Search

Virtual Reality (VR) is a key industry for the development of the digital economy in the future. Mobile VR has advantages in terms of mobility, lightweight and cost-effectiveness, which has gradually become the mainstream implementation of VR. In this paper, a mobile VR video adaptive transmission mechanism based on intelligent caching and hierarchical buffering strategy in Mobile Edge Computing (MEC)-equipped 5G networks is proposed, aiming at the low latency requirements of mobile VR services and flexible buffer management for VR video adaptive transmission. To support VR content proactive caching and intelligent buffer management, users' behavioral similarity and head movement trajectory are jointly used for viewpoint prediction. The tile-based content is proactively cached in the MEC nodes based on the popularity of the VR content. Second, a hierarchical buffer-based adaptive update algorithm is presented, which jointly considers bandwidth, buffer, and predicted viewpoint status to update the tile chunk in client buffer. Then, according to the decomposition of the problem, the buffer update problem is modeled as an optimization problem, and the corresponding solution algorithms are presented. Finally, the simulation results show that the adaptive caching algorithm based on 5G intelligent edge and hierarchical buffer strategy can improve the user experience in the case of bandwidth fluctuations, and the proposed viewpoint prediction method can significantly improve the accuracy of viewpoint prediction by 15%.

The application of artificial intelligence technology in Internet of Vehicles (IoV) has attracted great research interests with the goal of enabling smart transportation and traffic management. Meanwhile, concerns have been raised over the security and privacy of the tons of traffic and vehicle data. In this regard, Federated Learning (FL) with privacy protection features is considered a highly promising solution. However, in the FL process, the server side may take advantage of its dominant role in model aggregation to steal sensitive information of users, while the client side may also upload malicious data to compromise the training of the global model. Most existing privacy-preserving FL schemes in IoV fail to deal with threats from both of these two sides at the same time. In this paper, we propose a Blockchain based Privacy-preserving Federated Learning scheme named BPFL, which uses blockchain as the underlying distributed framework of FL. We improve the Multi-Krum technology and combine it with the homomorphic encryption to achieve ciphertext-level model aggregation and model filtering, which can enable the verifiability of the local models while achieving privacy-preservation. Additionally, we develop a reputation-based incentive mechanism to encourage users in IoV to actively participate in the federated learning and to practice honesty. The security analysis and performance evaluations are conducted to show that the proposed scheme can meet the security requirements and improve the performance of the FL model.

Human Activity Recognition (HAR) has seen remarkable advances in recent years, driven by the widespread use of wearable devices and the increasing demand for personalized healthcare and activity tracking. Federated Learning (FL) is a promising paradigm for HAR that enables the collaborative training of machine learning models on decentralized devices while preserving data privacy. It improves not only data privacy but also training efficiency as it utilizes the computing power and data of potentially millions of smart devices for parallel training. In addition, it helps end-user devices avoid sending users’ private data to the cloud, eliminates the need for a network connection, and saves the latency of back-and-forth communication. FL also offers significant advantages for communication by reducing the amount of data transmitted over the network, alleviating network congestion and reducing communication costs. By distributing the training process across devices, FL minimizes the need for centralized data storage and processing, leading to more scalable and resilient systems. This paper provides a comprehensive survey of the integration of FL into HAR applications. Unlike existing reviews, this paper uniquely focuses on the intersection of FL and HAR, providing an in-depth analysis of recent advances and their practical implications. We explore key advances in FL-based HAR methodologies, including model architectures, optimization techniques, and different applications. Furthermore, we highlight the major challenges and future research questions in this domain, such as model personalization and robustness, privacy concerns, concept drift, and the limited capacity of edge devices.

The wireless communication landscape in beyond 5G and 6G systems, particularly in dense smart city environments, presents significant interference challenges. UAV-mounted Reconfigurable Intelligent Surfaces (RIS) offer a promising solution to counter interference from unknown jammers. However, the system’s dynamic nature, especially real-time fluctuations in device and jammer distribution and UAV resources, complicates UAV and RIS management. Current approaches, which rely on a single UAV-mounted RIS or a fixed number of UAVs covering static device clusters, fail to adapt to these dynamic conditions. Smaller swarms may lead to inadequate coverage, while larger swarms can cause inefficiency and higher energy consumption. Additionally, these approaches often target a single objective, such as maximizing sum rates or minimizing energy use, without considering UAV battery constraints. Our work introduces an adaptive UAV swarm formation and dynamic device clustering technique designed for efficient anti-jamming in dynamic multi-user clusters threatened by unknown jammers during critical public events. This approach creates a flexible UAV-borne RIS swarm that dynamically adjusts the number of UAVs and the clustering to real-time changes of mobile devices and jammers, ensuring uninterrupted operations through UAV recharging and swapping while conserving total energy by deploying the minimum sufficient number of UAVs. Using Reinforcement Learning (RL), our solution optimizes the number of UAVs, device-to-UAV associations, UAV trajectories, RIS phase shifts, and base station power to effectively balance the sum rate and energy consumption. Simulations demonstrate the superior performance of our approach in coverage, jamming mitigation, energy conservation, connectivity, and scalability compared to existing methods and baselines.

As next-generation networking environments become increasingly complex and integral to the fabric of digital transformation as the traditional perimeter-based security model proves inadequate. The Zero Trust framework emerges as a critical solution to this challenge, advocating for a security model that assumes no implicit trust and requires verification at every step. The rapid growth of the Internet of Things (IoT) creates an environment of millions of interacting devices that radically transform today’s digital environment. In such conditions, the problem of identifying malicious and compromised nodes among IoT devices becomes mandatory to maintain trustworthy environment. The main objective of this research is to implement an advanced trust management mechanism, with the main transformation on the framework of security within which IoT environments become workable. To overcome this, an approach based on intelligent ensemble learning is presented in this paper by formulating a dataset consists of IoT-23, N-BaIoT, Edge-IIoTset, and AutoTrust-IoTDS. This work is specialized by selecting a diversified combination of features from these datasets to construct an effective dataset that would further enhance inculcation of trust in the IoT networks. The study proposed two notable models, i.e., XGBoost with logistic regression and AdaBoost with decision tree to achieve the efficiency and scalability of the proposed models. The results shows significant improvement in the efficiency, and having both the mentioned models to offer a precision, recall and F1-score of 0.99 representing efficient mechanism in ensuring a secure and dependable IoT ecosystem.

