• The Korean Journal of Applied Statistics
• /
• v.33 no.5
• /
• pp.615-625
• /
• 2020

The document-term frequency matrix is a term extracted from documents in which the group information exists in text mining. In this study, we generated the document-term frequency matrix for document classification according to research field. We applied the traditional term weighting function term frequency-inverse document frequency (TF-IDF) to the generated document-term frequency matrix. In addition, we applied term frequency-inverse gravity moment (TF-IGM). We also generated a document-keyword weighted matrix by extracting keywords to improve the document classification accuracy. Based on the keywords matrix extracted, we classify documents using a deep neural network. In order to find the optimal model in the deep neural network, the accuracy of document classification was verified by changing the number of hidden layers and hidden nodes. Consequently, the model with eight hidden layers showed the highest accuracy and all TF-IGM document classification accuracy (according to parameter changes) were higher than TF-IDF. In addition, the deep neural network was confirmed to have better accuracy than the support vector machine. Therefore, we propose a method to apply TF-IGM and a deep neural network in the document classification.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.4
• /
• pp.380-386
• /
• 2002

Conventional post-processing as like confidence measure (CM) proposed by Rahim calculates phones' CM using the likelihood between phoneme model and anti-model, and then word's CM is obtained by averaging phone-level CMs[1]. In conventional method, CMs of some specific keywords are tory low and they are usually rejected. The reason is that statistics of phone-level CMs are not consistent. In other words, phone-level CMs have different probability density functions (pdf) for each phone, especially sri-phone. To overcome this problem, in this paper, we propose normalized confidence measure. Our approach is to transform CM pdf of each tri-phone to the same pdf under the assumption that CM pdfs are Gaussian. For evaluating our method we use common keyword spotting system. In that system context-dependent HMM models are used for modeling keyword utterance and contort-independent HMM models are applied to non-keyword utterance. The experiment results show that the proposed NCM reduced FAR (false alarm rate) from 0.44 to 0.33 FA/KW/HR (false alarm/keyword/hour) when MDR is about 8%. It achieves 25% improvement of FAR.

• Journal of Internet Computing and Services
• /
• v.13 no.3
• /
• pp.107-114
• /
• 2012

In this paper, we proposed an automatic monitoring system for contact center in order to manage customer's complaint and agent's quality. The proposed system allows more accurate monitoring using emotion recognition and keyword spotting method for neutral/anger voice emotion. The system can provide professional consultation and management for the customer with language violence, such as abuse and sexual harassment. We developed a method of building robust algorithm on heterogeneous speech DB of many unspecified customers. Experimental results confirm the stable and improved performance using real contact center speech data.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.2
• /
• pp.37-42
• /
• 2008

In this paper, the vocabulary-independent continuous speech recognition system for speech control of intelligent home-network is presented. This study suggests a conversational scenario of continuous natural vocabulary based upon keywords for recognition on natural speech command, and a way of optimizing the recognition system by constructing a recognition system and database based upon keywords.

• Speech Sciences
• /
• v.10 no.3
• /
• pp.225-239
• /
• 2003

In this paper, we develop a keyword spotting system using vocabulary-independent speech recognition technique, and investigate several non-keyword modeling and post-processing methods to improve its performance. In order to model non-keyword speech segments, monophone clustering and Gaussian Mixture Model (GMM) are considered. We employ likelihood ratio scoring method for the post-processing schemes to verify the recognition results, and filler models, anti-subword models and N-best decoding results are considered as an alternative hypothesis for likelihood ratio scoring. We also examine different methods to construct anti-subword models. We evaluate the performance of our system on the automatic telephone exchange service task. The results show that GMM-based non-keyword modeling yields better performance than that using monophone clustering. According to the post-processing experiment, the method using anti-keyword model based on Kullback-Leibler distance and N-best decoding method show better performance than other methods, and we could reduce more than 50% of keyword recognition errors with keyword rejection rate of 5%.

