IoT-Cloud Empowered Aerial Scene Classification for Unmanned Aerial Vehicles

Recent trends in communication technologies and unmanned aerial vehicles(UAVs)find its application in several areas such as healthcare,surveillance,transportation,etc.Besides,the integration of Internet of things(IoT)with cloud computing environment offers several benefits for the UAV communication.At the same time,aerial scene classification is one of the major research areas in UAV-enabledMEC systems.In UAV aerial imagery,efficient image representation is crucial for the purpose of scene classification.The existing scene classification techniques generate mid-level image features with limited representation capabilities that often end up in producing average results.Therefore,the current research work introduces a new DL-enabled aerial scene classificationmodel forUAV-enabledMECsystems.The presented model enables theUAVs to capture aerial imageswhich are then transmitted to MEC for further processing.Next,CapsuleNetwork(CapsNet)-based feature extraction technique is applied to derive a set of useful feature vectors from the aerial image.It is important to have an appropriate hyperparameter tuning strategy,since manual parameter tuning of DL model tend to produce several configuration errors.In order to achieve this and to determine the hyperparameters of CapsNetmodel,Shuffled Shepherd Optimization(SSO)algorithm is implemented.Finally,Backpropagation Neural Network(BPNN)classification model is applied to determine the appropriate class labels of aerial images.The performance of SSO-CapsNet model was validated against two openly-accessible datasets namely,UC Merced(UCM)Land Use dataset andWHU-RS dataset.The proposed SSO-CapsNet model outperformed the existing state-of-the-art methods and achieved maximum accuracy of 0.983,precision of 0.985,recall of 0.982,and F-score of 0.983.

State-Based Offloading Model for Improving Response Rate of IoT Services

The Internet of Things(IoT)is a heterogeneous information sharing and access platform that provides services in a pervasive manner.Task and computation offloading in the IoT helps to improve the response rate and the availability of resources.Task offloading in a service-centric IoT environment mitigates the complexity in response delivery and request processing.In this paper,the state-based task offloading method(STOM)is introduced with a view to maximize the service response rate and reduce the response time of the varying request densities.The proposed method is designed using the Markov decision-making model to improve the rate of requests processed.By defining optimal states and filtering the actions based on the probability of response and request analysis,this method achieves less response time.Based on the defined states,request processing and resource allocations are performed to reduce the backlogs in handling multiple requests.The proposed method is verified for the response rate and time for the varying requests and processing servers through an experimental analysis.From the experimental analysis,the proposed method is found to improve response rate and reduce backlogs,response time,and offloading factor by 11.5%,20.19%,20.31%,and 8.85%,respectively.

Intrusion Detection System for Big Data Analytics in IoT Environment

In the digital area,Internet of Things(IoT)and connected objects generate a huge quantity of data traffic which feeds big data analytic models to discover hidden patterns and detect abnormal traffic.Though IoT networks are popular and widely employed in real world applications,security in IoT networks remains a challenging problem.Conventional intrusion detection systems(IDS)cannot be employed in IoT networks owing to the limitations in resources and complexity.Therefore,this paper concentrates on the design of intelligent metaheuristic optimization based feature selection with deep learning(IMFSDL)based classification model,called IMFSDL-IDS for IoT networks.The proposed IMFSDL-IDS model involves data collection as the primary process utilizing the IoT devices and is preprocessed in two stages:data transformation and data normalization.To manage big data,Hadoop ecosystem is employed.Besides,the IMFSDL-IDS model includes a hill climbing with moth flame optimization(HCMFO)for feature subset selection to reduce the complexity and increase the overall detection efficiency.Moreover,the beetle antenna search(BAS)with variational autoencoder(VAE),called BAS-VAE technique is applied for the detection of intrusions in the feature reduced data.The BAS algorithm is integrated into the VAE to properly tune the parameters involved in it and thereby raises the classification performance.To validate the intrusion detection performance of the IMFSDL-IDS system,a set of experimentations were carried out on the standard IDS dataset and the results are investigated under distinct aspects.The resultant experimental values pointed out the betterment of the IMFSDL-IDS model over the compared models with the maximum accuracy 95.25%and 97.39%on the applied NSL-KDD and UNSW-NB15 dataset correspondingly.

A Novel Approach Based on Hybrid Algorithm for Energy Efficient Cluster Head Identification in Wireless Sensor Networks

The Wireless Sensor Networks(WSN)is a self-organizing network with random deployment of wireless nodes that connects each other for effective monitoring and data transmission.The clustering technique employed to group the collection of nodes for data transmission and each node is assigned with a cluster head.The major concern with the identification of the cluster head is the consideration of energy consumption and hence this paper proposes an hybrid model which forms an energy efficient cluster head in the Wireless Sensor Network.The proposed model is a hybridization of Glowworm Swarm Optimization(GSO)and Artificial Bee Colony(ABC)algorithm for the better identification of cluster head.The performance of the proposed model is compared with the existing techniques and an energy analysis is performed and is proved to be more efficient than the existing model with normalized energy of 5.35%better value and reduction of time complexity upto 1.46%.Above all,the proposed model is 16%ahead of alive node count when compared with the existing methodologies.