The autonomous connected ambulance (ACA) has been an unprecedented necessity in the demand–supply management sector of the healthcare sector. However, the traditional prototypes designed for such an unmanned vehicle do not match the demands of the advanced communication technologies incorporated in today’s sophisticated distributed networks. As a result, in the current era of edge computing strengthened by many AI-enabled algorithms, there is an urgent need to design a route resource recommendation (R3) protocol for ACA under Edge-AI. Designing such a protocol requires addressing the major challenges to optimize the routes for ACA and, thereby, enhance the services of emergency eHealth centers through a governing telehealth monitoring administrator. Therefore, in this article, a dedicated and novel ACA-R3 protocol is proposed to address the issues of connectivity and resource management in ACA to optimize the routes for ACA. The ACA-R3 protocol abides by the operational standards of both the eHealth protocol and governing protocol. The primary objective of the current research work was to reduce the handover time and simplify the patient-information exchange during the time of demanded emergencies. The proposed ACA-R3 protocol can enhance the collaborative distributive resource management for reliable decision making from the data generated by the GPS tracking unit in ACA and Edge-AI. The experimental results obtained from three different cases of traffic congestion are evaluated, validated, and reported in this article.

Road traffic crashes are one of the prime issues in the world. Every year 1.35 million people die, 20–50 million fatal injuries, and many incur a disability due to road traffic crashes. 50% of the total death, injuries, and disabilities are among vulnerable road users (VRUs), such as motorcyclists, cyclists, and pedestrians. Among these VRUs, highly vulnerable is pedestrians. In this article, we are dealing with providing safety and alert system to pedestrians and vehicles to reduce and/or avoid the causes of road traffic crashes in metropolitan areas. In this article, we develop a cooperative communication framework between pedestrians and nearby vehicles as well as traffic light systems using mobile agent systems and apps. The proposed cooperative communication framework controls the mobility of vehicles as well as pedestrians to avoid accidents. We have developed an application that will notify the pedestrian if there is any automobile within the range of 200 m of the pedestrian. If there are any vehicles in this range, using direct Wi-Fi, connect the vehicles and pedestrians to notify them about their presence of them. The proposed system is implemented and tested in real time as well as simulated in the SUMO, Veins, OMNeT++, and MiXiM simulator. The proposed system’s results (real time, simulation, and comparison) show real-time deployability, accuracy, and reliability.

Industrial cloud computing and Internet of Things have transformed the healthcare industry with the rapid growth of distributed healthcare data. Security and privacy of healthcare data are crucial challenges in the healthcare industry. This article proposes a novel technique using deep learning and blockchain techniques for electronic health record privacy-preservation. The processed dataset classified normal and abnormal users using the convolutional neural network approach. Then, by using blockchain integrated with a cryptography-based federated learning module, the abnormal users have been processed and removed from the database along with the accessibility for the health records. The simulation has been done in the Python tool and experimental results show that the model’s classification results and performance are better than other existing techniques.

Coronavirus disease (COVID-19) is a harmful disease caused by the new SARS-CoV-2 virus. COVID-19 disease comprises symptoms such as cold, cough, fever, and difficulty in breathing. COVID-19 has affected many countries and their spread in the world has put humanity at risk. Due to the increasing number of cases and their stress on administration as well as health professionals, different prediction techniques were introduced to predict the coronavirus disease existence in patients. However, the accuracy was not improved, and time consumption was not minimized during the disease prediction. To address these problems, least square regressive Gaussian neuro-fuzzy multi-layered data classification (LSRGNFM-LDC) technique is introduced in this article. LSRGNFM-LDC technique performs efficient COVID prediction with better accuracy and lesser time consumption through feature selection and classification. The preprocessing is used to eliminate the unwanted data in input features. Preprocessing is applied to reduce the time complexity. Next, Deming Least Square Regressive Feature Selection process is carried out for selecting the most relevant features through identifying the line of best fit. After the feature selection process, Gaussian neuro-fuzzy classifier in LSRGNFM-LDC technique performs the data classification process with help of fuzzy if-then rules for performing prediction process. Finally, the fuzzy if-then rule classifies the patient data as lower risk level, medium risk level and higher risk level with higher accuracy and lesser time consumption. Experimental evaluation is performed by Novel Corona Virus 2019 Dataset using different metrics like prediction accuracy, prediction time, and error rate. The result shows that LSRGNFM-LDC technique improves the accuracy and minimizes the time consumption as well as error rate than existing works during COVID prediction.

