Chaotic Flower Pollination with Deep Learning Based COVID-19 Classification Model

The Coronavirus Disease(COVID-19)pandemic has exposed the vulnerabilities of medical services across the globe,especially in underdeveloped nations.In the aftermath of the COVID-19 outbreak,a strong demand exists for developing novel computer-assisted diagnostic tools to execute rapid and cost-effective screenings in locations where many screenings cannot be executed using conventional methods.Medical imaging has become a crucial component in the disease diagnosis process,whereas X-rays and Computed Tomography(CT)scan imaging are employed in a deep network to diagnose the diseases.In general,four steps are followed in image-based diagnostics and disease classification processes by making use of the neural networks,such as network training,feature extraction,model performance testing and optimal feature selection.The current research article devises a Chaotic Flower Pollination Algorithm with a Deep Learning-Driven Fusion(CFPADLDF)approach for detecting and classifying COVID-19.The presented CFPA-DLDF model is developed by integrating two DL models to recognize COVID-19 in medical images.Initially,the proposed CFPA-DLDF technique employs the Gabor Filtering(GF)approach to pre-process the input images.In addition,a weighted voting-based ensemble model is employed for feature extraction,in which both VGG-19 and the MixNet models are included.Finally,the CFPA with Recurrent Neural Network(RNN)model is utilized for classification,showing the work’s novelty.A comparative analysis was conducted to demonstrate the enhanced performance of the proposed CFPADLDF model,and the results established the supremacy of the proposed CFPA-DLDF model over recent approaches.

Advance IoT Intelligent Healthcare System for Lung Disease Classification Using Ensemble Techniques

In healthcare systems,the Internet of Things(IoT)innovation and development approached new ways to evaluate patient data.A cloud-based platform tends to process data generated by IoT medical devices instead of high storage,and computational hardware.In this paper,an intelligent healthcare system has been proposed for the prediction and severity analysis of lung disease from chest computer tomography(CT)images of patients with pneumonia,Covid-19,tuberculosis(TB),and cancer.Firstly,the CT images are captured and transmitted to the fog node through IoT devices.In the fog node,the image gets modified into a convenient and efficient format for further processing.advanced encryption Standard(AES)algorithm serves a substantial role in IoT and fog nodes for preventing data from being accessed by other operating systems.Finally,the preprocessed image can be classified automatically in the cloud by using various transfer and ensemble learning models.Herein different pre-trained deep learning architectures(Inception-ResNet-v2,VGG-19,ResNet-50)used transfer learning is adopted for feature extraction.The softmax of heterogeneous base classifiers assists to make individual predictions.As a meta-classifier,the ensemble approach is employed to obtain final optimal results.Disease predicted image is consigned to the recurrent neural network with long short-term memory(RNN-LSTM)for severity analysis,and the patient is directed to seek therapy based on the outcome.The proposed method achieved 98.6%accuracy,0.978 precision,0.982 recalls,and 0.974 F1-score on five class classifications.The experimental findings reveal that the proposed framework assists medical experts with lung disease screening and provides a valuable second perspective.

Depth Map Prediction of Occluded Objects Using Structure Tensor with Gain Regularization

The creation of the 3D rendering model involves the prediction of an accurate depth map for the input images.A proposed approach of a modified semi-global block matching algorithm with variable window size and the gradient assessment of objects predicts the depth map.3D modeling and view synthesis algorithms could effectively handle the obtained disparity maps.This work uses the consistency check method to find an accurate depth map for identifying occluded pixels.The prediction of the disparity map by semi-global block matching has used the benchmark dataset of Middlebury stereo for evaluation.The improved depth map quality within a reasonable process-ing time outperforms the other existing depth map prediction algorithms.The experimental results have shown that the proposed depth map predictioncould identify the inter-object boundaryeven with the presence ofocclusion with less detection error and runtime.We observed that the Middlebury stereo dataset has very few images with occluded objects,which made the attainment of gain cumbersome.Considering this gain,we have created our dataset with occlu-sion using the structured lighting technique.The proposed regularization term as an optimization process in the graph cut algorithm handles occlusion for different smoothing coefficients.The experimented results demonstrated that our dataset had outperformed the Tsukuba dataset regarding the percentage of occluded pixels.

