The COVID-19 emerged at the end of 2019 and has become a global pandemic. There are many methods for COVID-19 prediction using a single modality. However, none of them predicts with 100% accuracy, as each individual exhibits varied symptoms for the disease. To decrease the rate of misdiagnosis, multiple modalities can be used for prediction. Besides, there is also a need for a self-diagnosis system to narrow down the risk of virus spread in testing centres. Therefore, we propose a robust IoT and deep learning-based multi-modal data classification method for the accurate prediction of COVID-19. Generally, highly accurate models require deep architectures. In this work, we introduce two lightweight models, namely CovParaNet for audio (cough, speech, breathing) classification and CovTinyNet for image (X-rays, CT scans) classification. These two models were identified as the best unimodal models after comparative analysis with the existing benchmark models. Finally, the obtained results of the five independently trained unimodal models are integrated by a novel dynamic multimodal Random Forest classifier. The lightweight CovParaNet and CovTinyNet models attain a maximum accuracy of 97.45% and 99.19% respectively even with a small dataset. The proposed dynamic multimodal fusion model predicts the final result with 100% accuracy, precision, and recall, and the online retraining mechanism enables it to extend its support even in a noisy environment. Furthermore, the computational complexity of all the unimodal models is minimized tremendously and the system functions effectively with 100% reliability even in the absence of any one of the input modalities during testing.

IPv6 mobility is an IETF standard that has added roaming capabilities of mobile node (MN). It allows MNs to travel from one network to another without any distraction in communication service. MNs register their current location to home stations and correspondent hosts via a process known as binding update. In IPv6 mobility, return routability protocol (RRP) is a standard procedure for updating the current location of MNs through binding update message to their communicants. However, RRP has several security threats and issues. Subsequently, RRP was integrated with identity-based encryption for improvement of security. Nevertheless, it suffers from some limitations such as inherent key escrow problem, lack of key revocation, high computational load and latency while providing security. Hence, this paper proposes a novel approach called optimised RRP using certificateless public key encryption to address these issues. The proposed protocol is simulated and validated using Automated Validation of Internet Security Protocols and Applications (AVISPA)-a model checker. Finally, the simulation and numerical results illustrate the extent to which the proposed protocol surpasses the existing method in terms of enhanced security and significant reduction in communication payload with minimised latency.

No abstract

Nowadays people using the internet for shopping, banking, mailing etc. Phishing is one of the major attacks on the website which people are facing in their day to day life. A phishing attack is one of cybercrime because it is the illegal attempt that gets sensitive information of the user such as username, password, and credit card detail. Too aware of such phishing attacks taken online so in this paper have to detect phishing Uniform Resource Locator (URL), that is, we loading the URL data from the Kaggle open source website which is an online community of data scientists and machine learning, owned by Google Limited Liability Company( LLC). In most of the phishing website, the attackers use a malicious URL which will display to the user like an authorized URL. Different algorithms like Naive Bayes, Random Forest, K nearest neighbor are performed in detection of the URL, by using algorithm their accuracy level will be different. So in this paper can adopt the best classification machine learning algorithm with SVM (Support Vector Machine), this predicts the phishing or non-phishing status of the given URL and it is the best algorithm in classification (based on the features of given data) and regression (is the continuous prediction of uniform data) from which we have to improve our accuracy level.

No abstract