• Title/Summary/Keyword: 효율적 훈련 방법

Search Result 220, Processing Time 0.031 seconds

An Efficient symbol Synchronization Scheme with an Interpolator for Receiving in OFDM (OFDM 전송방식의 수신기를 위한 보간기의 효율적인 심볼 동기방법의 성능분석)

  • 김동옥;윤종호
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.6 no.4
    • /
    • pp.567-573
    • /
    • 2002
  • In this paper, we propose a new symbol time synchronization scheme suitable for the OFDM system with an interpolator. The proposed scheme performs the following three steps. In the first step, the coarse symbol time synchronization is achieved by continuously measuring the average power of the received envelope signal. Based on this average power, the detection possibility for the symbol time synchronization is determined. It the signal is sufficient for synchronization, we next perform a relatively accurate symbol time synchronization by measuring the correlation between a short training signal and the received envelope signal. Finally, an additional frequency synchronization is performed with a long training signal to correct symbol synchronization errors caused by the phase rotation. From the simulation results, one can see that the proposed synchronization scheme provides a good synchronization performance over frequency selective channels.

Efficient Rapid Speaker Adaptation Using Merging Eigenvoices (Eigenvoice 병합을 이용한 효율적인 고속 화자 적응)

  • Choi Dong-jin;Oh Yung-Hwan
    • Proceedings of the Acoustical Society of Korea Conference
    • /
    • autumn
    • /
    • pp.115-118
    • /
    • 2004
  • 음성 인식 분야에서는 화자 적응을 통해 화자 독립 시스템의 성능을 화자 종속 시스템에 근접시키려는 여러 가지 노력이 시도되고 있다. 특히 30 초미만의 매우 적은 양의 적응 자료를 이용하는 고속 화자 적응에 대한 관심이 증가하고 있다. 고속 화자 적응에 적합한 eigenvoice 를 이용한 적응 방법은 eigenvoice 를 구성하기 위해 너무 많은 계산량과 메모리를 요구한다. 본 논문에서는 각각 따로 계산된 eigenvoice 들을 한 번에 구성한 eigenvoice 들과 거의 같은 정확도를 갖도록 병합하여 고속 화자 적응에 이용하는 방법을 제안한다. 이 방법을 이용하면 훈련 자료의 추가시 처음부터 새롭게 eigenvoice 를 구하는 대신 추가된 자료에 대한 eigenvoice 를 구하고 병합함으로써 계산량과 메모리양을 현저히 줄일 수 있다. 실험 결과, 메모리와 계산량은 추가되는 화자 종속 모델의 수에 따라 감소하며 성능 저하는 거의 없었다.

  • PDF

Design and Implementation of Smart phone-based Records Management Application for Sports Clubs (운동부 지도자들을 위한 스마트폰 기반 기록관리 어플리케이션의 설계 및 구현)

  • Ha, Tai-Hyun;Kim, Se-Min
    • Journal of Digital Convergence
    • /
    • v.10 no.11
    • /
    • pp.395-402
    • /
    • 2012
  • This study has been conducted to design and implement smart phone-based application which can keep records effectively to improve athletes' ability. To boost their performance, they need to receive training as realistic as possible. As a way to do that, training should be performed with some fitness equipments, sporting apparatus, facilities, and conditions. However, it is also possible to improve their ability by motivating athletes with checking and recording their performance. This study ascertains that using scoring records actually motivates athletes when comparing the result of youth basketball team using the records keeping system with that of not using it. Accordingly, smart phone-based records keeping application has been designed and developed. Also, through a survey targeting athletic coaches who have used the system, training efficiency has been measured and it turns out that it actually motivates athletes to improve their abilities.

Method for Detecting Errors of Korean-Chinese MT Using Parallel Corpus (병렬 코퍼스를 이용한 한중 기계번역 오류 탐지 방법)

