Vehicular ad-hoc network (VANET) model is easy to arrange and inexpensive answer for clever traffic control and traffic failure protective measures. Generally, the nodes present in VANET utilize broadcast protocols for effectively transmitting safety information, although nodes do not perform based on routing protocols. The misbehavior can produce through targeted attack in which aggressive vehicle can purposely send malevolent packets to damage. Moreover, due to the reason of dynamic behavior of nodes in VANET plus routing difficulties, unexpected misconduct also occurs owing to the software or hardware failures in vehicle. The challenges faced by existing techniques are provided here. VANET becomes a most significant concern to enhance the expediency, mobility, and security application in ITS. Precautions are further tough owing to its rapid mobility, wireless communication and large coverage of nodes. Also, the computational time required for executing independent operations are conspicuously maximum when, the number of vehicles is maximized. In order to overcome these challenges, in this paper, hybrid optimization-based Deep Maxout Network (DMN) is developed for attack classification in VANET. The Cluster Head (CH) selection and routing process is performed using designed hybrid optimization algorithm. The feature selection process is more significant in order to perform effective classification process. In addition, the attack classification is carried out using DMN and it is taught by introduced optimization algorithm. The developed optimization-based DMN model obtained better classification performance with precision and recall of 0.9395, and 0.9462 as well as routing performance with energy and trust of 0.2454J, and 0.4402. 

Hybrid optimization enabled trust-based secure routing with deep learning-based attack detection in VANET

A systematic literature review of artificial intelligence in the healthcare sector: Benefits, challenges, methodologies, and functionalities

The paper presents the full-size Russian corpus of Internet users’ reviews on medicines with complex named entity recognition (NER) labeling of pharmaceutically relevant entities. We evaluate the accuracy levels reached on this corpus by a set of advanced deep learning neural networks for extracting mentions of these entities. The corpus markup includes mentions of the following entities: medication (33,005 mentions), adverse drug reaction (1778), disease (17,403), and note (4490). Two of them—medication and disease—include a set of attributes. A part of the corpus has a coreference annotation with 1560 coreference chains in 300 documents. A multi-label model based on a language model and a set of features has been developed for recognizing entities of the presented corpus. We analyze how the choice of different model components affects the entity recognition accuracy. Those components include methods for vector representation of words, types of language models pre-trained for the Russian language, ways of text normalization, and other pre-processing methods. The sufficient size of our corpus allows us to study the effects of particularities of annotation and entity balancing. We compare our corpus to existing ones by the occurrences of entities of different types and show that balancing the corpus by the number of texts with and without adverse drug event (ADR) mentions improves the ADR recognition accuracy with no notable decline in the accuracy of detecting entities of other types. As a result, the state of the art for the pharmacological entity extraction task for the Russian language is established on a full-size labeled corpus. For the ADR entity type, the accuracy achieved is 61.1% by the F1-exact metric, which is on par with the accuracy level for other language corpora with similar characteristics and ADR representativeness. The accuracy of the coreference relation extraction evaluated on our corpus is 71%, which is higher than the results achieved on the other Russian-language corpora.

/pdf/analysis-of-the-full-size-russian-corpus-of-internet-drug-hxrnq3q0.pdf

Analysis of the Full-Size Russian Corpus of Internet Drug Reviews with Complex NER Labeling Using Deep Learning Neural Networks and Language Models

Vehicular Ad-hoc network (VANET) is an imminent technology having both exciting prospects and substantial challenges, especially in terms of security. Due to its distributed network and frequently changing topology, it is extremely prone to security attacks. The researchers have proposed different strategies for detecting various forms of network attacks. However, VANET is still exposed to several attacks, specifically Sybil attack. Sybil Attack is one of the most challenging attacks in VANETS, which forge false identities in the network to undermine communication between network nodes. This attack highly impacts transportation safety services and may create traffic congestion. In this regard, a novel collaborative framework based on majority voting is proposed to detect the Sybil attack in the network. The framework works by ensembling individual classifiers, i.e., K-Nearest Neighbor, Naïve Bayes, Decision Tree, SVM, and Logistic Regression in a parallel manner. The Majority Voting (Hard and Soft) mechanism is adopted for a final prediction. A comparison is made between Majority Voting Hard and soft to choose the best approach. With the proposed approach, 95% accuracy is achieved. The proposed framework is also evaluated using the Receiver operating characteristics curve (ROC-curve).