The integration of Artificial Intelligence (AI) and Wearable Internet of Things (WIoT) for mental health detection is a promising area of research with the potential to revolutionize mental health monitoring and diagnosis. Since early detection of mental diseases, i.e., depression, is of great importance for diagnosis and treatment, a fast and convenient way is urgently needed. Traditional diagnostic methods are time-consuming, laborious, over-subjective, and easily lead to misdiagnosis. The advance in information techniques and wearable devices brings innovation to mental disease detection. Therefore, this article first compares intelligent depression detection methods and traditional methods to illustrate the significance and then analyzes the opportunities of the wearable device. Then we provide specific psychophysiological data measured by wearable devices and introduce relevant datasets for depression detection. An illustrative example of depression detection with sleep data is presented and discussed and our proposed ensemble method has improved nearly 10% to baselines. Analytical results demonstrate the great potential of using wearable device-measured psychophysiological data to detect depression intelligently.

Non-fungible tokens (NFTs) have become an exciting technology that provides a fresh perspective on asset ownership, provenance, and value exchange. NFTs, a blockchain-based technology, are distinct and indivisible cryptographic tokens used to confirm and record the ownership of digital and physical assets in an immutable and transparent way. The fundamental block of NFT is a smart contract built on a blockchain network. This contract contains specific information about the asset it represents, such as its unique identifier, metadata, and ownership details. The information is kept private and tamper-proof due to the decentralized and distributed structure of the blockchain, boosting faith in the token’s authenticity. The NFT is gaining popularity, but it is still in the developing stage. There is a need for a comprehensive survey to guide future research and development in NFTs. Thus, this paper presents the technical components of NFTs, their features, and the minting process. Further, this survey paper describes different token standards for NFTs. It presents various applications of NFTs in healthcare, supply chain, gaming, identity verification, agriculture, intellectual property, smart cities, charity and donation, and education. The article also emphasizes the significant difficulties faced currently in implementing NFT technology from the viewpoints of ownership, governance, and property rights, as well as security, privacy, and environmental effects. This work also elucidates the future directions to overcome the challenges in adopting NFTs in various applications.

Preserving human health is of utmost importance, and unrestricted availability of medications is essential for overall wellness. Pharmaceuticals, which consist of a wide range of therapeutic substances utilized to diagnose, treat, and improve various diseases and conditions, play a crucial part in healthcare. However, the drug research and development process is widely recognized for its lengthy duration, demanding nature, and substantial expenses. To enhance the effectiveness of this complex process, interdisciplinary groups have converged, giving rise to the field known as “Bioinformatics”. The emergence and future advancements of Quantum Computing (QC) technologies have the potential to significantly enhance and accelerate the complex process of drug discovery and development. This paper explores various disciplines, such as Computer-Aided Drug Design (CADD), quantum simulations, quantum chemistry, and clinical trials, that stand to gain significant advantages from the rapidly advancing field of quantum technology. This study explores a range of fundamental quantum principles, intending to facilitate a thorough understanding of this revolutionary technology.

Advancements in lung health assessment, a critical component in diagnosing respiratory conditions, have gained prominence in medical research. This is especially true with the advent of non-invasive techniques such as spirometry. Central to this diagnostic method are three key metrics: Forced Vital Capacity (FVC), Forced Expiratory Volume in 1 second (FEV1), and Peak Expiratory Flow (PEF). In light of the increasing need for accurate and reliable assessment tools, developing comprehensive datasets is imperative for advancing research in this field. Our paper presents RespiroDynamics: A Comprehensive Multimodal Respiratory Dataset, a total of more than 2k samples, compiled from 60 participants, covering a wide range of age, weight, height and others. This dataset incorporates various data types, including Red-Green-Blue (RGB) and Thermal videos, Heart Rate (HR), ECG readings and metadata, all synchronized with observed respiratory activities. We elaborate on the data collection methodology, post-processing techniques employed, and the analytical approach to extract meaningful patterns and insights. Our evaluation, using a 5-fold cross-validation method on binary classification models for FEV1/FVC, revealed remarkable accuracies: 99.7% for the RGB model and a perfect 100% for the thermal model. For the PEF 3-class model, accuracies were 97.14% for both RGB and 96.0% for thermal models. This study aims to underscore the dataset’s potential in establishing and enhancing a robust deep-learning model for lung health diagnostics.

ChatGPT has been acknowledged as a powerful tool that can radically boost productivity across a wide range of industries. It reveals potential in cybersecurity-related tasks such as social engineering. Nevertheless, this possibility raises important concerns regarding the thin line separating moral use of this technology from its harmful usage. It is imperative to address the challenges of distinguishing between legitimate and malevolent use of ChatGPT. This research paper investigates the many concerns of ChatGPT in cybersecurity, privacy and enterprise settings. It covers harmful attacker uses such as injecting malicious prompts, testing brute force attacks, preparing and developing ransomware attacks, etc. Defenders’ proactive activities are also addressed, highlighting ChatGPT’s significance in security operations and threat intelligence. These defensive operations are classified based on the National Institute of Standards and Technology cybersecurity framework. They involve analyzing configuration files, inquiring about authoritative server, improving security in various systems, etc. Moreover, secure enterprise practices and mitigations spread through five classes are proposed, with an emphasis on clear usage standards and guidelines establishment, personally identifiable information protection, adversarial attack prevention, watermarking generated content, etc. An integrated discussion digs into the interaction of offensive and defensive applications, covering ethical and practical concerns. Future attacks are also discussed, along with potential solutions such as content filtering and collaboration. Finally, a comparative analysis with recent research on ChatGPT security concerns is directed. The paper provides a thorough framework to comprehend the range of implications associated with ChatGPT, enabling the navigation of cybersecurity and privacy challenges.

Generative artificial intelligence (GAI) can be broadly described as an artificial intelligence system capable of generating images, text, and other media types with human prompts. GAI models like ChatGPT, DALL-E, and Bard have recently caught the attention of industry and academia equally. GAI applications span various industries like art, gaming, fashion, and healthcare. In healthcare, GAI shows promise in medical research, diagnosis, treatment, and patient care and is already making strides in real-world deployments. There has yet to be any detailed study concerning the applications and scope of GAI in healthcare. Addressing this research gap, we explore several applications, real-world scenarios, and limitations of GAI in healthcare. We examine how GAI models like ChatGPT and DALL-E can be leveraged to aid in the applications of medical imaging, drug discovery, personalized patient treatment, medical simulation and training, clinical trial optimization, mental health support, healthcare operations and research, medical chatbots, human movement simulation, and a few more applications. Along with applications, we cover four real-world healthcare scenarios that employ GAI: visual snow syndrome diagnosis, molecular drug optimization, medical education, and dentistry. We also provide an elaborate discussion on seven healthcare-customized LLMs like Med-PaLM, BioGPT, DeepHealth, etc.,Since GAI is still evolving, it poses challenges like the lack of professional expertise in decision making, risk of patient data privacy, issues in integrating with existing healthcare systems, and the problem of data bias which are elaborated on in this work along with several other challenges. We also put forward multiple directions for future research in GAI for healthcare.

Collaborative machine learning is considered as the bedrock of the intelligent B5G networks, where distributed agents collaborate with each other to train learning models in a distributed fashion, without sharing data at a central entity. Despite its broad applicability, the main issue of collaborative learning is the need of local computing to build local learning models as well as iterative information exchange among agents, which may lead to high resource overhead unaffordable in many practical resource-limited systems such as unmanned aerial vehicles (UAVs) and Internet of Things (IoT). To alleviate this resource issue, it is essential to devise resource-efficient collaborative learning techniques, that can optimize the resource overhead in terms of communication, computing, and energy cost, and hence achieve satisfactory optimization/learning performance simultaneously.

Enabling accurate and automated identification of wireless devices is critical for allowing network access monitoring and ensuring data authentication for large-scale IoT networks. RF fingerprinting has emerged as a solution for device identification by leveraging the transmitters’ inevitable hardware impairments that occur during manufacturing. Although deep learning is proven efficient in classifying devices based on hardware impairments, the performance of deep learning models suffers greatly from variations of the wireless channel conditions, across time and space. To the best of our knowledge, we are the first to propose leveraging MIMO capabilities to mitigate the channel effect and provide a channel-resilient device classification framework. We begin by showing that for AWGN channels, combining multiple received signals improves the testing accuracy by up to 30%. We then show that for more realistic Rayleigh channels, blind channel estimation enabled by MIMO increases the testing accuracy by up to 50% when the models are trained and tested over the same channel, and by up to 69% when the models are tested on a channel that is different from that used for training.

Presents corrections to the paper, RespiroDynamics: A Multifaceted Dataset for Enhanced Lung Health Assessment Using Deep Learning.

Machine learning, powered by cloud servers, has found application in medical diagnosis, enhancing the capabilities of smart healthcare services. Research literature demonstrates that the support vector machine (SVM) consistently demonstrates remarkable accuracy in medical diagnosis. Nonetheless, safeguarding patients’ health data privacy and preserving the intellectual property of diagnosis models is of paramount importance. This concern arises from the common practice of outsourcing these models to third-party cloud servers that may not be entirely trustworthy. Few studies in the literature have delved into addressing these issues within SVM-based diagnosis systems. These studies, however, typically demand substantial communication and computational resources and may fail to conceal classification results and protect model intellectual property. This paper aims to tackle these limitations within a multi-class SVM medical diagnosis system. To achieve this, we have introduced modifications to an inner product encryption cryptosystem and incorporated it into our medical diagnosis framework. Notably, our cryptosystem proves to be more efficient than the Paillier and multi-party computation cryptography methods employed in previous research. Although we focus on a medical application in this paper, our approach can also be used for other applications that need the evaluation of machine learning models in a privacy-preserving way such as electricity theft detection in the smart grid, electric vehicle charging coordination, and vehicular social networks. To assess the performance and security of our approach, we conducted comprehensive analyses and experiments. Our findings demonstrate that our proposed method successfully fulfills our security and privacy objectives while maintaining high classification accuracy and minimizing communication and computational overhead.

Existing techniques for incremental learning are computationally expensive and produce duplicate features leading to higher false positive and true negative rates. We propose a novel privacy-preserving intrusion detection pipeline for distributed incremental learning. Our pre-processing technique eliminates redundancies and selects unique features by following innovative extraction techniques. We use autoencoders with non-negativity constraints, which help us extract less redundant features. More importantly, the distributed intrusion detection model reduces the burden on the edge classifier and distributes the load among IoT and edge devices. Theoretical analysis and numerical experiments have shown lower space and time costs than state of the art techniques, with comparable classification accuracy. Extensive experiments with standard data sets and real-time streaming IoT traffic give encouraging results.

The Internet of Things (IoT) is playing a vital role in the rapid automation of the healthcare sector. The branch of IoT dedicated towards medical science is at times termed as Healthcare Internet of Things (H-IoT). The key elements of all H-IoT applications are data gathering and processing. Due to the large amount of data involved in healthcare, and the enormous value that accurate predictions hold, the integration of machine learning (ML) algorithms into H-IoT is imperative. This paper aims to serve both as a compilation as well as a review of the various state of the art applications of ML algorithms currently being integrated with H-IoT. Some of the most widely used ML algorithms have been briefly introduced and their use in various H-IoT applications has been analyzed in terms of their advantages, scope, and possible improvements. Applications have been divided into the domains of diagnosis, prognosis and spread control, assistive systems, monitoring, and logistics. In healthcare, practical use of a model requires it to be highly accurate and to have ample measures against security attacks. The applications of ML algorithms in H-IoT discussed in this paper have shown experimental evidence of accuracy and practical usability. The constraints and drawbacks of each of these applications have also been described.

In the past decades, the internet has emerged as the fastest way to access information. However, this revolutionary information age comes with its own set of challenges. The privacy of Internet users is at increasing risk with the advances in surveillance techniques. Users' online behavior, activities, and even personal information are being tracked by ISPs and major tech companies. In response to the increasing need for preserving and protecting the privacy of online users, anonymity networks were developed. Tor anonymity network is a low-latency anonymity network that has gained quite a good reputation over the past years and is being adopted by thousands of users. With the great attention Tor's network is getting, the original design of Tor was proven to have performance limiting issues. With the motivation for addressing the performance limitation in Tor, we present QuicTor, a datagram-based design to solve Tor's transport-layer limiting issue. We evaluated the performance of QuicTor in comparison to vanilla Tor as well as other performance-enhancing proposals. QuicTor achieved significant performance improvements for interactive applications as well as streaming applications. Running Tor over a datagram-based protocol entails a careful security analysis. In this article, we assess the behavior of QuicTor under side-channel attacks aiming to de-anonymize Tor's clients. We show that the performance improvements brought by QuicTor do not reduce the anonymity of clients under the investigated types of attacks.

Due to their high computational and memory demand, deep learning applications are mainly restricted to high-performance units, e.g., cloud and edge servers. Particularly, in Internet of Things (IoT) systems, the data acquired by pervasive devices is sent to the computing servers for classification. However, this approach might not be always possible because of the limited bandwidth and the privacy issues. Furthermore, it presents uncertainty in terms of latency because of the unstable remote connectivity. To support resource and delay requirements of such paradigm, joint and real-time deep co-inference framework with IoT synergy was introduced. However, scheduling the distributed, dynamic and real-time Deep Neural Network (DNN) inference requests among resource-constrained devices has not been well explored in the literature. Additionally, the distribution of DNN has drawn the attention to the privacy protection of sensitive data. In this context, various threats have been presented, including white-box attacks, where malicious devices can accurately recover received inputs if the DNN model is fully exposed to participants. In this paper, we introduce a methodology aiming at distributing the DNN tasks onto the resource-constrained devices of the IoT system, while avoiding to reveal the model to participants. We formulate such an approach as an optimization problem, where we establish a trade-off between the latency of co-inference, the privacy of the data, and the limited resources of devices. Next, due to the NP-hardness of the problem, we shape our approach as a reinforcement learning design adequate for real-time applications and highly dynamic systems, namely RL-PDNN. Our system proved its ability to outperform existing static approaches and achieve close results compared to the optimal solution.

