The Internet of Things (IoT) has become a popular computing technology paradigm. It is increasingly being utilized to facilitate human life processes through a variety of applications, including smart healthcare, smart grids, smart finance, and smart cities. Scalability, interoperability, security, and privacy, as well as trustworthiness, are all issues that IoT applications face. Blockchain solutions have recently been created to help overcome these difficulties. The purpose of this paper is to provide a survey and tutorial on the use of blockchain in IoT systems. The importance of blockchain technology in terms of features and benefits for constituents of IoT applications is discussed. We propose a blockchain taxonomy for IoT applications based on the most significant factors. In addition, we examine the most widely used blockchain platforms for IoT applications. Furthermore, we discuss how blockchain technology can be used to broaden the spectrum of IoT applications. Besides, we discuss the recent advances and solutions offered for IoT environments. Finally, we discuss the challenges and future research directions of the use of blockchain for the IoT.

Quality of Service (QoS) refers to techniques that function on a network to dependably execute high-priority applications and traffic reliably run high-priority applications and traffic even when the network’s capacity is limited. It is expected that data transmission over next-generation WSNs (Wireless Sensor Networks) 5G (5th generation) and beyond will increase significantly, especially for multimedia content such as video. Installing multiple IoT (Internet of Things refers to the network of devices that are all connected to each other) nodes on top of 5G networks makes the design more challenging. Maintaining a minimal level of service quality becomes more challenging as data volume and network density rise. QoS is critical in modern networks because it ensures critical performance metrics and improves end-user experience. Every client attempts to fulfill QoS access needs by selecting the optimal access device(s). Controllers will then identify optimum routes to meet clients’ core QoS needs in their core network. QoS-aware delivery is one of the most important aspects of wireless communications. Various models are proposed in the literature; however, an adaptive buffer size according to service type, priority, and incoming communication requests is required to ensure QoS-aware wireless communication. This article offers a hybrid end-to-end QoS delivery method involving customers and controllers and proposes a QoS-aware service delivery model for various types of communication with an adaptive buffer size according to the priority of the incoming service requests. For this purpose, this paper evaluates various QoS delivery models devised for service delivery in real time over IP networks. Multiple vulnerabilities are outlined that weaken QoS delivery in different models. Performance optimization is needed to ensure QoS delivery in next-generation WSN networks. This paper addresses the shortcomings of the existing service delivery models for real-time communication. An efficient queuing mechanism is adopted that assigns priorities based on input data type and queue length. This queuing mechanism ensures QoS efficiency in limited bandwidth networks and real-time traffic. The model reduces the over-provisioning of resources, delay, and packet loss ratio. The paper contributes a symmetrically-designed traffic engineering model for QoS-ensured service delivery for next-generation WSNs. A dynamic queuing mechanism that assigns priorities based on input data type and queue length is proposed to ensure QoS for wireless next-generation networks. The proposed queuing mechanism discusses topological symmetry to ensure QoS efficiency in limited bandwidth networks with real-time communication. The experimental results describe that the proposed model reduces the over-provisioning of resources, delay, and packet loss ratio.

With the growing number of cloud users, shared data auditing is becoming increasingly important. However, these schemes have issues with the certificate management. Although there is a certificate-shared auditing scheme, it is ineffective in dealing with dynamic data and protecting data privacy. The verifier cannot access the data content to ensure data integrity due to security concerns. This paper proposes a novel technique to ensure the integrity and improve the access control. A novel enhanced storage retrieval mechanism is used to improve the performance of the cloud’s storage and retrieval mechanisms to achieve this. The technique is evaluated in concern of the upload, download, encryption, and decryption time. As the file size grows, so does the time it takes to upload it. Similarly, the time taken to encrypt files of various formats and sizes evidenced that it depends on the file size and format. Thus, the encryption time increases as the file sizes increases, demonstrating the performance of the proposed system.

In medical informatics, deep learning-based models are being used to predict and diagnose cardiovascular diseases (CVDs). These models can detect clinical signs, recognize phenotypes, and pick treatment methods for complicated illnesses. One approach to predicting CVDs is to collect a large dataset of patient medical records and use it to train a deep learning model. This study investigated CVDs for early prediction using deep learning-based regression analysis on a dataset of 2621 medical records from UAE hospitals, including age, symptoms, and CVD information. We propose a long short-term memory-based deep neural network for early prediction of CVDs by leveraging the regression analysis. It can be seen that the accuracy level of the diseases increased when they were simulated in pairs of one disease with another due to the overlapping symptoms. The study’s results suggest that coronary heart disease has been predicted with an 71.5% accuracy level, with 84.4% overlapping with Dyspnea; when accuracy measured with a combination of three conditions the accuracy was 86.7%, Dyspnea, Chest Pain, and Cyanosis, it has been increased up to 88.9%. Weakness, Fatigue, and Emptysis showed a value of 89.8%. In our proposed work, the combinations were Dyspnea, Chest Pain, Cyanosis, Weakness and Fatigue, Emptysis, and discomfort pressure in the chest have shown the ideal value of accuracy measured up to 90.6%, and with Fever, the accuracy is 91%. We show the effectiveness of our proposed method on several evaluation benchmarks.

The analysis of individuals’ movement behaviors is an important area of research in geographic information sciences, with broad applications in smart mobility and transportation systems. Recent advances in information and communication technologies have enabled the collection of vast amounts of mobility data for investigating movement behaviors using trajectory data mining techniques. Trajectory clustering is one commonly used method, but most existing methods require a complete similarity matrix to quantify the similarities among users’ trajectories in the dataset. This creates a significant computational overhead for large datasets with many user trajectories. To address this complexity, an efficient clustering-based method for network constraint trajectories is proposed, which can help with transportation planning and reduce traffic congestion on roads. The proposed algorithm is based on spatiotemporal buffering and overlapping operations and involves the following steps: (i) Trajectory preprocessing, which uses an efficient map-matching algorithm to match trajectory points to the road network. (ii) Trajectory segmentation, where a Compressed Linear Reference (CLR) technique is used to convert the discrete 3D trajectories to 2D CLR space. (iii) Spatiotemporal proximity analysis, which calculates a partial similarity matrix using the Longest Common Subsequence similarity indicator in CLR space. (iv) Trajectory clustering, which uses density-based and hierarchical clustering approaches to cluster the trajectories. To verify the proposed clustering-based method, a case study is carried out using real trajectories from the GeoLife project of Microsoft Research Asia. The case study results demonstrate the effectiveness and efficiency of the proposed method compared with other state-of-the-art clustering-based methods.

Multiple sclerosis impacts the central nervous system, causing symptoms like fatigue, pain, and motor impairments. Diagnosing multiple sclerosis often requires complex tests, and MRI analysis is critical for accuracy. Machine learning has emerged as a key tool in neurological disease diagnosis. This paper introduces the multiple sclerosis diagnosis network (MSDNet), a stacked ensemble of deep learning classifiers for multiple sclerosis detection. The MSDNet uses min-max normalization, the artificial hummingbird algorithm for feature selection, and a combination of LSTM, DNN, and CNN models. Hyperparameters are optimized using the enhanced walrus optimization algorithm. Experimental results show MSDNet's superior performance compared to recent methods.