Abstract Lung cancer is a worldwide precarious disease and it is encouraged by the abnormal growth of cells in bronchi. Spotting the cancer cells is unknown until it leads to respiration issues and the muddling of organs working. Due to problems, limited or incorrect selection of hypothesis space, and dropping into local minima, single learners often give erratic output in an existing approach. The ensemble method accomplished a dataset that is free and composed of computed tomography (CT) images. The annotation process reveals observed lung lesions and provides a degree of malignancy for each lesion. Detection of benign and malignant nodules is recognized using deep convolutional frameworks AlexNet, SqueezeNet, GoogleNet, ResNet, and Inception ResNet, achieves higher accuracy (93%) than other convolutional neural networks (CNNs). Eight machine learning methods are involved for achieving better performance. The prediction probability obtained from CNN is applied as input to support vector machines (SVM), K‐nearest neighbours (KNN), naive Bayes (NB), multi‐layer perceptron (MLP), decision trees (DT), gradient boosted regression trees (GBRT), and adaptive boosting. The composition of GoogleNet model and AdaBoost classifier reached the most coherent classification accuracy as 99%. This is one of the best ways to analyse early detection and it increases the survival rate. Therefore, the result from the proposed deep CNN and ML technique achieves better precision than sputum cytology, X‐Ray process, and earlier detection of lung cancer.

Internet-of-Things (IoT) enabled cyber-physical systems (CPS) is a system in which communication between the physical devices and the cyber environment runs independently without any user interaction. Several optimization algorithms have been used for determining the optimal solutions that can reduce the production cost and/or enhance the production efficiency with in limited time-periods. However, existing optimization approaches have failed to solve the issues in the complex manufacturing process. To overcome this issue, a novel technique called directed acyclic graph theory based multiobjective oppositional learnt artificial ant colony resource optimization (DAGT-MOLAACRO) technique has been introduced in this study for solving the complex manufacturing process in the industry. Initially, IoT devices are used in the industrial sector for sensing and collecting data. Then the collected data is sent to the cyberspace of the CPS system with the least latency. Then, the CPS system collects the data generated from the industrial IoT devices that is stored in cyberspace with lesser memory consumption. MOLAACRO is applied to find the optimal solution among the population that satisfies the resource constraints by constructing the directed acyclic graph. In this way, the DAGT-MOLAACRO technique reduces the time complexity with minimal latency and computation overhead. For verification purposes, our experimental work has been carried out using different performance metrics such as data latency, time complexity, and computation overhead with respect to the number of IoT devices and the amount of data collected. The results show that the DAGT-MOLAACRO technique has better performance with reductions in terms of time complexity by 10%, latency by 17%, and the computation overhead by 11% against the existing works in literature.

Internet of Things (IoT) data is one of the most important assets in business models for offering various ubiquitous and brilliant services. The IoT is provided with the advantage of susceptibility that cybercriminals and other malicious users. Even though smart cities are intended to extend productivity and efficiency, residents and authorities face risks when they avoid cybersecurity. The conventional blockchain methods were introduced to ensure the secure management and examination of the smart city big data. But, the blockchains are found to have computationally high costs, and failed to improve the security, not adequate resource-constrained IoT devices have been designated for smart cities. In order to address these issues, the proposed novel blockchain model called blockchain secured Merkle hash zero correlation distinguisher (BSMH-ZCD) is suitable for IoT devices within the cloud infrastructure. The objective of the BSMH-ZCD method is to enhance security and reduce the run time and computational overhead. Initially, the Merkle hash tree is used to create the hash value with every transaction. Next, the zero correlation distinguisher is applied to perform the data encryption and decryption operation for the ARX block for obtaining proficient secure data access in the IoT devices. Experimental assessment of the proposed BSMH-ZCD method and existing methods are carried out by using the taxi driver data set and Novel Corona Virus 2019 data set with different factors, such as running time, computational complexity, and security with respect to a number of blocks and executions. By using the taxi driver data set, the experimental results reveal that the BSMH-ZCD method performs better with a 19% improvement in security, 20% reduction of computational complexity, and 29% faster running time for IoT compared to existing works.

Search engine optimization (SEO) is a significant problem for enhancing a website's visibility with search engine results. SEO issues, such as Site Popularity, Content Quality, Keyword Density, and Publicity, were not considered during the search engine optimization process. Therefore, the retrieval rate of the existing techniques is inadequate. In this study, Triangular Fuzzy Deep Structured Learning-Based Predictive Page Ranking (TFDSL-PPR) technique is proposed to solve these limitations. First, the TFDSL-PPR technique takes a number of user queries as input in the input layer, and then it employs four hidden layers in order to deeply analyze the web pages based on an input query. The first hidden layer determines the keywords from the user query. The second hidden layer measures the site popularity, content quality, keyword density and publicity of all web pages in the search engine. It then accomplishes Goodman and Kruskal's Gamma Predictive Ranking process in the third hidden layer, where it ranks the web pages by considering their similarities. The proposed TFDSL-PPR technique is applied to the ClueWeb09 Dataset with respect to a variety of user queries. The results are benchmarked by existing methods based on several metrics such as retrieval rate, time, and false-positive rate.

