection based on overall experimental results, the MLP model showed highest performance with weighted average precision, weighted average recall, and f1 score were 0.85 in the model (n=3,000, term=15). This study is meaningful in practice as it attempted to commercialize a deep learning-based recommendation system where influencer's promotion data is being accumulated, pactical personalized recommendation service is not yet commercially applied yet.

• Proceedings of the Korea Contents Association Conference
• /
• 2008.05a
• /
• pp.732-737
• /
• 2008

As e-learning is recognized in new education form, Learning Management System that manage general activity of learning to maximize effect of education is being developed actively. Usually, Learning Management System includes course registration and learning as well as learner's learning recording and tracking, evaluation in online. But, most systems is lacking a tool that learners can collaborate with companion learners, and planning learning and set valuation basis as leading. In this paper, we can expect effective collaborative learning activities because can make debate and team project smooth by suggesting collaborative learning module that can drive voluntary participation such as group formation, learning plan, mutually estimation as leading to learner in Learning Management System of blended learning base that support online and offline environment both.

• 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.

• Journal of The Korean Association of Information Education
• /
• v.10 no.1
• /
• pp.93-104
• /
• 2006

The purpose of this study is to examine the effects of GLAS(Guided-Learner Adaptable Scaffolding) strategies in web-based collaborative learning environments. Through the extensive literature reviews, web-based collaborative learning environments considering GLAS types were developed. 93 sixth graders were selected from a elementary school in Seoul, and they learned in the web-based system for 4 weeks. The results revealed that the impact of scaffolding on transfer of learning, cognitive overload by reflective scaffolding, learning motivation affected intrinsic scaffolding.

• Journal of The Korean Association of Information Education
• /
• v.22 no.1
• /
• pp.151-158
• /
• 2018

The purpose of this study is to develop a system for predicting students' collaborative problem solving ability based on the ICT factors of PISA 2015 that affect collaborative problem solving ability. The PISA 2015 computer-based collaborative problem-solving capability evaluation included 5,581 students in Korea. As a research method, correlation analysis was used to select meaningful variables. And the collaborative problem solving ability prediction model was created by using the deep learning method. As a result of the model generation, we were able to predict collaborative problem solving ability with about 95% accuracy for the test data set. Based on this model, a collaborative problem solving ability prediction system was designed and implemented. This research is expected to provide a new perspective on applying big data and artificial intelligence in decision making for ICT input and use in education.