  • Jin, Yun;Kim, Young-Kil
    • Annual Conference on Human and Language Technology
    • /
    • 2008.10a
    • /
    • pp.113-117
    • /
    • 2008
  • 본 논문에서는 패턴기반 자동번역시스템의 효율적인 번역 성능 향상을 위해 병렬 코퍼스(parallel corpus)를 이용한 오류 자동 탐지 방법을 제안하고자 한다. 번역시스템에 존재하는 대부분 오류는 크게 지식 오류와 엔진 오류로 나눌 수 있는데 통상 이런 오류는 이중 언어가 가능한 훈련된 언어학자가 대량의 자동번역 된 결과 문장을 읽음으로써 오류를 탐지하고 분석하여 번역 지식을 수정/확장하거나 또는 엔진을 개선하게 된다. 하지만, 이런 작업은 많은 시간과 노력을 필요로 하게 된다. 따라서 본 논문에서는 병렬 코퍼스 중의 목적 언어(Target Language) 문장 즉, 정답 문장과 자동번역 된 결과 문장을 다양한 방법으로 비교하면서 번역시스템에 존재하고 있는 지식 및 엔진 오류를 자동으로 탐지하는 방법을 제안한다. 제안한 방법은 한-중 자동번역시스템에 적용하여 그 정확률과 재현률을 측정하였으며, 자동적으로 오류를 탐지하여 추출 할 수 있음을 증명하였다.

  • PDF

The Effect of Mindfulness Training on the Job Stress, Burnout, Teacher Efficacy of Middle School and High School Teachers (마음챙김 훈련이 중등교사의 직무스트레스와 소진, 교사효능감에 미치는 영향)

  • Kim, Tae-Kyun;Moon, Jung-Soon
    • Journal of Digital Convergence
    • /
    • v.16 no.4
    • /
    • pp.363-369
    • /
    • 2018
  • This study examines the effects of mindfulness training on job stress, burnout, and teacher efficacy for middle school and high school teachers. For this study, twenty-four middle school and high school teachers were divided into experimental and control groups. Data analysis was performed using a Mixed ANOVA for teacher's job stress, burnout, and teacher efficacy according to pre-training, post-training and delayed post-training periods. As a result, we found support for time interval and between-group interaction effects for all the dependent variables. In order to investigate any delayed effects, a t-test was performed to analyze measurements taken one month after the completion of training period. The delayed post-training results indicated a significant effect between pre and post scores, meaning the program effects were sustained. Therefore, this study indicates that the mindfulness training program implemented in this research is an effective method for preventing job stress and burnout, as well as influencing the efficiency of work performance for middle school and high school teachers.

Multistep Prediction-Based Blind Equalization and Efficient Adaptive Implementation (Multistep Prediction을 이용한 블라인드 등화기와 효율적인 적응 알고리듬)

  • 안경승;조주필;백흥기
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.26 no.6B
    • /
    • pp.776-783
    • /
    • 2001
  • 통신 채널에서 블라인드 채널 등화는 훈련신호나 채널의 사전 정보가 필요하지 않기 때문에 전송 효율을 높일 수 있는 매우 중요한 문제이다. 선형 예측 오차 방법은 블라인드 등화기의 차수 추정 오차에 대하여 강인하며 적응 알고리듬을 이용하여 효율적으로 구현할 수 있는 장점이 있다. 시스템 지연은 등화기의 성능에 많은 영향을 끼치지만 기존의 one-step 선형 예측은 등화기의 임의의 시스템 지연에 대해서는 구현할 수 없는 단점이 있다. 순방향 선형 예측과 역방향 선형 예측은 각각 시스템 지연이 0과 최대인 블라인드 등화와 관련이 있다. 그러나 Multistep 예측은 임의의 시스템 지연을 갖는 블라인드 등화기를 구현할 수 있는 장점이 있다. 본 논문에서는 최적의 시스템 지연을 구한 후 RLS 알고리듬과 LMS 알고리듬을 이용한 multistep 선형 예측을 이용한 블라인드 채널 등화기를 제안하였다. 그리고 기존의 알고리듬들과 본 논문에서 제안한 알고리듬의 성능을 모의실험을 통하여 기존의 알고리듬들과 비교·평가하였다.

  • PDF

Phoneme Similarity Error Correction System using Bhattacharyya Distance Measurement Method (바타챠랴 거리 측정법을 이용한 음소 유사율 오류 보정 개선 시스템)

  • Ahn, Chan-Shik;Oh, Sang-Yeob
    • Journal of the Korea Society of Computer and Information
    • /
    • v.15 no.6
    • /
    • pp.73-80
    • /
    • 2010
  • Vocabulary recognition system is providing inaccurate vocabulary and similar phoneme recognition due to reduce recognition rate. It's require method of similar phoneme recognition unrecognized and efficient feature extraction process. Therefore in this paper propose phoneme likelihood error correction improvement system using based on phoneme feature Bhattacharyya distance measurement. Phoneme likelihood is monophone training data phoneme using HMM feature extraction method, similar phoneme is induced recognition able to accurate phoneme using Bhattacharyya distance measurement. They are effective recognition rate improvement. System performance comparison as a result of recognition improve represent 1.2%, 97.91% by Euclidean distance measurement and dynamic time warping(DTW) system.

