• 한국멀티미디어학회논문지
• /
• 제22권6호
• /
• pp.655-664
• /
• 2019

In this paper, we propose a novel way of combining multiple deep convolutional neural network (DCNN) architectures which work well for accurate video face identification by adopting a serial combination of 3D and 2D DCNNs. The proposed method first divides an input video sequence (to be recognized) into a number of sub-video sequences. The resulting sub-video sequences are used as input to the 3D DCNN so as to obtain the class-confidence scores for a given input video sequence by considering both temporal and spatial face feature characteristics of input video sequence. The class-confidence scores obtained from corresponding sub-video sequences is combined by forming our proposed class-confidence matrix. The resulting class-confidence matrix is then used as an input for learning 2D DCNN learning which is serially linked to 3D DCNN. Finally, fine-tuned, serially combined DCNN framework is applied for recognizing the identity present in a given test video sequence. To verify the effectiveness of our proposed method, extensive and comparative experiments have been conducted to evaluate our method on COX face databases with their standard face identification protocols. Experimental results showed that our method can achieve better or comparable identification rate compared to other state-of-the-art video FR methods.

• KIEAE Journal
• /
• 제15권4호
• /
• pp.105-110
• /
• 2015

Purpose: This study aimed at finding the optimal input variables of the artificial neural network-based predictive model for the optimal controls of the indoor temperature environment. By applying the optimal input variables to the predictive model, the required time for restoring the current indoor temperature during the setback period to the normal setpoint temperature can be more precisely calculated for the cooling season. The precise prediction results will support the advanced operation of the cooling system to condition the indoor temperature comfortably in a more energy-efficient manner. Method: Two major steps employing the numerical computer simulation method were conducted for developing an ANN model and finding the optimal input variables. In the first process, the initial ANN model was intuitively determined to have input neurons that seemed to have a relationship with the output neuron. The second process was conducted for finding the statistical relationship between the initial input variables and output variable. Result: Based on the statistical analysis, the optimal input variables were determined.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1989년도 하계종합학술대회 논문집
• /
• pp.531-534
• /
• 1989

In this paper, the way that input voltage and input line current as a control variable is provided as one unit is projected. Till no, have denied with three phase balanced load. But, in that case, total power factor compensation is difficult, for to control each phase at unbalanced load. Therefor, in this paper suggest of the scheme that three phase unbalanced load is controlled by each phase and input total power factor is compensated unit input factor. therefore, in this paper suggest that three phase unbalanced load is controlled and the method in compensation of unit input factor to be attended by unbalanced load. Besides, the object of control is calculating quantity for input voltage and input line current for the point at issuse make to improve of control method at unbalanced load. As a result, control system of each phase could maintain as a unit input total power factor has been state diviation error of 2% with unbalanced load.

• Structural Engineering and Mechanics
• /
• 제37권4호
• /
• pp.351-365
• /
• 2011

This study proposes an inverse estimation method for the input forces of a fixed beam structural system. The estimator includes the fuzzy Kalman Filter (FKF) technology and the fuzzy weighted recursive least square method (FWRLSM). In the estimation method, the effective estimator are accelerated and weighted by the fuzzy accelerating and weighting factors proposed based on the fuzzy logic inference system. By directly synthesizing the robust filter technology with the estimator, this study presents an efficient robust forgetting zone, which is capable of providing a reasonable trade-off between the tracking capability and the flexibility against noises. The period input of the fixed beam structure system can be effectively estimated by using this method to promote the reliability of the dynamic performance analysis. The simulation results are compared by alternating between the constant and adaptive and fuzzy weighting factors. The results demonstrate that the application of the presented method to the fixed beam structure system is successful.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1993년도 한국자동제어학술회의논문집(국제학술편); Seoul National University, Seoul; 20-22 Oct. 1993
• /
• pp.1-6
• /
• 1993

This report proposes a novel method of identification of continuous time-delay systems from sampled input-output data. By the aid of a digital pre-filter, an approximated discrete-time estimation model is first derived, in which the system parameters remain in their original form and the time delay need not be an integral multiple of th sampling period. Then an identification method combining the common linear least squares(LS) method or the instrumental variable(IV) method with the genetic algorithm(GA) is proposed. That is, the time-delay is selected by the GA, and the system parameters are estimated by the LS or IV method. Furthermore, the proposed method is extended to the case of multi-input multi-output systems where the time-delays in the individual input channels may differ each other. Simulation resutls show that our method yields consistent estimates even in the presence of high measurement noises.

