• Journal of Information Processing Systems
• /
• 제14권5호
• /
• pp.1114-1135
• /
• 2018

A multiple classification system based on a new boosting technique has been approached utilizing different biometric traits, that is, color face, iris and eye along with fingerprints of right and left hands, handwriting, palm-print, gait (silhouettes) and wrist-vein for person authentication. The images of different biometric traits were taken from different standard databases such as FEI, UTIRIS, CASIA, IAM and CIE. This system is comprised of three different super-classifiers to individually perform person identification. The individual classifiers corresponding to each super-classifier in their turn identify different biometric features and their conclusions are integrated together in their respective super-classifiers. The decisions from individual super-classifiers are integrated together through a mega-super-classifier to perform the final conclusion using programming based boosting. The mega-super-classifier system using different super-classifiers in a compact form is more reliable than single classifier or even single super-classifier system. The system has been evaluated with accuracy, precision, recall and F-score metrics through holdout method and confusion matrix for each of the single classifiers, super-classifiers and finally the mega-super-classifier. The different performance evaluations are appreciable. Also the learning and the recognition time is fairly reasonable. Thereby making the system is efficient and effective.

• Journal of Information Processing Systems
• /
• 제16권5호
• /
• pp.1145-1157
• /
• 2020

A convolution neural networks (CNNs) has demonstrated outstanding performance compared to other algorithms in the field of face recognition. Regarding the over-fitting problem of CNN, researchers have proposed a residual network to ease the training for recognition accuracy improvement. In this study, a novel face recognition model based on game theory for call-over in the classroom was proposed. In the proposed scheme, an image with multiple faces was used as input, and the residual network identified each face with a confidence score to form a list of student identities. Face tracking of the same identity or low confidence were determined to be the optimisation objective, with the game participants set formed from the student identity list. Game theory optimises the authentication strategy according to the confidence value and identity set to improve recognition accuracy. We observed that there exists an optimal mapping relation between face and identity to avoid multiple faces associated with one identity in the proposed scheme and that the proposed game-based scheme can reduce the error rate, as compared to the existing schemes with deeper neural network.

• 대한조선학회논문집
• /
• 제51권5호
• /
• pp.396-408
• /
• 2014

In this study, uncertainty analysis based on ITTC(International Towing Tank Conference) Recommended Procedures is carried out in the towing-tank experiment for motion responses and added resistance. The experiment was conducted for KVLCC2 model in head sea condition. The heave, pitch and added resistance were measured in different wave conditions, and the measurement was repeated up to maximum 15 times in each wave condition in order to observe the uncertainty of measured data. The uncertainty analysis was carried out by adopting the ISO-GUM(International Organization for Standardization, Guide to the Expression of Uncertainty in Measurements) method recommended by ITTC. This paper describes the details about the analysis method, uncertainty and the measured uncertainty for each source. The uncertainty analysis results are summarized as a tabular form. To validate the accuracy of the present measurement, the experimental results are compared with the results of numerical computation and other experiment. From the present uncertainty analysis, the main sources of uncertainty are identified, which can be very useful to improve the accuracy for added resistance experiment.

• 한국전기전자재료학회논문지
• /
• 제27권2호
• /
• pp.91-96
• /
• 2014

Aspheric lenses used in the thermal imaging are typically fabricated using expensive single-crystal materials (Ge and ZnS, etc.) by the costly single point diamond turning (SPDT) process. As a potential solution to reduce cost, compression molding method using chalcogenide glass has been attracted to fabricate IR optic. Thermal deformation of a molded lens should be compensated to fabricate chalcogenide aspheric lens with form accuracy of the submicron-order. The thermal deformation phenomenon of molded lens was analyzed ant then compensation using mold iteration process is followed to fabricate the high accuracy optic. Consequently, it is obvious that compensation of thermal deformation is critical and useful enough to be adopted to fabricate the lens by molding method.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제4권11호
• /
• pp.361-368
• /
• 2015

대공화기사격통제장치에서 유효사거리는 정지한 표적에 대해 충분한 파괴력을 가질 수 있도록 탄속이 음속 이상을 유지하는 거리로 정의되고 있다. 접근하는 표적은 탄과 표적 간 상대속도가 증가하므로 실질적인 교전 사거리는 위의 유효사거리보다 더욱 연장된다. 그러나 기존에 제시된 TOF 계산식은 유효사거리 내에서만 정확하고 유효사거리를 벗어나면 정확하지 못하다. 본 논문은 교전사거리를 보장할 수 있도록 유효사거리 내에서와 유효사거리 밖에서도 충분한 정확도를 가진 실시간 처리가 가능한 탄자비행시간 계산 기법을 제시한다. 시뮬레이션을 통해 30미리 대공 탄에 대한 본 논문의 유용성을 보인다.

