Intrusion Detection System in Wireless Sensor Network Using Conditional Generative Adversarial Network

Wireless communication networks have much data to sense, process, and transmit. It tends to develop a security mechanism to care for these needs for such modern-day systems. An intrusion detection system (IDS) is a solution that has recently gained the researcher’s attention with the application of deep learning techniques in IDS. In this paper, we propose an IDS model that uses a deep learning algorithm, conditional generative adversarial network (CGAN), enabling unsupervised learning in the model and adding an eXtreme gradient boosting (XGBoost) classifier for faster comparison and visualization of results. The proposed method can reduce the need to deploy extra sensors to generate fake data to fool the intruder 1.2–2.6%, as the proposed system generates this fake data. The parameters were selected to give optimal results to our model without significant alterations and complications. The model learns from its dataset samples with the multiple-layer network for a refined training process. We aimed that the proposed model could improve the accuracy and thus, decrease the false detection rate and obtain good precision in the cases of both the datasets, NSL-KDD and the CICIDS2017, which can be used as a detector for cyber intrusions. The false alarm rate of the proposed model decreases by about 1.827%.

     

Influence of metal ion concentration in the glycol mediated synthesis of Gd2O3:Eu nanophosphor

The solvothermal synthesis of highly luminescent and homogeneous Gd₂O₃:Eu³⁺ nanophosphor using diethylene glycol as medium, followed by controlled combustion with citric acid as fuel is reported. The influence of concentrations of carboxylic acid and metal cations on the structure, morphology and luminescence properties are investigated in detail. The microscopic investigations indicate the nanocrystalline nature and the strong influence of cation concentration on the size, shape and agglomeration of the particles. It is found that increase in concentration of metal cations lead to the reduction in agglomeration of nanophosphors. The large value of intensity parameter Ω_2, suggested that Eu³⁺ ions reside in a more asymmetric environment, resulted in intense emission due to ⁵D₀–⁷F₂ electric dipole transition. Emission decay analysis of the samples exhibited one exponential nature. The samples prepared under optimum conditions showed a quantum efficiency of 78.63% and a moderately high life time of 1.217 ms.     

Simulation of microphysical structure associated with tropical cloud clusters using mesoscale model and comparison with TRMM observations

An attempt has been made in the present study to examine the microphysical structure of a non‐squall Tropical Cloud Cluster (TCC). Three‐dimensional model simulations of cloud microphysical structure associated with a non‐squall TCC occurred on 26 October 2005 over the South Bay of Bengal have been carried out. The initial conditions for the model simulations were improved by incorporating upper air radiosonde observations and Indian Mesosphere Stratosphere Troposphere (MST) radar wind observations through analysis nudging. The horizontal and vertical distribution of the cloud hydrometeor fields observed from the Tropical Rainfall Measuring Mission (TRMM) Microwave Imager (TMI) are compared to those simulated by a mesoscale model using a sophisticated microphysical scheme. Substantial differences are noticed in the amounts of cloud microphysical parameters, with simulated values of hydrometeors being higher than TMI retrievals. Spatial distribution of Cloud Liquid Water (CLW) and Rain Water (RNW) from TMI and model simulations correspond well with each other. The cloud microphysical structure during the initial and mature phases of the storm is also investigated. Comparisons of horizontal and vertical reflectivity structure from the TRMM‐Precipitation Radar (PR) and those simulated by the model show reflectivity cores of values greater than 30 dBZ. The TRMM‐PR echo tops are 3–4 km higher than the simulated echo tops. The 24 hr accumulated precipitation from model simulations are then verified with the combined rainfall product from the TRMM observations.     

Prediction and analysis of process failures by ANN classification during wire-EDM of Inconel 718

Wire breakages and spark absence are two typical machining failures that occur during wire electric discharge machining (wire-EDM), if appropriate parameter settings are not maintained. Even after several attempts to optimize the process, machining failures cannot be eliminated completely. An offline classification model is presented herein to predict machining failures. The aim of the current study is to develop a multiclass classification model using an artificial neural network (ANN). The training dataset comprises 81 full factorial experiments with three levels of pulse-on time, pulse-off time, servo voltage, and wire feed rate as input parameters. The classes are labeled as normal machining, spark absence, and wire breakage. The model accuracy is tested by conducting 20 confirmation experiments, and the model is discovered to be 95% accurate in classifying the machining outcomes. The effects of process parameters on the process failures are discussed and analyzed. A microstructural analysis of the machined surface and worn wire surface is conducted. The developed model proved to be an easy and fast solution for verifying and eliminating process failures.The full text can be downloaded at https://link.springer.com/article/10.1007/s40436-020-00327-w     

