Metaheuristics with Machine Learning Enabled Information Security on Cloud Environment

The increasing quantity of sensitive and personal data being gathered by data controllers has raised the security needs in the cloud environment.Cloud computing(CC)is used for storing as well as processing data.Therefore,security becomes important as the CC handles massive quantity of outsourced,and unprotected sensitive data for public access.This study introduces a novel chaotic chimp optimization with machine learning enabled information security(CCOML-IS)technique on cloud environment.The proposed CCOML-IS technique aims to accomplish maximum security in the CC environment by the identification of intrusions or anomalies in the network.The proposed CCOML-IS technique primarily normalizes the networking data by the use of data conversion and min-max normalization.Followed by,the CCOML-IS technique derives a feature selection technique using chaotic chimp optimization algorithm(CCOA).In addition,kernel ridge regression(KRR)classifier is used for the detection of security issues in the network.The design of CCOA technique assists in choosing optimal features and thereby boost the classification performance.A wide set of experimentations were carried out on benchmark datasets and the results are assessed under several measures.The comparison study reported the enhanced outcomes of the CCOML-IS technique over the recent approaches interms of several measures.

Drift DetectionMethod Using DistanceMeasures and Windowing Schemes for Sentiment Classification

Textual data streams have been extensively used in practical applications where consumers of online products have expressed their views regarding online products.Due to changes in data distribution,commonly referred to as concept drift,mining this data stream is a challenging problem for researchers.The majority of the existing drift detection techniques are based on classification errors,which have higher probabilities of false-positive or missed detections.To improve classification accuracy,there is a need to develop more intuitive detection techniques that can identify a great number of drifts in the data streams.This paper presents an adaptive unsupervised learning technique,an ensemble classifier based on drift detection for opinion mining and sentiment classification.To improve classification performance,this approach uses four different dissimilarity measures to determine the degree of concept drifts in the data stream.Whenever a drift is detected,the proposed method builds and adds a new classifier to the ensemble.To add a new classifier,the total number of classifiers in the ensemble is first checked if the limit is exceeded before the classifier with the least weight is removed from the ensemble.To this end,a weighting mechanism is used to calculate the weight of each classifier,which decides the contribution of each classifier in the final classification results.Several experiments were conducted on real-world datasets and the resultswere evaluated on the false positive rate,miss detection rate,and accuracy measures.The proposed method is also compared with the state-of-the-art methods,which include DDM,EDDM,and PageHinkley with support vector machine(SVM)and Naive Bayes classifiers that are frequently used in concept drift detection studies.In all cases,the results show the efficiency of our proposed method.

Efficiency Effect of Obstacle Margin on Line-of-Sight in Wireless Networks

Line-of-sight clarity and assurance are essential because they are considered the golden rule in wireless network planning,allowing the direct propagation path to connect the transmitter and receiver and retain the strength of the signal to be received.Despite the increasing literature on the line of sight with different scenarios,no comprehensive study focuses on the multiplicity of parameters and basic concepts that must be taken into account when studying such a topic as it affects the results and their accuracy.Therefore,this research aims to find limited values that ensure that the signal reaches the future efficiently and enhances the accuracy of these values’results.We have designed MATLAB simulation and programming programs by Visual Basic.NET for a semi-realistic communication system.It includes all the basic parameters of this system,taking into account the environment’s diversity and the characteristics of the obstacle between the transmitting station and the receiving station.Then we verified the correctness of the system’s work.Moreover,we begin by analyzing and studying multiple and branching cases to achieve the goal.We get several values from the results,which are finite values,which are a useful reference for engineers and designers of wireless networks.

Optimal Load Forecasting Model for Peer-to-Peer Energy Trading in Smart Grids

Peer-to-Peer(P2P)electricity trading is a significant research area that offers maximum fulfilment for both prosumer and consumer.It also decreases the quantity of line loss incurred in Smart Grid(SG).But,uncertainities in demand and supply of the electricity might lead to instability in P2P market for both prosumer and consumer.In recent times,numerous Machine Learning(ML)-enabled load predictive techniques have been developed,while most of the existing studies did not consider its implicit features,optimal parameter selection,and prediction stability.In order to overcome fulfill this research gap,the current research paper presents a new Multi-Objective Grasshopper Optimisation Algorithm(MOGOA)with Deep Extreme Learning Machine(DELM)-based short-term load predictive technique i.e.,MOGOA-DELM model for P2P Energy Trading(ET)in SGs.The proposed MOGOA-DELM model involves four distinct stages of operations namely,data cleaning,Feature Selection(FS),prediction,and parameter optimization.In addition,MOGOA-based FS technique is utilized in the selection of optimum subset of features.Besides,DELM-based predictive model is also applied in forecasting the load requirements.The proposed MOGOA model is also applied in FS and the selection of optimalDELM parameters to improve the predictive outcome.To inspect the effectual outcome of the proposed MOGOA-DELM model,a series of simulations was performed using UK Smart Meter dataset.In the experimentation procedure,the proposed model achieved the highest accuracy of 85.80%and the results established the superiority of the proposed model in predicting the testing data.

