• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.8
• /
• pp.898-906
• /
• 1999

A control structure is introduced for the purpose of rejecting periodic (or repetitive) disturbances on a tracking system. The objective of the proposed structure is to drive the output of the system to the reference input that will result in perfect following without any changing the inner configuration of the system. The structure includes an adaptation block which learns the dynamics of the periodic disturbance and forces the interferences, caused by disturbances, on the output of the system to be reduced. Since the control structure acquires the dynamics of the disturbance by on-line adaptation, it is possible to generate control signals that reject any slowly varying time-periodic disturbance provided that its amplitude is bounded. The artificial neural network is adopted as the adaptation block. The adaptation is done at an on-line process. For this , the real-time recurrent learning (RTRL) algoritnm is applied to the training of the artificial neural network.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.2
• /
• pp.21-26
• /
• 2001

An expectation-maximization (EM) based Bayesian adaptation method for the mean of noise is proposed for noise-robust speech recognition. In the algorithm, the on-line testing utterances are used for the unsupervised Bayesian adaptation and the prior distribution of the noise mean is estimated using the off-line training data. For the noisy speech modeling, the parallel model combination (PMC) method is employed. The proposed method has shown to be effective compared with the conventional PMC method for the speech recognition experiments in a car-noise condition.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.32A no.8
• /
• pp.11-18
• /
• 1995

This paper proposes a nonlinear adaptive equalizer which is based on fuzzy rules and fuzzy inference of several affine mapping for the received channel data. The proposed nolonlinear adaptive equalizers with the significantly lower computational complexity. Also it can be applied to the on-line adaptation environments owing to its fast convergence characteristics and the lower computational load. When using the decision feedback vectors, this equaalizer can be easily realized in the form of the DFE structure with out the requirement for the perfect channel knowledge as in the case of the fuzzy adaptive filter.

• The Journal of Advanced Prosthodontics
• /
• v.3 no.2
• /
• pp.69-75
• /
• 2011

This study assessed the effect of preparation design on marginal adaptation and also compared the sensitivity and specificity of clinical evaluation techniques for marginal accuracy of cast restorations to stereomicroscopy. MATERIALS AND METHODS. Three Ivorine molar teeth of different designs were prepared. (A)-A complete crown preparation with buccal shoulder and beveled finish line. (B)-A complete crown preparation with chamfer finish line. (C)-A three-quarter crown preparation with proximal boxes and beveled finish line. Twenty four castings were prepared with eight castings for each design respectively. Each casting underwent examination with an explorer, disclosing media, and a stereomicroscope. Stereomicroscopy at a value less than or equal to 30 microns was used as a gold standard to evaluate the significance of different designs on marginal adaptation. Chi-square tests of independence and Kruskal-Wallis were used to evaluate the effect of preparation design and compare the agreement between examination methods for detection of marginal gap size of greater than or equal to 30 microns (${\alpha}$=.05). Sensitivity and specificity for explorer and disclosing media as compared to stereomicroscope was calculated using statistical formula given by Park. RESULTS. The preparation design did not significantly affect overall marginal adaptation. Examination by explorer and disclosing media at $30 \;{mu}m$ revealed 39% and 10.06% sensitivity and 91% and 82% specificity respectively. CONCLUSION. Preparation designs examined in this study did not significantly affect the marginal adaptation of the castings. Commonly used clinical evaluation techniques using explorer and disclosing media appeared to be inadequate for assessment of marginal accuracy.

• Therapeutic Science for Rehabilitation
• /
• v.6 no.2
• /
• pp.37-45
• /
• 2017

Background: The presence of visuospatial impairment can make patients slow functional recovery and impede the rehabilitation process in TBI patients. Objective: The aim of this study is to investigate effects of prism adaptation treatment for functional outcomes in patients following traumatic brain injury. Methods: The subject received prism adaptation treatment for 2 weeks additionally during traditional rehabilitation for 4 weeks. The Patient has prism adaptation treatment while wearing wedge prisms that shift the external environment about $12^{\circ}$ leftward. The patient received 10 sessions, 15-20min each session. Outcome measures were visuospatial deficit(line bisection, latter cancellation), Visual and spatial perception(LOTCA-visual perception and spatial perception), motor function of upper extremity(FMA U/E; Fugl-Meyer motor assessment upper extremity, ARAT; Action research arm test), balance(BBS; Berg Balance Scale), mobility(FAC; Functional ambulation classification) and functional level(FIM; Functional independent measure). All Assessments took place on study entry and post-treatment assessments were performed at discharge from the hospital. Results: After prism adaptation, the visuospatial impairment scores improved as indicated in the line bisection(-15.2 to -6.02), latter cancellation(2 to 0) and LOTCA- spatial perception scores(7 to 9). The upper motor function improved as indicated in the scores of affected FMA U/E(21 to 40) and ARAT(4 to 22). Ambulation and balance improved as indicated in the BBS scores(25 to 38) and FAC scores(0 to 4). ADL function improved as indicated in the FIM total scores 54 to 70(motor 34 to 61, cognition 20 to 29). Conclusion: Prism adaptation did improve functional level such as motor functions and ADL abilities in TBI patient. Further research is recommended.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.127-130
• /
• 2003

