• Journal of Hydrospace Technology
• /
• 제2권2호
• /
• pp.24-35
• /
• 1996

This paper describes parameter identification techniques formulated for the estimation of maneuvering coefficients of a submerged body. The first part of this paper is concerned with the identifiability of the system parameters. The relationship between a stochastic linear time-invariant system and the equivalent dynamic system is investigated. The second is concerned with the development of the numerically stable identification technique. Two identification techniques are tested; one is the ma7mum likelihood (ML) methods using the Holder & Mead simplex search method and using the modified Newton-Raphson method, and the other is the modified extended Kalman filter (MEKF) method with a square-root algorithm, which can improve the numerical accuracy of the extended Kalman filter. As a results, it is said that the equations of motion for a submerged body have higher probability to generate simultaneous drift phenomenon compared to general state equations and only the ML method using the Holder & Mead simplex search method and the MEKF method with a square-root algorithm gives acceptable results.

• 복합신소재구조학회 논문집
• /
• 제3권3호
• /
• pp.38-46
• /
• 2012

The method based on various mathematical characteristic equations for identifying tensile forces in the cable structure system are used as response data to reflect the properties of the dynamic sensitivity. The vibration tests have been conducted with respect to levels of applied weight for the sagged cable. In this study, a set of natural frequencies are extracted from the measured dynamic data. Next, existing characteristic equation methods based these extracted natural frequencies are applied to identify tensil forces of the sagged cable system. Through several verification procedures, the proposed methods could be applied to a sagged cable system when the initial material data are insufficiency.

• Nuclear Engineering and Technology
• /
• 제54권12호
• /
• pp.4684-4692
• /
• 2022

Radionuclide identification is an important part of the nuclear material identification system. The development of artificial intelligence and machine learning has made nuclide identification rapid and automatic. However, many methods directly use existing deep learning models to analyze the gamma-ray spectrum, which lacks interpretability for researchers. This study proposes an explainable radionuclide identification algorithm based on the convolutional neural network and class activation mapping. This method shows the area of interest of the neural network on the gamma-ray spectrum by generating a class activation map. We analyzed the class activation map of the gamma-ray spectrum of different types, different gross counts, and different signal-to-noise ratios. The results show that the convolutional neural network attempted to learn the relationship between the input gamma-ray spectrum and the nuclide type, and could identify the nuclide based on the photoelectric peak and Compton edge. Furthermore, the results explain why the neural network could identify gamma-ray spectra with low counts and low signal-to-noise ratios. Thus, the findings improve researchers' confidence in the ability of neural networks to identify nuclides and promote the application of artificial intelligence methods in the field of nuclide identification.

• 한국음향학회지
• /
• 제25권8호
• /
• pp.375-382
• /
• 2006

본 논문에서는 음성신호에 포함된 감정정보를 자동으로 식별하는 방법과 특정 감정을 검출하는 방법에 대해 다룬다. 자동 감정식별 및 검출을 위해 장구간 (long-term) 음향 특징을 사용하였고, F-score 기반의 특징선택 기법을 적용하여 최적의 특징 파라미터들을 선정하였다. 기존의 일반적인 SVM을 확률출력 SVM으로 변환하여 감정식별 및 감정검출 시스템을 구축하였으며, 가설검정에 기반한 감정검출을 위해 세 가지의 대수 우도비 (log-likelihood) 근사법을 제안하여 그 성능을 비교하였다. SUSAS 데이터베이스를 사용한 실험 결과, F-score를 이용한 특징선택 기법에 의해 감정식별 성능이 향상되었으며, 확률출력 SVM의 유효성을 검증할 수 있었다. 감정검출의 경우, 제안한 방법에 의해 91.3%의 정확도로 화난 감정을 검출할 수 있었다.