Parkinson’s Detection Using RNN-Graph-LSTM with Optimization Based on Speech Signals

Early detection of Parkinson’s Disease(PD)using the PD patients’voice changes would avoid the intervention before the identification of physical symptoms.Various machine learning algorithms were developed to detect PD detection.Nevertheless,these ML methods are lack in generalization and reduced classification performance due to subject overlap.To overcome these issues,this proposed work apply graph long short term memory(GLSTM)model to classify the dynamic features of the PD patient speech signal.The proposed classification model has been further improved by implementing the recurrent neural network(RNN)in batch normalization layer of GLSTM and optimized with adaptive moment estimation(ADAM)on network hidden layer.To consider the importance of feature engineering,this proposed system use Linear Discriminant analysis(LDA)for dimensionality reduction and SparseAuto-Encoder(SAE)for extracting the dynamic speech features.Based on the computation of energy content transited from unvoiced to voice(onset)and voice to voiceless(offset),dynamic features are measured.The PD datasets is evaluated under 10 fold cross validation without sample overlap.The proposed smart PD detection method called RNN-GLSTM-ADAM is numerically experimented with persistent phonations in terms of accuracy,sensitivity,and specificity andMatthew correlation coefficient.The evaluated result of RNN-GLSTM-ADAM extremely improves the PD detection accuracy than static feature based conventional ML and DL approaches.

Artificial Intelligence-Based Fusion Model for Paddy Leaf Disease Detection and Classification

In agriculture,rice plant disease diagnosis has become a challenging issue,and early identification of this disease can avoid huge loss incurred from less crop productivity.Some of the recently-developed computer vision and Deep Learning(DL)approaches can be commonly employed in designing effective models for rice plant disease detection and classification processes.With this motivation,the current research work devises an Efficient Deep Learning based FusionModel for Rice Plant Disease(EDLFM-RPD)detection and classification.The aim of the proposed EDLFM-RPD technique is to detect and classify different kinds of rice plant diseases in a proficient manner.In addition,EDLFM-RPD technique involves median filtering-based preprocessing and K-means segmentation to determine the infected portions.The study also used a fusion of handcrafted Gray Level Co-occurrence Matrix(GLCM)and Inception-based deep features to derive the features.Finally,Salp Swarm Optimization with Fuzzy Support Vector Machine(FSVM)model is utilized for classification.In order to validate the enhanced outcomes of EDLFM-RPD technique,a series of simulations was conducted.The results were assessed under different measures.The obtained values infer the improved performance of EDLFM-RPD technique over recent approaches and achieved a maximum accuracy of 96.170%.

Coyote Optimization Using Fuzzy System for Energy Efficiency in WSN

In recent days,internet of things is widely implemented in Wireless Sensor Network(WSN).It comprises of sensor hubs associated together through the WSNs.The WSNis generally affected by the power in battery due to the linked sensor nodes.In order to extend the lifespan of WSN,clustering techniques are used for the improvement of energy consumption.Clustering methods divide the nodes in WSN and form a cluster.Moreover,it consists of unique Cluster Head(CH)in each cluster.In the existing system,Soft-K means clustering techniques are used in energy consumption in WSN.The soft-k means algorithm does not work with the large-scale wireless sensor networks,therefore it causes reliability and energy consumption problems.To overcome this,the proposed Load-Balanced Clustering conjunction with Coyote Optimization with Fuzzy Logic(LBC-COFL)algorithm is used.The main objective is to perform the lifespan by balancing the gateways with the load of less energy.The proposed algorithm is evaluated using the metrics such as energy consumption,throughput,central tendency,network lifespan,and total energy utilization.

Locomotion of Bioinspired Underwater Snake Robots Using Metaheuristic Algorithm

Snake Robots(SR)have been successfully deployed and proved to attain bio-inspired solutions owing to its capability to move in harsh environments,a characteristic not found in other kinds of robots(like wheeled or legged robots).Underwater Snake Robots(USR)establish a bioinspired solution in the domain of underwater robotics.It is a key challenge to increase the motion efficiency in underwater robots,with respect to forwarding speed,by enhancing the locomotion method.At the same time,energy efficiency is also considered as a crucial issue for long-term automation of the systems.In this aspect,the current research paper concentrates on the design of effectual Locomotion of Bioinspired Underwater Snake Robots using Metaheuristic Algorithm(LBIUSR-MA).The proposed LBIUSR-MA technique derives a bi-objective optimization problem to maximize the ForwardVelocity(FV)and minimize the Average Power Consumption(APC).LBIUSR-MA technique involves the design ofManta Ray Foraging Optimization(MRFO)technique and derives two objective functions to resolve the optimization issue.In addition to these,effective weighted sum technique is also used for the integration of two objective functions.Moreover,the objective functions are required to be assessed for varying gait variables so as to inspect the performance of locomotion.A detailed set of simulation analyses was conducted and the experimental results demonstrate that the developed LBIUSR-MA method achieved a low Average Power Consumption(APC)value of 80.52W underδvalue of 50.The proposed model accomplished the minimum PAC and maximum FV of USR in an effective manner.