Using smartphones, tablets, and other portable/handheld devices, we have become more reliant on the video streaming services for entertainment and remote work. Mobile data traffic has grown eighteen folds over the past five years accounting for the majority of IP traffic. YouTube Live, Facebook Live, Twitch, DouYu and other streaming as well as video conferencing services have increased in popularity so at any given moment they serve thousands of live video streams to millions of users. The Enhanced Multimedia Broadcast Multimedia Service (eMBMS) is the standard multicast protocol for 5G networks. Cellular multicast has gained considerable attention to efficiently utilize the limited spectrum to transmit multimedia content to cellular sites with co-located viewers, lowering the cost, and maximizing the Quality of Experience (QoE). However, popular live video content providers use unicast mode for live video delivery and have limited support in the eMBMS service-oriented network architecture. In this paper, we propose an overlay network architecture to augment eMBMS to address the limitations of the standard eMBMS architecture and enable service-less multicast for crowdsourced live video providers. We propose a Virtual Network Function (VNF) service that identifies potential multicast scenarios based on user requests for a live video within a confined area. The VNF Application Server collects information, validates a potential multicast scenario, and initiates an ad-hoc multicast service on the fly. We use a real-world dataset of Facebook Live videos to evaluate the proposed architecture. The simulation results depict considerable advantages in terms of cost, efficiency, and Quality of Experience (QoE). Our results show that the proposed architecture provides significant benefits in bandwidth saving at the backhaul, transit, and RAN links.

Modern technologies empower water distribution systems (WDS) for better services in the processes of water supply, storage, distribution, and recycling. They improve real-time monitoring, automating, and managing. However, the limitations of these technologies introduce cyber-physical attacks to the WDS. The main goals of cyber-physical attacks include disrupting normal operations and tampering the critical data, which have negative impacts on the WDS. Therefore, it is vital to develop and implement solutions to increase the security of the WDS by detecting and mitigating cyber-physical attacks. Since security for WDS is relatively new, there are no surveys on this topic despite its vital importance. Therefore, in this paper, we provide a comprehensive survey for the common cyber-physical attacks and common detection mechanisms for the WDS. We compare the attacks and detection methods with emphasis on ideas, methods, evaluation results, advantages, limitations, etc. We further provide a future research direction. We realize that there are still not many research attempts in this area and we hope that this work can trigger more research activities related to the WDS.

The wide spread of the novel COVID-19 virus all over the world has caused major economical and social damages combined with the death of more than two million people so far around the globe. Therefore, the design of a model that can predict the persons that are most likely to be infected is a necessity to control the spread of this infectious disease as well as any other future novel pandemic. In this paper, an Internet of Things (IoT) sensing network is designed to anonymously track the movement of individuals in crowded zones through collecting the beacons of WiFi and Bluetooth devices from mobile phones to triangulate and estimate the locations of individuals inside buildings without violating their privacy. A mathematical model is presented to compute the expected time of exposure between users. Furthermore, a virus spread mathematical model as well as iterative spread tracking algorithms are proposed to predict the probability of individuals being infected even with limited data.

In order to maintain a satisfactory performance in the midst of rapid growth of mobile traffic, the mobile network infrastructure needs to be scaled. Thus there has been significant interest in scalability of mobile core networks and a variety of scaling solutions have been proposed that rely on horizontal scaling or vertical scaling. These solutions handle the scaling of the mobile core networks’ elements on virtual machines (which normally take at while to create) with the help of customized modules at the cost of increased overheads. Utilizing Amazon Web Services (AWS) embedded features, we present two predictive horizontal auto-scalers for containerized and non-containerized versions of EPC that scales the two versions of the EPC according to their respective CPU utilization. Additionally, we propose an efficient task assignment scheme for AWS that aims to maximize throughput and achieve fairness among competing instances. In particular, we propose two solutions: Relaxed Optimized Solution (ROS) and a Heuristic Approach (HA). Leveraging AWS environment, we implemented and evaluated the two proposed auto-scaling models based on the attachment success rate, latency, CPU usage and RAM usage. Our findings show the superiority of container-based model over VM-based model in terms of resource utilization. The obtained results for the two proposed task assignment solutions demonstrates a significant improvement both in fairness and throughput compared to other existing solutions.

High Altitude Platform (HAP) systems comprise airborne base stations deployed above 20 km and below 50 km to provide wireless access to devices in large areas. In this paper, two types of applications using HAP systems: one with HAP Station (HAPS) and the other with HAPS as International Mobile Telecommunication (IMT) Base Station (HIBS) are introduced. The HAP system with HAPS has already received wide recognition from the academia and the industry and is considered as an effective solution to provide internet access between fixed points in suburban and rural areas as well as emergencies. HAP systems with HIBS to serve IMT user terminal have just started to draw attention from researchers. The HIBS application is expected to be an anticipate mobile service application complementing the IMT requirement for cell phone or other mobile user terminals in which the service field of HAPS application cannot reach. After describing and characterizing the two types of systems, coexistence studies and simulation results using both the Power Fluxed Density (PFD) mask and separation distance based methods are presented in this paper. This paper also predicts future trends of the evolution paths for the HAP systems along with challenges and possible solutions from the standpoint of system architectures and spectrum regulation.

Software defined network and network function visualization enhance the network flexibility and management agility, which increase network fragility and complexity. However, the vast majority of network parameters are manually configured, which makes the configuration failures still inevitable. Future networks should be self-configuring, self-managing, and self-optimizing. Intent-driven network (IDN) is a self-driving network that uses decoupling network control logic and closed-loop orchestration techniques to automate application intents. At present, a unified definition of IDN has not yet been presented, and the research background and current status of IDN are not clear. Considering the emerging applications and research of IDN, in this article, we survey existing technologies, clarify definitions, and summarize features for IDN. Specifically, we discuss the basic architecture and key technologies of IDN. In addition, diversity gains and challenges are analyzed briefly. Finally, some future work is highlighted and wider applications of IDN are provided for further research.