Experimental investigations on impaction pin nozzles for inlet fogging system

Increasing power demands have necessitated the development of energy efficient systems in the industrial sector. At present, about 10% of the overall electric power used by large industrial plants is consumed by high-capacity compressors supplying compressed air. Likewise, in a gas turbine power plant, nearly half the generated power is used for driving the compressor. The work of compression is proportional to inlet air temperature, and cooling the inlet air can save considerable amount of power in large turbo machines during hot summer months. Inlet fogging is a popular means of inlet air cooling, and fog nozzles are the most critical components in an inlet fogging installation. Majority of these installations employ impaction pin nozzles. In the present work, experiments are conducted over a wide range of operating parameters in variable length wind tunnels of different cross sections in order to investigate the performance of impaction pin nozzle in inlet fogging. Flow visualization and measurements are carried out to analyze the fog behavior and identify suitable nozzle locations in typical air ducts. The results show that impaction pin nozzles are suitable for inlet fogging applications.     

A multiscale virtual element method for the analysis of heterogeneous media

We introduce a novel heterogeneous multiscale method for the elastic analysis of two-dimensional domains with a complex microstructure. To this end, the multiscale finite element method is revisited and originally upgraded by introducing virtual element discretizations at the microscale, hence allowing for generalized polygonal and nonconvex elements. The microscale is upscaled through the numerical evaluation of a set of multiscale basis functions. The solution of the equilibrium equations is performed at the coarse scale at a reduced computational cost. We discuss the computation of the multiscale basis functions and corresponding virtual projection operators. The performance of the method in terms of accuracy and computational efficiency is evaluated through a set of numerical examples.     

A three-phase inverter circuit using half-bridge cells and T-NPC for medium-voltage applications

Three-phase single DC-source based multilevel inverter topologies play a pivotal role in industrial applications due to the reduced number of components and higher efficiency. This paper emphasizes the inverter for medium-voltage applications that employ a conventional three-phase T-type structure (T-NPC). The primary circuit of the proposed configuration consists of a T-NPC structure connected to the half-bridge cells at the top and the bottom sides of each phase. The secondary circuit consists of DC-link capacitors whose voltage balancing is attained through a separate voltage balancing circuit (VBC). Using the proposed configuration, the number of components and independent DC supplies are reduced compared with the conventional topologies such as a neutral point clamped (NPC) inverter, a flying capacitor (FC) inverter, and a cascaded H-bridge (CHB) inverter for the same number of output voltage levels. Hence, the proposed topology results in the reduction of weight, volume, and power losses of the inverter. A sine-triangle comparison method is employed in the field programmable gate array (FPGA) platform to generate the firing pulses of the circuit switches. The effectiveness of the proposed topology is verified with simulation studies and is experimentally validated with a scaled-down prototype.     

Computational investigation on the flow characteristics in beam dyeing process

Abstract

Ensuring uniform addition of coloring material to the fabric is an essential requirement in the textile dyeing process. Beam dyeing machine consists of a special beam, the barrel of which is evenly perforated with holes. The dye liquor is forced into the fabric material through this beam. For uniform fabric coloring, an equal distribution of the dye liquor through the porous beam has to be ensured. The present methodology employs theoretical and computational fluid dynamics aspects of beam dyeing process to obtain better performance. The analysis of a beam with a single row of branches shows that nonuniformity increases with an increase in inlet mass flow. Further beam flow distribution with and without fabric are studied for different parameters, such as branch diameter, inlet mass flow rate, operating conditions, and flow reversal. The present results provide guidelines to improve the levelness of the dye distribution in the fabric material.     

Differential nano-bio interactions and toxicity effects of pristine versus functionalized graphene

We report the effect of carboxyl functionalization of graphene in pacifying its strong hydrophobic interaction with cells and associated toxic effects. Pristine graphene was found to accumulate on the cell membrane causing high oxidative stress leading to apoptosis, whereas carboxyl functionalized hydrophilic graphene was internalized by the cells without causing any toxicity.     

Numerical analysis on thermo-fluid dynamic behavior of hydrogen gas during fast high pressure filling

Environmental pollution and rapid depletion of fossil fuels had necessitated the search for alternative technologies and energy sources for transportation. Hydrogen fuel can be an environment friendly alternative. High pressure gas is a widely used storage mode for hydrogen fuel. Refueling of a vehicular hydrogen tank should be reasonably short to gain consumer acceptability. However, quick filling at high pressures can result in high temperatures. This should be avoided because of safety reasons. A numerical model can aid in optimizing the filling up process. The paper reports the numerical simulation of the refueling of high pressure hydrogen tanks using computational fluid dynamics method. Real gas equations are included to accurately simulate the process at the high temperature and pressure associated with the fast filling. Local temperature distribution in the tank is obtained at different durations of the fill. The numerical results obtained are validated with available experimental data. The results give an accurate visualization of the thermo fluid dynamic behavior of hydrogen gas during fast filling.