• Title/Summary/Keyword: Error Characteristics

Search Result 3,489, Processing Time 0.03 seconds

Speech Recognition Error Compensation using MFCC and LPC Feature Extraction Method (MFCC와 LPC 특징 추출 방법을 이용한 음성 인식 오류 보정)

  • Oh, Sang-Yeob
    • Journal of Digital Convergence
    • /
    • v.11 no.6
    • /
    • pp.137-142
    • /
    • 2013
  • Speech recognition system is input of inaccurate vocabulary by feature extraction case of recognition by appear result of unrecognized or similar phoneme recognized. Therefore, in this paper, we propose a speech recognition error correction method using phoneme similarity rate and reliability measures based on the characteristics of the phonemes. Phonemes similarity rate was phoneme of learning model obtained used MFCC and LPC feature extraction method, measured with reliability rate. Minimize the error to be unrecognized by measuring the rate of similar phonemes and reliability. Turned out to error speech in the process of speech recognition was error compensation performed. In this paper, the result of applying the proposed system showed a recognition rate of 98.3%, error compensation rate 95.5% in the speech recognition.

Optimal Cutting Condition in Side Wall Milling Considering Form Accuracy (측벽 엔드밀 가공에서 형상 정밀도를 고려한 최적 절삭 조건)

  • 류시형;최덕기;주종남
    • Journal of the Korean Society for Precision Engineering
    • /
    • v.20 no.10
    • /
    • pp.31-40
    • /
    • 2003
  • In this paper, optimal cutting condition to minimize the form error in side wall machining with a flat end mill is studied. Cutting forces and tool deflection are calculated considering surface shape generated by the previous cutting such as roughing. Using the form error prediction method from tool deflection, optimal cutting condition considering form accuracy is investigated. Also, the effects of tool teeth number, tool geometry and cutting conditions on form error are analyzed. The characteristics and the difference of generated surface shape in up and down milling are discussed and over-cut free condition in up milling is presented. Form error reduction method through successive up and down milling is also suggested. The effectiveness and usefulness of the presented method are verified from a series of cutting experiments under various cutting conditions. It is confirmed that form error prediction from tool deflection in side wall machining can be used in optimal cutting condition selection and real time surface error simulation for CAD/CAM systems. This study also contributes to cutting process optimization for the improvement of form accuracy especially in precision die and mold manufacturing.

A Modified Residual-based Extended Kalman Filter to Improve the Performance of WiFi RSSI-based Indoor Positioning (와이파이 수신신호세기를 사용하는 실내위치추정의 성능 향상을 위한 수정된 잔차 기반 확장 칼만 필터)

  • Cho, Seong Yun
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.21 no.7
    • /
    • pp.684-690
    • /
    • 2015
  • This paper presents a modified residual-based EKF (Extended Kalman Filter) for performance improvement of indoor positioning using WiFi RSSI (Received Signal Strength Indicator) measurement. Radio signal strength in indoor environments may have irregular attenuation characteristics due to obstacles such as walls, furniture, etc. Therefore, the performance of the RSSI-based positioning with the conventional trilateration method or Kalman filter is insufficient to provide location-based accurate information services. In order to enhance the performance of indoor positioning, in this paper, error analysis of the distance calculated by using the WiFi RSSI measurement is performed based on the radio propagation model. Then, an IARM (Irregularly Attenuated RSSI Measurement) error is defined. Also, it shows that the IARM error is included in the residual of the positioning filter. The IARM error is always positive. So, it is presented that the IARM error can be estimated by taking the absolute value of the residual. Consequently, accurate positioning can be achieved based on the IEM (IARM Error Mitigated) EKF with the residual modified by using the estimated IARM error. The performance of the presented IEM EKF is verified experimentally.

Relationship between Normal Measurement and Error Rate of Output Voltage Linear Ratio of Seismic Accelerometer in Use (사용 중 지진 가속도계의 정상 측정과 출력전압 선형비 오차율 관계 분석)

  • Min-Jun Kim;Seong-Cheol Cho;Yong-Hun Jung;Jeong-Hun Won
    • Journal of the Korean Society of Safety
    • /
    • v.39 no.2
    • /
    • pp.65-74
    • /
    • 2024
  • We analyzed the relationship between the normal measurement of the seismic accelerometer (SA) and the error rate of the output voltage linear ratio to propose an evaluation method to determine whether the SA in use is measuring normally. Utilizing a test bed, the regular operation of SA in use was evaluated using acceleration data measured through impact tests since there are no regulations regarding performance testing of SA in use. For the used SA, the error rate of the output voltage linear ratio, which is a major performance criterion, was evaluated. We analyzed common characteristics of the SA that satisfied the impact test and the performance criteria of the output voltage linear ratio error rate. The results indicated that we must consider the decreasing trend and convergence of the error rate as the measurement angle increases, ensuring that the average value of the output voltage linear ratio error rate is within 1%.

Channel Condition Adaptive Error Concealment using Scalability Coding (채널상태에 적응적인 계층 부호화를 이용한 오류 은닉 방법 연구)

  • Han Seung-Gyun;Park Seung-Ho;Suh Doug-Young
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.29 no.1B
    • /
    • pp.8-17
    • /
    • 2004
  • In this paper: we propose the adaptive error concealment technique for scalable video coding over wireless network error prove environment. We prove it is very effective that Error concealment techniques proposed in this paper are applied to scalable video data. In this paper, we propose two methods of error concealment. First one is that the en·or is concealed using the motion vector of base layer and previous VOP data. Second one is that according to existence of motion vector in error position, the error is concealed using the same position data of base layer when the motion vector is existing otherwise using the same position data of previous VOP when the motion vector is 0(zero) adaptively. We show that according to various error pattern caused by condition of wireless network and characteristics of sequence, we refer decoder to base layer data or previous enhancement layer data to effective error concealment. Using scalable coding of MPEG-4 In this paper, this error concealment techniques are available to be used every codec based on DCT.