Vehicular Ad-hoc Network (VANET) is a modern era of dynamic information distribution among societies. VANET provides an extensive diversity of applications in various domains, such as Intelligent Transport System (ITS) and other road safety applications. VANET supports direct communications between vehicles and infrastructure. These direct communications cause bandwidth problems, high power consumption, and other similar issues. To overcome these challenges, clustering methods have been proposed to limit the communication of vehicles with the infrastructure. In clustering, vehicles are grouped together to formulate a cluster based on certain rules. Every cluster consists of a limited number of vehicles/nodes and a cluster head (CH). However, the significant challenge for clustering is to preserve the stability of clusters. Furthermore, a secure mechanism is required to recognize malicious and compromised nodes to overcome the risk of invalid information sharing. In the proposed approach, we address these challenges using components of trust. A trust-based clustering mechanism allows clusters to determine a trustworthy CH. The novel features incorporated in the proposed algorithm includes trust-based CH selection that comprises of knowledge, reputation, and experience of a node. Also, a backup head is determined by analyzing the trust of every node in a cluster. The major significance of using trust in clustering is the identification of malicious and compromised nodes. The recognition of these nodes helps to eliminate the risk of invalid information. We have also evaluated the proposed mechanism with the existing approaches and the results illustrate that the mechanism is able to provide security and improve the stability by increasing the lifetime of CHs and by decreasing the computation overhead of the CH re-selection. The StabTrust also successfully identifies malicious and compromised vehicles and provides robust security against several potential attacks.

The current cellular technology and vehicular networks cannot satisfy the mighty strides of vehicular network demands. Resource management has become a complex and challenging objective to gain expected outcomes in a vehicular environment. The 5G cellular network promises to provide ultra-high-speed, reduced delay, and reliable communications. The development of new technologies such as the network function virtualization (NFV) and software defined networking (SDN) are critical enabling technologies leveraging 5G. The SDN-based 5G network can provide an excellent platform for autonomous vehicles because SDN offers open programmability and flexibility for new services incorporation. This separation of control and data planes enables centralized and efficient management of resources in a very optimized and secure manner by having a global overview of the whole network. The SDN also provides flexibility in communication administration and resource management, which are of critical importance when considering the ad-hoc nature of vehicular network infrastructures, in terms of safety, privacy, and security, in vehicular network environments. In addition, it promises the overall improved performance. In this paper, we propose a flow-based policy framework on the basis of two tiers virtualization for vehicular networks using SDNs. The vehicle to vehicle (V2V) communication is quite possible with wireless virtualization where different radio resources are allocated to V2V communications based on the flow classification, i.e., safety-related flow or non-safety flows, and the controller is responsible for managing the overall vehicular environment and V2X communications. The motivation behind this study is to implement a machine learning-enabled architecture to cater the sophisticated demands of modern vehicular Internet infrastructures. The inclination towards robust communications in 5G-enabled networks has made it somewhat tricky to manage network slicing efficiently. This paper also presents a proof of concept for leveraging machine learning-enabled resource classification and management through experimental evaluation of special-purpose testbed established in custom mininet setup. Furthermore, the results have been evaluated using Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and Deep Neural Network (DNN). While concluding the paper, it is shown that the LSTM has outperformed the rest of classification techniques with promising results.

Due to the powerful ability of data fitting, deep neural networks have been applied in a wide range of applications in many key areas. However, in recent years, it was found that some adversarial samples easily fool the deep neural networks. These input samples are generated by adding a few small perturbations based on the original sample, making a very significant influence on the decision of the target model in the case of not being perceived. Image segmentation is one of the most important technologies in the medical image and automatic driving field. This paper mainly explores the security of deep neural network models based on the image segmentation tasks. Two lightweight image segmentation models on the embedded device suffered from the white-box attack by using local perturbations and universal perturbations. The perturbations are generated indirectly by a noise function and an intermediate variable so that the gradient of pixels can be propagated unlimitedly. Through experiments, we find that different models have different blind spots, and the adversarial samples trained for a single model have no transferability. In the end, multiple models are attacked by our joint learning. Finally, under the constraint of low perturbation, most of the pixels in the attacked area have been misclassified by both lightweight models. The experimental result shows that the proposed adversary is more likely to affect the performance of the segmentation model compared with the FGSM.

The unprecedented outbreak of the 2019 novel coronavirus, termed as COVID-19 by the World Health Organization (WHO), has placed numerous governments around the world in a precarious position. The impact of the COVID-19 outbreak, earlier witnessed by the citizens of China alone, has now become a matter of grave concern for virtually every country in the world. The scarcity of resources to endure the COVID-19 outbreak combined with the fear of overburdened healthcare systems has forced a majority of these countries into a state of partial or complete lockdown. The number of laboratory-confirmed coronavirus cases has been increasing at an alarming rate throughout the world, with reportedly more than 3 million confirmed cases as of 30 April 2020. Adding to these woes, numerous false reports, misinformation, and unsolicited fears in regards to coronavirus, are being circulated regularly since the outbreak of the COVID-19. In response to such acts, we draw on various reliable sources to present a detailed review of all the major aspects associated with the COVID-19 pandemic. In addition to the direct health implications associated with the outbreak of COVID-19, this study highlights its impact on the global economy. In drawing things to a close, we explore the use of technologies such as the Internet of Things (IoT), Unmanned Aerial Vehicles (UAVs), blockchain, Artificial Intelligence (AI), and 5G, among others, to help mitigate the impact of COVID-19 outbreak.

Machine learning techniques are becoming mainstream in intrusion detection systems as they allow real-time response and have the ability to learn and adapt. By using a comprehensive dataset with multiple attack types, a well-trained model can be created to improve the anomaly detection performance. However, high dimensional data present a significant challenge for machine learning techniques. Processing similar features that provide redundant information increases the computational time, which is a critical problem especially for users with constrained resources (battery, energy). In this paper, we propose two models for intrusion detection and classification scheme Trust-based Intrusion Detection and Classification System (TIDCS) and Trust-based Intrusion Detection and Classification System- Accelerated (TIDCS-A) for secure network. TIDCS reduces the number of features in the input data based on a new algorithm for feature selection. Initially, the features are grouped randomly to increase the probability of making them participating in the generation of different groups, and sorted based on their accuracy scores. Only the high ranked features are then selected to obtain a classification for any received packet from the nodes in the network, which is saved as part of the node's past performance. TIDCS proposes a periodic system cleansing where trust relationships between participant nodes are evaluated and renewed periodically. TIDCS-A proposes a dynamic algorithm to compute the exact time for nodes cleansing states and restricts the exposure window of the nodes. The final classification decision for both models is estimated by incorporating the node's past behavior with the machine learning algorithm. Any detected attack reduces the trustworthiness of the nodes involved, leading to a dynamic system cleansing. An evaluation of TIDCS and TIDCS-A using the NSL-KDD and UNSW datasets shows that both models can detect malicious behaviors providing higher accuracy, detection rates, and lower false alarm than state-of-art techniques. For instance, for UNSW dataset, the accuracy detection is 91% for TICDS, 83.47%by using online AODE, 88% for CADF, 90% for EDM, 90% for TANN and 69.6% for NB. Consequently, TICDS has better performance than the state of art techniques in terms of accuracy detection, while providing good detection and false alarm rates.

