Optimal Deep Learning Enabled Statistical Analysis Model for Traffic Prediction

Due to the advances of intelligent transportation system(ITSs),traffic forecasting has gained significant interest as robust traffic prediction acts as an important part in different ITSs namely traffic signal control,navigation,route mapping,etc.The traffic prediction model aims to predict the traffic conditions based on the past traffic data.For more accurate traffic prediction,this study proposes an optimal deep learning-enabled statistical analysis model.This study offers the design of optimal convolutional neural network with attention long short term memory(OCNN-ALSTM)model for traffic prediction.The proposed OCNN-ALSTM technique primarily preprocesses the traffic data by the use of min-max normalization technique.Besides,OCNN-ALSTM technique was executed for classifying and predicting the traffic data in real time cases.For enhancing the predictive outcomes of the OCNN-ALSTM technique,the bird swarm algorithm(BSA)is employed to it and thereby overall efficacy of the network gets improved.The design of BSA for optimal hyperparameter tuning of the CNN-ALSTM model shows the novelty of the work.The experimental validation of the OCNNALSTM technique is performed using benchmark datasets and the results are examined under several aspects.The simulation results reported the enhanced outcomes of the OCNN-ALSTM model over the recent methods under several dimensions.

Intelligent Deep Learning Based Multi-Retinal Disease Diagnosis and Classification Framework

In past decades,retinal diseases have become more common and affect people of all age grounds over the globe.For examining retinal eye disease,an artificial intelligence(AI)based multilabel classification model is needed for automated diagnosis.To analyze the retinal malady,the system proposes a multiclass and multi-label arrangement method.Therefore,the classification frameworks based on features are explicitly described by ophthalmologists under the application of domain knowledge,which tends to be time-consuming,vulnerable generalization ability,and unfeasible in massive datasets.Therefore,the automated diagnosis of multi-retinal diseases becomes essential,which can be solved by the deep learning(DL)models.With this motivation,this paper presents an intelligent deep learningbased multi-retinal disease diagnosis(IDL-MRDD)framework using fundus images.The proposed model aims to classify the color fundus images into different classes namely AMD,DR,Glaucoma,Hypertensive Retinopathy,Normal,Others,and Pathological Myopia.Besides,the artificial flora algorithm with Shannon’s function(AFA-SF)basedmulti-level thresholding technique is employed for image segmentation and thereby the infected regions can be properly detected.In addition,SqueezeNet based feature extractor is employed to generate a collection of feature vectors.Finally,the stacked sparse Autoencoder(SSAE)model is applied as a classifier to distinguish the input images into distinct retinal diseases.The efficacy of the IDL-MRDD technique is carried out on a benchmark multi-retinal disease dataset,comprising data instances from different classes.The experimental values pointed out the superior outcome over the existing techniques with the maximum accuracy of 0.963.

Networking Controller Based Real Time Traffic Prediction in Clustered Vehicular Adhoc Networks

The vehicular ad hoc network(VANET)is an emerging network tech-nology that has gained popularity because to its low cost,flexibility,and seamless services.Software defined networking(SDN)technology plays a critical role in network administration in the future generation of VANET withfifth generation(5G)networks.Regardless of the benefits of VANET,energy economy and traffic control are significant architectural challenges.Accurate and real-time trafficflow prediction(TFP)becomes critical for managing traffic effectively in the VANET.SDN controllers are a critical issue in VANET,which has garnered much interest in recent years.With this objective,this study develops the SDNTFP-C technique,a revolutionary SDN controller-based real-time trafficflow forecasting technique for clustered VANETs.The proposed SDNTFP-C technique combines the SDN controller’s scalability,flexibility,and adaptability with deep learning(DL)mod-els.Additionally,a novel arithmetic optimization-based clustering technique(AOCA)is developed to cluster automobiles in a VANET.The TFP procedure is then performed using a hybrid convolutional neural network model with atten-tion-based bidirectional long short-term memory(HCNN-ABLSTM).To optimise the performance of the HCNN-ABLSTM model,the dingo optimization techni-que was used to tune the hyperparameters(DOA).The experimental results ana-lysis reveals that the suggested method outperforms other current techniques on a variety of evaluation metrics.

Fuzzy-Based Secure Clustering with Routing Technique for VANETs

Due to the advanced developments in communication technologies,Internet of vehicles and vehicular adhoc networks(VANET)offers numerous opportunities for effectively managing transportation problems.On the other,the cloud environment needs to disseminate the emergency message to the vehicles which are consistently distributed on the roadway so that every vehicle gets the messages from closer vehicles in a straightforward way.To resolve this issue,clustering and routing techniques can be designed using computational intelligence approaches.With this motivation,this paper presents a new type-2 fuzzy sets based clustering with metaheuristic optimization based routing(T2FSCMOR)technique for secure communication in VANET.The T2FSC-MOR technique aims to elect CHs and optimal routes for secure intercluster data transmission in VANET.The proposed model involves T2FSC technique for the selection of CHs and construction of clusters.The T2FSC technique uses different parameters namely traveling speed(TS),link quality(LQ),trust factor(TF),inter-vehicle distance(IVD),and neighboring node count(NCC).The inclusion of trust factor helps to select the proper cluster heads(CHs)for secure data dissemination process.Moreover,trust aware seagull optimization based routing(TASGOR)approach was derived for the optimal selection of routes in VANET.In order to validate the enhanced performance of proposed technique,the set of simulations take place and the outcomes are examined interms of different measures.The experimental outcomes highlighted the improved performance of the proposed model over the other state of art techniques with a higher throughput of 98%.