• Journal of Digital Contents Society
• /
• v.18 no.2
• /
• pp.339-346
• /
• 2017

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. Therefore, in this study, we propose topic modeling using LDA to automatically classify new query topics. The proposed method enables the generation of a dictionary of question topics and the automatic classification of topics relevant to new questions. Experimentation showed high automatic classification of over 0.7 in some queries. The more new queries were included in the various topics, the better the automatic classification results.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.5
• /
• pp.119-126
• /
• 2019

Typical software developed and used by North Korea is Red Star and internal application software. However, most of the existing research on the North Korean software is the software installation method and general execution screen analysis. One of the ways to identify software vulnerabilities is file fuzzing, which is a typical method for identifying security vulnerabilities. In this paper, we use file fuzzing to analyze the security vulnerability of the software used in North Korea's Seogwang Document Processing System. At this time, we propose the analysis of open document text (ODT) file produced by Seogwang Document Processing System, extraction of node based on Document Object Mode (DOM) to determine test target, and generation of mutation file through insertion and substitution, this increases the number of crash detections at the same testing time.

• Smart Media Journal
• /
• v.8 no.2
• /
• pp.58-65
• /
• 2019

Automatic text summarization is a process of shortening a text document by either extraction or abstraction. The abstraction approach inspired by deep learning methods scaling to a large amount of document is applied in recent work. Abstractive text summarization involves utilizing pre-generated word embedding information. Low-frequent but salient words such as terminologies are seldom included to dictionaries, that are so called, out-of-vocabulary(OOV) problems. OOV deteriorates the performance of Encoder-Decoder model in neural network. In order to address OOV words in abstractive text summarization, we propose a copy mechanism to facilitate copying new words in the target document and generating summary sentences. Different from the previous studies, the proposed approach combines accurate pointing information and selective copy mechanism based on bidirectional RNN and bidirectional LSTM. In addition, neural network gate model to estimate the generation probability and the loss function to optimize the entire abstraction model has been applied. The dataset has been constructed from the collection of abstractions and titles of journal articles. Experimental results demonstrate that both ROUGE-1 (based on word recall) and ROUGE-L (employed longest common subsequence) of the proposed Encoding-Decoding model have been improved to 47.01 and 29.55, respectively.

• Journal of KIISE
• /
• v.42 no.4
• /
• pp.451-458
• /
• 2015

Previous multimodal learning methods focus on problem-solving aspects, such as image and video search and tagging, rather than on knowledge acquisition via content modeling. In this paper, we propose the Multimodal Concept Hierarchy (MuCH), which is a content modeling method that uses a cartoon video dataset and a character-based subtitle generation method from the learned model. The MuCH model has a multimodal hypernetwork layer, in which the patterns of the words and image patches are represented, and a concept layer, in which each concept variable is represented by a probability distribution of the words and the image patches. The model can learn the characteristics of the characters as concepts from the video subtitles and scene images by using a Bayesian learning method and can also generate character-based subtitles from the learned model if text queries are provided. As an experiment, the MuCH model learned concepts from 'Pororo' cartoon videos with a total of 268 minutes in length and generated character-based subtitles. Finally, we compare the results with those of other multimodal learning models. The Experimental results indicate that given the same text query, our model generates more accurate and more character-specific subtitles than other models.

• ETRI Journal
• /
• v.23 no.4
• /
• pp.168-176
• /
• 2001

This paper discusses two important issues of corpus-based synthesis: synthesis unit generation based on phrase break strength information and pruning redundant synthesis unit instances. First, the new sentence set for recording was designed to make an efficient synthesis database, reflecting the characteristics of the Korean language. To obtain prosodic context sensitive units, we graded major prosodic phrases into 5 distinctive levels according to pause length and then discriminated intra-word triphones using the levels. Using the synthesis unit with phrase break strength information, synthetic speech was generated and evaluated subjectively. Second, a new pruning method based on weighted vector quantization (WVQ) was proposed to eliminate redundant synthesis unit instances from the synthesis database. WVQ takes the relative importance of each instance into account when clustering similar instances using vector quantization (VQ) technique. The proposed method was compared with two conventional pruning methods through objective and subjective evaluations of synthetic speech quality: one to simply limit the maximum number of instances, and the other based on normal VQ-based clustering. For the same reduction rate of instance number, the proposed method showed the best performance. The synthetic speech with reduction rate 45% had almost no perceptible degradation as compared to the synthetic speech without instance reduction.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.13 no.1
• /
• pp.87-101
• /
• 2017

As people increasingly rely on mobile networks in modern society, mobile communication security is becoming more and more important. In the Long Term Evolution/System Architecture Evolution (LTE/SAE) architecture, the 3rd Generation Partnership (3GPP) team has also developed the improved Evolved Packet System Authentication and Key Agreement (EPS AKA) protocol based on the 3rd Generation Authentication and Key Agreement (3G AKA) protocol in order to provide mutual authentication and secure communication between the user and the network. Unfortunately, the EPS AKA also has several vulnerabilities such as sending the International Mobile Subscriber Identity (IMSI) in plain text (which leads to disclosure of user identity and further causes location and tracing of the user, Mobility Management Entity (MME) attack), man-in-middle attack, etc. Hence, in this paper, we analyze the EPS AKA protocol and point out its deficiencies and then propose an Efficient and Security Enhanced Authentication and Key agreement (ESE-EPS AKA) protocol based on hybrid of Dynamic Pseudonym Mechanism (DPM) and Public Key Infrastructure (PKI) retaining the original framework and the infrastructure of the LTE network. Then, our evaluation proves that the proposed new ESE-EPS AKA protocol is relatively more efficient, secure and satisfies some of the security requirements such as confidentiality, integrity and authentication.

• Journal of Korea Society of Industrial Information Systems
• /
• v.4 no.4
• /
• pp.60-70
• /
• 1999

Internet based on web service is growing rapidly and the effort to standardize the next generation web is wold-widely being made. When the web was developed for the first time, HTTP, HTML, and URL were designed based on the structure of text background. Through those asynchronous search and simple unified expression patterns have been used But recently many data on internet me becoming complicated Consequently new structure and expression patterns including synchronous multimedia information are requested The currently used standard language among user interface domain of W3C is SMIL which is XML-based one SMIL describes where and how long the multimedia factors are integrated on the web. In this paper the standardization trend and important issues related to SMIL are reviewed and analysed Also the development of technology is discussed.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.4 no.2
• /
• pp.116-122
• /
• 2009

In this paper, we propose a new method which generates the trajectory of the mouth shape for the characters by the user inputs. It is based on the character at a basis syllable and can be suitable to the mouth shape generation. In this paper, we understand the principle of the Korean language creation and find the similarity for the form of the mouth shape and select it as a basic syllable. We also consider the articulation of this phoneme for it and create a new mouth shape trajectory and apply at face of an 3D avatar.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.3
• /
• pp.688-702
• /
• 1998

In this paper, we propose sign language morpheme generation rule corresponding to morpheme analysis for each part of speech. Korean natural sign language has extremely limited vocabulary, and the number of grammatical components eing currently used are limited, too. In this paper, therefore, we define natural sign language grammar corresponding to Korean language grammar in order to translate natural Korean language sentences to the corresponding sign language. Each phrase should define sign language morpheme generation grammar which is different from Korean language analysis grammar. Then, this grammar is applied to morpheme analysis/combination rule and sentence structure analysis rule. It will make us generate most natural sign language by definition of this grammar.

• Wind and Structures
• /
• v.37 no.2
• /
• pp.79-94
• /
• 2023

This paper traces the drafting of the new EN 1991-1-4 Eurocode 1 - Actions on structures - Part 1-4: General actions - Wind actions within Mandate M/515 of the European Commission to CEN, for the evolution of structural Eurocodes towards their Second Generation. Work of the Project Team started in August 2017 and ended in April 2020, with delivery of a final draft for public enquiry. The revised document contains several modifications with respect to the existing 2005 version, and new sections were added, covering aspect not dealt with in the previous version. It has a renovated structure, with a main text limited in size and containing only fundamental material; all the remaining information, either normative or informative is arranged into thirteen annexes. Common to other Eurocode Parts, general requests from CEN were those of reducing the number of Nationally Determined Parameters and of enhancing the ease of use. More specific requests were those of (a) the drafting of a European design wind map, (b) improving wind models, (c) reviewing force and pressure coefficients, (d) reviewing the procedures for evaluation of the dynamic response, as well as (e) making editorial improvements aimed at a more user friendly document. The author had the privilege to serve as Project Team member for the drafting of the new document, and this paper brings his personal view concerning some general aspects of wind code writing, and some more specific aspects about the particular document.