Mobile applications are advancing toward higher network and compute requirements, which are similar to the requirements of server applications. Users prefer to perform their tasks on the go from mobile devices instead of stationary desktop and server systems. Modern mobile applications limit mobile battery times as charging is lost quickly due to high processing and data demands. Resources other than energy are also limited in mobile devices (memory, CPU millions of instructions per second, etc.).Mobile edge computing (MEC) technologies facilitate resource-scarcemobile devices to enhance their capabilities and execute data/computeintensive applications while collaborating with resource-rich network servers to enable ubiquitous computing. On the other hand, mobile cloud computing provides higher resources for applications that have low response requirements (noninteractive applications). Bothmobile edge computing andmobile cloud computing enable technologies for Internet of Things (IoT), smart grids, and e-health applications.

Multi-access Edge Computing (MEC) is a key solution that enables operators to open their networks to new services and IT ecosystems to leverage edge-cloud benefits in their networks and systems. Located in close proximity from the end users and connected devices, MEC provides extremely low latency and high bandwidth while always enabling applications to leverage cloud capabilities as necessary. In this article, we illustrate the integration of MEC into a current mobile networks' architecture as well as the transition mechanisms to migrate into a standard 5G network architecture. We also discuss SDN, NFV, SFC and network slicing as MEC enablers. Then, we provide a state-of-the-art study on the different approaches that optimize the MEC resources and its QoS parameters. In this regard, we classify these approaches based on the optimized resources and QoS parameters (i.e., processing, storage, memory, bandwidth, energy and latency). Finally, we propose an architectural framework for a MEC-NFV environment based on the standard SDN architecture.

With the exponentially growing COVID-19 (coronavirus disease 2019) pandemic, clinicians continue to seek accurate and rapid diagnosis methods in addition to virus and antibody testing modalities. Because radiographs such as X-rays and computed tomography (CT) scans are cost-effective and widely available at public health facilities, hospital emergency rooms (ERs), and even at rural clinics, they could be used for rapid detection of possible COVID-19-induced lung infections. Therefore, toward automating the COVID-19 detection, in this paper, we propose a viable and efficient deep learning-based chest radiograph classification (DL-CRC) framework to distinguish the COVID-19 cases with high accuracy from other abnormal (e.g., pneumonia) and normal cases. A unique dataset is prepared from four publicly available sources containing the posteroanterior (PA) chest view of X-ray data for COVID-19, pneumonia, and normal cases. Our proposed DL-CRC framework leverages a data augmentation of radiograph images (DARI) algorithm for the COVID-19 data by adaptively employing the generative adversarial network (GAN) and generic data augmentation methods to generate synthetic COVID-19 infected chest X-ray images to train a robust model. The training data consisting of actual and synthetic chest X-ray images are fed into our customized convolutional neural network (CNN) model in DL-CRC, which achieves COVID-19 detection accuracy of 93.94% compared to 54.55% for the scenario without data augmentation (i.e., when only a few actual COVID-19 chest X-ray image samples are available in the original dataset). Furthermore, we justify our customized CNN model by extensively comparing it with widely adopted CNN architectures in the literature, namely ResNet, Inception-ResNet v2, and DenseNet that represent depth-based, multi-path-based, and hybrid CNN paradigms. The encouragingly high classification accuracy of our proposal implies that it can efficiently automate COVID-19 detection from radiograph images to provide a fast and reliable evidence of COVID-19 infection in the lung that can complement existing COVID-19 diagnostics modalities.

Retracted.

To promote the expansion and adoption of Digital Twins (DTs) in Smart Cities (SCs), a detailed review of the impact of DTs and digitalization on cities is made to assess the progression of cities and standardization of their management mode. Combined with the technical elements of DTs, the coupling effect of DTs technology and urban construction and the internal logic of DTs technology embedded in urban construction are discussed. Relevant literature covering the full range of DTs technologies and their applications is collected, evaluated, and collated, relevant studies are concatenated, and relevant accepted conclusions are summarized by modules. First, the historical process and construction content of a Digital City (DC) under modern demand are analyzed, and the main ideas of a DC design and construction are discussed in combination with the key technology of DTs. Then, the metaverse is the product of the combination of various technologies in different scenes. It is a key component to promote the integration of the real world and the digital world and can provide more advanced technical support in the construction of the DC. DTs urban technology architecture is composed of an infrastructure terminal information center terminal and application server end. Urban intelligent management is realized through physical urban data collection, transmission, processing, and digital urban visualization. The construction of DTs urban platform can improve the city’s perception and decision-making ability and bring a broader vision for future planning and progression. The interactive experience of the virtual world covered by the metaverse can effectively support and promote the integration of the virtual and real, and will also greatly promote the construction of SCs. In summary, this work is of important reference value for the overall development and practical adoption of DTs cities, which improves the overall operation efficiency and the governance level of cities.

Recently, the Infrastructure as a Service Cloud (IaaS) (e.g., Amazon EC2) has been widely used by many organizations. However, some IaaS security issues create serious threats to its users. A typical issue is the timing channel. This kind of channel can be a cross-VM information channel, as proven by many researchers. Owing to the fact that it is covert and traceless, the traditional identification methods cannot build an accurate analysis model and obtain a compromised result. We investigated the underlying behavior of the timing channel from the perspective of the memory activity records and summarized the signature of the timing channel in the underlying memory activities. An identification method based on the long-term behavior signatures was proposed. We proposed a complete set of forensics steps including evidence extraction, identification, record reserve, and evidence reports. We studied four typical timing channels, and the experiments showed that these channels can be detected and investigated, even with the disturbances from normal processes.

Mobile crowd-sensing (MCS) is a new sensing paradigm that takes advantage of the extensive use of mobile phones that collect data efficiently and enable several significant applications. MCS paves the way to explore new monitoring applications in different fields such as social networks, lifestyle, healthcare, green applications, and intelligent transportation systems. Hence, MCS applications make use of sensing and wireless communication capabilities provided by billions of smart mobile devices, e.g., Android and iOS-based mobile devices. The aim of this paper is to identify and explore the new paradigm of MCS that is using smartphone for capturing and sharing the sensed data between many nodes. We discuss the main components of the infrastructure required to support the proposed framework. The existing and potential applications leveraging MCS are laid out. Furthermore, this paper discusses the current challenges facing the collection methodologies of the participants’ data in task management. The recent issues in the MCS findings are reviewed as well as the opportunities and challenges in sensing methods are analyzed. Finally, open research issues and future challenges facing MCS are highlighted.