Abstract Internet of things (IoTs) enabled cyber‐physical systems is a system that provides communication between physical devices and cyber environment. They run independently without any user interaction. Because the IoT devices are vulnerable to a variety of attacks, security is a noteworthy factor in the development process during communication. To improve secure communication with minimum time consumption, a novel technique called jackknife regressive Schmidt Samoa cryptography‐based deep artificial structure learning (JRSSC‐DASL) is introduced. Initially, the data is monitored by IoT devices and is collected from the dataset. The proposed deep artificial structure learning technique trains the gathered data with multiple layers. Then, the collected data is analysed in the first hidden layer with the help of the jackknife regression function by learning the feature and it classifies the data with higher accuracy. The classified data is sent to the next hidden layer where encryption is performed using Schmidt Samoa (SS) encryption algorithm. Then, the encrypted data is sent to the cloud server where the decryption is performed using the SS decryption algorithm. The cloud server obtains the original data and it is stored in their database for further processing. This process enhances the security of data communication and achieves high data confidentiality with less processing time. Experimental estimation is performed on the factors such as classification accuracy, confidentiality rate, processing time and memory usage to the number of data sensed from IoT device. Conferred results reveal that the proposed JRSSC‐DASL technique has high confidentiality rate and minimum processing time as well as memory usage when compared to state‐of‐the‐art methods.

Deep learning artificial intelligence (AI) is a booming area in the research field. It allows the development of end-to-end models to predict outcomes based on input data without the need for manual extraction of features. This paper aims for evaluating the automatic crack detection process that is used in identifying the cracks in building structures such as bridges, foundations or other large structures using images. A hybrid approach involving image processing and deep learning algorithms is proposed to detect automatic cracks in structures. As cracks are detected in the images they are segmented using a segmentation process. The proposed deep learning models include a hybrid architecture combining Mask R-CNN with single layer CNN, 3-layer CNN, and8-layer CNN. These models utilizes depth wise convolution with varying dilation rates for efficiently extracting diversified features from the crack images. Further, performance evaluation shows that Mask R-CNN with a single layer CNN achieves an accuracy of 97.5% on a normal dataset and 97.8% on a segmented dataset. The Mask R-CNN with 2-layer convolution resulted in an accuracy of 98.32% on a normal dataset and 98.39% on a segmented dataset. The Mask R-CNN with 8-layers convolution achieves an accuracy of 98.4% on a normal dataset and 98.75% on a segmented dataset. The proposed Mask R-CNN have proved its feasibility in detecting cracks in huge building and structures.

In Medicine Deep Learning has become an essential tool to achieve outstanding diagnosis on image data. However, one critical problem is that Deep Learning comes with complicated, black-box models so it is not possible to analyze their trust level directly. So, Explainable Artificial Intelligence (XAI) methods are used to build additional interfaces for explaining how the model has reached the outputs by moving from the input data. Of course, that's again another competitive problem to analyze if such methods are successful according to the human view. So, this paper comes with two important research efforts: (1) to build an explainable deep learning model targeting medical image analysis, and (2) to evaluate the trust level of this model via several evaluation works including human contribution. The target problem was selected as the brain tumor classification, which is a remarkable, competitive medical image-based problem for Deep Learning. In the study, MR-based pre-processed brain images were received by the Subtractive Spatial Lightweight Convolutional Neural Network (SSLW-CNN) model, which includes additional operators to reduce the complexity of classification. In order to ensure the explainable background, the model also included Class Activation Mapping (CAM). It is important to evaluate the trust level of a successful model. So, numerical success rates of the SSLW-CNN were evaluated based on the peak signal-to-noise ratio (PSNR), computational time, computational overhead, and brain tumor classification accuracy. The objective of the proposed SSLW-CNN model is to obtain faster and good tumor classification with lesser time. The results illustrate that the SSLW-CNN model provides better performance of PSNR which is enhanced by 8%, classification accuracy is improved by 33%, computation time is reduced by 19%, computation overhead is decreased by 23%, and classification time is minimized by 13%, as compared to state-of-the-art works. Because the model provided good numerical results, it was then evaluated in terms of XAI perspective by including doctor-model based evaluations such as feedback CAM visualizations, usability, expert surveys, comparisons of CAM with other XAI methods, and manual diagnosis comparison. The results show that the SSLW-CNN provides good performance on brain tumor diagnosis and ensures a trustworthy solution for the doctors.