• Title/Summary/Keyword: 자동 응답

Search Result 362, Processing Time 0.028 seconds

Decision of the Korean Speech Act using Feature Selection Method (자질 선택 기법을 이용한 한국어 화행 결정)

  • 김경선;서정연
    • Journal of KIISE:Software and Applications
    • /
    • v.30 no.3_4
    • /
    • pp.278-284
    • /
    • 2003
  • Speech act is the speaker's intentions indicated through utterances. It is important for understanding natural language dialogues and generating responses. This paper proposes the method of two stage that increases the performance of the korean speech act decision. The first stage is to select features from the part of speech results in sentence and from the context that uses previous speech acts. We use x$^2$ statistics(CHI) for selecting features that have showed high performance in text categorization. The second stage is to determine speech act with selected features and Neural Network. The proposed method shows the possibility of automatic speech act decision using only POS results, makes good performance by using the higher informative features and speed up by decreasing the number of features. We tested the system using our proposed method in Korean dialogue corpus transcribed from recording in real fields, and this corpus consists of 10,285 utterances and 17 speech acts. We trained it with 8,349 utterances and have test it with 1,936 utterances, obtained the correct speech act for 1,709 utterances(88.3%). This result is about 8% higher accuracy than without selecting features.

Complexity Metrics for Analysis Classes in the Unified Software Development Process (Unified Process의 분석 클래스에 대한 복잡도 척도)

  • 김유경;박재년
    • The KIPS Transactions:PartD
    • /
    • v.8D no.1
    • /
    • pp.71-80
    • /
    • 2001
  • Object-Oriented (OO) methodology to use the concept like encapsulation, inheritance, polymorphism, and message passing demands metrics that are different from structured methodology. There are many studies for OO software metrics such as program complexity or design metrics. But the metrics for the analysis class need to decrease the complexity in the analysis phase so that greatly reduce the effort and the cost of system development. In this paper, we propose new metrics to measure the complexity of analysis classes which draw out in the analysis phase based on Unified Process. By the collaboration complexity, is denoted by CC, we mean the maximum number of the collaborations can be achieved with each of the collaborator and detennine the potential complexity. And the interface complexity, is denoted by IC, shows the difficulty related to understand the interface of collaborators each other. We prove mathematically that the suggested metrics satisfy OO characteristics such as class size and inheritance. And we verify it theoretically for Weyuker' s nine properties. Moreover, we show the computation results for analysis classes of the system which automatically respond to questions of the it's user using the text mining technique. As we compared CC and IC to CBO and WMC, the complexity can be represented by CC and IC more than CBO and WMC. We expect to develop the cost-effective OO software by reviewing the complexity of analysis classes in the first stage of SDLC (Software Development Life Cycle).

  • PDF

The Study on Design of lead monoxide based radiation detector for Checking the Position of a Radioactive Source in an NDT (비파괴검사 분야에서 방사선원의 위치 확인을 위한 산화납 기반 방사선 검출기 설계에 관한 연구)

  • Ahn, Ki-Jung
    • Journal of the Korean Society of Radiology
    • /
    • v.11 no.4
    • /
    • pp.183-188
    • /
    • 2017
  • In recent years, the automatic remote control controller of the gamma ray irradiator malfunctions, and radiation workers are continuously exposed to radiation exposure accidents. In the non-destructive testing field, much time and resources are invested in establishing a radioactive source monitoring system in order to prevent potential incidents of radiation. In this study, the gamma-ray response properties of the lead monoxide-based radiation detector were estimated through monte carlo simulation as a previous study for the development of a radioactive source location monitoring system that can be applied universally to various non-destructive testing equipment. As a result of the study, the optimized thickness of the radiation detector varies according to the gamma-ray energy emitted from the radioactive source, and the optimized thickness gradually increases with increasing energy. In conclusion, the optimized thickness of the lead monoxide-based radiation detector was $200{\mu}m$ for the Ir-192, $150{\mu}m$ for the Se-75 and $300{\mu}m$ for the Co-60. Based on these results, the appropriate thickness of lead monoxide-based radiation detector considering secondary-electron equilibrium was evaluated to be $300{\mu}m$ for general application. These results can be used as a basic data for determining the appropriate thickness required in the radiation detector when developing a radiation source location monitoring system for universal application to various non-destructive testing equipment in the future.

A Study on the Development of the Single Station Fixed Temperature Detector of Low Power Consumption for Residential Fire Prevention (주택화재 예방을 위한 저소비 전력형 단독경보형 정온식감지기 개발에 관한 연구)

  • Park, Se-Hwa;Cho, Jae-Cheol
    • Fire Science and Engineering
    • /
    • v.24 no.6
    • /
    • pp.61-68
    • /
    • 2010
  • In this paper, a research and development result for the implementation of single station fixed temperature detector for residential fire prevention is described. The detector was developed for the certification in Japanese market because of very low domestic market situation. It is in the situation that there is no other regulation especially for residential detectors in Korea, Japanese case has been reviewed. Investigation of domestic legal circumstances and a comparative study for the test standard owned by KFI (Korea Institute of Fire Industry & Technology) and JFEII (Japan Fire Equipment Inspection Institute) respectively are also indicated. The detector alarms with a buzzer and an indicating LED. In the implementation ultra low power MCU(Micro Controller Unit) is applied to control the sleeping state and the monitoring state properly with low current consumption. To sense the temperature fast response thermistor is adopted in the design of fixed temperature residential detector. Automatic test function and alarm stop function are also considered in the design. The major factors which influence to current consumption are explained for the purpose of design reference. Main electronics circuit parts related to it's characteristics of the detector are described. It is explained that the measured current and experimental result of the battery discharge can be met over 10 years operation.

Automatic measurement of voluntary reaction time after audio-visual stimulation and generation of synchronization signals for the analysis of evoked EEG (시청각자극 후의 피험자의 자의적 반응시간의 자동계측과 유발뇌파분석을 위한 동기신호의 생성)

  • 김철승;엄광문;손진훈
    • Science of Emotion and Sensibility
    • /
    • v.6 no.4
    • /
    • pp.15-23
    • /
    • 2003
  • Recently, there have been many attempts to develop BCI (brain computer interface) based on EEG (electroencephalogram). Measurement and analysis of EEG evoked by particular stimulation is important for the design of brain wave pattern and interface of BCI. The purpose of this study is to develop a general-purpose system that measures subject's reaction time after audio-visual stimulation which can work together with any other biosignal measurement systems. The entire system is divided into four modules, which are stimulation signal generation, reaction time measurement, evoked potential measurement and synchronization. Stimulation signal generation module was implemented by means of Flash. Measurement of the reaction time (the period between the answer request and the subject reaction) was achieved by self-made microcontroller system. EEG measurement was performed using the ready-made hardware and software without any modification. Synchronization of all modules was achieved by, first, the black-and-white signals on the stimulation screen synchronized with the problem presentation and the answer request, second, the photodetectors sensing the signals. The proposed method offers easy design of purpose-specific system only by adding simple modules (reaction time measurement, synchronization) to the ready-made stimulation and EEG system, and therefore, it is expected to accelerate the researches requiring the measurement of evoked response and reaction time.

