• International Journal of Computer Science & Network Security
• /
• v.21 no.9
• /
• pp.203-211
• /
• 2021

Image tampering detection and localization have become an active area of research in the field of digital image forensics in recent times. This is due to the widespread of malicious image tampering. This study presents a new method for image tampering detection and localization that combines the advantages of dilated convolution, residual network, and UNET Architecture. Using the UNET architecture as a backbone, we built the proposed network from two kinds of residual units, one for the encoder path and the other for the decoder path. The residual units help to speed up the training process and facilitate information propagation between the lower layers and the higher layers which are often difficult to train. To capture global image tampering artifacts and reduce the computational burden of the proposed method, we enlarge the receptive field size of the convolutional kernels by adopting dilated convolutions in the residual units used in building the proposed network. In contrast to existing deep learning methods, having a large number of layers, many network parameters, and often difficult to train, the proposed method can achieve excellent performance with a fewer number of parameters and less computational cost. To test the performance of the proposed method, we evaluate its performance in the context of four benchmark image forensics datasets. Experimental results show that the proposed method outperforms existing methods and could be potentially used to enhance image tampering detection and localization.

• Journal of Computational Design and Engineering
• /
• v.3 no.3
• /
• pp.226-249
• /
• 2016

The symbiotic organisms search (SOS) algorithm is an effective metaheuristic developed in 2014, which mimics the symbiotic relationship among the living beings, such as mutualism, commensalism, and parasitism, to survive in the ecosystem. In this study, three modified versions of the SOS algorithm are proposed by introducing adaptive benefit factors in the basic SOS algorithm to improve its efficiency. The basic SOS algorithm only considers benefit factors, whereas the proposed variants of the SOS algorithm, consider effective combinations of adaptive benefit factors and benefit factors to study their competence to lay down a good balance between exploration and exploitation of the search space. The proposed algorithms are tested to suit its applications to the engineering structures subjected to dynamic excitation, which may lead to undesirable vibrations. Structure optimization problems become more challenging if the shape and size variables are taken into account along with the frequency. To check the feasibility and effectiveness of the proposed algorithms, six different planar and space trusses are subjected to experimental analysis. The results obtained using the proposed methods are compared with those obtained using other optimization methods well established in the literature. The results reveal that the adaptive SOS algorithm is more reliable and efficient than the basic SOS algorithm and other state-of-the-art algorithms.

• Proceedings of the KIPE Conference
• /
• 2019.07a
• /
• pp.77-79
• /
• 2019

Islanding detection is one of the most important issues for the distributed generation (DG) systems connected to the power grid. The conventional passive islanding detection methods inherently have a non-detection zone (NDZ), and active islanding detection methods may deteriorate the power quality of a power system. This paper proposes a novel hybrid islanding detection method based on Digital Lock-In Amplifier with no NDZ by monitoring the harmonics present in the grid. Proposed method detects islanding by passively monitoring the grid voltage harmonics and verify it by injecting small perturbation for only three-line cycles. Unlike FFT for the harmonic extraction, DLA HC have lower computational burden, moreover, DLA can monitor harmonic in real time, whereas, FFT has certain propagation delay. The simulation results are presented to highlight the effectiveness of the proposed technique. In order to prove the performance of the proposed method it is compared with several passive islanding detection methods. The experimental results confirm that the proposed method exhibits outstanding performance as compared to the conventional methods.

• Journal of Computational Design and Engineering
• /
• v.3 no.2
• /
• pp.91-101
• /
• 2016

The automated part quality inspection poses many challenges to the engineers, especially when the part features to be inspected become complicated. A large quantity of part inspection at a faster rate should be relied upon computerized, automated inspection methods, which requires advanced quality control approaches. In this context, this work uses innovative methods in remote part tracking and quality control with the aid of the modern equipment and application of support vector machine (SVM) learning approach to predict the outcome of the quality control process. The classifier equations are built on the data obtained from the experiments and analyzed with different kernel functions. From the analysis, detailed outcome is presented for six different cases. The results indicate the robustness of support vector classification for the experimental data with two output classes.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2004.04a
• /
• pp.463-469
• /
• 2004

This paper discusses 2D lattice models of beams for simulating the fracture of brittle materials. A simulation of an experiment on a connote beam subjected to bending, in which two overlapping cracks occur, is used to study the effect of individual beam characteristics and different arrangements of the beams in the overall lattice. It was found that my regular orientation of the beams influences the resulting crack patterns. Methods to implement a wide range of poisson's ratios are also developed, the use of the lattice to study arbitrary micro-structures is outlined The crack pattern that n obtained with lattice m in good agreement with the experimental results. Also, numerical simulations of the tests were performed by means of a lattice model, and non-integer dimensions were measured on the predicted lattice damage patterns.