RFID Indoor Location Recognition Using Neural Network (신경망을 이용한 RFID 실내 위치 인식)

  • Lee, Myeong-hyeon;Heo, Joon-bum;Hong, Yeon-chan
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.19 no.3
    • /
    • pp.141-146
    • /
    • 2018
  • Recently, location recognition technology has attracted much attention, especially for locating people or objects in an indoor environment without being influenced by the surrounding environment GPS technology is widely used as a method of recognizing the position of an object or a person. GPS is a very efficient, but it does not allow the positions of objects or people indoors to be determined. RFID is a technology that identifies the location information of a tagged object or person using radio frequency information. In this study, an RFID system is constructed and the position is measured using tags. At this time, an error occurs between the actual and measured positions. To overcome this problem, a neural network is trained using the measured and actual position data to reduce the error. In this case, since the number of read tags is not constant, they are not suitable as input values for training the neural network, so the neural network is trained by converting them into center-of-gravity inputs and median value inputs. This allows the position error to be reduce by the neural network. In addition, different numbers of trained data are used, viz. 50, 100, 200 and 300, and the correlation between the number of data input values and the error is checked. When the training is performed using the neural network, the errors of the center-of-gravity input and median value input are compared. It was found that the greater the number of trained data, the lower the error, and that the error is lower when the median value input is used than when the center-of-gravity input is used.

Experiencing Design Foundation in On-Line Education - By Using The Basic Graphic Tools - (디지털 학습 환경에서의 기초디자인 교육 - 기초디자인 훈련 도구(Basic Graphic Tools)의 개발을 중심으로 -)

  • Lee, Eun-Joo
    • Archives of design research
    • /
    • v.18 no.2 s.60
    • /
    • pp.255-264
    • /
    • 2005
  • The development of personal computers and the Internet led to changes of instructor-student and student-student relationships in design education. New resources of design education with proper materials and tools have to be offered for teaching and learning. The purpose of this research is to develop Basic Graphic Tools(BGTs) on screen that help students to practice the design principles, and to evaluate the BGTs' usability to enhance the credibility of extra tools for online design learning. The BGTs has to be developed to minimize the gap between the online and traditional classroom settings and to maximize the diverse advantage of lecture content driven from technology. Students were given certain design requirements to explore BGTs and a learning guide/performance test after the lecture to evaluate the tools. The test was performed under the e-learning program serviced by C college. This research has presented some encouraging results and raises questions toward future work: how do BGTs impact the feasibility of an online design lecture.

  • PDF

Development of a Occupation-Based Bilateral Upper Extremity Training Protocol in a Medical Setting for Stroke Patients (뇌졸중 환자를 대상으로 한 병원 환경에서의 작업 기반 양측성 상지 훈련 프로토콜 개발)

  • Kim, Sun-Ho;Kim, Jung Ran;Park, Hae Yean;Han, A-Reum;Kim, Jong-Bae;Park, Ji-Hyuk
    • Therapeutic Science for Rehabilitation
    • /
    • v.9 no.1
    • /
    • pp.24-44
    • /
    • 2020
  • Objective : To develop an occupation-based bilateral upper extremity training protocol that can be effectively applied in a medical setting Methods : The research process using the delphi technique was carried out in 3 stages. The first stage was an open questionnaire development stage, The first draft is prepared through literature review and open questions were developed through preliminary research based on the draft. The second stage was the delphi survey. Based on the responses of the experts obtained through the open Delphi survey, the adequacy of the training protocol was shown on a Likert 5 point scale. The items were edited and deleted, reconstructed by analyzing the mean and standard deviation, stability, convergence degree, consensus, and content validity ratio through the questionnaire. The third step was the completion of the protocol. After discussions between researchers, the finalized protocol contents were reorganized to complete the occupation-based bilateral upper extremity training protocol for medical setting. Results : The final protocol consisted of 9 items across 3 areas in the occupation-based intervention selection domain and 81 items across 4 areas in the bilateral upper extremity training domain, intervention period, and evaluation. Conclusions : This study suggests an evidence-based method that collects the opinions of occupational therapists in order to use occupation-based activities as interventions in a situation that currently sees occupational therapy primarily performed in hospitals. It is also meaningful that the bilateral upper extremity training can be applied effectively in clinical situations by concretely presenting.