Analysis of Steady State Error on Simple FLC (단순 FLC의 정상상태오차 해석)

  • Lee, Kyoung-Woong;Choi, Han-Soo
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.17 no.9
    • /
    • pp.897-901
    • /
    • 2011
  • This paper presents a TS (Takagi-Sugeno) type FLC (Fuzzy Logic Controller) with only 3 rules. The choice of parameters of FLC is very difficult job on design FLC controller. Therefore, the choice of appropriate linguistic variable is an important part of the design of fuzzy controller. However, since fuzzy controller is nonlinear, it is difficult to analyze mathematically the affection of the linguistic variable. So this choice is depend on the expert's experience and trial and error method. In the design of the system, we use a variety of response characteristics like stability, rising time, overshoot, settling time, steady-state error. In particular, it is important for a stable system design to predict the steady-state error because the system's steady-state response of the system is related to the overall quality. In this paper, we propose the method to choose the consequence linear equation's parameter of T-S type FLC in the view of steady-state error. The parameters of consequence linear equations of FLC are tuned according to the system error that is the input of FLC. The full equation of T-S type FLC is presented and using this equation, the relation between output and parameters can represented. As well as the FLC parameters of consequence linear equations affect the stability of the system, it also affects the steady-state error. In this study, The system according to the parameter of consequence linear equations of FLC predict the steady-state error and the method to remove the system's steady-state error is proposed using the prediction error value. The simulation is carried out to determine the usefulness of the proposed method.

Tracking control for multi-axis system using two-degrees-of-freedom controller

  • Park, Ho-Joon;Lee, Je-Hee;Huh, Uk-Youl
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 1996.10a
    • /
    • pp.380-384
    • /
    • 1996
  • This paper represents an adaptive position controller with the disturbance observer for multi-axis servo system. The overall control system consists of three parts : the position controller, the disturbance observer with free parameters and cross-coupled controller which enhances contouring performance by reducing errors. Using two-degrees-of freedom conception, we design the command input response and the closed loop characteristics independently. The servo system can improve the closed loop characteristics without affecting the command input response. The characteristics of the closed loop system is improved by suppressing disturbance torque effectively with the disturbance observer. Moreover, the cross-coupled controller enhances tracking performance. Thus total position control performance is improved. Finally, the performance of the proposed controller shows that it improves the contouring performance along with the reference trajectory in the XY-table.

  • PDF

The characteristics and compensation of friction of X-Y table (X-Y 테이블의 마찰력 특성 및 보상)

  • Park, Eun-Chan;Im, Hyuk;Choi, Jong-Ho
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 2000.10a
    • /
    • pp.261-261
    • /
    • 2000
  • This paper analyzes the characteristics of pre-sliding friction of an X-Y table of CNC machining center at velocity reversal, and presents a simple and effective method of friction compensation based on this characteristics. At velocity reversal, a large position tracking error occurs because of the discontinuous change of friction. The relationship between the occurrence time of maximum position tracking error and the acceleration at zero velocity is analyzed by using the spring-like friction model. Furthermore, the experimental observation verifies this relation. From this, the state transition tine from pre-sliding regime into sliding regime can be predicted. Using the predicted transition time, the friction can be effectively compensated and table experimental results show its effectiveness.

  • PDF

A systematic method of probing channel characteristics of home power line communication network applied to the Internet accessed control of home appliances (인터넷 가전 제어를 위한 전력선 통신망 채널 특성 추정 기법에 관한 연구)

  • Ahn, N.H.;Chang, T.G.;Kim, H.
    • Proceedings of the KIEE Conference
    • /
    • 2002.07d
    • /
    • pp.2559-2561
    • /
    • 2002
  • This paper presents a systematic method of probing channel characteristics and communication reliabilities of home PLC (power line communication) network applied to the Internet accessed control of home appliances. The effects of the three performance deterioating factors, i.e., additive noise, channel attenuation, and intersymbol interference, can be systematically measured by applying the channel probing waveform in the frequency range from 100kHz to 450kHz. The agreement between the derived probability of bit error and the measured probability of bit error supports the validity of the proposed approach of probing home power line channel characteristics. The experimental results performed with the constructed test-bed applying the proposed channel probing method also support the feasibility of commercially deploying the PLC modem installed home appliances and their services for the Internet accessed home automation.

  • PDF

An analysis of data transmission characteristics in railway using MATLAB (MATLAB에 의한 열차 데이터 전달 특성 해석)

  • Ahn, Sang-Kwon;Choi, Gui-Man;Kim, Yang-Mo
    • Proceedings of the KIEE Conference
    • /
    • 1997.07a
    • /
    • pp.367-369
    • /
    • 1997
  • In signal system such as MAGLEV, the transmission channel that has wireless transmission line between on-board and ground-site is susceptible to have interference and may introduce data error on transmission. In this paper, by applying inductive wireless and FSK(frequency shift keying) modulation using widely in railway signal system, we intend to analyze the data transmission characteristics. In this case, noise may have effect on transmission channel. Therefore transmission channel should be lessened the data error from random noise. Considering the transmission medium, the objective of this study is to analyze the transmission characteristics between on-board and ground-site and to obtain transmission performance.

  • PDF