• The Journal of the Acoustical Society of Korea
• /
• v.38 no.5
• /
• pp.607-613
• /
• 2019

This paper proposes LF-MMI (Lattice Free Maximum Mutual Information)-based acoustic modeling using external knowledge for speech recognition. Note that an external knowledge refers to text data other than training data used in acoustic model. LF-MMI, objective function for optimization of training DNN (Deep Neural Network), has high performances in discriminative training. In LF-MMI, a phoneme probability as prior probability is used for predicting posterior probability of the DNN-based acoustic model. We propose using external knowledges for training the prior probability model to improve acoustic model based on DNN. It is measured to relative improvement 14 % as compared with the conventional LF-MMI-based model.

• Journal of the Korean Society for Library and Information Science
• /
• v.55 no.4
• /
• pp.267-291
• /
• 2021

Due to the global pandemic caused by COVID-19 in 2020, there have been major changes in the education sites. Universities have fully introduced remote learning, which was considered as an auxiliary education, and non-face-to-face classes have become commonplace, and professors and students are making great efforts to adapt to the new educational environment. In order to improve the quality of non-face-to-face lectures amid these changes, it is necessary to study the factors affecting lecture satisfaction. Therefore, This paper presents a new methodology using big data to identify the factors affecting university lecture satisfaction changed before and after COVID-19. We use Topic Modeling method to analyze lecture reviews before and after COVID-19, and identify factors affecting lecture satisfaction. Through this, we suggest the direction for university education to move forward. In addition, we can identify the factors of satisfaction and dissatisfaction of lectures from multiangle by establishing a topic classification model with an F1-score of 0.84 based on KoBERT, a deep learning language model, and further contribute to continuous qualitative improvement of lecture satisfaction.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.9 no.3
• /
• pp.747-756
• /
• 2019

Students studying interpretation perform additional study and training in addition to regular class. In simultaneous interpreting and consecutive interpreting, interpreter should memorize speaker's announcement because of different language structure. To improve short-term memory, students perform memory training that requires a pair of students. Therefore, they can not perform self-learning, and therefore, efficiency of studying decreases. To resolve this problem, computer based short-term memory training system has been proposed. Student can perform self-learning by changing words in text to special character in the training system. However, efficiency of studying decreases because computer has low portability. Since the number of words is larger than the number of words to be switched into special character, learning difficulty decreases. To resolve this problem, smart device based short-term memory training system has been proposed. Student can perform smart device based training system without space constraints. Since the proposed training system increases the number of words to be changed into special character, learning difficulty increases. We implemented and evaluated the functionalities of the proposed training system.

• Journal of the Korean Society for information Management
• /
• v.36 no.1
• /
• pp.191-213
• /
• 2019

The process of obtaining scientific knowledge is conducted through research. Researchers deal with the uncertainty of science and establish certainty of scientific knowledge. In other words, in order to obtain scientific knowledge, uncertainty is an essential step that must be performed. The existing studies were predominantly performed through a hedging study of linguistic approaches and constructed corpus with uncertainty word manually in computational linguistics. They have only been able to identify characteristics of uncertainty in a particular research field based on the simple frequency. Therefore, in this study, we examine pattern of scientific knowledge based on uncertainty word according to the passage of time in biomedical literature where biomedical claims in sentences play an important role. For this purpose, biomedical propositions are analyzed based on semantic predications provided by UMLS and DMR topic modeling which is useful method to identify patterns in disciplines is applied to understand the trend of entity based topic with uncertainty. As time goes by, the development of research has been confirmed that uncertainty in scientific knowledge is moving toward a decreasing pattern.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.1
• /
• pp.101-108
• /
• 2021

This paper builds a real-time home security system based on the OneNet cloud platform to control the status of the house through a smartphone. The system consists of a local part and a cloud part. The local part has I/O devices, router and Raspberry Pi (RPi) that collects and monitors sensor data and sends the data to the cloud, and the Flask web server is implemented on a Rasberry Pi. When a user is at home, the user can access the Flask web server to obtain the data directly. The cloud part is OneNet in China Mobile, which provides remote access service. The hybrid App is designed to provide the interaction between users and the home security system in the smartphone, and the EDP and RTSP protocol is implemented to transmit data and video stream. Experimental results show that users can receive sensor data and warning text message through the smartphone and monitor, and control home status through OneNet cloud.

