Search

In the modern era, breast cancer (BC) is one of the most prevalent diseases affecting the lifespan of women. Single nucleotide polymorphism (SNP) elucidates an enormous proportion of the hazard in women with a solid family history. Different types of human disorders have been analyzed using Machine Learning methods to locate the vital SNP. The identification of an optimal feature set is the primary constraint in the existing methods owing to the ill effects of multidimensionality. Thus, a novel Bio-Inspired Ensemble Feature Selection (BIEFS) technique has been proposed in this paper to identify the most relevant SNP for accurate classification of BC. An initial feature subset is generated from each base feature selector such as Membership Weight Salp Swarm Algorithm (MWSSA), Crossover Horse Herd Optimization (CHHO), and Levy Mutation Manta-Ray Foraging Optimization (LMMRFO). Then the proposed BIEFS technique obtains the optimized weight of each feature subset through the mutation operator. Finally, the Self-Organizing Deep Auto-Encoder (SODAE) is employed for BC classification. A Gene Expression Omnibus (GEO) dataset is used to assess the proposed methodology. Simulation results validate that the proposed methodology attains a maximum accuracy of 98.75% as compared to the conventional techniques. [ABSTRACT FROM AUTHOR]

Absrtact: Distributed Denial-Of-Service (DDoS) attacks are one of the all the more difficult security issues on the Internet today. They can without much of a stretch, fumes the assets of the potential Victims. The issue is much more extreme since the aggressors regularly produce their IP delivers to shroud their character. The current guard mechanism against DDoS attacks, the attack traffic will be filtered at the victim's side. For this situation, regardless of whether the attacking traffic is filtered by the victim, the attacker may achieve the objective of blocking access to the victim's bandwidth. IP-Traceback approaches enable the victim to traceback to the wellspring of an attack and they will not be able to minimize the attack when the attack is in progress. Hence in this work we proposed a hybrid method to minimize the quantity of malicious packets entering into the network. We introduce a quantum annealing technique at the server side to identify and mitigate the DDoS attack. The attack messages are minimized by utilizing client puzzle as a part of the ingress router; the path fingerprint is used at the egress side. Simulation studies prove that the proposed mechanism is optimally successful in recognizing and mitigating the DDoS attacks. [ABSTRACT FROM AUTHOR]

The main aim of this work was to utilize the winery biomass waste as a useful feedstock for CI engines, which otherwise would have been disposed as solid waste, leading to environmental pollution. Maximum utilization of this fuel in CI engines with reduced emissions was the motivation of this study. In this work, grapeseed oil derived from winery biomass waste was used. The trans-esterified methyl ester was blended with varying dosage of nanofluid additives to improve the engine performance characteristics and reduce the emission parameters. Zinc oxide (ZnO) and cerium oxide (CeO2) nanoemulsions were prepared by mixing them with water at concentration levels of 50 and 100 ppm each. Five percent of nanoemulsion and 1% Span 80 surfactant were mixed with grapeseed biodiesel to obtain biodiesel nanoemulsion blends. The test fuels were neat diesel, grapeseed biodiesel (GSBD), GSBD ZnO50, GSBD ZnO100, GSBD CeO250 and GSBD CeO2100, respectively. Analysis of experimental results shows an improvement in brake thermal efficiency of 29.34% and 29.23% for GSBD ZnO100 and GSBD CeO2100, respectively. Combustion phenomena and emission values were satisfactory for GSBD ZnO100. Peak pressure attained and heat release rate were better than GSBD fuel due to the improved thermophysical properties, however lesser than that of neat diesel. NOx emissions were slightly reduced by 10.8% due to fast evaporation rate of water particles in the nanoemulsion. HC and CO emissions were reduced by 13% and 4.6% for GSBD ZnO100 blend. Summary of results shows that GSBD produced from winery waste is suitable for use in CI engines, and the additives helped in improving the combustion efficiency and reducing the exhaust emissions. [ABSTRACT FROM AUTHOR]

WBAN consists of several tiny sensors that are located inside and outside human body for continuous monitoring of vital parameters of patients suffering from chronic diseases. The wearable sensor unit consists of transmitter, receiver and central process unit (gateway). The gateway is used to connect wearable sensors on human body to the internet. To increase the lifetime of such networks, the energy spent by the sensors has to be minimized. In this work we analyzed the feasibility and performance of fountain code based raptor code for error correction to overcome the energy and reliability issues. Versatility of raptor code in terms of code rate and coding gain is advantageous to increase the energy efficiency of WBAN network. Simulation results considering different fading channels show that the raptor coded packet transmission is more energy efficient than that of LT code, traditional BCH code and ARQ error control technique. [ABSTRACT FROM AUTHOR]

There was a typo in the second author's name in the original article. The correct name is S. Karthik, as listed here. The original article has been corrected. [ABSTRACT FROM AUTHOR]