• 대한기계학회논문집
• /
• 제15권2호
• /
• pp.497-506
• /
• 1991

In this paper, a new construction for training simulator of R/C helicopter based on two types of servo controller is proposed. Two modified algorithms (algorithm I and II) for servo controller design are presented. Algorithm I is developed by adopting Davison's method in the case that the expressions for the homogeneous differential equations of reference input and disturbance are different types, and algorithm II is done by considering error weighting function for the servo controller of algorithm I . The linear fractional transformation method is incorporated in both design methods in order to assign the closed loop poles of the servo system in a specified region. The helicopter simulator is composed by the gimbals with two freedom of rolling and pitching. The reliability and validity for the design methods of the proposed servo controller are investigated through the practical experiment for the simulator by using 16bits micro-computer with A/D and D/A converters. It can be observered from the experimental results that the proposed servo controller is applicable to practical plants since the simulator is robust for the arbitrary disturbance and it follows to the given reference input without significant steady state error.

• ETRI Journal
• /
• 제17권1호
• /
• pp.11-22
• /
• 1995

This paper proposes a modified error function to improve the error back-propagation (EBP) algorithm for multi-Layer perceptrons (MLPs) which suffers from slow learning speed. It can also suppress over-specialization for training patterns that occurs in an algorithm based on a cross-entropy cost function which markedly reduces learning time. In the similar way as the cross-entropy function, our new function accelerates the learning speed of the EBP algorithm by allowing the output node of the MLP to generate a strong error signal when the output node is far from the desired value. Moreover, it prevents the overspecialization of learning for training patterns by letting the output node, whose value is close to the desired value, generate a weak error signal. In a simulation study to classify handwritten digits in the CEDAR [1] database, the proposed method attained 100% correct classification for the training patterns after only 50 sweeps of learning, while the original EBP attained only 98.8% after 500 sweeps. Also, our method shows mean-squared error of 0.627 for the test patterns, which is superior to the error 0.667 in the cross-entropy method. These results demonstrate that our new method excels others in learning speed as well as in generalization.

• Journal of Communications and Networks
• /
• 제7권3호
• /
• pp.243-247
• /
• 2005

We propose an efficient block least-mean-square (BLMS) adaptive algorithm, in conjunction with error control coding, for direct-sequence code division multiple access (DS-CDMA) systems. The proposed adaptive receiver incorporates decision feedback detection and channel encoding in order to improve the performance of the standard LMS algorithm in convolutionally coded systems. The BLMS algorithm involves two modes of operation: (i) The training mode where an uncoded training sequence is used for initial filter tap-weights adaptation, and (ii) the decision-directed where the filter weights are adapted, using the BLMS algorithm, after decoding/encoding operation. It is shown that the proposed adaptive receiver structure is able to compensate for the signal-to­noise ratio (SNR) loss incurred due to the switching from uncoded training mode to coded decision-directed mode. Our results show that by using the proposed adaptive receiver (with decision feed­back block adaptation) one can achieve a much better performance than both the coded LMS with no decision feedback employed. The convergence behavior of the proposed BLMS receiver is simulated and compared to the standard LMS with and without channel coding. We also examine the steady-state bit-error rate (BER) performance of the proposed adaptive BLMS and standard LMS, both with convolutional coding, where we show that the former is more superior than the latter especially at large SNRs ($SNR\;\geq\;9\;dB$).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권1호
• /
• pp.368-391
• /
• 2018

Face recognition (FR) with a single sample per person (SSPP) is common in real-world face recognition applications. In this scenario, it is hard to predict intra-class variations of query samples by gallery samples due to the lack of sufficient training samples. Inspired by the fact that similar faces have similar intra-class variations, we propose a virtual sample generating algorithm called k nearest neighbors based virtual sample generating (kNNVSG) to enrich intra-class variation information for training samples. Furthermore, in order to use the intra-class variation information of the virtual samples generated by kNNVSG algorithm, we propose image set based multimanifold discriminant learning (ISMMDL) algorithm. For ISMMDL algorithm, it learns a projection matrix for each manifold modeled by the local patches of the images of each class, which aims to minimize the margins of intra-manifold and maximize the margins of inter-manifold simultaneously in low-dimensional feature space. Finally, by comprehensively using kNNVSG and ISMMDL algorithms, we propose k nearest neighbor virtual image set based multimanifold discriminant learning (kNNMMDL) approach for single sample face recognition (SSFR) tasks. Experimental results on AR, Multi-PIE and LFW face datasets demonstrate that our approach has promising abilities for SSFR with expression, illumination and disguise variations.

• 한국농공학회지
• /
• 제36권2호
• /
• pp.88-95
• /
• 1994

This paper is to evaluate the applicability of neural networks to the estimation of evapotranspiration. Two neural networks were developed to forecast daily evapotranspiration of the rice crop with back-propagation and counter-propagation algorithm. The neural network trained by back-propagation algorithm with delta learning rule is a three-layer network with input, hidden, and output layers. The other network with counter-propagation algorithm is a four-layer network with input, normalizing, competitive, and output layers. Training neural networks was conducted using daily actual evapotranspiration of rice crop and daily climatic data such as mean temperature, sunshine hours, solar radiation, relative humidity, and pan evaporation. During the training, neural network parameters were calibrated. The trained networks were applied to a set of field data not used in the training. The created response of the back-propagation network was in good agreement with desired values and showed better performances than the counter-propagation network did. Evaluating the neural network performance indicates that the back-propagation neural network may be applied to the estimation of evapotranspiration of the rice crop. This study does not provide with a conclusive statement as to the ability of a neural network to evapotranspiration estimating. More detailed study is required for better understanding and evaluating the behavior of neural networks.

