• Journal of Electrical Engineering and Technology
• /
• 제12권1호
• /
• pp.363-372
• /
• 2017

This paper presents a novel face recognition algorithm based on the deep convolution neural network and key point detection jointed local binary pattern methodology to enhance the accuracy of face recognition. We firstly propose the modified face key feature point location detection method to enhance the traditional localization algorithm to better pre-process the original face images. We put forward the grey information and the color information with combination of a composite model of local information. Then, we optimize the multi-layer network structure deep learning algorithm using the Fisher criterion as reference to adjust the network structure more accurately. Furthermore, we modify the local binary pattern texture description operator and combine it with the neural network to overcome drawbacks that deep neural network could not learn to face image and the local characteristics. Simulation results demonstrate that the proposed algorithm obtains stronger robustness and feasibility compared with the other state-of-the-art algorithms. The proposed algorithm also provides the novel paradigm for the application of deep learning in the field of face recognition which sets the milestone for further research.

• 한국문헌정보학회지
• /
• 제46권2호
• /
• pp.175-197
• /
• 2012

The art museums in South Korea are mostly small-scaled institutions with small amount of art works. Thus, internationally accepted metadata standards such as CDWA and VRA Core may not be efficient to manage their collections. Because of these distinct local characteristics, there is a need to create a set of metadata elements that can be used for the art museum community in the country. This research aims to propose a set of metadata elements customized to fit into the context of small-scaled art museums in South Korea. The construction of the element set was not from scratch but on the basis of existing standards such as CDWA, VRA Core, and Dublin Core. By identifying core elements that are indispensable in describing art works and collecting opinions of experts in art museums, the proposed set of metadata elements is expected to support the operation and management of art works and satisfy the localized needs of the art museum community.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2007년도 추계학술대회논문집
• /
• pp.754-759
• /
• 2007

This study exploits the data discriminating capability of silhouette statistics, which combines wavelet-based vertical energy threshold technique for the purpose of extracting damage-sensitive features and clustering signals of the same class. This threshold technique allows to first obtain a suitable subset of the extracted or modified features of our data, i.e., good predictor sets should contain features that are strongly correlated to the characteristics of the data without considering the classification method used, although each of these features should be as uncorrelated with each other as possible. The silhouette statistics have been used to assess the quality of clustering by measuring how well an object is assigned to its corresponding cluster. We use this concept for the discriminant power function used in this paper. The simulation results of damage detection in a truss structure show that the approach proposed in this study can be successfully applied for locating both open- and breathing-type damage even in the presence of a considerable amount of process and measurement noise.

• 한국정보보호학회:학술대회논문집
• /
• 한국정보보호학회 2006년도 하계학술대회
• /
• pp.251-257
• /
• 2006

The performance of face recognition methods using subspace projection is directly related to the characteristics of their basis images, especially in the cases of local distortion or partial occlusion. In order for a subspace projection method to be robust to local distortion and partial occlusion, the basis images generated by the method should exhibit a part-based local representation. We propose an effective part-based local representation method named locally salient ICA (LS-ICA) method for face recognition that is robust to local distortion and partial occlusion. The LS-ICA method only employs locally salient information from important facial parts in order to maximize the benefit of applying the idea of 'recognition by parts.' It creates part-based local basis images by imposing additional localization constraint in the process of computing ICA architecture I basis images. We have contrasted the LS-ICA method with other part-based representations such as LNMF (Localized Non-negative Matrix Factorization)and LFA (Local Feature Analysis). Experimental results show that the LS-ICA method performs better than PCA, ICA architecture I, ICA architecture II, LFA, and LNMF methods, especially in the cases of partial occlusions and local distortion

• 한국시스템다이내믹스연구
• /
• 제7권2호
• /
• pp.57-80
• /
• 2006

Nuclear technology made a great contribution to the national economy and society by localization of nuclear power plant design, and by stabilization of electricity price, etc. It is very important to conduct the retrospective analysis for the nuclear technology contribution to the national economy and society, but it is more important to conduct prospective analysis for the nuclear technology contribution. The term "technology value" is often used in the prospective analysis to value the result of technology development. There are various definitions of technology value, but generally it means the increment of future revenue or the reduction of future cost by technology development. These technology valuation methods are widely used in various fields (information technology or energy technology, etc). The main objective of this research is to develop valuation methodology that represents unique characteristics of nuclear power technology. The valuation methodology that incorporates market share changes of generation technologies was developed. The technology valuation model which consists of five modules (electricity demand forecast module, technology development module, market share module, electricity generation module, total cost module) to incorporate market share changes of generation technologies was developed. The nuclear power technology value assessed by this technology valuation model was 3 times more than the value assessed by the conventional method. So it was confirmed that it is very important to incorporates market share changes of generation technologies. The valuation results of nuclear power technology in this study can be used as policy data for ensuring the benefits of nuclear power R&D (Research and Development) investment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권11호
• /
• pp.5527-5545
• /
• 2019