Novel Homomorphic Encryption for Mitigating Impersonation Attack in Fog Computing

Fog computing is a rapidly growing technology that aids in pipelining the possibility of mitigating breaches between the cloud and edge servers.It facil-itates the benefits of the network edge with the maximized probability of offering interaction with the cloud.However,the fog computing characteristics are suscep-tible to counteract the challenges of security.The issues present with the Physical Layer Security(PLS)aspect in fog computing which included authentication,integrity,and confidentiality has been considered as a reason for the potential issues leading to the security breaches.In this work,the Octonion Algebra-inspired Non-Commutative Ring-based Fully Homomorphic Encryption Scheme(NCR-FHE)was proposed as a secrecy improvement technique to overcome the impersonation attack in cloud computing.The proposed approach was derived through the benefits of Octonion algebra to facilitate the maximum security for big data-based applications.The major issues in the physical layer security which may potentially lead to the possible security issues were identified.The potential issues causing the impersonation attack in the Fog computing environment were identified.The proposed approach was compared with the existing encryption approaches and claimed as a robust approach to identify the impersonation attack for the fog and edge network.The computation cost of the proposed NCR-FHE is identified to be significantly reduced by 7.18%,8.64%,9.42%,and 10.36%in terms of communication overhead for varying packet sizes,when compared to the benchmarked ECDH-DH,LHPPS,BF-PHE and SHE-PABF schemes.

Effect of tool tilt angle on strength and microstructural characteristics of friction stir welded lap joints of AA2014-T6 aluminum alloy

Friction stir welding(FSW)has been extensively adopted to fabricate aluminium alloy joints by incorporating various welding parameters that include welding speed,rotational speed,diameters of shoulder and pin and tool tilt angle.FSW parameters significantly affect the weld strength.Tool tilt angle is one of the significant process parameters among the weld parameters.The present study focused on the effect of tool tilt angle on strength of friction stir lap welding of AA2014-T6 aluminium alloy.The tool tilt angle was varied between 0°and 4°with an equal increment of 1°.Other process parameters were kept constant.Macrostructure and microstructure analysis,microhardness measurement,scanning electron micrograph,transmission electron micrograph and energy dispersive spectroscopy analysis were performed to evaluate the lap shear strength of friction stir lap welded joint.Results proved that,defect-free weld joint was obtained while using a tool tilt angle of 1°to 3°.However,sound joints were welded using a tool tilt angle of 2°,which had the maximum lap shear strength of 14.42 kN and microhardness of HV 132.The joints welded using tool tilt angles of 1°and 3°yielded inferior lap shear strength due to unbalanced material flow in the weld region during FSW.

Energy Efficient Cluster-Based Optimal Resource Management in IoT Environment

Internet of Things(IoT)is a technological revolution that redefined communication and computation of modern era.IoT generally refers to a network of gadgets linked via wireless network and communicates via internet.Resource management,especially energy management,is a critical issue when designing IoT devices.Several studies reported that clustering and routing are energy efficient solutions for optimal management of resources in IoT environment.In this point of view,the current study devises a new Energy-Efficient Clustering-based Routing technique for Resource Management i.e.,EECBRM in IoT environment.The proposed EECBRM model has three stages namely,fuzzy logic-based clustering,Lion Whale Optimization with Tumbling(LWOT)-based routing and cluster maintenance phase.The proposed EECBRMmodel was validated through a series of experiments and the results were verified under several aspects.EECBRM model was compared with existing methods in terms of energy efficiency,delay,number of data transmission,and network lifetime.When simulated,in comparison with other methods,EECBRM model yielded excellent results in a significant manner.Thus,the efficiency of the proposed model is established.

