• Title/Summary/Keyword: recognition gap

Search Result 171, Processing Time 0.023 seconds

A STUDY ON THE RECOGNITION OF SPOKEN KOREAN LOCAL-NAMES USING SPATIO TEMPORAL

  • Song, Do-Sun;Kim, Suk-Dong;Lee, Haing-Sei
    • Proceedings of the Acoustical Society of Korea Conference
    • /
    • 1994.06a
    • /
    • pp.1003-1008
    • /
    • 1994
  • This paper is about an experiment of speaker-independent automation Korean spoken words recognition using Multi-Layered Perceptron and Error Back-propagation algorithm. The words were not segmented into syllables or phonemes, and some feature components extracted from the words in equal gap were applied to the neural network. This paper tried to find out the optimum conditions through various experiment which are comparison between total and pre-classified training.

  • PDF

The Analysis of e-Learning Gap among Regions in the Context of Adult Learning (성인 인적자원개발 영역에서의 지역 간 교육격차 및 e-Learning 인식 수준 연구)

  • Cho, Jae-Jeong;Lee, Sook-Young
    • Journal of Digital Contents Society
    • /
    • v.11 no.2
    • /
    • pp.265-276
    • /
    • 2010
  • The purpose of this study was to investigate the Korean Local Government's recognition on the educational gap among regions in the filed of adult learning including vocational education and life long-learning. The study also tried to figure out the local government's recognition and infrastructure of e-Learning which is suggested as one of the solutions on the regional gap of educational opportunities and quality. This study took 12 HRD(Human Resources Development) centers funded and operated by the Korean Local Governments except Seoul and Kyong-Gi classified by the metropolitan areas in Korea. As a result, firstly it was found that the local governments had perception on the difference and gap of educational opportunities and quality among regions in the area of adult education. Especially, the perception was relatively more serious on quality than quantity. Secondly, the result showed the large gap among regions on the area of opening educational and training programs, the quality of teachers and tutors, the effectiveness and outcomes of educational programs. Thirdly, they perceived more serious educational gap on face-to-face classes rather than e-Learning in the context of educational methodology. It also revealed that the local governments had relatively better foundations on physical systems than other infrastructures and resources such as human-ware, culture-ware and soft-ware(contents, programs etc.). It was recommended to consider these findings in developing and implementing future educational policies to solve the problem of regional gap on education.

The Study on the Difference of Regulation Recognition among Generations (연령별 규제 인식 차이에 관한 연구)

  • Choi, Seong-Rak
    • The Journal of the Korea Contents Association
    • /
    • v.16 no.3
    • /
    • pp.586-595
    • /
    • 2016
  • The difference of generation is the main cause of society transition. If we know about the gap of generations, then we know where we go in future. This study focus on the differences of a regulation recognition among the generations. When we understand the differences of regulation recognition among the generations, we can realize the trait of regulation in society. In result, there are a lot of differences of regulation recognition among the generations. The older they are, the more they are positive to regulation. And the younger they are, the more they are negative to regulation. In particular, 50's generation have the opposite regulation recognition to 20's generation in specialty of regulation and in a conglomerate regulation.

Ontology-based Object-Image Recognition by Using Information on Inner-Objects (내부 객체 정보를 이용한 온톨로지 기반의 객체 영상 인식)

  • Lee, In-K.;Seo, Suk-T.;Seok, Ji-Kwon;Kwon, Soon-H.
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.19 no.6
    • /
    • pp.760-765
    • /
    • 2009
  • Since the features in object-images such as color and shape cannot clearly express the characteristic of objects, those features lead to vagueness of object-image recognition. Recently there have been studied on object-image recognition based on knowledge base in order to reduce the vagueness. However, because images are represented by numerical information but knowledge bases are represented by conceptual information, combining two kinds of information is difficult. In this paper, we compose knowledge base by using ontology to reduce the gap between the two kinds of information, and propose a method for object-image recognition to reduce the vagueness by using information on inner-object. Moreover, we confirm the usefulness of the proposed method through the experiments on object-image recognition in fruit domain.

Using Utterance and Semantic Level Confidence for Interactive Spoken Dialog Clarification

  • Jung, Sang-Keun;Lee, Cheong-Jae;Lee, Gary Geunbae
    • Journal of Computing Science and Engineering
    • /
    • v.2 no.1
    • /
    • pp.1-25
    • /
    • 2008
  • Spoken dialog tasks incur many errors including speech recognition errors, understanding errors, and even dialog management errors. These errors create a big gap between the user's intention and the system's understanding, which eventually results in a misinterpretation. To fill in the gap, people in human-to-human dialogs try to clarify the major causes of the misunderstanding to selectively correct them. This paper presents a method of clarification techniques to human-to-machine spoken dialog systems. We viewed the clarification dialog as a two-step problem-Belief confirmation and Clarification strategy establishment. To confirm the belief, we organized the clarification process into three systematic phases. In the belief confirmation phase, we consider the overall dialog system's processes including speech recognition, language understanding and semantic slot and value pairs for clarification dialog management. A clarification expert is developed for establishing clarification dialog strategy. In addition, we proposed a new design of plugging clarification dialog module in a given expert based dialog system. The experiment results demonstrate that the error verifiers effectively catch the word and utterance-level semantic errors and the clarification experts actually increase the dialog success rate and the dialog efficiency.

