• Journal of KIISE:Software and Applications
• /
• v.31 no.9
• /
• pp.1171-1179
• /
• 2004

We describe word boundary detection that extracts the boundary between speech and non-speech. The proposed method uses two features. One is the normalized root mean square of speech signal, which is insensitive to white noises and represents temporal information. The other is the normalized met-frequency band energy of voice signal, which is frequency information of the signal. Our method detects word boundaries using a recurrent fuzzy associative memory(RFAM) that extends FAM by adding recurrent nodes. Hebbian learning method is employed to establish the degree of association between an input and output. An error back-propagation algorithm is used for teaming the weights between the consequent layer and the recurrent layer. To confirm the effectiveness, we applied the suggested system to voice data obtained from KAIST.

• Journal of applied mathematics & informatics
• /
• v.10 no.1_2
• /
• pp.333-351
• /
• 2002

This paper introduces a search method based on conceptual graph. A hyperlink information is essential to construct conceptual graph in web. The information is very useful as it provides summary and further linkage to construct conceptual graph that has been provided by human. It also has a property which shows review, relation, hierarchy, generality, and visibility. Using this property, we extracted the keywords of web documents and made up of the conceptual graph among the keywords sampled from web pages. This paper extracts the keywords of web pages using anchor text one out of hyperlink information and makes hyperlink of web pages abstract as the link relation between keywords of each web page. 1 suggest this useful search method providing querying word extension or domain knowledge by conceptual graph of keywords. Domain knowledge was conceptualized knowledged as the conceptual graph. Then it is not listing web documents which is the defect of previous search system. And it gives the index of concept associating with querying word.

• The KIPS Transactions:PartB
• /
• v.8B no.5
• /
• pp.447-454
• /
• 2001

The automatic document classification is a method that assigns unlabeled documents to the existing classes. The automatic document classification can be applied to a classification of news group articles, a classification of web documents, showing more precise results of Information Retrieval using a learning of users. In this paper, we use the weighted Bayesian classifier that weights with keywords of a document to improve the classification accuracy. If the system cant classify a document properly because of the lack of the number of words as the feature of a document, it uses relevance word cluster to supplement the feature of a document. The clusters are made by the automatic word clustering from the corpus. As the result, the proposed system outperformed existing classification system in the classification accuracy on Korean documents.

• Annual Conference on Human and Language Technology
• /
• 2006.10e
• /
• pp.15-21
• /
• 2006

본 논문에서는 올바른 한국어 생활과 한국어 실력 향상을 위하여, 한국어 어휘에 대한 풍부한 정보를 담고 있는 한국어사전, 사용자 어휘지능망(User-Word Intelligent Network : U-WIN)등의 언어자원을 이용한 자동문제생성기술을 소개하고, 이를 이용한 한국어 어휘학습시스템을 제시한다. 대부분의 학습시스템에서 사용하는 문제 은행식 출제 방식의 문제점을 해소할 수 있는 하나의 방법으로서, 기존의 한국어 어휘문제의 문항을 분석하여 8가지 문제 유형으로 재편성하고, 각 유형별 자동 문제 생성패턴에 따라 언어자원이 가지고 있는 한국어 어휘의 형태적 정보, 의미적 정보를 이용하여 한국어 어휘 문제를 자동 출제하는 한국어 어휘학습시스템을 구현하였다.

• The KIPS Transactions:PartB
• /
• v.16B no.1
• /
• pp.85-92
• /
• 2009

As World Wide Web is more popularized nowadays, the environment is flooded with the information through the web pages. However, despite such convenience of web, it is also creating many problems due to uncontrolled flood of information. The pornographic, violent and other harmful information freely available to the youth, who must be protected by the society, or other users who lack the power of judgment or self-control is creating serious social problems. To resolve those harmful words, various methods proposed and studied. This paper proposes and implements the protecting system that it protects internet youth user from harmful contents. To classify effective harmful/harmless contents, this system uses two step classification systems that is harmful word filtering and SVM learning based filtering. We achieved result that the average precision of 92.1%.