Through-wall ultra-wide band (UWB) radar has been considered as one of the preferred and non-contact technologies for the targets detection owing to the better time resolution and stronger penetration. The high time resolution is a result of a larger of bandwidth of the employed UWB pulses from the radar system, which is a useful tool to separate multiple targets in complex environment. The article emphasised on human subject localization and detection. Human subject usually can be detected via extracting the weak respiratory signals of human subjects remotely. Meanwhile, the range between the detection object and radar is also acquired from the 2D range-frequency matrix. However, it is a challenging task to extract human respiratory signals owing to the low signal to clutter ratio. To improve the feasibility of human respiratory signals detection, a new method is developed via analysing the standard deviation based kurtosis of the collected pulses, which are modulated by human respiratory movements in slow time. The range between radar and the detection target is estimated using joint time-frequency analysis (JTFA) of the analysed characteristics, which provides a novel preliminary signature for life detection. The breathing rates are obtained using the proposed accumulation method in time and frequency domain, respectively. The proposed method is validated and proved numerically and experimentally.

• Computers and Concrete
• /
• 제7권4호
• /
• pp.365-386
• /
• 2010

This paper presents the physical formulation of a 1D material model suitable for seismic applications. It is written within the framework of thermodynamics with internal variables that is, especially, very efficient for the phenomenological representation of material behaviors at macroscale: those of the representative elementary volume. The model can reproduce the main characteristics observed for concrete, that is nonsymetric loading rate-dependent (viscoelasticity) behavior with appearance of permanent deformations and local hysteresis (continuum plasticity), stiffness degradation (continuum damage), cracking due to displacement localization (discrete plasticity or damage). The parameters have a clear physical meaning and can thus be easily identified. Although this point is not detailed in the paper, this material model is developed to be implemented in a finite element computer program. Therefore, for the benefit of the robustness of the numerical implementation, (i) linear state equations (no local iteration required) are defined whenever possible and (ii) the conditions in which the presented model can enter the generalized standard materials class - whose elements benefit from good global and local stability properties - are clearly established. To illustrate the capabilities of this model - among them for Earthquake Engineering applications - results of some numerical applications are presented.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1992년도 춘계학술대회
• /
• pp.213-217
• /
• 1992

An inductively coupled magnetical signal (pulse wave, 0.7 to 60Hz, eighteen volts peak to Peak) that was applied non-invasively on the skin surface overlying the approximate site(measure position). In the group with unipolar pulse signal currents produced smaller than in the group with bipolar pulse signal. The signal was transmitted to the active coil, including a time-varying magnetic field: this in turn induced a the-varying electrical field in the field in the bone. It is very important to determine system parameters due to treatment time(healing) and the simplicity. This paper investigation was designed to compare the relative effects of pulsed unipolar currents with the effects of an identical pulsed bipolar currents. Since Inductive coupling is non-invasive and involves portable equipment, it is easy to apply and requires precise localization, it has distinct advantages and field characteristics along the bone for each different signal.

• 한국소음진동공학회논문집
• /
• 제18권8호
• /
• pp.823-831
• /
• 2008

Since it needs the light computational load and small database, sound source localization method using time delay of arrival(TDOA method) is applied at many research fields such as a robot auditory system, teleconferencing and so on. Researches for time delay estimation, which is the most important thing of TDOA method, had been studied broadly. However studies about factors for time delay estimation are insufficient, especially in case of real environment application. In 1997, Brandstein and Silverman announced that performance of time delay estimation deteriorates as reverberant time of room increases. Even though reverberant time of room is same, performance of estimation is different as the specific part of signals. In order to know that reason, we studied and analyzed the factors for time delay estimation using speech signal and room impulse response. In result, we can know that performance of time delay estimation is changed by different R/D ratio and signal characteristics in spite of same reverberant time. Also, we define the performance index(PI) to show a similar tendency to R/D ratio, and propose the method to improve the performance of time delay estimation with PI.

• 대한전자공학회논문지SP
• /
• 제41권6호
• /
• pp.221-229
• /
• 2004

본 논문에서는 기존의 영상 압축 표준과 호환되며 영상 또는 비디오의 특성에 따라 워터마크를 삽입하는 새로운 방법을 제안한다. 워터마크를 최대의 강도로 삽입하기 위해 블록내의 DCT 계수의 계층구조를 이용한 가중치 함수를 정의한다. 이 구조를 이용하면 DCT 블록 내에서 공간-주파수 지역화 특성을 이용할 수 있다. 워터마크의 검출 단계에서는 통계적 분석을 통한 주어진 오검출 확률에 대한 최적의 사후 임계값을 계산하는 방법을 제시한다. 실험결과는 제안된 방법이 여러 가지 신호처리 공격과 널리 사용되는 JPEG, MPEG 부호화에 강인함을 보여준다.