• 대한임상전기생리학회지
• /
• 제5권1호
• /
• pp.59-71
• /
• 2007

The purpose of this study was to study for the change of neural adaptation by muscle contraction force when neuromuscular electrical stimulation(NMES) was applied. Sixteen subjects(8 male, 8 female) without neuromuscular disease volunteered to participate in the study. All subjects were divided into two subgroups: control(no electrical stimulation) group, NMES(50% maximal voluntary isometric contraction) group. NMES training program was performed in the calf muscle over three times a week for 12 weeks. Before and after experiment MVIC of ankle plantar flexor was measured by use of dynamometer. H-reflex and V-wave in tibial nerve were measured. The following results were obtained; MVIC and V/Mmax ratio were significantly increased in the electrical stimulation groups. However, H/Mmax ratio was not changed. It was closely relationship between MVIC and V/Mmax ratio. In this study, the effect of neural adaptation of central neural adaptation was found in this study. Accordingly, NMES means not only a change of muscle fiber and skeletal muscle volume but also a effect of neural adaptation of central neural drive. Also, it was found that there was closely relationship between MVIC and neural adaptation of central neural drive by NMES.

• 제어로봇시스템학회논문지
• /
• 제5권8호
• /
• 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.

• 센서학회지
• /
• 제30권5호
• /
• pp.290-294
• /
• 2021

Experts have designed popular and successful model architectures, which, however, were not the optimal option for different scenarios. Despite the remarkable performances achieved by deep neural networks, manually designed networks for classification tasks are the backbone of object detection. One major challenge is the ImageNet pre-training of the search space representation; moreover, the searched network incurs huge computational cost. Therefore, to overcome the obstacle of the pre-training process, we introduce a network adaptation technique using a pre-trained backbone model tested on ImageNet. The adaptation method can efficiently adapt the manually designed network on ImageNet to the new object-detection task. Neural architecture search (NAS) is adopted to adapt the architecture of the network. The adaptation is conducted on the MobileNetV2 network. The proposed NAS is tested using SSDLite detector. The results demonstrate increased performance compared to existing network architecture in terms of search cost, total number of adder arithmetics (Madds), and mean Average Precision(mAP). The total computational cost of the proposed NAS is much less than that of the State Of The Art (SOTA) NAS method.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 1996년도 10월 학술대회지
• /
• pp.464-467
• /
• 1996

This paper aims to exploit inter/intra-speaker phoneme sub-class variations as criteria for adaptation in a phoneme recognition system based on a novel neural network architecture. Using a subcluster neural network design based on the One-Class-in-One-Network (OCON) feed forward subnets, similar to those proposed by Kung (2) and Jou (1), joined by a common front-end layer. the idea is to adapt only the neurons within the common front-end layer of the network. Consequently resulting in an adaptation which can be concentrated primarily on the speakers vocal characteristics. Since the adaptation occurs in an area common to all classes, convergence on a single class will improve the recognition of the remaining classes in the network. Results show that adaptation towards a phoneme, in the vowel sub-class, for speakers MDABO and MWBTO Improve the recognition of remaining vowel sub-class phonemes from the same speaker

• ETRI Journal
• /
• 제41권1호
• /
• pp.109-116
• /
• 2019

This paper explores new techniques that are based on a hidden-layer linear transformation for fast speaker adaptation used in deep neural networks (DNNs). Conventional methods using affine transformations are ineffective because they require a relatively large number of parameters to perform. Meanwhile, methods that employ singular-value decomposition (SVD) are utilized because they are effective at reducing adaptive parameters. However, a matrix decomposition is computationally expensive when using online services. We propose the use of an extended diagonal linear transformation method to minimize adaptation parameters without SVD to increase the performance level for tasks that require smaller degrees of adaptation. In Korean large vocabulary continuous speech recognition (LVCSR) tasks, the proposed method shows significant improvements with error-reduction rates of 8.4% and 17.1% in five and 50 conversational sentence adaptations, respectively. Compared with the adaptation methods using SVD, there is an increased recognition performance with fewer parameters.

• Journal of information and communication convergence engineering
• /
• 제21권2호
• /
• pp.139-144
• /
• 2023

Engineers prefer deep neural networks (DNNs) for solving computer vision problems. However, DNNs pose two major problems. First, neural networks require large amounts of well-labeled data for training. Second, the covariate shift problem is common in computer vision problems. Domain adaptation has been proposed to mitigate this problem. Recent work on adversarial-learning-based unsupervised domain adaptation (UDA) has explained transferability and enabled the model to learn robust features. Despite this advantage, current methods do not guarantee the distinguishability of the latent space unless they consider class-aware information of the target domain. Furthermore, source and target examples alone cannot efficiently extract domain-invariant features from the encoded spaces. To alleviate the problems of existing UDA methods, we propose the mixup regularization in adversarial discriminative domain adaptation (ADDA) method. We validated the effectiveness and generality of the proposed method by performing experiments under three adaptation scenarios: MNIST to USPS, SVHN to MNIST, and MNIST to MNIST-M.