This paper describes an efficient method for unsupervised speaker adaptation. This method is based on selecting a subset of speakers who are acoustically close to a test speaker, and calculating adapted model parameters according to the previously stored sufficient HMM statistics of the selected speakers' data. In this method, only a few unsupervised test speaker's data are required for the adaptation. Also, by using the sufficient HMM statistics of the selected speakers' data, a quick adaptation can be done. Compared with a pre-clustering method, the proposed method can obtain a more optimal speaker cluster because the clustering result is determined according to test speaker's data on-line. Experiment results show that the proposed method attains better improvement than MLLR from the speaker independent model. Moreover the proposed method utilizes only one unsupervised sentence utterance, while MLLR usually utilizes more than ten supervised sentence utterances.

• Proceedings of the KIEE Conference
• /
• 1999.07b
• /
• pp.519-521
• /
• 1999

An adaptive fuzzy controller is constructed from a set of fuzzy IF-THEN rules whose parameters are adjusted on-line according to some adaptation law for the purpose of controlling the plant to track a given trajectory. Adaptive fuzzy controller of this paper is designed based on the Lyapunov synthesis approach The adaptive fuzzy controller is designed through the following steps: first, construct an initial controller based on linguistic descriptions(in the form of fuzzy IF-THEN rules) about the unknown plant from human experts; then, develop an adaptation law to adjust the parameters of the fuzzy controller on-line, the adaptive fuzzy controllers are used to control the inverted pendulum to track a given trajectory.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.75.3-75
• /
• 2002

1. introduction 2. Related Work 3. Overview of the Avatar Control System 4. A Hybrid Control Method 5. Motion Conversion 6. Experimental result and Conclusion References

• The Journal of Korean Society for School & Community Health Education
• /
• v.22 no.4
• /
• pp.25-37
• /
• 2021

Objectives: Reportedly, the main influential factors on students' adaptation to their college life were social support, stress, adaptation resilience, self-esteem, and satisfaction with their major. This study tried to find the actual influence of these factors on dental hygiene students, and to find an intervention plan for improving their adaptation to college life and preventing their dropout. Methods: An online questionnaire survey had been conducted with 270 dental hygiene students from June 21 to July 2, 2021. The collected data were analyzed with the use of SPSS Program Version 22.0. Results: Firstly, students living together with their family, those satisfied with their major, and those doing a club activity related to their major scored high points in terms of the adaptation to college life. In addition, the adaptation points were high in those whose school entrance motivation was arbitrary, and in those who entered in the dental hygiene department in consideration of their aptitude. Secondly, college life stress was high in those whose entrance motivation was in other persons' will, those who entered in the department due to their school record and occupation, rather than aptitude, those who were also doing a part-time job, and those whose economic level was low. Thirdly, adaptation resilience, social support, and self-esteem were high in those who were highly satisfied with their major, those who entered in the department in consideration of aptitude, and those whose economic level was high. Fourthly, the biggest influential factor on their adaptation to college life was college life stress, followed by self-esteem, satisfaction with major, and adaptation resilience in order. Conclusion: Given all the results, it is necessary to analyze dental hygiene students' levels of stress, self-esteem, social support, and adaptation resilience from the beginning of their entrance, and to operate a school life adaptation program in line with school years. If any customized support and training are given to these students to deal with a variety of stress situations resiliently and wisely and achieve their jobs successfully, it is expected to improve their self-esteem and adaptation resilience, and thereby increase their adaptation to college life.

• Journal of Power Electronics
• /
• v.13 no.4
• /
• pp.516-527
• /
• 2013

This paper presents a new overall system for state-of-available-power (SoAP) prediction for a lithium-ion battery pack. The essential part of this method is based on an adaptive network architecture which utilizes both fuzzy model (FIS) and artificial neural network (ANN) into the framework of adaptive neuro-fuzzy inference system (ANFIS). While battery aging proceeds, the system is capable of delivering accurate power prediction not only for room temperature, but also at lower temperatures at which power prediction is most challenging. Due to design property of ANN, the network parameters are adapted on-line to the current battery states (state-of-charge (SoC), state-of-health (SoH), temperature). SoC is required as an input parameter to SoAP module and high accuracy is crucial for a reliable on-line adaptation. Therefore, a reasonable way to determine the battery state variables is proposed applying a combination of several partly different algorithms. Among other SoC boundary estimation methods, robust extended Kalman filter (REKF) for recalibration of amp hour counters was implemented. ANFIS then achieves the SoAP estimation by means of time forward voltage prognosis (TFVP) before a power pulse occurs. The trade-off between computational cost of batch-learning and accuracy during on-line adaptation was optimized resulting in a real-time system with TFVP absolute error less than 1%. The verification was performed on a software-in-the-loop test bench setup using a 53 Ah lithium-ion cell.