• 응용통계연구
• /
• 제28권2호
• /
• pp.269-279
• /
• 2015

본 논문에서는 임의효과에 대한 추론 문제가 다루어졌으며 이 추론에서 신뢰분포를 사용하는 것이 제안되었다. 신뢰분포를 이용한 방법은 표본의 크기가 작아도 임의절편들이 있는 로지스틱 회귀분석에서 좋은 결과를 보여주었으며, 자료분석을 통해서도 각 개체가 가지는 임의효과들에 대한 세밀한 분석이 가능함을 확인하였다.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2005년도 추계 학술대회 발표논문집
• /
• pp.51-54
• /
• 2005

This paper analyzes the vocal tract area estimation algorithm used as a part of a speech analysis program to help deaf children correct their pronunciations by comparing their vocal tract shape with normal children's. Assuming that a vocal tract is a concatenation of cylinder tubes with a different cross section, we compute the relative vocal tract area of each tube using the reflection coefficients obtained from linear predictive coding. Then, obtain the absolute vocal tract area by computing the height of lip opening with a formula modified for children's speech. Using the speech data for five Korean vowels (/a/, /e/, /i/, /o/, and /u/), we investigate the effects of the sampling frequency, frame size, and model order. We compare vocal tract shapes obtained from deaf and normal children's speech.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제15권3호
• /
• pp.145-152
• /
• 2015

We consider an online selective-sample learning problem for sequence classification, where the goal is to learn a predictive model using a stream of data samples whose class labels can be selectively queried by the algorithm. Given that there is a limit to the total number of queries permitted, the key issue is choosing the most informative and salient samples for their class labels to be queried. Recently, several aggressive selective-sample algorithms have been proposed under a linear model for static (non-sequential) binary classification. We extend the idea to hidden Markov models for multi-class sequence classification by introducing reasonable measures for the novelty and prediction confidence of the incoming sample with respect to the current model, on which the query decision is based. For several sequence classification datasets/tasks in online learning setups, we demonstrate the effectiveness of the proposed approach.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2009년도 춘계학술대회
• /
• pp.711-714
• /
• 2009

잡음환경 하의 회화에서 잡음량을 줄이고 신호처리 시스템의 성능을 향상시키기 위해서는 잡음량에 따라서 적응적으로 처리되는 신호처리 시스템이 필요하다. 또한 잡음이 중첩된 음성으로부터 잡음을 제거하기 위해서는 잡음의 크기에 따라서 음성 처리 시스템의 파라미터를 변경하는 것이 양호한 음질의 음성을 재생하는데 바람직하다. 따라서 본 논문에서는 음성 속에 포함되는 잡음량을 인식하는 방법으로 선형예측계수를 구하여 시간지연신경회로망(Time-delay neural network: TDNN)의 입력으로 사용하여 학습시키는 잡음량을 인식하는 방법을 제안한다. 본 잡음량 인식은 다양한 배경잡음에 의하여 열화된 3종류의 음성이 TDNN에 의하여 학습되어진다. 본 실험에서는 Aurora2 데이터베이스를 사용하여 여러 잡음에 대하여 양호한 인식결과를 확인할 수 있었다.

• Computers and Concrete
• /
• 제21권6호
• /
• pp.649-659
• /
• 2018

Adaptive neuro-fuzzy inference systems (ANFIS) can be efficient in modelling non-linear, complex and ambiguous behavior of cement-based materials undergoing combined damage factors of different forms (physical and chemical). The current work investigates the use of ANFIS to model the behavior (time of failure (TF)) of a wide range of concrete mixtures made with different types of cement (ordinary and portland limestone cement (PLC)) without or with supplementary cementitious materials (SCMs: fly ash and nanosilica) under various exposure regimes with the most widely used chloride-based de-icing salts (individual and combined). The results show that predictions of the ANFIS model were rational and accurate, with marginal errors not exceeding 3%. In addition, sensitivity analyses of physical penetrability (magnitude of intruding chloride) of concrete, amount of aluminate and interground limestone in cement and content of portlandite in the binder showed that the predictive trends of the model had good agreement with experimental results. Thus, this model may be reliably used to project the deterioration of customized concrete mixtures exposed to such aggressive conditions.