/pdf/collaborative-learning-based-sybil-attack-detection-in-2xlbagvq.pdf

Collaborative Learning Based Sybil Attack Detection in Vehicular AD-HOC Networks (VANETS)

Vehicular ad hoc networks (VANETs) connect two or more vehicles wirelessly to enable data exchange in an Internet of Things (IoT) environment. In VANETs, location privacy is the most crucial piece of information, and its protection is the top priority. However, the location privacy threats have not been adequately addressed in positioning for IoT in VANETs. This paper provides an overview of location privacy attacks and their solutions to address the problems caused by attacks in any IoT environment. Secondly, we have analyzed specific solutions based on anonymity (pseudonym) and cryptographic solutions using a digital signature technique. This enables to improve user privacy and security of location-based services for IoT in VANET. Moreover, we have proposed a faster 5G solution for the VANETs as it rapidly disseminates the data in fast-moving vehicles. 

A Survey on Location Privacy Attacks and Prevention Deployed with IoT in Vehicular Networks

Vehicular ad-hoc networks (VANET) technology, which is an open-access network, renders a quick, simple to deploy, and cheap solution for intelligent traffic control as well as traffic disaster preventive measure but it is prone to disparate sorts of attacks. The Sybil attack (SA) is the most harmful attacks that the VANET has to face. In this, the attacker generates manifold identities to fake manifold nodes. It is extremely onerous to defend as well as detect, especially if it is commenced by means of some connived attackers utilizing their genuine identities. Here, a deep learning-centered intrusion detections system (IDS) is proposed utilizing CMEHA-DNN for detecting the SA in VANET. The proposed technique encompasses ‘4’ steps: (i) cluster formation (CF), (ii) cluster head (CH) selection, (iii) attack detection, and (iv) security of VANET. Initially, the MKHM clustering algorithm clusters the vehicles. Next, the Floyd–Warshall algorithm (FWA) selects the CH as of the clusters. Subsequent to CH selection, the malevolent CH is identified utilizing the deep leaning model CMEHA-DNN by means of extracting the pertinent features as of the CH. Lastly, subsequent to detection, if the CH is a normal one, the information contained by means of the CH is securely sent to the cloud utilizing the MD5-ECC. The proposed work attains an accuracy of 98.37% and a security level of 98.2%, which is better compared to existing methods.

Sybil attack detection and secure data transmission in VANET using CMEHA-DNN and MD5-ECC

In recent years, Vehicular ad hoc networks (VANETs) could facilitate the decision-making progress of the drivers for example trip planning with the consideration of traffic. In the VANET, the Sybil attack is a very serious attack that collapses the security. In literature, some of the methods are reviewed to detect Sybil attacks in VANETs, but it fails to achieve Sybil attack detection. Hence, in this paper, Emperor Penguin Optimization-based Routing protocol (EPORP) is developed for detecting the Sybil attack which enhances the VANETs security. The main motive of the research is detecting the Sybil attack in VANETs for enhancing the secure operation. In the proposed approach, the Sybil attack will be detected with the help of the Rumour riding technique. To enhance the security of the VANETs, the Split XOR (SXOR) operation is utilized. In the SXOR operation, the optimal key is selected with the help of Emperor Penguin Optimization (EPO). The proposed method is implemented in the NS2 platform and performances are evaluated by metrics such as delay, throughput, delay, encryption time, and decryption time. The proposed method is compared with existing methods such as Whale Optimization Algorithm (WOA), Particle Swarm Optimization (PSO), and Firefly Algorithm (FA) respectively. While analyzing the delivery ratio, the proposed method has 0.96 s, and the WOA, PSO, and FA are 0.94, 0.92, and 0.90 respectively. From the analysis, the proposed method has a high delivery ratio value compared with the WOA, PSO, and FA methods. Similarly, the other parameters are analyzed and compared with the existing methods.