• Proceedings of the Korea Contents Association Conference
• /
• 2005.05a
• /
• pp.31-35
• /
• 2005

In this paper, we designed and implemented the web-based instruction system to improve quality of education and achieve efficient instruction-learning throughout the WBI. This web-based evaluation system lets learners make up their lesson in a self-oriented and effective way, by letting instructors diagnose learners level of understanding trigonometric function and letting learners take part in evaluation as well. The system also lets instructors easily make out items for evaluation by using 한글(Korean Language Word processor) and present them on the Web.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.137-152
• /
• 2005

In this Paper, we Propose an efficient web-based video learning evaluation system that is tailored to individual student's characteristics through the use of user profile-based information filtering. As a means of giving video-based questions, keyframes are extracted based on the location, size, and color information, and question-making intervals are extracted by means of differences in gray-level histograms as well as time windows. In addition, through a combination of the category-based system and the keyword-based system, questions for examination are given in order to ensure efficient evaluation. Therefore, students can enhance school achievement by making up for weak areas while continuing to identify their areas of interest.

• International Journal of Computer Science & Network Security
• /
• v.21 no.9
• /
• pp.281-291
• /
• 2021

The Islamic jurisprudential legal system represents an essential component of the Islamic religion, that governs many aspects of Muslims' daily lives. This creates many questions that require interpretations by qualified specialists, or Muftis according to the main sources of legislation in Islam. The Islamic jurisprudence is usually classified into branches, according to which the questions can be categorized and classified. Such categorization has many applications in automated question-answering systems, and in manual systems in routing the questions to a specialized Mufti to answer specific topics. In this work we tackle the problem of automatic categorisation of Islamic jurisprudential legal questions using deep learning techniques. In this paper, we build a hierarchical deep learning model that first extracts the question text features at two levels: word and sentence representation, followed by a text classifier that acts upon the question representation. To evaluate our model, we build and release the largest publicly available dataset of Islamic questions and answers, along with their topics, for 52 topic categories. We evaluate different state-of-the art deep learning models, both for word and sentence embeddings, comparing recurrent and transformer-based techniques, and performing extensive ablation studies to show the effect of each model choice. Our hierarchical model is based on pre-trained models, taking advantage of the recent advancement of transfer learning techniques, focused on Arabic language.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.11
• /
• pp.329-331
• /
• 2020

Edutech is a compound word of education and technology, and is an educational paradigm in the era of the 4th industrial revolution. This refers to next-generation education using information and communication technology (ICT) such as big data, artificial intelligence (AI), robots, and virtual reality (VR) of the 4th industrial revolution. e-Learning is being used as an online lecture for education in ICT, but edutech is attracting attention along with e-learning as the feeding of non-face-to-face education has rapidly increased due to COVID-19. Therefore, this paper summarizes the reviewed papers on the blockchain-based badge service platform, simulation-based collaborative e-Learning system, video English dictionary, and blockchain-based access control audit system.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1114-1121
• /
• 2021

In this paper, we implement a recipe recommendation system using ingredient harmonization analysis based on recipe data. The proposed system receives an image of a food ingredient purchase receipt to recommend ingredients and recipes to the user. Moreover, it performs preprocessing of the receipt images and text extraction using the OCR algorithm. The proposed system can recommend recipes based on the combined data of ingredients. It collects recipe data to calculate the combination for each food ingredient and extracts the food ingredients of the collected recipe as training data. And then, it acquires vector data by learning with a natural language processing algorithm. Moreover, it can recommend recipes based on ingredients with high similarity. Also, the proposed system can recommend recipes using replaceable ingredients to improve the accuracy of the result through preprocessing and postprocessing. For our evaluation, we created a random input dataset to evaluate the proposed recipe recommendation system's performance and calculated the accuracy for each algorithm. As a result of performance evaluation, the accuracy of the Word2Vec algorithm was the highest.