• International journal of advanced smart convergence
• /
• 제11권4호
• /
• pp.57-67
• /
• 2022

The demand for personal training (PT), through which high exercise effects can be achieved within short-term, has recently increased. PT can achieve an exercise amount improvement effect, only if accurate postures are maintained upon performing PT, and exercise with inaccurate postures can cause injuries. However, research is insufficient on exercise amount comparisons and judging exercise accuracy on PT. This study proposes an exercise accuracy measurement algorithm and compares differences in exercise amounts according to exercise postures through experiments using a respiratory gas analyzer. The exercise accuracy measurement algorithm acquires Euler anglesfrom major body parts operated upon exercise through a motion device, based on which the joint angles are calculated. By comparing the calculated joint angles with each reference angle in each exercise step, the status of exercise accuracy is judged. The calculated results of exercise accuracy on squats, lunges, and push-ups showed 0.02% difference in comparison with actually measured results through a goniometer. As a result of the exercise amount comparison experiment according to accurate posture through a respiratory gas analyzer, the exercise amount was higher by 45.19% on average in accurate postures. Through this, it was confirmed that maintaining accurate postures contributes to exercise amount improvement.

• 응용통계연구
• /
• 제26권5호
• /
• pp.847-856
• /
• 2013

본 연구에서는 Liu 등의 학습 알고리즘과 Wu와 Zhang의 초기 가중값의 범위 설정, 그리고 Gunaseeli와 Karthikeyan의 초기 가중값에 관한 연구 결과를 이용하여 일반화 네트워크를 구할 수 있는 개선된 학습을 제안하고, 최적화된 신경망 학습률들을 이용하여 개선된 학습 과정의 학습효율등을 비교해 본다. 제시된 알고리즘을 이용한 학습에서 학습 초기에는 가장 단순한 학습 패턴과 은닉층으로부터 학습을 시작한다. 신경망 학습과정 중에 지역 최소값에 수렴되는 경우에는 가중값 범위 조정을 통하여 지역 최소값 문제를 해결하고, 지역 최소값으로부터 탈출이 용이하지 않으면 은닉노드를 점차적으로 하나씩 추가하면서 학습한다. 각 단계에서 새롭게 추가된 노드에 대한 초기 가중값의 선택은 이차계획법을 이용한 최적 처리절차를 이용한다. 최적 처리절차는 은닉층의 노드가 추가된 후의 새로운 네트워크에서 학습회수를 단순히 증가시키지 않아도 주어진 학습 허용오차를 만족시킬 수 있다. 본 연구에서 적용한 개선된 알고리즘을 이용하면서 초기 가중값들에 관한 기존 연구들을 적용하면 신경망 학습시의 수렴 정도를 높여주고 최소한의 단순 구조를 갖는 일반화 네트워크로 추정할 수 있게 된다. 이러한 학습률들을 변화시키는 모의실험을 통하여 기존의 연구 결과와의 학습 효율을 비교하고 향후 연구 방향을 제시하고자 한다.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2004년도 춘계 종합학술대회 논문집
• /
• pp.56-62
• /
• 2004

시간/경제적 문제 혹은 수집 대상의 제한으로 충분한 수의 학습패턴을 모을 수 없는 경우에 인간의 두뇌를 모방한 교사학습 및 비교사학습 모델을 이용하여 새로운 학습패턴을 생성한 후 이를 이용하여 학습한 경우 성능이 향상됨을 보였다.

• Journal of Electrical Engineering and Technology
• /
• 제7권1호
• /
• pp.109-114
• /
• 2012

In this paper, we utilize training strategy of hidden Markov model (HMM) to use in versatile issues such as classification of time-series sequential data such as electric transient disturbance problem in power system. For this, an automatic means of optimizing HMMs would be highly desirable, but it raises important issues: model interpretation and complexity control. With this in mind, we explore the possibility of using genetic algorithm (GA) and harmony search (HS) algorithm for optimizing the HMM. GA is flexible to allow incorporating other methods, such as Baum-Welch, within their cycle. Furthermore, operators that alter the structure of HMMs can be designed to simple structures. HS algorithm with parameter-setting free technique is proper for optimizing the parameters of HMM. HS algorithm is flexible so as to allow the elimination of requiring tedious parameter assigning efforts. In this paper, a sequential data analysis simulation is illustrated, and the optimized-HMMs are evaluated. The optimized HMM was capable of classifying a sequential data set for testing compared with the normal HMM.

• Journal of Power Electronics
• /
• 제17권4호
• /
• pp.1014-1026
• /
• 2017

The traditional fault diagnosis method for photovoltaic (PV) inverters has a difficult time meeting the requirements of the current complex systems. Its main weakness lies in the study of nonlinear systems. In addition, its diagnosis time is long and its accuracy is low. To solve these problems, a hidden Markov model (HMM) is used that has unique advantages in terms of its training model and its recognition for diagnosing faults. However, the initial value of the HMM has a great influence on the model, and it is possible to achieve a local minimum in the training process. Therefore, a genetic algorithm is used to optimize the initial value and to achieve global optimization. In this paper, the HMM is combined with a genetic algorithm (GHMM) for PV inverter fault diagnosis. First Matlab is used to implement the genetic algorithm and to determine the optimal HMM initial value. Then a Baum-Welch algorithm is used for iterative training. Finally, a Viterbi algorithm is used for fault identification. Experimental results show that the correct PV inverter fault recognition rate by the HMM is about 10% higher than that of traditional methods. Using the GHMM, the correct recognition rate is further increased by approximately 13%, and the diagnosis time is greatly reduced. Therefore, the GHMM is faster and more accurate in diagnosing PV inverter faults.