• Annual Conference on Human and Language Technology
• /
• 2001.10d
• /
• pp.457-461
• /
• 2001

본 논문은 동사의 의미표상과 명사의 한정성의 강호관계를 중심으로 목적어의 생략현상을 검토하였다. 한국어는 영어 같은 언어와 달리 주어, 목적어 등이 자주 생략된다. 이 연구는 한국어의 목적어 생략이 단순히 인간성 (humanness), 주체성 (agency), 한정성(definiteness) 등 명사의 의미자질에 의해서만 결정되는 것이 아니라, 다음 두 가지 제약이 결정적으로 작용함을 제안하고자 한다. 첫째, 목적어 생략은 행동양상 (mold of agent act)과 원인 (cause)을 심층적으로 포함하는 소위 '핵심 타동사 (core transitive)'와 선행사의 한정성 정도에 의해 결정되는데, 구체적으로 목적어 생략은 한정성 자질을 가진 선행사가 없는 담화에서는 허용되지 않는다는 제약이다. 둘째, 타동사와 명사의 한정성과는 독립적으로, 한국어의 목적어 생략은 또한, 추론에 의거하여 보다 더 적절히 해석될 수 있는 경우를 실증적으로 보이고자 한다.

• Journal of Digital Convergence
• /
• v.20 no.2
• /
• pp.203-215
• /
• 2022

The study is to investigate research trends and knowledge structures in the Smart Farm field. To achieve the research purpose, keywords and the relationship among keywords were analyzed targeting 104 Korean academic journals related to the Smart Farm in KCI(Korea Citation Index), and topics were analyzed using the LDA Topic Modeling technique. As a result of the analysis, the main keywords in the Korean Smart Farm-related research field were 'environment', 'system', 'use', 'technology', 'cultivation', etc. The results of Degree, Betweenness, and Eigenvector Centrality were presented. There were 7 topics, such as 'Introduction analysis of Smart Farm', 'Eco-friendly Smart Farm and economic efficiency of Smart Farm', 'Smart Farm platform design', 'Smart Farm production optimization', 'Smart Farm ecosystem', 'Smart Farm system implementation', and 'Government policy for Smart Farm' in the results of Topic Modeling. This study will be expected to serve as basic data for policy development necessary to advance Korean Smart Farm research in the future by examining research trends related to Korean Smart Farm.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.1199-1201
• /
• 2011

본 논문은 의미적 정보처리에서 걸림돌이 되는 두문자어(Acronym)의 의미처리를 위한 전체적인 구조설계를 포함하고 있다. 두문자어는 일반적으로 복합어에서 의미가 큰 단어의 첫 번째 문자들로 구성된다. 두문자어를 구성하는 복합어는 다른 일반 명사들과 달리 대부분 고유한 의미를 갖고 있기 때문에 정보처리에서 의미 파악의 핵심적인 역할을 수행할 수 있다. 본 논문은 문서에서 출현하는 두문자어의 정확한 의미를 판단하기 위한 방법을 제안하며 현재까지 진행된 결과에 대해 언급하도록 한다.

• 한국정보통신설비학회:학술대회논문집
• /
• 2003.08a
• /
• pp.88-90
• /
• 2003

최근 들어 폭발적인 관심을 끌고 있는 패킷망에 음성을 실어 전달하는 IP 텔레포니에 관한 소개와 기업의 경쟁력을 향상시키기 위해 필수적으로 도입해야 하는 핵심 기술의 Avaya IP 텔레포니의 도입 혜택에 대한 전반적인 핵심 논점 등을 살펴보고 이를 분석하기로 한다.

• Journal of Society of Occupational Therapy for the Aged and Dementia
• /
• v.12 no.2
• /
• pp.67-74
• /
• 2018

Objective : The purpose of this study is to quantitatively analyze the role of occupational therapy in long - term care insurance for the elderly using text mining, one of the big data analysis techniques. Method : For the analysis of newspaper articles, "Long - Term Care Insurance for the Elderly + Occupational Therapy for the Elderly" was collected after the period from 2007 to 208. Naver, which has a high share of the domestic search engine, utilized the database of Naver News by utilizing Textom, a web crawling tool. After collecting the article title and original text of 510 news data from the collection of the elderly long term care insurance + occupational therapy search, we analyzed the article frequency and key words by year. Result : In terms of the frequency of articles published by year, the number of articles published in 2015 and 2017 was the highest with 70 articles (13.7%), and the top 10 terms of the key word analysis showed the highest frequency of 'dementia' (344) In terms of key words, dementia, treatment, hospital, health, service, rehabilitation, facilities, institution, grade, elderly, professional, salary, industrial complex and people are related. Conclusion : In this study, it is meaningful that the textual mining technique was used to more objectively confirm the social needs and the role of the occupational therapist for the dementia and rehabilitation in the related key keywords based on the media reporting trend of the elderly long - term care insurance for 11 years. Based on the results of this study, future research should expand research field and period and supplement the research methodology through various analysis methods according to the year.