• ETRI Journal
• /
• 제43권1호
• /
• pp.82-94
• /
• 2021

In this work, six voiced/unvoiced speech classifiers based on the autocorrelation function (ACF), average magnitude difference function (AMDF), cepstrum, weighted ACF (WACF), zero crossing rate and energy of the signal (ZCR-E), and neural networks (NNs) have been simulated and implemented in real time using the TMS320C6713 DSP starter kit. These speech classifiers have been integrated into a linear-predictive-coding-based speech analysis-synthesis system and their performance has been compared in terms of the percentage of the voiced/unvoiced classification accuracy, speech quality, and computation time. The results of the percentage of the voiced/unvoiced classification accuracy and speech quality show that the NN-based speech classifier performs better than the ACF-, AMDF-, cepstrum-, WACF- and ZCR-E-based speech classifiers for both clean and noisy environments. The computation time results show that the AMDF-based speech classifier is computationally simple, and thus its computation time is less than that of other speech classifiers, while that of the NN-based speech classifier is greater compared with other classifiers.

• Current Optics and Photonics
• /
• 제5권6호
• /
• pp.641-651
• /
• 2021

To handle the servo delay in a real-time adaptive optics system, a linear subspace system identification algorithm was employed to model the system, and the accuracy of the system identification was verified by numerical calculation. Experimental verification was conducted in a real test bed system. Through analysis and comparison of the experimental results, the convergence can be achieved only 200 times with prediction and 300 times without prediction. After the wavefront peak-to-valley value converges, its mean values are 0.27, 4.27, and 10.14 ㎛ when the communication distances are 1.2, 4.5, and 10.2 km, respectively. The prediction algorithm can effectively improve the convergence speed of the peak-to-valley value and improve the free-space optical communication performance.

• 대한전자공학회논문지
• /
• 제23권4호
• /
• pp.429-438
• /
• 1986

In this paper we have designed and implemented a real-time, full-duplex SBC (sub-band coding) codec at 16kbps using a high speed digital signal processor, NEC 7720. The SBC codec employs a QMF(quadrature mirror filter) filter bank based on the tree structures of two-band analysis-synthesis pairs to partition speech signal into 4 octabe bands. Computer simulation has been done to investigate the effect of fixed-point computation of the NEC 7720. Three different performance measures, the conventional signal-to-noise ratio, the informal listening test, and an LPC(linear predictive coding)distance measure, have been used in this simulation. The necessary parameters have been optimized through the simulation. The developed hardware and software have been tested in real-time operation using a hardware emulator.

• Structural Engineering and Mechanics
• /
• 제88권6호
• /
• pp.535-549
• /
• 2023

Deep extreme learning machine (DELM) and multi-verse optimization algorithms (MVO) are hybridized for designing an optimal and adaptive control framework for uncertain buildings. In this approach, first, a robust model predictive control (RMPC) scheme is developed to handle the problem uncertainty. The optimality and adaptivity of the proposed controller are provided by the optimal determination of the tunning weights of the linear programming (LP) cost function for clustered external loads using the MVO. The final control policy is achieved by collecting the clustered data and training them by DELM. The efficiency of the introduced control scheme is demonstrated by the numerical simulation of a ten-story benchmark building subjected to earthquake excitations. The results represent the capability of the proposed framework compared to robust MPC (RMPC), conventional MPC (CMPC), and conventional DELM algorithms in structural motion control.

• Structural Engineering and Mechanics
• /
• 제89권4호
• /
• pp.399-409
• /
• 2024

Assessment of existing concrete bridges is a challenge for owners. It has greater economic impact when compared to designing new bridges. When using conventional linear analyses, judgment of the engineer is required to understand the behavior of redundant structures after the first element in the structural system reaches its ultimate capacity. The alternative is to use a predictive tool such as advanced nonlinear finite element analyses (ANFEA) to assess the overall structural behavior. This paper proposes a new reliability framework for the assessment of existing bridge structures using ANFEA. A general framework defined in previous works, accounting for material uncertainties and concrete model performance, is adapted to the context of the assessment of existing bridges. A "shifted" reliability problem is defined under the assumption of quasi-deterministic dead load effects. The overall exercise is viewed as a progressive pushover analysis up to structural failure, where the actual safety index is compared at each event to a target reliability index.