IoMT-Cloud Task Scheduling Using AI

The internet of medical things(IoMT)empowers patients to get adaptable,and virtualized gear over the internet.Task scheduling is the most fundamental problem in the IoMT-cloud since cloud execution commonly relies on it.Thus,a proposition is being made for a distinct scheduling technique to suitably meet these solicitations.To manage the scheduling issue,an artificial intelligence(AI)method known as a hybrid genetic algorithm(HGA)is proposed.The proposed AI method will be justified by contrasting it with other traditional optimization and AI scheduling approaches.The CloudSim is utilized to quantify its effect on various parameters like time,resource utilization,cost,and throughput.The proposed AI technique enhanced the viability of task scheduling with a better execution rate of 32.47ms and a reduced time of 40.16ms.Thus,the experimented outcomes show that the HGA reduces cost as well as time profoundly.

A comprehensive survey on security issues in vehicle-to-grid networks

Vehicle to grid(V2G)is the most hopeful approach to transfer energy as well as information in the bidirectional way.V2G network is formed by electric vehicles which connect with smart metres for information and energy transfer in a wireless manner.Even though many security preserving schemes developed in V2G networks,they were prone to enormous number of security breaches.A countless deal of works has been done towards it,but security mechanisms in V2G networks are not effective.This survey work provides a summary about the V2G network characteristics,significance,security services and the security challenges.Moreover,this work offers a summary of some foremost security attacks on various security services such as accessibility,confidentiality,authentication,integrity and non-repudiation and the related countermeasures to make the V2G communications more protected.

Comparative Evaluation and Comprehensive Analysis of Machine Learning Models for Regression Problems

Artificial intelligence and machine learning applications are of significant importance almost in every field of human life to solve problems or support human experts. However, the determination of the machine learning model to achieve a superior result for a particular problem within the wide real-life application areas is still a challenging task for researchers. The success of a model could be affected by several factors such as dataset characteristics, training strategy and model responses. Therefore, a comprehensive analysis is required to determine model ability and the efficiency of the considered strategies. This study implemented ten benchmark machine learning models on seventeen varied datasets. Experiments are performed using four different training strategies 60:40, 70:30, and 80:20 hold-out and five-fold cross-validation techniques. We used three evaluation metrics to evaluate the experimental results: mean squared error, mean absolute error, and coefficient of determination(R2score). The considered models are analyzed, and each model’s advantages, disadvantages, and data dependencies are indicated. As a result of performed excess number of experiments, the deep Long-Short Term Memory(LSTM) neural network outperformed other considered models, namely, decision tree, linear regression, support vector regression with a linear and radial basis function kernels, random forest, gradient boosting, extreme gradient boosting, shallow neural network, and deep neural network. It has also been shown that cross-validation has a tremendous impact on the results of the experiments and should be considered for the model evaluation in regression studies where data mining or selection is not performed.