• The Journal of the Korea Contents Association
• /
• v.21 no.1
• /
• pp.333-342
• /
• 2021

In this study, we analyzed the vocabulary, lemmas, keywords, and n-grams in 『Treasure Island』 to identify certain linguistic features of this British-American children's adventure novel. The current study found that, contrary to the popular claim that frequently-used words are important and essential to a story, the set of frequently-used words in 『Treasure Island』 were mostly function words and proper nouns that were not directly related to the plot found in 『Treasure Island』. We also ascertained that a list of keywords using a statistical method making use of a corpus program was not good enough to surmise the story of 『Treasure Island』. However, we managed to extract 30 keywords through the first quantitative keyword analysis and then a second qualitative keyword analysis. We also carried out a series of n-gram analyses and were able to discover lexical bundles that were preferred and frequently used by the author of 『Treasure Island』. We hope that the results of this study will help spread this knowledge among British-American children's literature as well as to further put forward corpus stylistic theory.

• Journal of Creative Information Culture
• /
• v.7 no.3
• /
• pp.157-165
• /
• 2021

As the use of various application services utilizing Web and IoT and the need for large amounts of data management expand accordingly, the importance of efficient data expression and exchange scheme and data query processing is increasing. JSON, characterized by its simplicity, is being used in various fields as a format for data exchange and data storage instead of XML, which is a standard data expression and exchange language on the Web. This means that it is important to develop indexing and query processing techniques to effectively access and search large amounts of data expressed in JSON. Therefore, in this paper, we modeled JSON data with a hierarchical structure in a tree form, and proposed indexing and query processing using the path concept. In particular, we designed an index structure using a suffix array widely used in text search and introduced simple and complex path-based JSON data query processing methods.

• Journal of Software Assessment and Valuation
• /
• v.16 no.1
• /
• pp.37-44
• /
• 2020

The similarity of the software is extracted by the verification of comparing with the source code. The source code is the intellectual copyright of the developer written in the programming language. And the source code written in text format contains the contents of the developer's expertise and ideas. The verification for judging the illegal use of software copyright is performed by comparing the structure and contents of files with the source code of the original and the illegal copy. However, there is hard to do the one-to-one comparison in practice. Cause the suspected source code do not submitted Intentionally or unconsciously. It is now increasing practically. In this case, the comparative evaluation with execution code should be performed, and indirect methods such as reverse assembling method, reverse engineering technique, and sequence analysis of function execution are applied. In this paper, we analyzed the effectiveness of indirect comparison results by practical evaluation . It also proposes a method to utilize to the system and executable code files as a verification results.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.2-5
• /
• 2022

With the advent of deep learning and the rapid development of ICT (Information and Communication Technology), research using artificial intelligence is being actively conducted in various fields of society such as politics, economy, and culture and so on. Deep learning-based artificial intelligence technology is subdivided into various domains such as natural language processing, image processing, speech processing, and recommendation system. In particular, as the industry is advanced, the need for a recommendation system that analyzes market trends and individual characteristics and recommends them to consumers is increasingly required. In line with these technological developments, this paper extracts and classifies attribute information from structured or unstructured text and image big data through deep learning-based technology development of 'language processing intelligence' and 'image processing intelligence', and We propose an artificial intelligence-based 'customized fashion advisor' service integration system that analyzes trends and new materials, discovers 'market-consumer' insights through consumer taste analysis, and can recommend style, virtual fitting, and design support.

• Korean Journal of Social Welfare Studies
• /
• v.42 no.2
• /
• pp.235-274
• /
• 2011

The purpose of this study is to understand suffering of torture for victims with suspicion of espionage under the military government in Korea by knowing meaning and structure of empirical phenomena. Methods is to applied to Phenomenological and heuristic Human Becoming Methodology, and the subjects of this study are text for three tortured victims. Results is the structure that the victims accepted their act of espionage under the torture and horror, living with retribution from heaven, surviving pressured times, and fighting for human rights upon release from prison. The conceptual integration of relationship issues were: valuing, imaging, languaging with powering and transforming under the process of revealing-concealing and enabling-limiting. Finally, discussion and practical meaning was reviewed.