Convolutional Neural Network Based Intelligent Handwritten Document Recognition

This paper presents a handwritten document recognition system based on the convolutional neural network technique. In today’s world, handwritten document recognition is rapidly attaining the attention of researchers due to its promising behavior as assisting technology for visually impaired users. This technology is also helpful for the automatic data entry system. In the proposed system prepared a dataset of English language handwritten character images. The proposed system has been trained for the large set of sample data and tested on the sample images of user-defined handwritten documents. In this research, multiple experiments get very worthy recognition results. The proposed system will first perform image pre-processing stages to prepare data for training using a convolutional neural network. After this processing, the input document is segmented using line, word and character segmentation. The proposed system get the accuracy during the character segmentation up to 86%. Then these segmented characters are sent to a convolutional neural network for their recognition. The recognition and segmentation technique proposed in this paper is providing the most acceptable accurate results on a given dataset. The proposed work approaches to the accuracy of the result during convolutional neural network training up to 93%, and for validation that accuracy slightly decreases with 90.42%.     

Wireless Brain Computer Interface for Smart Home and Medical System

Wireless Personal Communications - The number of aged and disabled people has been increasing worldwide. To look after these people is a big challenge in this era. However, scientists overcome the...     

A comprehensive survey of AI-enabled phishing attacks detection techniques

In recent times, a phishing attack has become one of the most prominent attacks faced by internet users, governments, and service-providing organizations. In a phishing attack, the attacker(s) collects the client’s sensitive data (i.e., user account login details, credit/debit card numbers, etc.) by using spoofed emails or fake websites. Phishing websites are common entry points of online social engineering attacks, including numerous frauds on the websites. In such types of attacks, the attacker(s) create website pages by copying the behavior of legitimate websites and sends URL(s) to the targeted victims through spam messages, texts, or social networking. To provide a thorough understanding of phishing attack(s), this paper provides a literature review of Artificial Intelligence (AI) techniques: Machine Learning, Deep Learning, Hybrid Learning, and Scenario-based techniques for phishing attack detection. This paper also presents the comparison of different studies detecting the phishing attack for each AI technique and examines the qualities and shortcomings of these methodologies. Furthermore, this paper provides a comprehensive set of current challenges of phishing attacks and future research direction in this domain.

     

Information Processing and Wireless Energy Harvesting in Interference-Aware Public Safety Networks

In a public safety environment, user equipments (UEs) located within the coverage area of evolved NodeB, relay network services to out-of-coverage UEs. However, relay UEs in public safety environments are typically energy constrained and cannot operate indefinitely without recharging. Radio frequency energy harvesting has been proposed as a solution for recharging wireless UEs. In this paper, we propose a scheme for extending the lifetime of a public safety network by wirelessly charging relay UEs. In addition, we propose a relay selection method considering the battery status of relay UEs. The proposed relay selection is defined as a bipartite graph matching problem and the optimal relay is obtained through matching games technique. The proposed scheme not only improves the network lifetime but also extend the network coverage. We also conduct system level simulations to evaluate the performance of the proposed scheme. Simulation results show that the overall performance of the system is improved in terms of achievable throughput and network lifetime.     

A Dual Ring Connectivity Model for VANET Under Heterogeneous Traffic Flow

Vehicular ad-hoc network (VANET) is characterized as a highly dynamic wireless network due to the dynamic connectivity of the network nodes. To achieve better connectivity under such dynamic conditions, an optimal transmission strategy is required to direct the information flow between the nodes. Earlier studies on VANET’s overlook the characteristics of heterogeneity in vehicle types, traffic structure, flow for density estimation, and connectivity observation. In this paper, we have proposed a heterogeneous traffic flow based dual ring connectivity model to enhance both the message disseminations and network connectivity. In our proposed model the availability of different types of vehicles on the road, such as, cars, buses, etc., are introduced in an attempt to propose a new communication structure for moving vehicles in VANETl under cooperative transmission in heterogeneous traffic flow. The model is based on the dual-ring structure that forms the primary and secondary rings of vehicular communication. During message disseminations, Slow speed vehicles (buses) on the secondary ring provide a backup path of communication for high speed vehicles (cars) moving on the primary ring. The Slow speed vehicles act as the intermediate nodes in the aforementioned connectivity model that helps improve the network coverage and end-to-end data delivery. For the evaluation and the implementation of dual-ring model a clustering routing scheme warning energy aware cluster-head is adopted that also caters for the energy optimization. The implemented dual-ring message delivery scheme under the cluster-head based routing technique does show improved network coverage and connectivity dynamics even under the multi-hop communication system.     

Statistical analysis of trace metals in the plasma of cancer patients versus controls

The plasma of cancer patients (n=112) and controls (n=118) were analysed for selected trace metals (Al, Ca, Cd, Co, Cr, Cu, Fe, K, Li, Mg, Mn, Mo, Na, Ni, Pb, Sb, Sr and Zn) by flame atomic absorption spectroscopy. In the plasma of cancer patients, mean concentrations of macronutrients/essential metals, Na, K, Ca, Mg, Fe and Zn were 3971, 178, 44.1, 7.59, 4.38 and 3.90 ppm, respectively, while the mean metal levels in the plasma of controls were 3844, 151, 74.2, 18.0, 6.60 and 2.50 ppm, respectively. Average concentrations of Cd, Cr, Cu, Mn, Mo, Ni, Pb, Sb, Sr and Zn were noted to be significantly higher in the plasma of cancer patients compared with controls. Very strong mutual correlations (r>0.70) in the plasma of cancer patients were observed between Fe-Mn, Ca-Mn, Ca-Ni, Ca-Co, Cd-Pb, Co-Ni, Mn-Ni, Mn-Zn, Cr-Li, Ca-Zn and Fe-Ni, whereas, Ca-Mn, Ca-Mg, Fe-Zn, Ca-Zn, Mg-Mn, Mg-Zn, Cd-Sb, Cd-Co, Cd-Zn, Co-Sb and Sb-Zn exhibited strong relationships (r>0.50) in the plasma of controls, all were significant at p<0.01. Principal component analysis (PCA) of the data extracted five PCs, both for cancer patients and controls, but with considerably different loadings. The average metals levels in male and female donors of the two groups were also evaluated and in addition, the general role of trace metals in the carcinogenesis was discussed. The study indicated appreciably different pattern of metal distribution and mutual relationships in the plasma of cancer patients in comparison with controls.     

Synthesis of TiC, TiC-Cu Composites, and TiC-Cu Functionally Graded Materials by Electrothermal Combustion

Titanium carbide and composites and functionally graded materials (FGMs) of TiC– x Cu were synthesized by an electrothermal combustion (ETC) method. TiC synthesized by ETC showed small amounts of porosity relative to those synthesized by ignition using radiative heating. Composites and FGMs with higher copper content can be synthesized by ETC. In the FGM products a nearly linear change in composition in the graded region was observed in samples with 0 ≤ x (wt%) ≤ 75.     

Effect of Particle Size on the Reaction Wave Propagation in the Combustion Synthesis of Al2O3-ZrO2-Nb Composites

The effect of reactant particle size on the kinetics of wave propagation in the thermite system Nb₂O₅+ Al₂Zr + nuAl₂O₃ (with alumina being a diluent) was investigated. Reactants in three size ranges were utilized: fine (1–3 µm), medium (<10 µm), and coarse (10–45 µm). Particle size had an effect on the mode and velocity of the self-propagating combustion wave. For fine particles, the combustion wave propagated in a steady-state mode for all values of dilutions investigated (0 ≤ nu ≤ 0.8). For medium particles with nu > 0.1 and for all coarse particles, wave propagation was in the spin mode. A significantly large difference between the calculated adiabatic combustion temperatures and the measured values was observed and is attributed to large heat losses arising from very wide reaction zones. For fine particles, the temperature dependence of the wave velocity showed a discontinuity at a temperature corresponding to the formation of the eutectic in the binary ZrO₂-Al₂O₃. The velocity can be more than a factor of 3 higher at the same temperature, depending on the amount of the eutectic liquid. The dependence of the wave velocity on particle size ( r ) was found to have the form v is proportional to 1/ r^m with 0.5 < m < 0.8. The upper limit approximates that of m = 1.0 for diffusion-controlled reaction kinetics, according to reported modeling studies. In all cases, regardless of the mode of wave propagation the reactions resulted in the desired products, Nb + ZrO₂+ Al₂O₃ with a microstructure exhibiting the eutectic of the binary ZrO₂-Al₂O₃.     

Systematic comparison of the use of annular and Zernike circle polynomials for annular wavefronts

The theory of wavefront analysis of a noncircular wavefront is given and applied for a systematic comparison of the use of annular and Zernike circle polynomials for the analysis of an annular wavefront. It is shown that, unlike the annular coefficients, the circle coefficients generally change as the number of polynomials used in the expansion changes. Although the wavefront fit with a certain number of circle polynomials is identically the same as that with the corresponding annular polynomials, the piston circle coefficient does not represent the mean value of the aberration function, and the sum of the squares of the other coefficients does not yield its variance. The interferometer setting errors of tip, tilt, and defocus from a four-circle-polynomial expansion are the same as those from the annular-polynomial expansion. However, if these errors are obtained from, say, an 11-circle-polynomial expansion, and are removed from the aberration function, wrong polishing will result by zeroing out the residual aberration function. If the common practice of defining the center of an interferogram and drawing a circle around it is followed, then the circle coefficients of a noncircular interferogram do not yield a correct representation of the aberration function. Moreover, in this case, some of the higher-order coefficients of aberrations that are nonexistent in the aberration function are also nonzero. Finally, the circle coefficients, however obtained, do not represent coefficients of the balanced aberrations for an annular pupil. The various results are illustrated analytically and numerically by considering an annular Seidel aberration function.     

Investigation of forestry wastes: Torrefaction and their thermal properties for use in energy recovery schemes

Three biomasses like Eucalyptus, Azadirachata, and Ficus religiosa were torrefied to investigate the effect of temperature and residence time was investigated on torrefied biomasses for yield, volatile matter, fixed carbon, ash, and Gross calorific value (GCV). Thermogravimetric analysis and Hardgrove grindability index (HGI) of three torrefied samples were studied at optimum conditions of temperature and residence time. According to the results, an optimum temperature was found to be 260°C at 45 min residence time. A maximum GCV of torrefied biomasses of Eucalyptus, Azadirachata, and F. religiosa were found to be 4,301, 3,190, and 3,278 kcal/kg, respectively. According to thermogravimetric analyzer results, the Azadirachata has shown higher weight loss compared to Eucalyptus and F. religiosa during thermogravimetirc study. The weight loss rate for Azadirachata was maximum to nearly 12.8%/min compared to 6.11 and 5.12%/min for Eucalyptus and F. religiosa, respectively. The order of reactivity based on mean reactivity and combustion characterization factor was found to be Azadirachata indica > Eucalyptus > F. religiosa. According to HGI results, Eucalyptus, Azadirachata, and F. religiosa have shown HGI values of 71, 60.7, and 81.7, respectively. The results of this study could be useful for the energy recovery schemes in the country.