Search Results (1,962)

Numerous real-life smart city application scenarios require joint analytics on unified views of georeferenced mobility data with environment contextual data including pollution and meteorological data. particularly, future urban planning requires restricting vehicle access to specific areas of a city to reduce the adverse effect of their engine combustion emissions on the health of dwellers and cyclers. Current editions of big spatial data management systems do not come with over-the-counter support for similar scenarios. To close this gap, in this paper, we show the design and prototyping of a novel system we term as EMDI for the enrichment of human and vehicle mobility data with pollution information, thus enabling integrated analytics on a unified view. Our system supports a variety of queries including single geo-statistics, such as ‘mean’, and Top-N queries, in addition to geo-visualization on the combined view. We have tested our system with real big georeferenced mobility and environmental data coming from the city of Bologna in Italy. Our testing results show that our system can be efficiently utilized for advanced combined pollution-mobility analytics at a scale with QoS guarantees. Specifically, a reduction in latency that equals roughly 65%, on average, is obtained by using EMDI as opposed to the plain baseline, we also obtain statistically significant accuracy results for Top-N queries ranging roughly from 0.84 to 1 for both Spearman and Pearson correlation coefficients depending on the geo-encoding configurations, in addition to significant single geo-statistics accuracy values expressed using Mean Absolute Percentage Error on the range from 0.00392 to 0.000195. Full article

Technology advancements have driven a boost in electronic commerce use in the present day due to an increase in demand processes, regardless of whether goods, products, services, or payments are being bought or sold. Various goods are purchased and sold online by merchants ($\mathcal{M}$)s for large amounts of money. Nonetheless, during the transmission of information via electronic commerce, $\mathcal{M}$s’ information may be compromised or attacked. In order to enhance the security of e-commerce transaction data, particularly sensitive $\mathcal{M}$ information, we have devised a protocol that combines the Fernet (FER) algorithm with the ElGamal (ELG) algorithm. Additionally, we have integrated data leakage detection (DLD) technology to verify the integrity of keys, encryptions, and decryptions. The integration of these algorithms ensures that electronic-commerce transactions are both highly secure and efficiently processed. Our analysis of the protocol’s security and performance indicates that it outperforms the algorithms used in previous studies, providing superior levels of security and performance. Full article

Federated learning (FL) is a transformative approach to Machine Learning that enables the training of a shared model without transferring private data to a central location. This decentralized training paradigm has found particular applicability in edge computing, where IoT devices and edge nodes often possess limited computational power, network bandwidth, and energy resources. While various techniques have been developed to optimize the FL training process, an important question remains unanswered: how should resources be allocated in the training workflow? To address this question, it is crucial to understand the nature of these resources. In physical environments, the allocation is typically performed at the node level, with the entire node dedicated to executing a single workload. In contrast, virtualized environments allow for the dynamic partitioning of a node into containerized units that can adapt to changing workloads. Consequently, the new question that arises is: how can a physical node be partitioned into virtual resources to maximize the efficiency of the FL process? To answer this, we investigate various resource allocation methods that consider factors such as computational and network capabilities, the complexity of datasets, as well as the specific characteristics of the FL workflow and ML backend. We explore two scenarios: (i) running FL over a finite number of testbed nodes and (ii) hosting multiple parallel FL workflows on the same set of testbed nodes. Our findings reveal that the default configurations of state-of-the-art cloud orchestrators are sub-optimal when orchestrating FL workflows. Additionally, we demonstrate that different libraries and ML models exhibit diverse computational footprints. Building upon these insights, we discuss methods to mitigate computational interferences and enhance the overall performance of the FL pipeline execution. Full article