  • PDF

수학적 모폴로지의 경계치 변화에 의한 도시환경 지형지물 추출 및 분리응용

  • O, Se-Gyeong;Lee, Gi-Won
    • 한국공간정보시스템학회:학술대회논문집
    • /
    • 2004.12a
    • /
    • pp.139-143
    • /
    • 2004
  • 최근 고 해상도 위성영상정보의 민간 활용에 대한 수요가 증가하면서 기존의 공간 정보를 다루는 여러 응용분야에서 이에 관련된 많은 연구를 하고 있다. 도시교통 환경 분석을 위하여 위성영상정보를 처리하는 과정에 있어서 도로, 건물, 기타 선 구조와 같은 지형지물을 분석하는 과정은 사용자에 따라 주관적일 수 있다. 이러한 배경에서 수학적 그레이 레벨 모폴로지는 하나의 효과적인 접근으로 간주된다. 본 연구에서 지형지물 추출을 위해 윈도우 운영체제에서 실행되는 실질적인 응용 프로그램을 구현하였다. 이 프로그램에서 주요한 지형지물은 그레이 레벨 영상을 이용하여 개방(opening), 폐쇄(closing), 침식(erosion), 팽창(dilation)의 순차적 처리를 통하여 자동적으로 추출된다. 결과적으로, GDPA, 허프 변환 또는 다른 알고리듬들과 비교시 하나의 이점이 된다. 모폴로지 처리와 같이 본 프로그램은 그레이 레벨 값의 범위에 기반하여 지형지물을 추출을 위한 density slicing 기능 또는 주어진 경계치 보다 작은 화소 군집을 제거하는 처리인 'sieve filtering'을 제공한다. 이러한 기능들은 형태학적으로 처리된 결과를 증대하고 지형지물 종류들을 분리하는데 유용하다. 또한 배경의 제거, 잡음 탐지, 도시 환경 원격 탐사에서의 지형지물 특성화에 기여한다. 본 프로그램을 이용하는데 있어서 IKONOS 위성영상을 이용하여 시험 구현하였다. 결과, 다중 경계치 또는 steve filtering을 이용한 그레이 레벨 모폴로지 처리는 복잡한 지형지물과 많은 데이터로 구성된 고해상도 영상 내의 주어진 대상에서 자동적인 처리와 사용자 정의 sieve filtering으로 인한 효과적인 지형지물 추출 방법으로 간주 된다. 시안을 작성 표준화를 위한 첫 단계 시도를 소개하였다.분석 결과는 문장, 그림 및 도표, 장 끝의 질문, 학생의 학습 활동 수 등이 $0.4{\sim}1.5$ 사이의 값으로 학생 참여를 적절히 유도하는 발견 지향적 인 것으로 조사되었다. 그러나 장의 요약은 본문 내용을 반복하는 내용으로 구성되었다. 이와 같이 공통과학 과목은 새로운 현대 사회에 부응하는 교과 목표와 체계를 지향하고 있지만 아직도 통합과학으로서의 내용과 체계를 완전히 갖추고 있지 못할 뿐만 아니라 현재 사용되고 있는 7종의 교과서가 교육 목표를 충분히 반영하지 못하고 있다. 따라서 교사의 역할이 더욱더 중요하게 되었다.괴리가 작아진다. 이 결과에 따르면 위탁증거금의 징수는 그 제도의 취지에 부합되고 있다. 다만 제도운용상의 이유이거나 혹은 우리나라 주식시장의 투자자들이 비합리적인 투자형태를 보임에 따라 그 정책적 효과는 때로 역기능적인 결과로 초래하였다. 그럼에도 불구하고 이 연구결과를 통하여 최소한 주식시장(株式市場)에서 위탁증거금제도는 그 제도적 의의가 여전히 있다는 사실이 확인되었다. 또한 우리나라 주식시장에서 통상 과열투기 행위가 빈번히 일어나 주식시장을 교란시킴으로써 건전한 투자풍토조성에 저해된다는 저간의 우려가 매우 커왔으나 표본 기간동안에 대하여 실증분석을 한 결과 주식시장 전체적으로 볼 때 주가변동율(株價變動率), 특히 초과주가변동율(超過株價變動率)에 미치는 영향이 그다지 심각한 정도는 아니었으며 오히려 우리나라의 주식시장은 미국시장에 비해 주가가 비교적 안정적인 수준을 유지해 왔다고 볼 수 있다.36.4%)와 외식을 선호(29.1%)${\lrcorner}$ 하기 때문에 패스트푸드를 이용하게 된 것으로 응답 하였으며,

  • PDF

Measurement of Classes Complexity in the Object-Oriented Analysis Phase (객체지향 분석 단계에서의 클래스 복잡도 측정)

  • Kim, Yu-Kyung;Park, Jai-Nyun
    • Journal of KIISE:Software and Applications
    • /
    • v.28 no.10
    • /
    • pp.720-731
    • /
    • 2001
  • Complexity metrics have been developed for the structured paradigm of software development are not suitable for use with the object-oriented(OO) paradigm, because they do not support key object-oriented concepts such as inheritance, polymorphism. message passing and encapsulation. There are many researches on OO software metrics such as program complexity or design metrics. But metrics measuring the complexity of classes at the OO analysis phase are needed because they provide earlier feedback to the development project. and earlier feedback means more effective developing and less costly maintenance. In this paper, we propose the new metrics to measure the complexity of analysis classes which draw out in the analysis based on RUP(Rational Unified Process). By the collaboration complexity, is denoted by CC, we mean the maximum number of the collaborations can be achieved with each of the collaborator and determine the potential complexity. And the interface complexity, is denoted by IC, shows the difficulty related to understand the interface of collaborators each other. We verify theoretically the suggested metrics for Weyuker's nine properties. Moreover, we show the computation results for analysis classes of the system which automatically respond to questions of the user using the text mining technique. As a result of the comparison of CC and CBO and WMC suggested by Chidamber and Kemerer, the class that have highly the proposed metric value maintain the high complexity at the design phase too. And the complexity can be represented by CC and IC more than CBO and WMC. We can expect that our metrics may provide us the earlier feedback and hence possible to predict the efforts, costs and time required to remainder processes. As a result, we expect to develop the cost-effective OO software by reviewing the complexity of analysis classes in the first stage of SDLC(Software Development Life Cycle).