In this paper, we propose a Blockchain-based infrastructure to support security- and privacy-oriented spatio-temporal smart contract services for the sustainable Internet of Things (IoT)-enabled sharing economy in mega smart cities. The infrastructure leverages cognitive fog nodes at the edge to host and process off loaded geo-tagged multimedia payload and transactions from a mobile edge and IoT nodes, uses AI for processing and extracting significant event information, produces semantic digital analytics, and saves results in Blockchain and decentralized cloud repositories to facilitate sharing economy services. The framework offers a sustainable incentive mechanism, which can potentially support secure smart city services, such as sharing economy, smart contracts, and cyber-physical interaction with Blockchain and IoT. Our unique contribution is justified by detailed system design and implementation of the framework.

The vast development of the Internet of Things (IoT) and cloud-enabled data processing solutions provide the opportunity to build novel and fascinating smart, connected healthcare systems. Smart healthcare systems analyze the IoT-generated patient data to both enhance the quality of patient care and reduce healthcare costs. A major challenge for these systems is how the Cloud of Things can handle the data generated from billions of connected IoT devices. Edge computing infrastructure offers a promising solution by operating as a middle layer between the IoT devices and cloud computing. The Edge of Things (EoT) can offer small-scale real-time computing and storage capabilities that ensures low latency and optimal utilization of the IoT resources. However, the EoT has privacy-preservation issues, which is a significant concern for the healthcare systems that contain sensitive patient data. This paper introduces a novel EoT computing framework for secure and smart healthcare surveillance services. Fully homomorphic encryption preserves data privacy and is stored and processed within an EoT framework. A distributed approach for clustering-based techniques is developed for the proposed EoT framework with the scalability to aggregate and analyze the large-scale and heterogeneous data in the distributed EoT devices independently before it is sent to the cloud. We demonstrate the proposed framework by evaluating a case study for the patient biosignal data. Our framework rapidly accelerates the analysis response time and performance of the encrypted data processing while preserving a high level of analysis accuracy and data privacy.

Software-defined network (SDN) is widely used in smart grid for monitoring and managing the communication network. Big data analytics for SDN-based smart grid has got increasing attention. It is a promising approach to use machine learning technologies to analyze a large amount of data generated in SDN-based smart grid. However, the disclosure of personal privacy information must receive considerable attention. For instance, data clustering in user electricity behavior analysis may lead to the disclosure of personal privacy information. In this paper, an optimizing and differentially private clustering algorithm named ODPCA is proposed. In the ODPCA, the differentially private K-means algorithm and K-modes algorithm are combined to cluster mixed data in a privacy-preserving manner. The allocation of privacy budgets is optimized to improve the accuracy of clustering results. Specifically, the loss function that considers both the numerical and categorical attributes between true centroids and noisy centroids is analyzed to optimize the allocation the privacy budget; the number of iterations of clustering is set to a fixed value based on the total privacy budget and the minimal privacy budget allocated to each iteration. It is proved that the ODPCA can meet the differential privacy requirements and has better performance by comparing with other popular algorithms.

A vision of the future Internet is introduced in such a fashion that various computing devices are connected together to form a network called Internet of Things (IoT). This network will generate massive data that may be leveraged for entertainment, security, and most importantly user trust. Yet, trust is an imperative obstruction that may hinder the IoT growth and even delay the substantial squeeze of a number of applications. In this survey, an extensive analysis of trust management techniques along with their pros and cons is presented in a different context. In comparison with other surveys, the goal is to provide a systematic description of the most relevant trust management techniques to help researchers understand that how various systems fit together to bring preferred functionalities without examining different standards. Besides, the lessons learned are presented, and the views are argued regarding the primary goal trust which is likely to play in the future Internet.

Nowadays, the recommendation systems are applied in the fields of e-commerce, video websites, social networking sites, which bring great convenience to people's daily lives. The types of information are diversified and abundant in recommendation systems; therefore the proportion of unstructured multimodal data such as text, image, and video is increasing. However, due to the representation gap between different modalities, it is intractable to effectively use unstructured multimodal data to improve the efficiency of recommendation systems. In this paper, we propose an end-to-end multimodal interest-related item similarity model (multimodal IRIS) to provide recommendations based on the multimodal data source. Specifically, the multimodal IRIS model consists of three modules, i.e., multimodal feature learning module, the interest-related network (IRN) module, and item similarity recommendation module. The multimodal feature learning module adds knowledge sharing unit among different modalities. Then, IRN learns the interest relevance between target item and different historical items respectively. Finally, the multimodal feature learning, IRN, and item similarity recommendation modules are unified into an integrated system to achieve performance enhancements and to accommodate the addition or absence of different modal data. Extensive experiments on real-world datasets show that, by dealing with the multimodal data which people may pay more attention to when selecting items, the proposed multimodal IRIS significantly improves accuracy and interpretability on top-N recommendation task over the state-of-the-art methods.

The use of unmanned aerial vehicles (UAVs) is growing rapidly across many civil application domains, including real-time monitoring, providing wireless coverage, remote sensing, search and rescue, delivery of goods, security and surveillance, precision agriculture, and civil infrastructure inspection. Smart UAVs are the next big revolution in the UAV technology promising to provide new opportunities in different applications, especially in civil infrastructure in terms of reduced risks and lower cost. Civil infrastructure is expected to dominate more than $45 Billion market value of UAV usage. In this paper, we present UAV civil applications and their challenges. We also discuss the current research trends and provide future insights for potential UAV uses. Furthermore, we present the key challenges for UAV civil applications, including charging challenges, collision avoidance and swarming challenges, and networking and security-related challenges. Based on our review of the recent literature, we discuss open research challenges and draw high-level insights on how these challenges might be approached.

Influence blocking maximization (IBM) is a key problem for viral marketing in competitive social networks. Although the IBM problem has been extensively studied, existing works neglect the fact that the location information can play an important role in influence propagation. In this paper, we study the location-based seeds selection for IBM problem, which aims to find a positive seed set in a given query region to block the negative influence propagation in a given block region as much as possible. In order to overcome the low efficiency of the simulation-based greedy algorithm, we propose a heuristic algorithm IS-LSS and its improved version IS-LSS+, both of which are based on the maximum influence arborescence structure and Quadtree index, while IS-LSS+ further improves the efficiency of IS-LSS by using an upper bound method and Quadtree cell lists. The experimental results on real-world datasets demonstrate that our proposed algorithms are able to achieve matching blocking effect to the greedy algorithm as the increase in the number of positive seeds and often better than other heuristic algorithms, whereas they are four orders of magnitude faster than the greedy algorithm.

