IPM-Model: AI and metaheuristic-enabled face recognition using image partial matching for multimedia forensics investigation with genetic algorithm

The rapid enhancement in the development of information technology has driven the development of human facial image recognition. Recently, facial recognition has been successfully applied in several distinct domains with the help of computing and information technology. This kind of application plays a significant role in the process of digital forensics investigation, recognizing the patterns of a human face based on the partial matching of images that would be in 24-bit color image format, including the spacing of the eyes, the bridging of the nose, the contour of the lips, ears, and chin. In this paper, we have proposed and implemented an image recognition model based on principal component analysis, genetic algorithms, and neural networks, in which PCA reduces the dimension of the benchmark dataset, while genetic algorithms and neural nets optimize the searching patterns of image matching and provide highly efficient output with a minimal amount of time. Through the experiment results on the human facial images dataset of the Georgia Institute of Technology, the overall match showed that the proposed model can achieve the recognition of human face images with an accuracy rate of 93.7%. Moreover, this model helps to examine, analyze, and detect individuals by partial matching with reidentification in the procedure of forensics investigation. The experimental result shows the robustness of the proposed model in terms of efficiency compared to other state-of-the-art methods.

     

Electromagnetohydrodynamic nanofluid flow past a porous Riga plate containing gyrotactic microorganism

Neural Computing and Applications - Here we have numerically examined the effects of EMHD in flow of nanofluid past a porous Riga surface with gyrotactic microorganism and nanoparticles. Modeling...     

Diffraction of waves by an oscillating source and an oscillating half plane

In this paper we have studied the problem of diffraction of cylindrical acoustic waves (emanating from a harmonic time dependent source) by an oscillating half plane. An analytical solution, using spatial and temporal Fourier transforms, complex Fourier series, the Wiener-Hopf technique and the method of steepest descent, is constructed. Some graphs showing the effects of various parameters on the diffracted field are also presented.     

Monte Carlo–based channel estimation and performance evaluation for UWOC links under geometric losses

Underwater wireless optical communication has been studied and proposed as a potential technology for various underwater applications including monitoring and surveillance using wireless sensor networks. In this context, we present a statistical model using an exhaustive Monte Carlo approach for an underwater wireless optical communication link between sensor nodes in a data mulling environment. This work provides insights into the science of photon transport underwater, its utilization in a communication system, evaluation, and optimization of underwater communication. We characterize the temporal channel behavior taking into account multiple scattering of photons involving the constraints of detector aperture diameter, field‐of‐view (FOV), and link distance for an aligned point‐to‐point link. We analyze the designed model in terms of total received power and bit error rate for clear ocean waters. Our simulation results show that the detector aperture and FOV has an impact towards a successful communication in the distance from 5 to 20 m. In addition, results show that the FOV is an affecting factor only in the presence of larger aperture sizes of the detector.     

Optimization of the Biotechnological Process for Hide Unhairing in Substitution of Toxic Sulfides

Screening and isolation of a new Bacillus subtilis strain and production of its proteases for leather unhairing are described. B. subtilis strain BLBc 11 was isolated from the aerobic sludge of a tannery. Optimization of enzyme production by this bacterium was carried out using the Plackett‐Burman and central composite design. Unhairing and inter‐fibrillary removal capabilities were evaluated by scanning electron microscopy and determination of proteoglycans and glycosaminoglycans. Crude enzymatic extracts of B. subtilis BLBc 11 cultures were applied for the unhairing process of hides with excellent results, suggesting that this safe enzymatic preparation can replace the toxic chemicals commonly used in this process.     

Integrated Sized-Based Buffer Management Policy for Resource-Constrained Delay Tolerant Network

Wireless Personal Communications - Delay tolerant network is a type of network where the end-to-end path is not available from source to destination due to the node mobility, dynamic topology and...     

The Role of Capillarity in the VAPEX Process

Abstract

The vapor extraction (VAPEX) process warrants the oil industry attention because of its applicability to recover viscous oil in the cases when steam assisted gravity drainage fails due to the presence of bottom water aquifer, low heat conductivity, thin pay zone, and excessive heat losses to the adjacent formations. Dilution of heavy oil and thus lowering the viscosity, density, interfacial tension, and capillary pressure is regarded as the basic mechanism of the VAPEX process. Although researchers have studied many influencing factors on oil recovery in VAPEX, the effect of capillary pressure has never been studied or understood completely. The objective of this study is to explore the effects of capillary pressure in the VAPEX process by combining experimental results with simulation studies. Extensive experimental studies are conducted in a rectangular transparent visual cell. Grain size distribution and model height are kept constant, while the viscosity of the targeted oil is varied. Capillary pressure and relative permeability data are obtained from flooding experiments to utilize in the simulator. Analysis of results reveals that capillary pressure acts in favor of the VAPEX process by shaping up the vapor chamber, reducing free gas production and also increasing drainage rate by increasing the effective contact area for molecular diffusion.     

Message Drop Control Buffer Management Policy for DTN Routing Protocols

In delay tolerant network interruptions will occur continuously because there is no end-to-end path exists for the longer period of time from source to destination. In this context, delays can be immensely large due to its environment contrails e.g. wildlife tracking, sensor network, deep space and ocean networks. Furthermore, larger replication of messages put into the network is to increase delivery probability. Due to this high buffer occupancy storage space and replication result in a huge overhead on the network. Consequently, well-ordered intelligent message control buffer drop policies are necessary to operate on buffer that allows control on messages drop when the node buffers are near to overflow. In this paper, we propose an efficient buffer management policy which is called message drop control source relay (MDC-SR) for delay tolerant routing protocols. We also illustrate that conventional buffer management policy like Drop oldest, LIFO and MOFO be ineffective to consider all appropriate information in this framework. The proposed MDC-SR buffer policy controls the message drop while at the same time maximizes the delivery probability and buffer time average and reduces the message relay, drop and hop count in the reasonable amount. Using simulations support on an imitation mobility models Shortest Path Map Based Movement and Map Route Movements, we show that our drop buffer management MDC-SR with random message sizes performs better as compared to existing MOFO, LIFO and DOA.