• International journal of advanced smart convergence
• /
• v.9 no.3
• /
• pp.207-214
• /
• 2020

Currently, the operation of unmanned aerial vehicle (UAV) is regulated to be able to fly only within the visible range, but in recent years, the needs for operation in the invisible area, in the urban area and at night have increased. In order to operate UAVs in the invisible area, at night, and in the urban area, a flight path for UAVs must be prepared like those operated by manned aircraft, and for this, it is necessary to establish an unmanned aircraft system traffic management (UTM). In order to establish the UTM, information on the minimum separation distance to prevent collisions with UAVs and buildings is required, and accordingly, information on the navigation performance of UAVs is required. In order to analyze the navigation performance of an UAV, total system error (TSE), which is the difference between the planned flight path and the actual location of the UAV, is required. If the collected data are insufficient and classification according to integrity, independence, and direction is not performed, accurate navigation performance is not derived. In this paper, propose a navigation performance analysis method of UAV that is derived TSE using flight data and modeled with normal distribution, analyze performance.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.5
• /
• pp.400-409
• /
• 2004

In this paper. a voice personality transformation method is proposed. which makes one person's voice sound like another person's voice. To transform the voice personality. vocal tract transfer function is used as a transformation parameter. Comparing with previous methods. the proposed method makes transformed speech closer to target speaker's voice in both subjective and objective points of view. Conversion between vocal tract transfer functions is implemented by classification of entire vector space followed by linear transformation for each cluster. LPC cepstrum is used as a feature parameter. A joint classification and transformation method is proposed, where optimum clusters and transformation matrices are simultaneously estimated in the sense of a minimum mean square error criterion. To evaluate the performance of the proposed method. transformation rules are generated from 150 sentences uttered by three male and on female speakers. These rules are then applied to another 150 sentences uttered by the same speakers. and objective evaluation and subjective listening tests are performed.

• The Korean Journal of Applied Statistics
• /
• v.10 no.1
• /
• pp.177-187
• /
• 1997

This article considers the power performance of the tests in unbalanced two way mixed linear models with one fixed factor. The generalized least squares (GLS) F statistic testing no differences among the effects of the levels of the fixed factor is estimated using Henderson's method III, minimum norm quadratic unbiased estimator (MINQUE) with prior guess 1, maximum likelihood (ML) and resticted maximum likelihood (REML). We investigate the power performance of these test statistics. It can be shown, through simulation, that the GLS F statistics using four estimators produce similar type I error rates and power performance.

• MALSORI
• /
• no.57
• /
• pp.165-174
• /
• 2006

In this paper we use a training algorithm, MCE (Minimum Classification Error), to improve the performance of a text-independent speaker identification system. The MCE training scheme takes account of possible competing speaker hypotheses and tries to reduce the probability of incorrect hypotheses. Experiments performed on a small set speaker identification task show that the discriminant training method using MCE can reduce identification errors by up to 54% over a baseline system trained using Bayesian adaptation to derive GMM (Gaussian Mixture Models) speaker models from a UBM (Universal Background Model).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.3
• /
• pp.443-449
• /
• 2001

This paper is simulation research to improve speech recognition rates under the noisy environment. We examines recognition ratio based on frequency-weighted HMM together with spectral subtraction. As results, frequency-weighted HMM with scaling coefficients is trained as a minimum error classification criterion, and is presents a higher recognition rates in noisy condition than a conventional method. Furthermore, spectral subtraction method gives 11 to 28% improvements for this frequency-weighted HMM in low SNR, and gives recognition rates of 81.7% at 6dB SNR of noisy speech.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.397-398
• /
• 2007

