Classification of sport videos using edge-based features and autoassociative neural network models

In this paper, we propose a method for classification of sport videos using edge-based features, namely edge direction histogram and edge intensity histogram. We demonstrate that these features provide discriminative information useful for classification of sport videos, by considering five sports categories, namely, cricket, football, tennis, basketball and volleyball. The ability of autoassociative neural network (AANN) models to capture the distribution of feature vectors is exploited, to develop class-specific models using edge-based features. We show that combining evidence from complementary edge features results in improved classification performance. Also, combination of evidence from different classifiers like AANN, hidden Markov model (HMM) and support vector machine (SVM) helps improve the classification performance. Finally, the performance of the classification system is examined for test videos which do not belong to any of the above five categories. A low rate of misclassification error for these test videos validates the effectiveness of edge-based features and AANN models for video classification.     

Rail RCF damage quantification and comparison for different damage models

There are several fatigue-based approaches that estimate the evolution of rolling contact fatigue(RCF)on rails over time and built to be used in tandem with mul...     

Selection of optimal process parameters in WEDM while machining Al7075/SiCp metal matrix composites

Aluminium metal matrix composites (MMCs) reinforced with silicon carbide particulate (SiCp) find several applications due to their improved mechanical properties over the conventional metals for a wide variety of aerospace and automotive applications. However, the presence of discontinuously distributed hard ceramic in the MMCs made them as difficult-to-cut materials for conventional machining methods. The wire electrical discharge machining (WEDM), as a widely adopted non-traditional machining method for difficult-to-cut precision components, found an appropriate metal removal process for MMCs to enhance quality of cut within the stipulated cost. While machining the advanced materials like MMCs, a clear understanding into the machining performance of the process for its control variables could make the process uncomplicated and economical. In light of the growing industrial need of making high performance-low cost components, the investigation aimed to explore the machining performance characteristics of SiCp reinforced Al7075 matrix composites (Al7075/SiCp) during WEDM. While conducting the machining experiments, surface roughness, metal removal rate, and wire wear ratio are considered the responses to evaluate the WEDM performance. Response surface methodology is used to develop the empirical models for these WEDM responses. SiC particulate size and volume percentages are considered the process variables along with pulse-on time, pulse-off time, and wire tension. Analysis of variance (ANOVA) is used to check the adequacy of the developed models. Since the machining responses are conflicting in nature, the problem is formulated as a multi-objective optimization problem and is solved using the Non-dominated Sorting Genetic Algorithm-II to obtain the set of Pareto-optimal solutions. The derived optimal process responses are confirmed by the experimental validation tests, and the results are analyzed by SEM.     

Assurance of system service level robustness in complex supply chain networks

Despite studies that consider service level rates of individual factories in a supply chain system, the interactions between connected factories and the impact of these interactions on the overall supply chain service level rate have been rarely studied. Moreover, due to uncertainties induced by various sources such as transportation delay and manufacturing processes variability, ensuring the robustness of system service level rate while considering these uncertainties in individual factories is a highly complex task. This paper studies uncertainty effect introduced by factory service level rates on the robustness of overall supply chain network performance, and presents a novel robust design optimization methodology to derive designs of factory service level rates in order to satisfy the service level rate requirement of the system and ensure its robustness. A case study with a multi-level multiple factories supply chain network is used to demonstrate the efficacy of the proposed methodology.     

Experimental and economic analysis of energy storage-based single-slope solar still with hollow-finned absorber basin

The paucity of drinking water is an alarming glitch across the globe. The conversion of available seawater into drinking water by utilizing renewable energy is the best way to surmount this challenge. Desalination through solar still is one of the notable, monetary, and viable processes among various desalination approaches. The current research aims to augment the potable water yield of single-slope solar still by using a hollow-finned absorber basin inserted into paraffin wax—phase change material (PCM). The effect of hollow-finned absorber basin on the yield of solar still is investigated separately, with and without PCM, and compared with the results of conventional solar still (CSS). In the first set of experiments, the CSS and solar still with a hollow-finned absorber basin without PCM (SSHF) are investigated. In the second set of experiments, the CSS and solar still with a hollow-finned absorber basin inserted into PCM (SSHFP) are investigated. The experimental results reported that the CSS is having almost the same yield on the 2 days of testing. The yield of SSHF and SSHFP is increased by 15.7% and 52.4%, respectively, when compared with CSS. The results of the economic analysis proved that the payback period and cost per liter of freshwater produced from SSHFP are comparatively better than SSHF and CSS.     

