Arithmetic Optimization with Ensemble Deep Transfer Learning Based Melanoma Classification

Melanoma is a skin disease with high mortality rate while earlydiagnoses of the disease can increase the survival chances of patients. Itis challenging to automatically diagnose melanoma from dermoscopic skinsamples. Computer-Aided Diagnostic (CAD) tool saves time and effort indiagnosing melanoma compared to existing medical approaches. In this background,there is a need exists to design an automated classification modelfor melanoma that can utilize deep and rich feature datasets of an imagefor disease classification. The current study develops an Intelligent ArithmeticOptimization with Ensemble Deep Transfer Learning Based MelanomaClassification (IAOEDTT-MC) model. The proposed IAOEDTT-MC modelfocuses on identification and classification of melanoma from dermoscopicimages. To accomplish this, IAOEDTT-MC model applies image preprocessingat the initial stage in which Gabor Filtering (GF) technique is utilized.In addition, U-Net segmentation approach is employed to segment the lesionregions in dermoscopic images. Besides, an ensemble of DL models includingResNet50 and ElasticNet models is applied in this study. Moreover, AOalgorithm with Gated Recurrent Unit (GRU) method is utilized for identificationand classification of melanoma. The proposed IAOEDTT-MC methodwas experimentally validated with the help of benchmark datasets and theproposed model attained maximum accuracy of 92.09% on ISIC 2017 dataset.

Blockchain Assisted Intrusion Detection System Using Differential Flower Pollination Model

Cyberattacks are developing gradually sophisticated,requiring effective intrusion detection systems(IDSs)for monitoring computer resources and creating reports on anomalous or suspicious actions.With the popularity of Internet of Things(IoT)technology,the security of IoT networks is developing a vital problem.Because of the huge number and varied kinds of IoT devices,it can be challenging task for protecting the IoT framework utilizing a typical IDS.The typical IDSs have their restrictions once executed to IoT networks because of resource constraints and complexity.Therefore,this paper presents a new Blockchain Assisted Intrusion Detection System using Differential Flower Pollination with Deep Learning(BAIDS-DFPDL)model in IoT Environment.The presented BAIDS-DFPDLmodelmainly focuses on the identification and classification of intrusions in the IoT environment.To accomplish this,the presented BAIDS-DFPDL model follows blockchain(BC)technology for effective and secure data transmission among the agents.Besides,the presented BAIDSDFPDLmodel designs Differential Flower Pollination based feature selection(DFPFS)technique to elect features.Finally,sailfish optimization(SFO)with Restricted Boltzmann Machine(RBM)model is applied for effectual recognition of intrusions.The simulation results on benchmark dataset exhibit the enhanced performance of the BAIDS-DFPDL model over other models on the recognition of intrusions.