/pdf/sybil-attack-with-rsu-detection-and-location-privacy-in-18s5qw7wwx.pdf

Sybil Attack with RSU Detection and Location Privacy in Urban VANETs: An Efficient EPORP Technique

Networking technology in the present scenario has the latest invention called ad hoc networks. VANET is a type of ad hoc network where vehicles communicate with each other in a network. From the last few decades, VANET is becoming popular where relocation, mobility, and converge of location by the vehicles were impossible to achieve by using a wired network. VANET provides the growth of intelligent transport systems by providing safety and comfort consideration for both drivers and passengers. VANET is an open-access network that may prone to various types of attacks. This paper is an overview of the study of various attacks in VANET focusing on Sybil attack in VANET which operates under the urban environment. A comparison of different methods of detection technique for Sybil attack is also included.

Sybil Attack in VANET Operating in an Urban Environment: An Overview

Health Care sector profoundly have found use for Artificial Intelligent Clinical Decision Support Systems (AI- CDSS) in making critical decisions using the prediction results of these systems. The minimizations of medical errors are the result of continuous diagnosis process that assists in making more informed and efficient decisions. However, the conventional Artificial Intelligence methodologies are not efficient enough to diagnose or predict heart failure rate in the absence of heart specialists. The paper proposes a hybrid model of Optimized Artificial Neural Network-Artificial Bee Colony (ABC) that could be employed to improve the prediction by using machinelearning approach to obtain the precise diagnosis of heart. Consequently, the proposed method also measures and compares the accuracy by improving the existing AI-CDSS prediction. In addition, the concordance rate between proposed hybrid AI- CDSS and state of art methods in Heart Failure (HF) was measured. The model provides a better accuracy for concordance rate with 99.3% proving that high diagnostic accuracy is obtained for the interpretation of heart failure than the existing conventional methods.

Designing a Hybrid Artificial Intelligent Clinical Decision Support System Using Artificial Neural Network and Artificial Bee Colony for Predicting Heart Failure Rate

Vehicular Ad hoc Network (VANET) has recently gained significant attention as a means of enhancing the mobility, efficiency, and safety of applications in the intelligent transportation system. However, because of its high-speed mobility, wireless connectivity, and extensive node coverage, security is a more difficult procedure. The Sybil security threat on VANET is a growing problem today. The Road Side Unit (RSU) failed to synchronise its clock with the legal vehicle, then unplanned vehicles are predicted, thereby incorrect messages are transferred to them. In this paper, Competitive Dolphin Echolocation Optimisation (CDEO)-based Deep Residual Network is proposed for Sybil attack and RSU misbehaviour detection. Here, the effective routing process is performed using Fractional Glow-Worm Swarm Optimisation (FGWSO)-based traffic-aware routing protocol. In the base station, the Sybil attack detection is done. The Sybil attack detection process is done using a Deep residual network, which is trained by the proposed CDEO algorithm. The CDEO algorithm is devised by incorporating Dolphin Echolocation Optimisation (DEO) technique and Competitive Swarm Optimiser (CSO). Additionally, using the Deep residual network, the RSU misbehaviour detection is done. The performance of the developed method is compared with certain performance metrics, like precision, F1-measure, and recall of 0.9197, 0.9121, and 0.9046. 

Nitha C. Velayudhan

Papers

Sybil attack detection and secure data transmission in VANET using CMEHA-DNN and MD5-ECC

Sybil Attack with RSU Detection and Location Privacy in Urban VANETs: An Efficient EPORP Technique

Sybil Attack in VANET Operating in an Urban Environment: An Overview

Designing a Hybrid Artificial Intelligent Clinical Decision Support System Using Artificial Neural Network and Artificial Bee Colony for Predicting Heart Failure Rate

An Optimisation driven Deep Residual Network for Sybil attack detection with reputation and trust-based misbehaviour detection in VANET