Generative artificial intelligence (AI) has emerged as a powerful technology with numerous applications in various domains. There is a need to identify the requirements and evaluation metrics for generative AI models designed for specific tasks. The purpose of the research aims to investigate the fundamental aspects of generative AI systems, including their requirements, models, input–output formats, and evaluation metrics. The study addresses key research questions and presents comprehensive insights to guide researchers, developers, and practitioners in the field. Firstly, the requirements necessary for implementing generative AI systems are examined and categorized into three distinct categories: hardware, software, and user experience. Furthermore, the study explores the different types of generative AI models described in the literature by presenting a taxonomy based on architectural characteristics, such as variational autoencoders (VAEs), generative adversarial networks (GANs), diffusion models, transformers, language models, normalizing flow models, and hybrid models. A comprehensive classification of input and output formats used in generative AI systems is also provided. Moreover, the research proposes a classification system based on output types and discusses commonly used evaluation metrics in generative AI. The findings contribute to advancements in the field, enabling researchers, developers, and practitioners to effectively implement and evaluate generative AI models for various applications. The significance of the research lies in understanding that generative AI system requirements are crucial for effective planning, design, and optimal performance. A taxonomy of models aids in selecting suitable options and driving advancements. Classifying input–output formats enables leveraging diverse formats for customized systems, while evaluation metrics establish standardized methods to assess model quality and performance. Full article

In the context of query-driven wireless sensor networks (WSNs), a unique scenario arises where sensor nodes are solicited by a base station, also known as a sink, based on specific areas of interest (AoIs). Upon receiving a query, designated sensor nodes are tasked with transmitting their data to the sink. However, the routing of these queries from the sink to the sensor nodes becomes intricate when the sink is mobile. The sink’s movement after issuing a query can potentially disrupt the performance of data delivery. To address these challenges, we have proposed an innovative approach called Query-driven Virtual Grid-based Routing Protocol (VGRQ), aiming to enhance energy efficiency and reduce data delivery delays. In VGRQ, we construct a grid consisting of square-shaped virtual cells, with the number of cells matching the count of sensor nodes. Each cell designates a specific node as the cell header (CH), and these CHs establish connections with each other to form a chain-like structure. This chain serves two primary purposes: sharing the mobile sink’s location information and facilitating the transmission of queries to the AoI as well as data to the sink. By employing the VGRQ approach, we seek to optimize the performance of query-driven WSNs. It enhances energy utilization and reduces data delivery delays. Additionally, VGRQ results in ≈10% and ≈27% improvement in energy consumption when compared with QRRP and QDVGDD, respectively. Full article

The Internet of Medical Things (IoMT) overcomes the flaws in the traditional healthcare system by enabling remote administration, more effective use of resources, and the mobility of medical devices to fulfil the patient’s needs. The IoMT makes it simple to review the patient’s cloud-based medical history in addition to allowing the doctor to keep a close eye on the patient’s condition. However, any communication must be secure and dependable due to the private nature of patient medical records. In this paper, we proposed an authentication method for the IoMT based on hyperelliptic curves and featuring dual signatures. The decreased key size of hyperelliptic curves makes the proposed scheme efficient. Furthermore, security validation analysis is performed with the help of the formal verification tool called Scyther, which shows that the proposed scheme is secure against several types of attacks. A comparison of the proposed scheme’s computational and communication expenses with those of existing schemes reveals its efficiency. Full article

This paper presents the mHealth Predictive Outbreak for COVID-19 (mPOC) framework, an autonomous platform based on wearable Internet of Medical Things (IoMT) devices for outbreak prediction and monitoring. It utilizes real-time physiological and environmental data to assess user risk. The framework incorporates the analysis of psychological and user-centric data, adopting a combination of top-down and bottom-up approaches. The mPOC mechanism utilizes the bidirectional Mobile Health (mHealth) Disaster Recovery System (mDRS) and employs an intelligent algorithm to calculate the Predictive Exposure Index (PEI) and Deterioration Risk Index (DRI). These indices trigger warnings to users based on adaptive threshold criteria and provide updates to the Outbreak Tracking Center (OTC). This paper provides a comprehensive description and analysis of the framework’s mechanisms and algorithms, complemented by the performance accuracy evaluation. By leveraging wearable IoMT devices, the mPOC framework showcases its potential in disease prevention and control during pandemics, offering timely alerts and vital information to healthcare professionals and individuals to mitigate outbreaks’ impact. Full article

Regulatory Technology (RegTech) is an emerging set of computing and network-based information systems and practices intended to enhance and improve regulatory compliance processes. Such technologies rely on collecting exclusive information from the environment and humans through automated Internet of Things (IoT) sensors and self-reported data. The key enablers of RegTech are the increased capabilities and reduced cost of IoT and Artificial Intelligence (AI) technologies. This article focuses on a survey of RegTech, highlighting the recent developments in various sectors. This work identifies the characteristics of existing implementations of RegTech applications in the financial industry. It examines the critical features that non-financial industries such as agriculture must address when using such technologies. We investigate the suitability of existing technologies applied in financial sectors to other industries and the potential gaps to be filled between them in terms of designing information systems for regulatory frameworks. This includes identifying specific operational parameters that are key differences between the financial and non-financial sectors that can be supported with IoT and AI technologies. These can be used by both producers of goods and services and regulators who need an affordable and efficient supervision method for managing relevant organizations. Full article

In the broad scientific field of time series forecasting, the ARIMA models and their variants have been widely applied for half a century now due to their mathematical simplicity and flexibility in application. However, with the recent advances in the development and efficient deployment of artificial intelligence models and techniques, the view is rapidly changing, with a shift towards machine and deep learning approaches becoming apparent, even without a complete evaluation of the superiority of the new approach over the classic statistical algorithms. Our work constitutes an extensive review of the published scientific literature regarding the comparison of ARIMA and machine learning algorithms applied to time series forecasting problems, as well as the combination of these two approaches in hybrid statistical-AI models in a wide variety of data applications (finance, health, weather, utilities, and network traffic prediction). Our review has shown that the AI algorithms display better prediction performance in most applications, with a few notable exceptions analyzed in our Discussion and Conclusions sections, while the hybrid statistical-AI models steadily outperform their individual parts, utilizing the best algorithmic features of both worlds. Full article

Task allocation in edge computing refers to the process of distributing tasks among the various nodes in an edge computing network. The main challenges in task allocation include determining the optimal location for each task based on the requirements such as processing power, storage, and network bandwidth, and adapting to the dynamic nature of the network. Different approaches for task allocation include centralized, decentralized, hybrid, and machine learning algorithms. Each approach has its strengths and weaknesses and the choice of approach will depend on the specific requirements of the application. In more detail, the selection of the most optimal task allocation methods depends on the edge computing architecture and configuration type, like mobile edge computing (MEC), cloud-edge, fog computing, peer-to-peer edge computing, etc. Thus, task allocation in edge computing is a complex, diverse, and challenging problem that requires a balance of trade-offs between multiple conflicting objectives such as energy efficiency, data privacy, security, latency, and quality of service (QoS). Recently, an increased number of research studies have emerged regarding the performance evaluation and optimization of task allocation on edge devices. While several survey articles have described the current state-of-the-art task allocation methods, this work focuses on comparing and contrasting different task allocation methods, optimization algorithms, as well as the network types that are most frequently used in edge computing systems. Full article

In the current era of prevailing information technology, the requirement for high availability and reliability of various types of services is critical. This paper focusses on the comparison and analysis of different high-availability solutions for Linux container environments. The objective was to identify the strengths and weaknesses of each solution and to determine the optimal container approach for common use cases. Through a series of structured experiments, basic performance metrics were collected, including average service recovery time, average transfer rate, and total number of failed calls. The container platforms tested included Docker, Kubernetes, and Proxmox. On the basis of a comprehensive evaluation, it can be concluded that Docker with Docker Swarm is generally the most effective high-availability solution for commonly used Linux containers. Nevertheless, there are specific scenarios in which Proxmox stands out, for example, when fast data transfer is a priority or when load balancing is not a critical requirement. Full article

In the era of digitalization and artificial intelligence (AI), the utilization of Metaverse technology has become increasingly crucial. As the world becomes more digitized, there is a pressing need to effectively transfer real-world assets into the digital realm and establish meaningful relationships between them. However, existing approaches have shown significant limitations in achieving this goal comprehensively. To address this, this research introduces an innovative methodology called the Meta-Metaverse, which aims to enhance the immersive experience and create realistic digital twins across various domains such as biology, genetics, economy, medicine, environment, gaming, digital twins, Internet of Things, artificial intelligence, machine learning, psychology, supply chain, social networking, smart manufacturing, and politics. The multi-layered structure of Metaverse platforms and digital twins allows for greater flexibility and scalability, offering valuable insights into the potential impact of advancing science, technology, and the internet. This article presents a detailed description of the proposed methodology and its applications, highlighting its potential to transform scientific research and inspire groundbreaking ideas in science, medicine, and technology. Full article

