A Decentralized Digital Watermarking Framework for Secure and Auditable Video Data in Smart Vehicular Networks
Visualisation Design Ideation with AI: A New Framework, Vocabulary, and Tool
Alquist 5.0: Dialogue Trees Meet Generative Models, a Novel Approach for Enhancing SocialBot Conversations
Time-Efficient Neural-Network-Based Dynamic Area Optimization Algorithm for High-Altitude Platform Station Mobile Communications
A Survey on Data Availability in Layer 2 Blockchain Rollups: Open Challenges and Future Improvements

Journal Description

Future Internet

Future Internet is an international, peer-reviewed, open access journal on internet technologies and the information society, published monthly online by MDPI.

Open Access— free for readers, with article processing charges (APC) paid by authors or their institutions.
High Visibility: indexed within Scopus, ESCI (Web of Science), Ei Compendex, dblp, Inspec, and other databases.
Journal Rank: JCR - Q2 (Computer Science, