• Information Systems Review
• /
• v.24 no.1
• /
• pp.1-19
• /
• 2022

Social media-based communication has become crucial part of our personal and official lives. Therefore, it is no surprise that social media sentiment analysis has emerged an important way of detecting potential customers' sentiment trends for all kinds of companies. However, social media sentiment analysis suffers from huge number of sentiment features obtained in the process of conducting the sentiment analysis. In this sense, this study proposes a novel method by using Bayesian Network. In this model MBFS (Markov Blanket-based Feature Selection) is used to reduce the number of sentiment features. To show the validity of our proposed model, we utilized online review data from Yelp, a famous social media about restaurant, bars, beauty salons evaluation and recommendation. We used a number of benchmarking feature selection methods like correlation-based feature selection, information gain, and gain ratio. A number of machine learning classifiers were also used for our validation tasks, like TAN, NBN, Sons & Spouses BN (Bayesian Network), Augmented Markov Blanket. Furthermore, we conducted Bayesian Network-based what-if analysis to see how the knowledge map between target node and related explanatory nodes could yield meaningful glimpse into what is going on in sentiments underlying the target dataset.

• Journal of Korea Multimedia Society
• /
• v.18 no.4
• /
• pp.533-540
• /
• 2015

We study relay selection in decode-and-forward (DF)-based relay networks consisting of a source, a destination, an eavesdropper, and multiple relays, where each terminal has a single antenna and operates in a half-duplex mode. In these networks, it is desirable to protect the confidential message from the source to the destination against the eavesdropper with the help of a single selected relay. Specifically, we begin by investigating DF-based networks for the scenario instantaneous signal-to-noise ratios (SNRs) related to the eavesdropper are available. For the scenario, we propose relay selection to maximize the secrecy rate of DF-based networks with and without direct-paths, and we derive the exact secrecy outage probabilities in closed-form.

• Cartoon and Animation Studies
• /
• s.47
• /
• pp.295-333
• /
• 2017

This study is a basic study to prepare policies related to selecting media to be included in textbooks. Researchers looked at previous studies focusing on how media affect children's and adolescent's emotions according to their developmental stages. Researchers also wanted to identify how the media is related to student emotions, health, and educational effectiveness. The researchers then examined a wide range of domestic media review and rating criteria, and argued that it is necessary to institutionalize the rating system of media at national level policy level. Based on the previous discussion, the researchers made seven suggestions. First, it is necessary to specify media selection criteria in the guidelines for issuing textbooks at the national level. Second, guidelines are needed to help review the political neutrality and human rights aspects of the media for inclusion in textbooks. Third, media selection guidelines in textbooks should be detailed with reference to categories and age based criteria of domestic and foreign media rating system. Fourth, the media rating system should be applied flexibly if there is a clear educational purpose. Fifth, institutional support is needed for setting guidelines for media collection of textbooks. Sixth, media experts should participate in the whole process of textbook development. Seventh, educational programs should be implemented to support teachers to use self directed learning by using educational media in classroom instruction.

• International journal of advanced smart convergence
• /
• v.8 no.1
• /
• pp.214-221
• /
• 2019

This study attempted to extend Korean Wave literature by investigating (a) the influence of protagonists' personality characteristics and the role of empathy under the affective disposition theory, and (b) the power of some external factors in the entertainment media selection. After watching an episode of the popular Korean drama, Secret Garden, participants completed a survey in the United States. Results demonstrated that (a) the effect of personality characteristics varied across gender and (b) external factors affects the entertainment media selection positively. Findings indicate that media enjoyment is dependent on the audience's external factors.

• Journal of Wetlands Research
• /
• v.21 no.4
• /
• pp.321-333
• /
• 2019

A primary aspect of low impact development (LID) design that affects performance efficiency, maintenance frequency, and lifespan of the facility is the type of filter media as well as the arrangement or media profile. Several LID guidelines providing media specifications are currently available and numerous studies have been published presenting the effectiveness of these systems. While some results are similar and consistent, some of them still varies and only a few focuses on the effect of filter media type and arrangement on system performance. This creates a certain level of uncertainty when it comes to filter media selection and design. In this review, a synthesis of filter media specifications from several LID design guidelines are presented and relevant results from different laboratory and field studies are highlighted. The LID systems are first classified as infiltration or non-infiltration structures, and vegetated or non-vegetated structures. Typical profiles of the media according to classification are shown including the different layers, materials, and depth. In addition, results from previous studies regarding the effect of filter media characteristics on hydraulic and hydrologic functions as well as pollutant removal are compared. Other considerations such as organic media leaching, clogging, media washing, and handling during construction were also briefly discussed. This review aims to provide a general guideline that can contribute to proper media selection and design for structural LIDs. In addition, it also identifies opportunities for future research.

• IE interfaces
• /
• v.11 no.1
• /
• pp.33-40
• /
• 1998

The objective of this paper is to help organizations select a suitable telecommunications media and dynamic route guidance system (DRGS) for an intelligent transport system (ITS) taking into account both cost and functionality. The media selection criteria and wireless communications for an ITS are discussed along with various DRGS. We describe which kind of telecommunication media and DRGS are suitable. The strategy of an ITS in Korea is described in regards to telecommunication media and DRGS.

• The Journal of the Korea Contents Association
• /
• v.20 no.10
• /
• pp.134-145
• /
• 2020

This study focused on the effects of Korean cosmetics selection attributes on Mongolian consumers' brand reliability and purchasing intentions. We are also to verify the relationship impacts between consumers brand reliability in advertising media and the purchase intention on the type of promotion. 255 questionnaires were collected for Mongolian consumers and analyzed using SPSS and AMOS. The analysis shows that product price, image and quality that they have a positive effect on brand reliability, while familiarity has not had a meaningful impact on brand reliability. Moreover, brand reliability has been shown to have a positive effect on purchasing intention. As a result of the adjustment effect test according to advertising media, the relationship impacts between product selection attributes and brand reliability were shown positive effect in part. Finally, the type of sales promotion were found to have a controlling effect between brand reliability and purchasing intention. These results show applicable implications for Korean cosmetics companies in terms of marketing and operations when entering Mongolia's cosmetics industry.

• Smart Media Journal
• /
• v.1 no.1
• /
• pp.36-41
• /
• 2012

Feature selection is the important technique of selecting a subset of relevant features for building robust pattern recognition systems. Various methods have been studied for feature selection from sequential search algorithms to stochastic algorithms. In this work, we adopted a Quantum-inspired Genetic Algorithm (QGA) which is based on the concept and principles of quantum computing such as Q-bits and superposition of state for feature selection. The performance of QGA is compared to that of the Conventional Genetic Algorithm (CGA) with respect to the classification rates and the number of selected features. The experimental result using UCI data sets shows that QGA is superior to CGA.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.11
• /
• pp.1598-1603
• /
• 2013

Recently, researches on analyzing relationship between the state of emotion and musical stimuli are increasing. In many previous works, data sets from all extracted channels are used for pattern classification. But these methods have problems in computational complexity and inaccuracy. This paper proposes a selection of optimal EEG channel to reflect the state of emotion efficiently according to music listening by analyzing stochastic feature vectors. This makes EEG pattern classification relatively simple by reducing the number of dataset to process.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.3
• /
• pp.460-469
• /
• 2012

The WiMedia Alliance has specified a Distributed Medium Access Control (D-MAC) protocol based on UWB for high speed wireless home networks and WPANs. In this paper, we propose a novel cooperative communication protocol adaptive to current UWB link transmission rate. The proposed cooperative communication protocol has compatibility with current WiMedia D-MAC and Wireless USB standard and is executed at each device according to a Relay Node Selection (RNS) criterion.