• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.4
• /
• pp.992-999
• /
• 2014

This paper presents an extensive experimental comparison of a variety of multi-label learning methods for the accurate prediction of subcellular localization of proteins which simultaneously exist at multiple subcellular locations. We compared several methods from three categories of multi-label classification algorithms: algorithm adaptation, problem transformation, and meta learning. Experimental results are analyzed using 12 multi-label evaluation measures to assess the behavior of the methods from a variety of view-points. We also use a new summarization measure to find the best performing method. Experimental results show that the best performing methods are power-set method pruning a infrequently occurring subsets of labels and classifier chains modeling relevant labels with an additional feature. futhermore, ensembles of many classifiers of these methods enhance the performance further. The recommendation from this study is that the correlation of subcellular locations is an effective clue for classification, this is because the subcellular locations of proteins performing certain biological function are not independent but correlated.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.680-685
• /
• 2017

The emergence of online media and their data has enabled data-driven methods to solve challenging and complex tasks such as rumor classification problems. Recently, deep learning based models have been shown as one of the fastest and the most accurate algorithms to solve such problems. These new models, however, either rely on complete data or several days-worth of data, limiting their applicability in real time. In this study, we go beyond this limit and test the possibility of super early rumor detection via recurrent neural networks (RNNs). Our model takes in social media streams as time series input, along with basic meta-information about the rumongers including the follower count and the psycholinguistic traits of rumor content itself. Based on analyzing millions of social media posts on 498 real rumors and 494 non-rumor events, our RNN-based model detected rumors with only 30 initial posts (i.e., within a few hours of rumor circulation) with remarkable F1 score of 0.74. This finding widens the scope of new possibilities for building a fast and efficient rumor detection system.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.1
• /
• pp.38-47
• /
• 2001

PDM is an integrated solution for managing various kinds of document and information for a whole life~cycle of product management. PDM system spans a huge and complex area and requires so many efforts and budgets for development. A framework has been considered a promising way to improve productivity by reusing the software architecture, not just one part of the design or just source code. This was the reaSon why we developed PDM (Product Data Management) framework. Framework can reduce the time and efforts to develop a new PDM application. However, it also requires supporting environment since a framework is a big set of classes where their interactions are so complex. With this supporting environment, it is easy to understand the framework at a glance and easy to identify what hot spots to be refined to meet new requirements. In this paper, a new framework-supporting reuse environment based on the meta-repository was constructed for easy and convenient reuse.

• Korean journal of communication and information
• /
• v.33
• /
• pp.193-225
• /
• 2006

This study attempts to reconsider the significance of political economy as a theory of knowledge and/or a method for explaining the convergence of broadcast and telecommunications. It is going to suggest what the domains of political economy should be in the future by both highlighting the characteristics and blind spots of previous studies and drawing some distinctive features of a new media environment. The principals and recent research trends in political economy are reviewed in order to make clear that the historical totality as a meta-framework of political economy needs to be reexamined in the era of convergence. Although the scope of political economy has been limited to criticize the structure of media ownerships, the study emphasizes the importance of media consumer theory. It also discusses the problems of free market theory, distortion of active media audience theory, and limitations and creative tension of audience commodity. Finally, this study stresses the significance of audience-oriented policies in order to make approach to practical sides of media politics.

• Journal of KIISE
• /
• v.43 no.4
• /
• pp.470-479
• /
• 2016

As the number of various types of media data such as UCC (User Created Contents) increases, research is actively being carried out in many different fields so as to provide meaningful media services. Amidst these studies, a semantic web-based media classification approach has been proposed; however, it encounters some limitations in video classification because of its underlying ontology derived from meta-information such as video tag and title. In this paper, we define recognized objects in a video and activity that is composed of video objects in a shot, and introduce a reasoning approach based on description logic. We define sequential rules for a sequence of shots in a video and describe how to classify it. For processing the large amount of increasing media data, we utilize Spark streaming, and a distributed in-memory big data processing framework, and describe how to classify media data in parallel. To evaluate the efficiency of the proposed approach, we conducted an experiment using a large amount of media ontology extracted from Youtube videos.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.3
• /
• pp.147-152
• /
• 2008

Ant System(AS) is new meta heuristic for hard combinatorial optimization problem. It is a population based approach that uses exploitation of positive feedback as well as greedy search. It was first proposed for tackling the well known Traveling Salesman Problem. In this paper, AS is applied to the Multicast Routing Problem. Multicast Routing is modeled as the NP-complete Steiner tree problem. This is the shortest path from source node to all destination nodes. We proposed new AS to resolve this problem. The proposed method selects the neighborhood node to consider all costs of the edge and the next node in state transition rule. Also, The edges which are selected elite agents are updated to additional pheromone. Simulation results of our proposed method show fast convergence and give lower total cost than original AS and $AS_{elite}$.

• Journal of the Korean Society for information Management
• /
• v.32 no.4
• /
• pp.249-272
• /
• 2015

Inappropriate applications of bibliometric approach and misinterpretation on the analysis in research evaluation have been found and recognized nationally and internationally as the use of the approach has been rapidly adopted in various sectors in research evaluation systems and research funding agencies. The flood of misuse led to several numbers of declarations and statements on appropriate research evaluation, including Leiden Manifesto, DORA, IEEE Statement, etc. The similar recommendations from five different declarations, Leiden Manifest, IEEE Statement, DORA, Institut de France, and Thomson Reuters White paper were reviewed and meta-analyzed in this study and it is revealed that most of them emphasize evaluation on quality in various aspects with multiple indicators. Research evaluation with assessing multiple aspects of individual research based on the understandings of its purpose and pertinent subject area was revealed as being mostly advised in the declarations, and this recommendation can be regarded as being mostly requested in national research evaluation system. For future study, interviews with relevant stakeholders of national research evaluation system in order to explore its application are needed to confirm the findings of this review.

• Journal of The Korean Association of Information Education
• /
• v.16 no.3
• /
• pp.337-352
• /
• 2012

In this paper, a smart education system is developed and implemented for ADHD students. Usually, ADHD students lack of self efficacy. Self efficacy is very important factor for improving social adaptability and learning effect of ADHD students. In the proposed system, MLE concept is adapted. MLE concept is used to improve self efficacy of ADHD students. The purpose of the proposed system is to help ADHD students have high study capability. The proposed system is applied an ADHD student. The following results are obtained. First, the system can improve study interests. In turn, the system is helpful to improve concentration and learning effect. Second, based on successful study experience, self efficacy is improved. Third, study achievement is improved by changing cognitive structure that is due to development of meta-cognition.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.23 no.9
• /
• pp.1048-1057
• /
• 2012

In this paper, a new compact dual-band unequal power divider is suggested. Instead of the quarter wavelength transmission line(TX-line)s for the branches of the conventional Wilkinson's power divider, we use composite right- and left-handed(CRLH) phase-shift lines and can reduce the physical length. With the non-linear dispersion of the meta-meterial, each branch in the proposed divider is designed to have $+90^{\circ}$ and $-90^{\circ}$ at $f_1$ and $f_2$ respectively. To validate the proposed method, the performances of the circuit and full-wave simulation results are shown with the CRLH dispersion curve. The measurement results are compared with the simulation results. Also, the size reduction effect by the proposed scheme is addressed.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.6
• /
• pp.1375-1386
• /
• 2016

This paper presents an efficient hash chain-based data authentication mechanism which can considerably reduce the overhead of processing and transmission for authenticating segments in CCN. The proposed method makes use of hash chain and MHT(Merkle Hash Tree). At first, it applies hash chain methods for data segments and encodes them to Data part. Then, it constitutes Meta part with the hash values generated at the previous step and properly applies both hash chain method and MHT-based signing for not only achieving efficiency, but also mitigating the drawback(data-loss, out-of-order transmission) of hash chain method. We have implemented our method in the CCNx library and measured the performance. When transmitting 100Mbyte of content, the proposed method generates only 2.596% of processing overhead and 1.803% of transmission overhead.