Information-centric networking (ICN) has gained significant attention due to its in-network caching and named-based routing capabilities. Caching plays a crucial role in managing the increasing network traffic and improving the content delivery efficiency. However, caching faces challenges as routers have limited cache space while the network hosts tens of thousands of items. This paper focuses on enhancing the cache performance by maximizing the cache hit ratio in the context of software-defined networking–ICN (SDN-ICN). We propose a statistical model that generates users’ content preferences, incorporating key elements observed in real-world scenarios. Furthermore, we introduce a graph neural network–double deep Q-network (GNN-DDQN) agent to make caching decisions for each node based on the user request history. Simulation results demonstrate that our caching strategy achieves a cache hit ratio 34.42% higher than the state-of-the-art policy. We also establish the robustness of our approach, consistently outperforming various benchmark strategies. Full article

Recently, the advent of blockchain (BC) has sparked a digital revolution in different fields, such as finance, healthcare, and supply chain. It is used by smart healthcare systems to provide transparency and control for personal medical records. However, BC and healthcare integration still face many challenges, such as storing patient data and privacy and security issues. In the context of security, new attacks target different parts of the BC network, such as nodes, consensus algorithms, Smart Contracts (SC), and wallets. Fraudulent data insertion can have serious consequences on the integrity and reliability of the BC, as it can compromise the trustworthiness of the information stored on it and lead to incorrect or misleading transactions. Detecting and preventing fraudulent data insertion is crucial for maintaining the credibility of the BC as a secure and transparent system for recording and verifying transactions. SCs control the transfer of assets, which is why they may be subject to several adverbial attacks. Therefore, many efforts have been proposed to detect vulnerabilities and attacks in the SCs, such as utilizing programming tools. However, their proposals are inadequate against the newly emerging vulnerabilities and attacks. Artificial Intelligence technology is robust in analyzing and detecting new attacks in every part of the BC network. Therefore, this article proposes a system architecture for detecting fraudulent transactions and attacks in the BC network based on Machine Learning (ML). It is composed of two stages: (1) Using ML to check medical data from sensors and block abnormal data from entering the blockchain network. (2) Using the same ML to check transactions in the blockchain, storing normal transactions, and marking abnormal ones as novel attacks in the attacks database. To build our system, we utilized two datasets and six machine learning algorithms (Logistic Regression, Decision Tree, KNN, Naive Bayes, SVM, and Random Forest). The results demonstrate that the Random Forest algorithm outperformed others by achieving the highest accuracy, execution time, and scalability. Thereby, it was considered the best solution among the rest of the algorithms for tackling the research problem. Moreover, the security analysis of the proposed system proves its robustness against several attacks which threaten the functioning of the blockchain-based healthcare application. Full article

Reconfigurable intelligent surface (RIS)-assisted non-orthogonal multiple access (NOMA) has the ability to overcome the challenges of the wireless environment like random fluctuations, shadowing, and mobility in an energy efficient way when compared to multiple input-multiple output (MIMO)-NOMA systems. The NOMA system can deliver controlled channel gains, improved coverage, increased energy efficiency, and enhanced fairness in resource allocation with the help of RIS. RIS-assisted NOMA will be one of the primary potential components of sixth-generation (6G) networks, due to its appealing advantages. The analytical outage probability expressions for smart RIS-assisted fixed NOMA (FNOMA) are derived in this paper, taking into account the instances of RIS as a smart reflector (SR) and an access point (AP). The analytical and simulation findings are found to be extremely comparable. In order to effectively maximize the sum capacity, the formulas for optimal powers to be assigned for a two-user case are also established. According to simulations, RIS-assisted FNOMA surpasses FNOMA in terms of outage and sum capacity. With the aid of RIS and the optimal power assignment, RIS-AP-FNOMA offers ≈62% improvement in sum capacity over the FNOMA system for a signal-to-noise ratio (SNR) of 10 dB and 32 elements in RIS. A significant improvement is also brought about by the increase in reflective elements. Full article