Energy Efficient Cluster Based Clinical Decision Support System in IoT Environment

Internet of Things(IoT)has become a major technological development which offers smart infrastructure for the cloud-edge services by the interconnection of physical devices and virtual things among mobile applications and embedded devices.The e-healthcare application solely depends on the IoT and cloud computing environment,has provided several characteristics and applications.Prior research works reported that the energy consumption for transmission process is significantly higher compared to sensing and processing,which led to quick exhaustion of energy.In this view,this paper introduces a new energy efficient cluster enabled clinical decision support system(EEC-CDSS)for embedded IoT environment.The presented EECCDSS model aims to effectively transmit the medical data from IoT devices and perform accurate diagnostic process.The EEC-CDSS model incorporates particle swarm optimization with levy distribution(PSO-L)based clustering technique,which clusters the set of IoT devices and reduces the amount of data transmission.In addition,the IoT devices forward the data to the cloud where the actual classification procedure is performed.For classification process,variational autoencoder(VAE)is used to determine the existence of disease or not.In order to investigate the proficient results analysis of the EEC-CDSS model,a wide range of simulations was carried out on heart disease and diabetes dataset.The obtained simulation values pointed out the supremacy of the EEC-CDSS model interms of energy efficiency and classification accuracy.

Gray-Hole Attack Minimization in IoMT with 5G Based D2D Networks

Reliable transmission is vital to the success of the next generation ofcommunications technologies and Fifth Generation (5G) networks. Many sensitive applications, such as eHealth and medical services, can benefit from a 5G network. The Internet of Medical Things (IoMT) is a new field that fosters themaintenance of trust among various IoMT Device to Device (D2D) modern technologies. In IoMT the medical devices have to be connected through a wirelessnetwork and constantly needs to be self-configured to provide consistent and effi-cient data transmission. The medical devices need to be connected with sophisticated protocols and architecture to handle the synergy of the monitoring devices.Today, one of the commonly used algorithms in D2D communication is the Optimized Link State Routing protocol (OLSR). The OLSR is considerably good ateffectively utilizing the bandwidth and reserving the paths. One of the majorattack against the OLSR is the Node isolation attack, also known as the Gray holedenial of service attack. The Gray hole attack exploits the vulnerabilities presentwith sharing the topological information of the network. The attackers may usethis topological information to maliciously disconnect the target nodes from theexisting network and stops rendering the communication services to the victimnode. Hence, considering the sensitivity and security concerns of the data usedin e-Health applications, these types of attacks must be detected and disabledproactively. In this work, a novel Node Authentication (NA) with OLSR is proposed. The simulation experiments illustrated that the proposed protocol has anexcellent Packet Delivery Ratio, minimal End-End delay, and minimal Packet losswhen compared to the Ad-hoc On-Demand Distance Victor (AODV) protocol andthe proposed authentication scheme was able to protect the OLSR protocol from anode isolation attack.

Transient Evolution of Inter Vessel Gap Pressure Due to Relative Thermal Expansion Between Two Vessels

In a typical liquid metal cooled fast breeder reactor (LMFBR), a cylindrical sodium filled main vessel, which carries the internals such as reactor core, pumps, intermediate heat exchangers etc. is surrounded by another vessel called safety vessel. The inter vessel gap is filled with nitrogen. During a thermal transient in the pool sodium, because of the relative delay involved in the thermal diffusion between MV and SV, they are subjected to relative thermal expansion or contraction between them. This in turn results in pressurisation and depressurisation of inter vessel gap nitrogen respectively. In order to obtain the external pressurization for the buckling design of MV, transient thermal models for obtaining the evolutions of MV, SV and inter gap nitrogen temperatures and hence their relative thermal expansion and inter vessel gap pressure have been developed. This paper gives the details of the mathematical model, assumptions made in the calculation and the results of the analysis.