Developement of 3-D Vision Monitoring System for Tailored Blank Welding (맞춤판재 용접용 3차원 비젼 감시기 개발)

  • Jang, Young-Gun;Lee, Keung-Don
    • Journal of the Korean Society for Precision Engineering
    • /
    • v.14 no.12
    • /
    • pp.17-23
    • /
    • 1997
  • A 3-D vision system is developed to evaluate blanks' line up and monitor gap and thickness difference between blanks in tailored blank welding system. A structured lighting method is used for 3-D vision recognition. Images of sheared portion in blanks are irregular according to roughness of blank surface, shape of sheared geometry and blurring. It is difficult to get accurate and reliable informations in the case of using binary image processing or contour detection techniques in real time for such images. We propoe a new energy integration method robust to blurring and changes of illumination. The method is computationally simple, and uses feature restoration concept, different to another digital image restoration methods which aim image itself restoration and may be used in conventional applications using structured line lighting technique. Experimental results show this system measuring repeatability is .+-. pixel for gap and thickness difference in static and dynamic tests. The data are expected to be useful for preview gap control.

  • PDF

A Study on the Reality of IoT Device and Service Information Gap in the Era of Digital Transformation (디지털 전환 시대에 IoT 기기와 서비스 정보 격차 실태 연구)

  • Lee, Sangho;Cho, Kwangmoon
    • Journal of Internet of Things and Convergence
    • /
    • v.7 no.1
    • /
    • pp.79-89
    • /
    • 2021
  • This study attempted to identify the information gap about Internet of Things (IoT) devices and services in the era of digital transformation. To this end, we analyzed differences in perception of predicting future issues about IoT devices and services, and analyzed differences in the need for digital technology and help in life according to perceptions and experience of using IoT devices and services. Also, the level of education and demand for education were analyzed. A survey was conducted from February 15th to March 7th, 2021 for residents in Gwangju Metropolitan City and Jeollanam-do, and 232 respondents responded. Analysis was performed using SPSS 21.0, and all statistical values were presented as average values. The results of the study are as follows. First, the future issues of the intelligent information society according to the recognition of the intelligent information society, the help of life provided by artificial intelligence devices and services, and the need for intelligent information technology were presented. Second, the difference in Life help provided by artificial intelligence according to the recognition and use experience of artificial intelligence devices was presented. Third, the difference in life help provided by artificial intelligence according to the recognition and use experience of artificial intelligence service was presented. Fourth, the difference in necessity according to artificial intelligence technology recognition and use experience was presented. Fifth, the educational level and educational demand of the intelligent information society were investigated and presented. Through the results of this study, a suggestion for resolving the information gap in the era of digital transformation was suggested.

A Study on Motion Control of the Pet-Robot using Voice-Recognition (음성인식을 이용한 반려 로봇의 모션제어에 대한 연구)

  • Ye-Jin, Cho;Hyun-Seok, Kim;Tae-Sung, Bae;Su-Haeng, Lee;Jin-Hyean, Kim;Jae-Wook, Kim
    • The Journal of the Korea institute of electronic communication sciences
    • /
    • v.17 no.6
    • /
    • pp.1089-1094
    • /
    • 2022
  • In this paper, a human coexistence-type companion robot that can communicate with people in daily life and alleviate the gap in care personnel was studied. Based on the voice recognition module, servo motor, and Arduino board, a companion robot equipped with a robot arm control function using voice recognition, a position movement function using RC cars, and a voice recognition function was tested and manufactured. As a result of the experiment, the speech recognition experiment according to distance showed the optimal recognition rate at a distance of 5 to 30 cm, and the speech recognition experiment according to gender showed a higher recognition rate in the first tone, monotonous tone. Through the evaluation results of these motion experiments, it was confirmed that a companion robot could be made.

Relevance of Change on the Subjective Recognition of Social Class and Medical Expenditure (주관적 계층인식 변화와 의료비지출과의 관련성)

  • Choi, Ryoung;Hwang, Byung Deog
    • The Korean Journal of Health Service Management
    • /
    • v.13 no.1
    • /
    • pp.31-42
    • /
    • 2019
  • Objectives: The purpose of this study is to analyze the relationship between the change gap in the perception of subjective hierarchy and medical expenditure and the factors influencing medical expenditure. Methods: An analysis based on the the data extracted from the Panel Study of Korea Health Panel for 2012-2013 (n=9,359) is conducted. Further in this study, data analysis included a chi-square test and logistic regression using SPSS version. 22.0 to analyze the factors influencing the turnover intention of industrial workers. Results: Model I showed decreases in medical expenditure by 1.247, 1.391, and 1.441 times in social classes one, two, and Model II showed an increase in medical expenditure by age, spouse, number of family members living together, insurance type, income class, economic activities, subjective health status, chronic illness and change on subjective recognition of social class. Conclusions: The study concludes that the state and community require psychological, social, and cultural support, in addition to individual efforts, to reduce medical expenditure.

Cognition of Korean Kinship Name : Investigating the Children's Recognition of Cognate Group Ranges (한국아동(韓國兒童)의 친척명(親戚名) 인지(認知))

  • Yi, Soon Hyung
    • Korean Journal of Child Studies
    • /
    • v.5
    • /
    • pp.21-45
    • /
    • 1984
  • The cognition of Korean kinship names was examined in children in the 1st, 3rd, 5th, and 9th grades (N=188) of public school. The task consisted of 43 items which identified the relative relationships of cognates and cognates-in-law. It was found that the main effects of age and residential area on cognition scores were significant and the interaction effects between the variables were also significant. As expected, older children performed the task more precisely than the younger children and children in Seoul performed better than in outlying regions. Under 15 years of age, the scores in Seoul were higher than in Andong, but at the age of l5, this trend was reversed. The gap between residential areas under 15 years of age could be explained by differences in cognitive ability and test effects, but the gap at 15 by culture.

  • PDF