• 한국지역지리학회지
• /
• 제8권4호
• /
• pp.480-491
• /
• 2002

본 연구의 목적은 정보가 계약된 조건하에서의 다지역에 대한 지역간 산업연관표를 작성하고 이에 대한 정확성을 평가하는 데 있다. 지역간 산업연관표의 작성 방법은 이미 지난 1950년대 초 Isard 및 Leontief 등에 의하여 개발된 이 후 다양한 기법들이 제시되어왔다. 이들 기법 중에서 정확성 면에서는 실제 조사를 통하여 지역간 산업연관표를 작성하는 것이 가장 바람직하지만, 이 경우 많은 시간과 경비를 부담해야만 하는 현실적 어려움이 수반된다. 따라서 은 연구에서는 정보, 특히 지역수준에서 최종수요 및 지역간 상품의 흐름에 대한 정보가 제약된 조건하에서 우리나라의 전국을 5개 지역으로, 그리고 전 산업을 13개 부문으로 구분하여 비조사방법에 의하여 지역간 산업연관표를 작성하였다. 비조사방법에 의하여 지역간 산업연관표를 작성하는 방법에도 여러 가지가 있지만, 본 인구에서는 기본적인 LQ 기법을 원용하여 이를 다지역 모형으로의 확장을 시도하였다. 끝으로 추정된 투입계수의 정확성을 평가하기 위하여, 특정 지역 투자의 지역 및 지역간 파급효과를 분석하고, 이를 기존의 실제 조사를 통한 투입계수와 비교 해 보았다.

• 설비공학논문집
• /
• 제3권2호
• /
• pp.103-113
• /
• 1991

This paper presents a method for estimating the noise source contribution of a pulse combustion burner in a multiple input system where the input sources may be coherent each other. By coherence function method, it is found that the biggest part of the noise source in the pulse combustion burner is generated by the part of the combustion chamber. This analysis is modeled as three input / single output system because the noise generating mechanism of the pulse combustion burner is very complicated. The coherence function method is proved to be useful tool for the identification of noise source. The overall levels of the radiated source pressure by coherence function method are compared with those measured and calculated by the frequency response function approach. The experimental results have shown a good agreement with the results calculated by the coherence function method when the input sources are coherent strongly each other. The estimation of shield effect by FRF method indicates that significant reduction can be achieved in sound radiation if only transmission path generated by the part of combustion chamber is acoustically shield.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2008년도 추계학술대회A
• /
• pp.779-784
• /
• 2008

This paper presents a the method for estimating the noise source contribution on the road noise of the vehicle in a multiple input system where the input sources may be coherent with each other. By coherence function method, it is found that the biggest part of the noise source in the road noise is generated by structural vibration on the mechanical-acoustic transfer functions of vehicles. This analysis is modeled as four input/single output system because the noise is generated with four wheels that mechanism of the road noise is very complicated. The coherence function method is proved to be useful tool for identifying of noise source. The overall levels of the interior noise be coherence function method are compared with those measured and calculated by the frequency response function approach using mechanical excitation test. The experimental results have shown a good agreement with the results calculated by the coherence function method when the input sources are coherent strongly each other. The estimation of the road noise indicates that significant coherent can be achieved in the vehicle interior noise.

• 한국소음진동공학회논문집
• /
• 제18권11호
• /
• pp.1206-1212
• /
• 2008

This paper presents a the method for estimating the noise source contribution on the road noise of the vehicle in a multiple input system where the input sources may be coherent with each other. By coherence function method, it is found that the biggest part of the noise source in the road noise is generated by structural vibration on the mechanical-acoustic transfer functions of vehicles. This analysis is modeled as four input/single output system because the noise is generated with four wheels that mechanism of the road noise is very complicated. The coherence function method is proved to be useful tool for identifying of noise source. The overall levels of the interior noise be coherence function method are compared with those measured and calculated by the frequency response function approach using mechanical excitation test. The experimental results have shown a good agreement with the results calculated by the coherence function method when the input sources are coherent strongly each other. The estimation of the road noise indicates that significant coherent can be achieved in the vehicle interior noise.

• 한국통신학회논문지
• /
• 제19권11호
• /
• pp.2255-2263
• /
• 1994

프로토콜 적합성 시험은 시험 대상인 구현물을 하나의 black box로서 고려하여 input에 대한 output 과 결과 상태를 확인하는 일련의 과정으로 구성된다. 특히 결과 상태를 확인하는 방법에 따라 Unique Input/Output(UIO) Sequence, Distinguishing Sequence(DS) 및 Characterization Set(CS) 등으로 구분할 수 있다. 또한 UIO sequence가 존재하지 않는 상태에 대한 시험을 위해서라고 Partial UIO Set(CS) 등으로 구분 할 수 이따. 또한 PUIO sequence가 존재하지 않는 상태에 대한 시험을 위해서도 Partial UIO sequence 방법이 제안되었다. 본 논문에서는 이러한 PUIO sequence를 제시하고 이를 이용한 개선된 PUIO sequence 제안하였으며, 그 적용 결과로서 PUIO sequence의 수가 56%정도 줄어드는 것을 확인할 수 있었다.