Vehicle in vehicular ad hoc networks (VANETs) broadcasts beacons about their traffic status wirelessly for improving traffic safety and efficiency. Before deployment of the VANET system, problems related to security and privacy should be carefully addressed. In this paper, we propose a lightweight authentication with conditional privacy-preserving scheme for guaranteeing secure communication in VANET. The proposed scheme is suitable for addressing issues related to security and privacy because it combines the tamper-proof device (TPD) based schemes with the roadside unit (RSU) based schemes. Based on elliptic curve cryptography, the proposed scheme preloads the initial public parameters and keys of the system in each TPD of RSU instead of the TPD of the on-border unit (OBU). Furthermore, the proposed scheme not only achieve security and privacy requirements but also resists common security attacks. The performance evaluation shows that the proposed scheme has a lower cost compared with other existing schemes in terms of computation cost and communication cost. INDEX TERMS Authentication, tamper proof device (TPD), privacy-preserving, vehicular ad-hoc networks (VANETs). I. INTRODUCTION Recently, the intelligent transportation system (ITS) has attracted more deliberate attention from the motor industry, academia, and even government in recent years since it is reducing traffic congestion, enhancing driving efficiency, improving traffic safety, minimizing environmental pollution and providing convenience [1], [2]. Vehicular ad hoc networks (VANETs) are an entity of ITS with a fully a selforganizing wireless ad hoc communication system containing vehicles equipped with onboard unit (OBU), a trusted authority (TA) which preloads the initial public parameters of the VANET, and a road side unit (RSU) deployed at intersections in country, as presented in Figure 1. The communications types in VANETs contain two main modes: vehicle-tovehicle (V2V) communication and vehicle-to-infrastructure (V2I) communication [3], [4]. Dedicated short-range communication (DSRC) protocol is an open wireless technology which allows the vehicle for FIGURE 1: A typical VANET scenario. processing, receiving, broadcasting and communicating with each other or nearby RSU and exchanging messages such as
Cancer is considered one of the most aggressive and destructive diseases that shortens the average lives of patients. Misdiagnosed brain tumours lead to false medical intervention, which reduces patients’ chance of survival. Accurate early medical diagnoses of brain tumour are an essential point for starting treatment plans that improve the survival of patients with brain tumours. Computer-aided diagnostic systems have provided consecutive successes for helping medical doctors make accurate diagnoses and have conducted positive strides in the field of deep and machine learning. Deep convolutional layers extract strong distinguishing features from the regions of interest compared with those extracted using traditional methods. In this study, different experiments are performed for brain tumour diagnosis by combining deep learning and traditional machine learning techniques. AlexNet and ResNet-18 are used with the support vector machine (SVM) algorithm for brain tumour classification and diagnosis. Brain tumour magnetic resonance imaging (MRI) images are enhanced using the average filter technique. Then, deep learning techniques are applied to extract robust and important deep features via deep convolutional layers. The process of combining deep and machine learning techniques starts, where features are extracted using deep learning techniques, namely, AlexNet and ResNet-18. These features are then classified using SoftMax and SVM. The MRI dataset contains 3,060 images divided into four classes, which are three tumours and one normal. All systems have achieved superior results. Specifically, the AlexNet+SVM hybrid technique exhibits the best performance, with 95.10% accuracy, 95.25% sensitivity, and 98.50% specificity.
Dementia and Alzheimer’s disease are caused by neurodegeneration and poor communication between neurons in the brain. So far, no effective medications have been discovered for dementia and Alzheimer’s disease. Thus, early diagnosis is necessary to avoid the development of these diseases. In this study, efficient machine learning algorithms were assessed to evaluate the Open Access Series of Imaging Studies (OASIS) dataset for dementia diagnosis. Two CNN models (AlexNet and ResNet-50) and hybrid techniques between deep learning and machine learning (AlexNet+SVM and ResNet-50+SVM) were also evaluated for the diagnosis of Alzheimer’s disease. For the OASIS dataset, we balanced the dataset, replaced the missing values, and applied the t-Distributed Stochastic Neighbour Embedding algorithm (t-SNE) to represent the high-dimensional data in the low-dimensional space. All of the machine learning algorithms, namely, Support Vector Machine (SVM), Decision Tree, Random Forest and K Nearest Neighbours (KNN), achieved high performance for diagnosing dementia. The random forest algorithm achieved an overall accuracy of 94% and precision, recall and F1 scores of 93%, 98% and 96%, respectively. The second dataset, the MRI image dataset, was evaluated by AlexNet and ResNet-50 models and AlexNet+SVM and ResNet-50+SVM hybrid techniques. All models achieved high performance, but the performance of the hybrid methods between deep learning and machine learning was better than that of the deep learning models. The AlexNet+SVM hybrid model achieved accuracy, sensitivity, specificity and AUC scores of 94.8%, 93%, 97.75% and 99.70%, respectively.
Recently, Pulse Coupled Oscillator (PCO)-based travelling waves have attracted substantial attention by researchers in wireless sensor network (WSN) synchronization. Because WSNs are generally artificial occurrences that mimic natural phenomena, the PCO utilizes firefly synchronization of attracting mating partners for modelling the WSN. However, given that sensor nodes are unable to receive messages while transmitting data packets (due to deafness), the PCO model may not be efficient for sensor network modelling. To overcome this limitation, this paper proposed a new scheme called the Travelling Wave Pulse Coupled Oscillator (TWPCO). For this, the study used a self-organizing scheme for energy-efficient WSNs that adopted travelling wave biologically inspired network systems based on phase locking of the PCO model to counteract deafness. From the simulation, it was found that the proposed TWPCO scheme attained a steady state after a number of cycles. It also showed superior performance compared to other mechanisms, with a reduction in the total energy consumption of 25%. The results showed that the performance improved by 13% in terms of data gathering. Based on the results, the proposed scheme avoids the deafness that occurs in the transmit state in WSNs and increases the data collection throughout the transmission states in WSNs.
Perceptions of lifelike marvels are viewed as the best data source of unconstrained synchronization. Such synchronization is imperative for the best possible coordination of intensity cycles for wireless sensor network (WSN) energy conservation. Fireflies, which have a comparative structure to WSN, utilize the guideline of pulse-Coupled Oscillators (PCOs) for light blaze outflow to pull in mating accomplices. This conduct can be impersonated for the improvement of WSNs and have decentralized energy efficiency conduct. In any case, a fascinating component of WSNs is that the PCO is utilized by the firefly synchronization to pull in mating accomplices; however, it cannot be utilized in genuine sensor networks. This is because of the failure of the sensor nodes to get data packets utilized by the first PCO model because of deafness. Subsequently, energy utilization turns out to be high and a large portion of the data is lost. For most situations, the PCO model is not appropriate for sensor networks because of high packet collision since WSNs cannot bear the cost of transmission and gathering data concurrently. It likewise expands energy utilization because the battery substitution is unthinkable upon the fatigue of a node battery energy strategy. Accordingly, this paper broadly surveys and talks about the algorithms developed to address the difficulties and the systems of incorporating energy-efficient firefly inspired time synchronization over WSNs and the properties of transmission state inside the deafness and packet collision. In particular, it is an exhaustive audit incorporating instrument, points of interest and detriments of past related work inside the transmission state. The paper helps scientists to (1) keep away from deafness that happens in the transmit state in WSNs, (2) prevent packet collision for the time of transmission in WSNs, and (3) increment the data gathering all through the transmission states in WSNs. It additionally features the recommendation of a few appropriate open issues as proposals for future research.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.