Kyungrog Kim

Recommender system design using movie genre similarity and preferred genres in SmartPhone

As e-commerce (e.g. www.amazon.com) and social media (e.g. www.facebook.com) services evolve, studies of recommender systems advance, especially concerning the application of collective intelligence to personalized service. With the development of smartphones and the new mobile environment, studies of customized services increase despite the physical limitations of mobile devices. A typical example combines customized services with location-based services. In this study, we propose a recommender system using movie genre similarity and preferred genres. A movie genre similarity profile is designed and generated to provide related services in a mobile experimental environment before prototyping and testing with data from MovieLens. In order to accomplish this, genre similarity correlations are determined with a Pearson correlation coefficient, and similar clusters are derived. The correlations within clusters are used to define genre similarity. Genre similarity is then used to recommend new genres to targeted customers.

Recommender System Using the Movie Genre Similarity in Mobile Service

Users of the various opinions and knowledge are generated and shared through the collective intelligence, a research on recommender systems are being continued at a variety of areas to use this at a personalized service. Also, despite the constraints of mobile device, personalized service is accelerating as development of the mobile environment. Therefore, we propose the recommender system using the genre similarity and preferred genre. After finding the relationship between genres by Pearson correlation coefficient, it produces a group by K-Means clustering. It creates a genre similarity profile by similar relationship between genres within a group. Suggest recommender system is reflected the genre similarity and preferred genre by target customer preferred genre. After designing and prototyping this to be able to be serviced at mobile experiment environment, it evaluates by applying to MovieLens Data set.

Teaching-Learning Activity Modeling Based on Data Analysis

Numerous studies are currently being carried out on personalized services based on data analysis to find and provide valuable information about information overload. Furthermore, the number of studies on data analysis of teaching-learning activities for personalized services in the field of teaching-learning is increasing, too. This paper proposes a learning style recency-frequency-durability (LS-RFD) model for quantified analysis on the level of activities of learners, to provide the elements of teaching-learning activities according to the learning style of the learner among various parameters for personalized service. This is to measure preferences as to teaching-learning activity according to recency, frequency and durability of such activities. Based on the results, user characteristics can be classified into groups for teaching-learning activity by categorizing the level of preference and activity of the learner.

A model for collecting and analyzing action data in a learning process based on activity theory

Research on learning analytics in technology-enhanced learning has recently been on the rise with the intent to support learners’ achievements, develop personalized learning environments, and improve learning methods. Learning analytics is a data analysis method intended to help understand learners’ tendencies toward activities and the significant aspects of such activities manifest in their teaching–learning process. In learning, an activity is comprised of a series of actions and then gives a couple of examples for different actions. To better understand a teaching–learning activity, the data from the stream of actions taking place need to be analyzed. To that end, this paper proposes a model for collecting and structuring the teaching–learning action data based on activity theory. The proposed model is designed to identify activities based on a series of learner actions over time. Among the components of activity theory, the model focuses on subjects, objects, and tools to collect data, which elucidates the use of tools that serve as the media between subjects (i.e., learners) and learning activities. The model offers insight into the continuity and persistence of objects or teaching–learning activity systems to better understand teaching–learning activities.

Activity index model for self-regulated learning with learning analysis in a TEL environment

Various learner-oriented teaching–learning models are spreading along with development of the technology-enhanced learning (TEL) environment and the spread of the massive open online course (MOOC). Vast amounts of various data are being created and accumulated from learning activities based on the TEL environment. Also, a self-regulated learning ability is required in the MOOC environment because the learning process is constituted on students making decisions by themselves. Accordingly, this study is aimed at suggesting an activity index model based on self-regulated learning and an activity index based on self-regulated learning. It is intended to provide a means to collect proof of what influences the teaching–learning activity. This model is intended to set a learning activity standard on the basis of general activity, interaction activity, and achievement activity by students. It will be possible to analyze the student’s participation level based on the activity index, which is based on self-regulated learning, to induce participation in the teaching–learning activity, and to recommend more appropriate learning activity elements. The student data are divided into score-related, time-related, and count-related groups for applications. The stabilization of the data was confirmed through time series analysis. In multiple regression analysis, the academic achievement element was set by the target variable, and the relationships among explanatory variables were confirmed. It was understood from the explanatory variables that similar student groups were highly concerned with notice participation in the learning activity. It will be possible to analyze the students’ participation levels, induce participation in the teaching–learning activities, and recommend more appropriate learning activity elements on the basis of an activity index based on self-regulated learning.

Topic Modeling for Learner Question and Answer Analytics

There is increasing interest in text analysis based on unstructured data such as articles and comments, questions and answers. This is because they can be used to identify, evaluate, predict, and recommend features from unstructured text data, which is the opinion of people. The same holds true for TEL, where the MOOC service has evolved to automate debating, questioning and answering services based on the teaching-learning support system in order to generate question topics and to automatically classify the topics relevant to new questions based on question and answer data accumulated in the system. To that end, the present study proposes an LDA-based topic modeling. The proposed method enables the generation of a dictionary of question topics and the automatic classification of topics relevant to new questions.

Sector Based Multiple Camera Collaboration for Active Tracking Applications

This paper presents a scalable multiple camera collaboration strategy for active tracking applications in large areas. The proposed approach is based on distributed mechanism but emulates the master-slave mechanism. The master and slave cameras are not designated but adaptively determined depending on the object dynamic and density distribution. Moreover, the number of cameras emulating the master is not fixed. The collaboration among the cameras utilizes global and local sectors in which the visual correspondences among different cameras are determined. The proposed method combines the local information to construct the global information for emulating the master-slave operations. Based on the global information, the load balancing of active tracking operations is performed to maximize active tracking coverage of the highly dynamic objects. The dynamics of all objects visible in the local camera views are estimated for effective coverage scheduling of the cameras. The active tracking synchronization timing information is chosen to maximize the overall monitoring time for general surveillance operations while minimizing the active tracking miss. The real-time simulation result demonstrates the effectiveness of the proposed method

Social Activity-Based Content Metadata Modeling

As Web 2.0 and social network service become sophisticated, knowledge generation and sharing activity become diversified. Especially, the contents that individuals have generated on SNC are informal and unofficial, but they provide the value as the information that can be provided just in time. Therefore, this study suggests the social activity-based contents metadata model (SACoM) for explaining and managing interactive activity elements generated on SNC and contents type that is changeable in real time. The SACoM model consists of interaction type and contents type expansion based on IEEE LOM. For the interaction type, the SNC activity element is added to the existing interactive element, and the contents type is subdivided into the real-time changeable type for expressing the real-time interaction activities and the fixed type for expressing the existing contents.