Aerial-terrestrial cloud networks (ATCNs), global integration of air and ground communication systems, pave a way for a large set of applications such as surveillance, on-demand transmissions, data-acquisition, and navigation. However, such networks suffer from crucial challenges of secure and reliable resource allocation and content-caching as the involved entities are highly dynamic and there is no fine-tuned strategy to accommodate their connectivity. To resolve this quandary, cog-chain, a novel paradigm for secure and reliable resource allocation and content-caching in ATCNs, is presented. Various requirements, key concepts, and issues with ATCNs are also presented along with basic concepts to establish a cog-chain in ATCNs. Feed and fetch modes are utilized depending on the involved entities and caching servers. In addition, a cog-chain communication protocol is presented which avails to evaluate the formation of a virtual cog-chain between the nodes and the content-caching servers. The efficacy of the proposed solution is demonstrated through consequential gains observed for signaling overheads, computational time, reliability, and resource allocation growth. The proposed approach operates with the signaling overheads ranging between 30.36 and 303.6 bytes*hops/sec and the formation time between 186 and 195 ms. Furthermore, the overall time consumption is 83.33% lower than the sequential-verification model and the resource allocation growth is 27.17% better than the sequential-verification model.

Deep brain stimulators (DBSs), a widely used and comprehensively acknowledged restorative methodology, are a type of implantable medical device which uses electrical stimulation to treat neurological disorders. These devices are widely used to treat diseases such as Parkinson, movement disorder, epilepsy, and psychiatric disorders. Security in such devices plays a vital role since it can directly affect the mental, emotional, and physical state of human bodies. In worst-case situations, it can even lead to the patient's death. An adversary in such devices, for instance, can inhibit the normal functionality of the brain by introducing fake stimulation inside the human brain. Nonetheless, the adversary can impair the motor functions, alter impulse control, induce pain, or even modify the emotional pattern of the patient by giving fake stimulations through DBSs. This paper presents a deep learning methodology to predict different attack stimulations in DBSs. The proposed work uses long short-term memory, a type of recurrent network for forecasting and predicting rest tremor velocity. (A type of characteristic observed to evaluate the intensity of the neurological diseases) The prediction helps in diagnosing fake versus genuine stimulations. The effect of deep brain stimulation was tested on Parkinson tremor patients. The proposed methodology was able to detect different types of emulated attack patterns efficiently and thereby notifying the patient about the possible attack.

Internet of Things (IoT) is proposed and used in diverse application domains. In IoT, nodes commonly have a low capacity to maintain security on their own expenses, which increases the vulnerability for several attacks. Many approaches have been proposed that are based on privacy and trust management to reduce these vulnerabilities. Existing approaches neglect the aspects of cross-domain node communications and the significance of cross-domain trust management. In this paper, we propose a Holistic Cross-domain trust management model (HoliTrust) that is based on multilevel central authorities. To provide multilevel security, the HoliTrust divides domains into communities on the basis of similarities and interests. Every community has its dedicated server to calculate and manage the degree of trust. In addition, these domains also have their dedicated servers to manage their specific domains, to communicate with the trust server, and to sustain trust among other domain servers. The trust sever is introduced in the HoliTrust that controls the domains, calculates the domain trust, manages the trust values, and distributes standard trust certificates to domains based on a degree of trust. Trust computation is performed on the basis of direct and indirect trust parameters. Furthermore, if a trustor communicates through the community, then the community server includes community trust of the trustee during the trust evaluation. If the communication of the trustor is across the domain, then the community server includes the domain trust along with the community trust of the trustee comprising direct and indirect observations. The overall trust evaluation of communities and domains is time-driven and the responsible authority computes trust after a specific interval of time. We have also compared the HoliTrust with the existing trust mechanisms by focusing on several holistic trust objectives, such as trust relation and decision, data perception trust, and privacy preservation.

Recently, the magnetic resonance imaging (MRI) images have limited and unsatisfactory resolutions due to various constraints such as physical, technological, and economic considerations. Super-resolution techniques can obtain high-resolution MRI images. The traditional methods obtained the resolution enhancement of brain MRI by interpolations, affecting the accuracy of the following diagnose process. The requirement for brain image quality is fast increasing. In this paper, we propose an image super-resolution method based on overcomplete dictionaries and the inherent similarity of an image to recover the high-resolution (HR) image from a single low-resolution (LR) image. We use the linear relationship among images in the measurement domain and frequency domain to classify image blocks into smooth, texture, and edge feature blocks in the measurement domain. The dictionaries for different blocks are trained using different categories. Consequently, an LR image block of interest may be reconstructed using the most appropriate dictionary. In addition, we explore the nonlocal similarity of the image to tentatively search for similar blocks in the whole image and present a joint reconstruction method based on compressed sensing (CS) and similarity constraints. The sparsity and self-similarity of the image blocks are taken as the constraints. The proposed method is summarized in the following steps. First, a dictionary classification method based on the measurement domain is presented. The image blocks are classified into smooth, texture, and edge parts by analyzing their features in the measurement domain. Then, the corresponding dictionaries are trained using the classified image blocks. Equally important, in the reconstruction part, we use the CS reconstruction method to recover the HR brain MRI image, considering both nonlocal similarity and the sparsity of an image as the constraints. This method performs better both visually and quantitatively than some existing methods.

In the promising time of the Internet, connected things have the ability to communicate and share information. The Internet of Things (IoT) cannot be implemented unless the security-related concerns have been resolved. Sharing information among different devices can compromise the private information of users. Thus, a suitable mechanism is needed to exclude the risk of malicious and compromised nodes. As follows, trust has been proposed in the literature as a useful technology to maintain users' security. Prior studies have proposed diverse trust management mechanisms to achieve adequate trust. The approach of cross-domain trust management is neglected that requires enormous considerations to address the difficulties related to cross-domain communication. In this paper, a cross-domain robust distributed trust management (RobustTrust) system is proposed, which makes a device fit for assessing trust towards different devices locally. In this system, the trust is divided into three components of security that help IoT nodes to become robust against compromised and malicious devices/nodes. The novelty of the proposed mechanism can be summarized in these aspects: A highly scalable trust mechanism, multiple components of evaluation to enhance robustness against attacks, and use of recommendations along with the feedback to build knowledge. Furthermore, the proposed mechanism is event-driven that helps nodes to evaluate trust more effectively as well as enhance the system efficiency. The proposed work is compared with the available trust evaluation schemes by concentrating on various attributes, such as trustworthiness, usability, and accuracy among others. The RobustTrust is validated by the extensive simulations considering absolute trust value's performance, the accuracy of trust estimation, and several potential attacks.