QoS Aware Multicast Routing Protocol for Video Transmission in Smart Cities

In recent years,Software Defined Networking(SDN)has become an important candidate for communication infrastructure in smart cities.It produces a drastic increase in the need for delivery of video services that are of high resolution,multiview,and large-scale in nature.However,this entity gets easily influenced by heterogeneous behaviour of the user’s wireless link features that might reduce the quality of video stream for few or all clients.The development of SDN allows the emergence of new possibilities for complicated controlling of video conferences.Besides,multicast routing protocol with multiple constraints in terms of Quality of Service(QoS)is a Nondeterministic Polynomial time(NP)hard problem which can be solved only with the help of metaheuristic optimization algorithms.With this motivation,the current research paper presents a new Improved BlackWidow Optimization with Levy Distribution model(IBWO-LD)-based multicast routing protocol for smart cities.The presented IBWO-LD model aims at minimizing the energy consumption and bandwidth utilization while at the same time accomplish improved quality of video streams that the clients receive.Besides,a priority-based scheduling and classifier model is designed to allocate multicast request based on the type of applications and deadline constraints.A detailed experimental analysis was carried out to ensure the outcomes improved under different aspects.The results from comprehensive comparative analysis highlighted the superiority of the proposed IBWO-LD model over other compared methods.

Deep Reinforcement Learning Enabled Smart City Recycling Waste Object Classification

The Smart City concept revolves around gathering real time data from citizen,personal vehicle,public transports,building,and other urban infrastructures like power grid and waste disposal system.The understandings obtained from the data can assist municipal authorities handle assets and services effectually.At the same time,the massive increase in environmental pollution and degradation leads to ecological imbalance is a hot research topic.Besides,the progressive development of smart cities over the globe requires the design of intelligent waste management systems to properly categorize the waste depending upon the nature of biodegradability.Few of the commonly available wastes are paper,paper boxes,food,glass,etc.In order to classify the waste objects,computer vision based solutions are cost effective to separate out the waste from the huge dump of garbage and trash.Due to the recent developments of deep learning(DL)and deep reinforcement learning(DRL),waste object classification becomes possible by the identification and detection of wastes.In this aspect,this paper designs an intelligence DRL based recycling waste object detection and classification(IDRL-RWODC)model for smart cities.The goal of the IDRLRWODC technique is to detect and classify waste objects using the DL and DRL techniques.The IDRL-RWODC technique encompasses a twostage process namely Mask Regional Convolutional Neural Network(Mask RCNN)based object detection and DRL based object classification.In addition,DenseNet model is applied as a baseline model for the Mask RCNN model,and a deep Q-learning network(DQLN)is employed as a classifier.Moreover,a dragonfly algorithm(DFA)based hyperparameter optimizer is derived for improving the efficiency of the DenseNet model.In order to ensure the enhanced waste classification performance of the IDRL-RWODC technique,a series of simulations take place on benchmark dataset and the experimental results pointed out the better performance over the recent techniques with maximal accuracy of 0.993.

Elevating Localization Accuracy in Wireless Sensor Networks:A Refined DV-Hop Approach

Localization is crucial in wireless sensor networks for various applications,such as tracking objects in outdoor environments where GPS(Global Positioning System)or prior installed infrastructure is unavailable.However,traditional techniques involve many anchor nodes,increasing costs and reducing accuracy.Existing solutions do not address the selection of appropriate anchor nodes and selecting localized nodes as assistant anchor nodes for the localization process,which is a critical element in the localization process.Furthermore,an inaccurate average hop distance significantly affects localization accuracy.We propose an improved DV-Hop algorithm based on anchor sets(AS-IDV-Hop)to improve the localization accuracy.Through simulation analysis,we validated that the ASIDV-Hop proposed algorithm is more efficient in minimizing localization errors than existing studies.The ASIDV-Hop algorithm provides an efficient and cost-effective solution for localization in Wireless Sensor Networks.By strategically selecting anchor and assistant anchor nodes and rectifying the average hop distance,AS-IDV-Hop demonstrated superior performance,achieving a mean accuracy of approximately 1.59,which represents about 25.44%,38.28%,and 73.00%improvement over other algorithms,respectively.The estimated localization error is approximately 0.345,highlighting AS-IDV-Hop’s effectiveness.This substantial reduction in localization error underscores the advantages of implementing AS-IDV-Hop,particularly in complex scenarios requiring precise node localization.