• 대한원격탐사학회지
• /
• 제38권2호
• /
• pp.199-213
• /
• 2022

비지도 도메인 적응은 연단위 작물 분류를 위해 매년 반복적으로 양질의 훈련자료를 수집해야 하는 비실용적인 문제를 해결할 수 있다. 이 연구에서는 작물 분류를 위한 딥러닝 기반 비지도 도메인 적응 모델의 적용성을 평가하였다. 우리나라 마늘, 양파 주산지인 합천군과 창녕군을 대상으로 무인기 영상을 이용한 작물 분류 실험을 통해 deep adaptation network (DAN), deep reconstruction-classification network, domain adversarial neural network (DANN)의 3개의 비지도 도메인 적응 모델을 정량적으로 비교하였다. 비지도 도메인 적응 모델의 분류 성능을 평가하기 위해 소스 베이스라인 및 대상 베이스라인 모델로 convolutional neural networks (CNNs)을 추가로 적용하였다. 3개의 비지도 도메인 적응 모델은 소스 베이스라인 CNN보다 우수한 성능을 보였으나, 소스 도메인 영상과 대상 도메인 영상의 자료 분포 간 불일치 정도에 따라 서로 다른 분류 성능을 보였다. DAN의 분류 성능은 두 도메인 영상 간 불일치가 작을 때 다른 두 모델에 비해 분류 성능이 높은 반면에 DANN은 두 도메인 영상 간 불일치가 클 때 가장 우수한 분류 성능을 보였다. 따라서 신뢰할 수 있는 분류 결과를 생성하기 위해 두 도메인 영상의 분포가 일치하는 정도를 고려해서 최상의 비지도 도메인 적응 모델을 선택해야 한다.

• 한국음향학회지
• /
• 제19권1호
• /
• pp.11-15
• /
• 2000

RM 음성 Corpus를 이용한 화자 적응 연속 음성 인식을 수행하였다. RM Corpus의 훈련용 데이터를 이용해서 기준화자에 대한 HMM 학습을 실시하고 평가용 데이터를 이용하여 화자 적응 인식에 대한 평가를 실시하였다. 화자 적응을 위해서는 훈련용 데이터의 일부가 사용되었다. DTW를 이용하여 인식 대상화자의 데이터를 기준화자의 데이터와 시간적으로 일치시키고 오차 역전파 신경회로망을 사용하여 인식 대상화자의 스펙트럼이 기준화자의 스펙트럼 특성을 지니도록 변환시켰다. 최적의 화자 적응이 이루어지도록 하기 위해 신경회로망의 여러 요소들을 변화시키면서 실험을 실시하고 그 결과를 제시하였다. 학습을 거쳐 적절한 가중치를 지닌 신경회로망을 이용하여 기준화자에 적응시킨 결과 단어 인식율이 최대 2.1배, 단어 정인식율이 최대 4.7배 증가하였다.

• 한국음향학회지
• /
• 제38권1호
• /
• pp.47-50
• /
• 2019

본 논문에서는 잡음 환경에서 효과적인 음성 인식을 위하여 DNN(Deep Neural Network) 기반의 잡음 오염 함수 예측을 이용한 음향 모델 적응 기법을 제안한다. 깨끗한 음성과 잡음 정보를 입력으로 하고 오염된 음성에 대한 특징 벡터를 출력으로 하는 DNN을 학습하여 비선형 관계를 갖는 잡음 오염 함수를 예측한다. 예측된 잡음 오염 함수를 음향모델의 평균 벡터에 적용하여 잡음 환경에 적응된 음향 모델을 생성한다. Aurora 2.0 데이터를 이용한 음성 인식 성능 평가에서 본 논문에서 제안한 모델 적응 기법이 기존의 전처리, 모델 적응 기법에 비해 일치, 불일치 잡음 환경에서 모두 평균적으로 우수한 성능을 나타낸다. 특히 불일치 잡음 환경에서 평균 오류율이 15.87 %의 상대 향상률을 나타낸다.

• 제어로봇시스템학회논문지
• /
• 제14권12호
• /
• pp.1226-1231
• /
• 2008

A design of attitude controller for a tiltrotor is presented augmenting L1 adaptive control, neural networks, and feedback linearization. The neural networks compensate for the modeling error caused by the lack of knowledge of tiltrotor dynamics while the L1 adaptive control allows high adaptation gains in adaptation laws thereby, satisfying tracking performance requirement. The efficacy of this control methodology is illustrated in high-fidelity nonlinear simulation of a tiltrotor by flying the tiltrotor in different flight modes from where the L1 adaptive controller with neural networks is originally designed for.