본 논문에서는 환경변화에 대해 강인하게 동작하는 음성인식 시스템을 위해 잡음적응 훈련과 변별학습 방식을 결합한 형태의 환경적응 방식을 제안한다. 다중환경 훈련과 잡음제거방식을 결합한 형태인 잡음적응 훈련 방식은 음성인식을 위한 MCE (Minimum Classification Error)의 목적과는 거리가 있고, 음성인식 시스템이 사용되는 모든 환경을 반영하는 것은 현실적으로 어렵다는 점에서 한계가 있다. 이에 잡음적응 훈련방식으로 훈련된 기본 음향모델을 목적환경에서 수집한 소량의 데이터를 이용한 변별학습을 통해 환경적응 모델로 변환함으로써 이러한 단점을 보완할 수 있는 잡음 적응 변별학습을 이용한 훈련방식을 제안한다.

• ETRI Journal
• /
• v.28 no.1
• /
• pp.111-114
• /
• 2006

An alternative human interface enabling people with severe motor disabilities to control an assistive system is presented. Since this interface relies on the biosignals originating from the contraction of muscles on the face during particular movements, even individuals with a paralyzed limb can use it with ease. For real-world application, a dedicated hardware module employing a general-purpose digital signal processor was implemented and its validity tested on an electrically powered wheelchair. Furthermore, an additional attempt to reduce error rates to a minimum for stable operation was also made based on the entropy information inherent in the signals during the classification phase. In the experiments, most of the five participating subjects could control the target system at their own will, and thus it is found that the proposed interface can be considered a potential alternative for the interaction of the severely disabled with electronic systems.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.33 no.11
• /
• pp.1225-1232
• /
• 2009

This study suggests a structural design process for the upper control arm installed at a vehicle. Static strength and durability are the most important responses in the structural design of a control arm. This study considers the static strength in the optimization process. The inertia relief method for FE analysis is utilized to simulate the static loading conditions. According to the classification of structural optimization, the structural design of a control arm is included in the category of shape optimization. In this study, the metamodel technique using the kriging method is adopted to obtain the minimum weight satisfying the strength constraint. Then, the final design is suggested by considering the durability criteria. The durability assessment is obtained by the index of fatigue durability called the SWT (Smith-Watson-Topper) index. The final optimum shape has been proposed by trial and error method.

• Speech Sciences
• /
• v.11 no.4
• /
• pp.43-52
• /
• 2004

Model parameters in HMM based speech recognition systems are normally estimated using Maximum Likelihood Estimation(MLE). The MLE method is based mainly on the principle of statistical data fitting in terms of increasing the HMM likelihood. The optimality of this training criterion is conditioned on the availability of infinite amount of training data and the correct choice of model. However, in practice, neither of these conditions is satisfied. In this paper, we propose a training algorithm, MCE(Minimum Classification Error), to improve the performance of a speech recognizer detecting mispronunciation of a foreign language. During the conventional MLE(Maximum Likelihood Estimation) training, the model parameters are adjusted to increase the likelihood of the word strings corresponding to the training utterances without taking account of the probability of other possible word strings. In contrast to MLE, the MCE training scheme takes account of possible competing word hypotheses and tries to reduce the probability of incorrect hypotheses. The discriminant training method using MCE shows better recognition results than the MLE method does.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.1
• /
• pp.46-51
• /
• 2004

his paper presents a novel design technique for the TS fuzzy classifier via linear matrix inequalities(LMI). To design the TS fuzzy classifier built by the TS fuzzy model, the consequent parameters are determined to maximize the classifier's performance. Differ from the conventional fuzzy classifier design techniques, convex optimization technique is used to resolve the determination problem. Consequent parameter identification problems are first reformulated to the convex optimization problem. The convex optimization problem is then efficiently solved by converting linear matrix inequality problems. The TS fuzzy classifier has the optimal consequent parameter via the proposed design procedure in sense of the minimum classification error. Simulations are given to evaluate the proposed fuzzy classifier; Iris data classification and Wisconsin Breast Cancer Database data classification. Finally, simulation results show the utility of the integrated linear matrix inequalities approach to design of the TS fuzzy classifier.