  • PDF

Exception based Dynamic Service Coordination Framework for Web Services (웹 서비스를 위한 예외 상황 기반 동적 서비스 연결 프레임워크)

  • Han Dong-Soo;Lee Sung-Doke;Jung Jong-Ha
    • Journal of KIISE:Software and Applications
    • /
    • v.33 no.8
    • /
    • pp.668-680
    • /
    • 2006
  • Web services on the Internet are not always reliable in terms of service availability and performance. Dynamic service coordination capability of a system or an application invoking Web services is essential to cope with such unreliable situations. In dynamic service coordination, if a Web service does not respond within a specific time constraint, it is replaced with another Web service at run time for reliable invocation of Web services. In this paper, we develop an exception based dynamic service coordination framework for Web services. In the framework, all necessary information for dynamic service coordination is explicitly specified and summarized as a set of attributes. Then classes and workflows, supporting dynamic service coordination and invoking Web services, are automatically created based on these attributes. Developers of Web services client programs can make the invocations of Web services reliable by calling the methods of the classes. Some performance loss has been observed in the indirect invocation of a Web service. However, when we consider the flexibility and reliability gained from the method, the performance loss would be acceptable in many cases.

A Usability Testing on the Tablet PC-based Korean High-tech AAC Software (태블릿 PC 기반 한국형 하이테크 AAC 소프트웨어의 사용성 평가)

  • Lee, Heeyeon;Hong, Ki-Hyung
    • Journal of the HCI Society of Korea
    • /
    • v.7 no.2
    • /
    • pp.35-42
    • /
    • 2012
  • The purpose of this study was to evaluate the usability of the tablet PC-based Korean high-tech AAC(Augmentative Alternative Communication System) software. In order to develop an AAC software which is appropriate to Korean cultural/linguistic contexts and communication needs of the users, we examined the necessity and ease of use for the communication functions that are required in native Korean communication, such as polite expressions, tense expressions, negative expressions, subject-verb auto-matching, and automatic sentence generation functions, using a scenario-based user testing. We also investigated the users' needs, preferences, and satisfaction for the tablet PC-based Korean high tech AAC using a semi-structured and open questionnaires. The participants of this study were 9 special education teachers, 6 speech therapists, and 6 parents whose children had communication disabilities. The results of the usability testing of the tablet PC-based Korean high-tech AAC software presented positive responses in general, by indicating overall scores of above 4 out of 5 except in tense and negative expressions. The necessity and ease of use in the tense and negative expressions were evaluated relatively low, and it might be related to the inconsistent interface with the polite expressions. In terms of the user interface(UI), there were users' needs for clear visual feedback in the symbol selection and display, consistent interface for all functions, more natural subject-verb auto-matching, and spacing in the text within symbols. The results of the usability testing and users' feedback might serve as a guideline to compensate and improve the function and UI of the existing AAC software.

  • PDF

A Study on vibration suppression of dual inertia system using controlling Parameter $\alpha$ of PID controller with 2-degree of freedom (2자유도 PID 제어기의 파라미터 $\alpha$ 추종을 이용한 2관성 시스템의 진동억제)

  • 박재현;추연규;김현덕;박연식
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2004.05b
    • /
    • pp.506-510
    • /
    • 2004
  • A torque transmission system composed of several gears and couplings is flexible. In order to get an exact response of motor, the torsional vibration due to an unexpected change of motor speed must be suppressed. Therefore, it is very important that motor control suppress vibration. Various methods to control it including dual inertia system are proposed. Specially, the method of vibration suppression is that vibration can be suppressed to fee㏈ack the estimated torsion torque via the disturbance observer filter being of normal filter. The suitable Proportional controller and coefficient parameter can be designed using CDM and the torsional vibration also be suppressed, but it has a low degree of adaptability to disturbance. The PID controller can be designed easily, but makes the excessive overshoot and oscillation for system response in the early period. To resolve these problems, simple and practical PID controller with two degree of freedom is proposed recently that it ran improve performance of obeying the reference unconcerned in any disturbance by changing the proportional gain by two degree of freedom parameter. But it has also the defect that parameter a must be changed to obtain the ideal Proportional parameter. On this paper, we design the controller which automatically adjusts parameter u using fuzzy Algorithm to overcome such defects. Also, we compare the proposed method with established one and evaluate them to confirm performance of the designed controller.

  • PDF