The modern scientific world continuously endeavors to battle and devise solutions for newly arising pandemics. One such pandemic which has turned the world’s accustomed routine upside down is COVID-19: it has devastated the world economy and destroyed around 45 million lives, globally. Governments and scientists have been on the front line, striving towards the diagnosis and engineering of a vaccination for the said virus. COVID-19 can be diagnosed using artificial intelligence more accurately than traditional methods using chest X-rays. This research involves an evaluation of the performance of deep learning models for COVID-19 diagnosis using chest X-ray images from a dataset containing the largest number of COVID-19 images ever used in the literature, according to the best of the authors’ knowledge. The size of the utilized dataset is about 4.25 times the maximum COVID-19 chest X-ray image dataset used in the explored literature. Further, a CNN model was developed, named the Custom-Model in this study, for evaluation against, and comparison to, the state-of-the-art deep learning models. The intention was not to develop a new high-performing deep learning model, but rather to evaluate the performance of deep learning models on a larger COVID-19 chest X-ray image dataset. Moreover, Xception- and MobilNetV2- based models were also used for evaluation purposes. The criteria for evaluation were based on accuracy, precision, recall, F1 score, ROC curves, AUC, confusion matrix, and macro and weighted averages. Among the deployed models, Xception was the top performer in terms of precision and accuracy, while the MobileNetV2-based model could detect slightly more COVID-19 cases than Xception, and showed slightly fewer false negatives, while giving far more false positives than the other models. Also, the custom CNN model exceeds the MobileNetV2 model in terms of precision. The best accuracy, precision, recall, and F1 score out of these three models were 94.2%, 99%, 95%, and 97%, respectively, as shown by the Xception model. Finally, it was found that the overall accuracy in the current evaluation was curtailed by approximately 2% compared with the average accuracy of previous work on multi-class classification, while a very high precision value was observed, which is of high scientific value.

Graphical abstract

Nowadays, traffic congestion and increasing road accidents have become a major concern for both developed and developing countries. To overcome this challenge, an internet of things- (IoT-) based Vehicular Ad Hoc Network (VANET) system is proposed in which vehicles interact with other vehicles and infrastructure. These self-organized ad hoc vehicle networks not only boost traffic safety but also enhances the efficiency of traffic management systems. The VANET systems are beneficial in busy locations, where improved data dissemination protocols are used to categorize a vehicle’s transmission. However, the performance of these VANETs is also hampered by network splits and insufficient connections. Under these situations, the proposed simulation model reduces broadcast storms by minimizing redundancies, which is equally beneficial for both rural and urban settings. The suggested Next Forwarder Vehicle (NFV) protocol is based on three factors: position, distance, and orientation. Moreover, the DDP4V technique is used to analyse each of these features. Results indicate that DDP4V is compatible with 96% of all traffic scenarios and simulation durations. It can transport data packets 60% faster due to its broadcast suppression capabilities. Also, in comparison to AID and DBRS, DDP4V has fewer dispersed packets, which results into reduced retransmissions. For 200 automobiles/km2, all these techniques accomplish 35–40% of the needed cars. However, the coverage also faces some restrictions since data packets only reach vehicles on the same side as the originating vehicle. Similarly, DDP4V delivers 90% coverage for 400 vehicles/km2, which is 30% greater than prior techniques. It is observed that the proposed protocol reduces broadcast storms by employing a waggon wheel to choose the next forwarding vehicle. In high-traffic areas, it outperforms standard techniques. Similarly, it employs a patchwork of vehicles outside of the impacted region to convey data. The industrial IoT-based VANETs provide an effective tool to monitor and control traffic besides reducing the number of traffic accidents.

Sentiment analysis is a method to identify people’s attitudes, sentiments, and emotions towards a given goal, such as people, activities, organizations, services, subjects, and products. Emotion detection is a subset of sentiment analysis as it predicts the unique emotion rather than just stating positive, negative, or neutral. In recent times, many researchers have already worked on speech and facial expressions for emotion recognition. However, emotion detection in text is a tedious task as cues are missing, unlike in speech, such as tonal stress, facial expression, pitch, etc. To identify emotions from text, several methods have been proposed in the past using natural language processing (NLP) techniques: the keyword approach, the lexicon-based approach, and the machine learning approach. However, there were some limitations with keyword- and lexicon-based approaches as they focus on semantic relations. In this article, we have proposed a hybrid (machine learning + deep learning) model to identify emotions in text. Convolutional neural network (CNN) and Bi-GRU were exploited as deep learning techniques. Support vector machine is used as a machine learning approach. The performance of the proposed approach is evaluated using a combination of three different types of datasets, namely, sentences, tweets, and dialogs, and it attains an accuracy of 80.11%.

In this new information era, the transfer of data and information has become a very important matter. Transferred data must be kept secured from unauthorized persons using cryptography. The science of cryptography depends not only on complex mathematical models but also on encryption keys. Amino acid encryption is a promising model for data security. In this paper, we propose an amino acid encryption model with two encryption keys. The first key is generated randomly using the genetic algorithm. The second key is called the protein key which is generated from converting DNA to a protein message. Then, the protein message and the first key are used in the modified Playfair matrix to generate the cypher message. The experimental results show that the proposed model survives against known attacks such as the Brute-force attack and the Ciphertext-only attack. In addition, the proposed model has been tested over different types of characters including white spaces and special characters, as all the data is encoded to 8-bit binary. The performance of the proposed model is compared with other models using encryption time and decryption time. The model also balances all three principles in the CIA triad.