• 대한토목학회논문집
• /
• 제7권2호
• /
• pp.89-98
• /
• 1987

X-Ray 사진측량(寫眞測量)은 인체에 대한 해부학적(解剖學的) 또는 생리학적(生理學的) 자료를 사진형태로 기록하여 해석하는 방법이다. 본 연구는 X-Ray를 이용하여 모델이 되는 피사체(被寫體)에 변형(變形)을 준 각 경우와, 인체 부분을 모델로 할 경우의 3 차원 좌표에 대한 정확도를 분석하므로써, X-Ray 사진(寫眞)에 의한 3 차원 위치결정의 정확도(正確度)를 향상시키고, 실용성을 높이는데 그 목적을 두고 있다. X-Ray를 이용하여 인체부분의 실제 피사체(被寫體)를 관측(觀測)한 결과, 높은 정확도(正確度)로 실제응용을 할 수 있었으며, X-Ray 사진을 이용하여 피사체(被寫體) 모든 면에 대한 삼차원(三次元) 좌표(座標)를 결정 할 수 있었다.

• Earthquakes and Structures
• /
• 제7권1호
• /
• pp.39-55
• /
• 2014

A modified procedure is presented for assessing the seismic response of elastic non-proportionate multistory buildings. This procedure retains the simplicity of the methodology presented by the author in earlier papers, but it presents higher accuracy in buildings composed by very dissimilar types of bents. As a result, not only frequencies and peak values of base resultant forces are determined with higher accuracy, but also the location of the first mode center of rigidity (m1-CR). The closeness of m1-CR with the axis passing through the centers of floor masses (mass axis) implies a reduced rotational response and it is demonstrated that in elastic systemsa practically translational response is obtained when this point lies on the mass axis.Besides, when common types of buildings are detailed as planar structures under a code load, this response is maintained in the inelastic phase of their response as a result of the almost concurrent yielding of all the resisting bents. This property of m1-CR can be used by the practicing engineer as a guideline to form a structural configuration which will sustain minimum rotational response, simply by allocating the resisting elements in such a way that this point lies close to the mass axis. Inelastic multistory building structures, detailed as above, may be regarded as torsionally balanced multistory systems and this is demonstrated in eight story buildings, composed by dissimilar bents, under the ground motions of Kobe 1995 (component KJM000) and Friuli 1976 (component Tolmezzo E-W).

• Structural Engineering and Mechanics
• /
• 제42권4호
• /
• pp.471-488
• /
• 2012

An efficient one dimensional finite element model has been presented for the dynamic analysis of composite laminated beams, using the efficient layerwise zigzag theory. To meet the convergence requirements for the weak integral formulation, cubic Hermite interpolation is used for the transverse displacement ($w_0$), and linear interpolation is used for the axial displacement ($u_0$) and shear rotation (${\psi}_0$). Each node of an element has four degrees of freedom. The expressions of variationally consistent inertia, stiffness matrices and the load vector are derived in closed form using exact integration. The formulation is validated by comparing the results with the 2D-FE results for composite symmetric and sandwich beams with various end conditions. The employed finite element model is free of shear locking. The present zigzag finite element results for natural frequencies, mode shapes of cantilever and clamped-clamped beams are obtained with a one-dimensional finite element codes developed in MATLAB. These 1D-FE results for cantilever and clamped beams are compared with the 2D-FE results obtained using ABAQUS to show the accuracy of the developed MATLAB code, for zigzag theory for these boundary conditions. This comparison establishes the accuracy of zigzag finite element analysis for dynamic response under given boundary conditions.

• Steel and Composite Structures
• /
• 제13권2호
• /
• pp.139-155
• /
• 2012

Serviceability rather than strength is the most critical design requirement for vibration-vulnerable floor constructions. Annoying vibrations due to normal walking activity have been observed more frequently on long-span lightweight floor systems in office and commercial retail buildings, raising the need for the development of floor vibration design procedures. This paper highlights some limitations of one of the most commonly used guidelines AISC/CISC DG11, and proposes improvements to this method. Design charts and approximate closed form formulas to estimate the walking response are developed in which various factors relating to the dynamic characteristics of both the floor and the excitation are considered. The accuracy of the proposed formulas and other proposals found in the literature is examined. The proposed modifications would be significant, especially with long-span floors where vibration levels may be underestimated by the current design procedure. The application of the proposed prediction method is illustrated by worked examples that reveal a good agreement with results obtained from finite element analyses and experiments. The presented work would enhance the accuracy and maintain the simplicity and convenience of the design guideline.

• 대한기계학회논문집
• /
• 제16권8호
• /
• pp.1429-1437
• /
• 1992

본 연구에서는 이완형 물성방정식을 바탕으로 하며 프와송 비가 일정하다는 가정을 하지 않는다. 또한 점탄성 지배방정식에 변분원리를 적용하고 유도되어진 식 에 유한요소해법을 사용하여 시스템 기본해석을 위한 연립방정식을 유도한다. 이와 함께 점탄성 물성함수의 유도 및 응력계산을 위한 공식화 과정도 설명한다. 제시된 방법론의 타당성 및 정확성을 보이기 위해서 평면응력 및 평면변형 문제의 변위 및 응력을 수치해석하여 이론해와 비교 검토하며, 아울러 시간증분의 변화와 Gauss poi- nts수가 수치정확도에 끼치는 영향을 조사한다.