• Journal of computational fluids engineering
• /
• v.15 no.4
• /
• pp.99-108
• /
• 2010

Fractional Step Methods(FSM) are popular in simulation of unsteady incompressible flow. In this study, we demonstrate that FSM, combined with a Volume-Of-Fluid method, can be further applied to simulation of multiphase flow. The interface between the fluids is constructed by the effective least squares volume-of-fluid interface reconstruction algorithm and advected by the velocity using the operator split advection algorithm. To verify our numerical methodology, our results are compared with other authors' numerical and experimental results for the benchmark problems, revealing excellent agreement. The present FSM sheds light on accurate simulation of turbulent multiphase flow which is found in many engineering applications.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.23 no.6
• /
• pp.627-633
• /
• 2010

This paper presents a method for identifying the parameter set of inelastic constitutive equations, which is based on an Evolutionary Algorithm. The advantage of the method is that appropriate parameters can be identified even when the measured data are subject to considerable errors and the model equations are inaccurate. The design of experiments suited for the parameter identification of a material model by Chaboche under the uniaxial loading and stationary temperature conditions was first considered. Then the parameter set of the model was identified by the proposed method from a set of experimental data. In comparison to those by other methods, the resultant stress-strain curves by the proposed method correlated better to the actual material behaviors.

• Computational Structural Engineering
• /
• v.10 no.4
• /
• pp.267-280
• /
• 1997

This paper deals with the development of simplified methods to predict the creep deformation of reinforced concrete beams. The layer approach based on a degenerate kernel of compliance function in form of Dirichlet series is mentioned and a simplified analytical method derived from the equilibrium equations and compatibility conditions is proposed to overcome the sophisticated calculation procedures in the classical creep analysis. Correlation studies between analytical and experimental results and design codes are conducted with the objective to establish the validity of the proposed methods. Besides, various parameter studies are conducted with the objective to identify the effects of cracking, steel ratio and sectional shape in the creep deformation and the obtained results are discussed.

• The KSFM Journal of Fluid Machinery
• /
• v.6 no.4 s.21
• /
• pp.50-57
• /
• 2003

The hydraulic performance analysis of a turbopump with an inducer for a liquid rocket engine was performed using three-dimensional Navier-Stokes equations. A simple mixing-plane method and a full interaction method were used to simulate inducer/impeller interaction. Two methods show almost similar results due to the weak interaction between the inducer and impeller since the inducer outlet blade angle is lather small. But, when the inducer and the impeller are closely spaced near the shroud region, flow angles at the impeller inlet show different results between two methods. Thus, the full interaction method predicts about $2\%$ higher pump performance than the mixing-plane method. And the effects of prewhirl at the impeller inlet are also investigated. As the inlet flow angle is increased, the head rise and the efficiency are decreased. The computational results are compared with measured ones. The computational results at the design point show good agreements with experimental data, however under-predicts the head rise at high mass flow rates compared to the experiment.

• Journal of the Optical Society of Korea
• /
• v.18 no.4
• /
• pp.388-394
• /
• 2014

In this paper, we propose a three-dimensional (3D) image correlator by use of computational integral imaging reconstruction based on the modified convolution property of periodic functions (CPPF) for recognition of partially occluded objects. In the proposed correlator, elemental images of the reference and target objects are picked up by a lenslet array, and subsequently are transformed to a sub-image array which contains different perspectives according to the viewing direction. The modified version of the CPPF is applied to the sub-images. This enables us to produce the plane sub-image arrays without the magnification and superimposition processes used in the conventional methods. With the modified CPPF and the sub-image arrays, we reconstruct the reference and target plane sub-image arrays according to the reconstruction plane. 3D object recognition is performed through cross-correlations between the reference and the target plane sub-image arrays. To show the feasibility of the proposed method, some preliminary experiments on the target objects are carried out and the results are presented. Experimental results reveal that the use of plane sub-image arrays enables us to improve the correlation performance, compared to the conventional method using the computational integral imaging reconstruction algorithm.