Effect of fluid property variations on the effectiveness of a cryogenic heat exchanger

Cryogenic heat exchangers are commonly used for industrial processes, such as air separation and natural gas liquefaction. Generally, the performance of heat exchangers is analyzed adopting constant properties for the working fluid. But, in cryogenic heat exchangers, fluids reach their critical states with significant variations in their properties. The current work is based on the effect of fluid property variations in the performance analysis of a two-fluid countercurrent cryogenic heat exchanger subject to ambient heat in a leak. Finite element method–subdomain method is used to conduct the performance analysis. The effect of fluid property variations is analyzed considering effectiveness, ∈, as the performance parameter. The percentage deviation in the effectiveness value on considering fluid property variation is determined. The relationship between effectiveness ∈ and the number of transfer units (NTUs) is obtained by plotting the ∈-NTU curve by varying the mass flow rate of the fluid flow. A maximum deviation of 16.108% in the effectiveness and 58.734% in the hot fluid exit temperature is obtained by considering fluid property variation.     

A Study of Chaotic Dynamics and Its Possible Control in a Predator-Prey Model with Disease in the Predator

Journal of Dynamical and Control Systems - The effect of parasites and pathogens in the prey population received a lot of attention, but disease in the predator population has been studied...     

Aqueous Corrosion Behavior of Micro Arc Oxidation (MAO)-Coated Magnesium Alloys: A Critical Review

Magnesium (Mg) and its alloys, in the current era of persistently growing engineering demands, have become the most promising materials finding widespread industrial applications. Numerous processes are available for surface protection of Mg and its alloys to potentially minimize corrosion damage. The micro arc oxidation (MAO), a fairly recent and eco-friendly coating process, emerged as a novel means to provide an adherent, hard, scratch-resistant, wear-resistant, and corrosion-resistant coatings on Mg alloys. However, the successful utilization of such coatings demands a thorough understanding of the influence of a relatively large number of process parameters such as electrolytic composition, presence of insoluble additives in the electrolyte, electrical parameters employed, and the composition of the Mg alloy substrate on the corrosion resistance. The detailed influence of all the above parameters on the corrosion behavior of Mg alloys is critically reviewed and presented in this article. In addition, this article also reviews the recent trends in terms of duplexing the MAO process using different techniques/processes such that the composite coatings are produced with enhanced corrosion resistance.     

Ratcheting Behavior of a Non-conventional Stainless Steel and Associated Microstructural Variations

Ratcheting fatigue behavior of a non-conventional stainless steel X12CrMnNiN17-7-5 has been investigated with varying combinations of mean stress (σ_m) and stress amplitude (σ_a) at room temperature using a servo-hydraulic universal testing machine. X-ray diffraction profile analysis has been carried out for assessing possible martensitic phase transformation in the steel subjected to ratcheting deformation. The results indicate that ratcheting strain as well as volume fraction of martensite increases with increasing σ_m and/or σ_a; the phenomenon of strain accumulation is considered to be governed by the associated mechanics of cyclic loading, increased plastic damage as well as martensitic transformation. A correlation between strain produced by ratcheting deformation and martensitic transformation has been established.     

Tunable microwave devices using low-sintering-temperature screen-printed barium strontium titanate (BST) thick films

A tunable microwave phase shifter composed of a low-sintering-temperature, screen-printable barium strontium titanate (BST) film and silver metallization was fabricated on an alumina substrate and co-fired at 900 °C for 3 h. The dielectric properties of the films were characterized in a frequency range of 0.8–8 GHz using scattering parameter measurements and a quasi-static coplanar waveguide transmission line model. The temperature dependency of the films was measured through capacitance measurements in a frequency range of 0.5–2.5 GHz. The figure of merit (phase shift/dB of insertion loss) of the phase shifter was found to be 14.6 at 3 GHz with an applied bias field strength of 2.5 V/μm. The performance of the phase shifter is briefly discussed and compared with other phase shifters fabricated by direct screen-printing of BST films.