• 대한전기학회논문지
• /
• 제43권6호
• /
• pp.877-884
• /
• 1994

In the power system state estimation, the J(x)-index test and normalized residuals ${\gamma}$S1NT have been the presence of bad measurements and identify their location. But, these methods require the complete re-estimation of system states whenever bad data is identified. This paper presents back-propagation neural network medel using autoregressive filter for identification of bad measurements. The performances of neural network method are compared with those of conventional mehtods and simulation results show the geed performance in the bad data identification based on the neural network under sample power system.

• 산업기술연구
• /
• 제31권B호
• /
• pp.37-43
• /
• 2011

In pattern analysis, dimensionality reduction and reasonable identification rule generation are very important parts. This paper performed effectively the dimensionality reduction by grouping the sensors of which the measured patterns are similar each other, where genetic algorithms were used for combination optimization. To identify the gas type, this paper constructed the hierarchically identifiable rule base with two frames by using rough set theory. The first frame is to accept measurement characteristics of each sensor and the other one is to reflect the identification patterns of each group. Thus, the proposed methods was able to accomplish effectively dimensionality reduction as well as accurate gas identification. In simulation, this paper demonstrated the effectiveness of the proposed methods by identifying five types of gases.

• 전기의세계
• /
• 제18권6호
• /
• pp.53-57
• /
• 1969

적응성 혹은 비선형 계통의 제어가 발달됨에 따라 평상시 작동상태에서 그 계통의 특성을 아는 것이 중요시 된다. 이 특성은 계통의 입력과 출력에서 얻게 되는데 이런 과정을 식별(Identification)이라고 하며 이중 특히 이미 그 계통의 "토포로지"는 알려지고 파라미터만을 구하는 문제에 대해서 사용코저 제시된 여러가지 방식을 종합하고 검토해보았다. 방식의 구분은 다소 임의적이나 편의상 사용키로한다.의상 사용키로한다.

• 한국통신학회:학술대회논문집
• /
• 한국통신학회 2004년도 추계종합학술대회 논문 초록집
• /
• pp.413-413
• /
• 2004

• 대한임베디드공학회논문지
• /
• 제16권3호
• /
• pp.89-97
• /
• 2021

Voice interface can not only make daily life more convenient through artificial intelligence speakers but also improve the working environment of the factory. This paper presents a voice-assisted work management system that supports both speech and speaker recognition. This system is able to provide machine control and authorized worker authentication by voice at the same time. We applied two speech recognition methods, Google's Speech application programming interface (API) service, and DeepSpeech speech-to-text engine. For worker identification, the SincNet architecture for speaker recognition was adopted. We implemented a prototype of the work management system that provides voice control with 26 commands and identifies 100 workers by voice. Worker identification using our model was almost perfect, and the command recognition accuracy was 97.0% in Google API after post- processing and 92.0% in our DeepSpeech model.

• 한국강구조학회 논문집
• /
• 제12권1호통권44호
• /
• pp.83-91
• /
• 2000

측정치를 이용하여 구조계를 규명하는 경우에 일반적으로 측정치를 주파수 영역으로 변환하고 이를 도식적으로 파악하는 방법이 주로 이용된다. 이러한 방법은 신뢰도가 낮고 토목구조물 특히 교량 구조물과 같이 근접한 모우드의 특성을 가지는 구조계의 규명에 불리한 것으로 알려져 있다. 본 논문에서는 시간영역에서의 데이터를 직접 이용하여 구조계의 모우드 특성을 규명하는 일련의 방법에 대한 적용성을 검토하였으며 이 때 발생할 수 있는 왜율에 대한 문제를 극복하기 위하여 최소자승법을 시간영역 규명기법에 중복하는 방법을 선택하였다. 제안된 방법의 타당성을 검토하기 위하여 현가계 모델을 이용하여 모의 해석을 수행하였다. 또한 실질적인 상황에서의 이용성을 검토하기 위하여 인위적인 잡음을 게재시켜 잡음에 대한 방범의 민감도를 검토하였다.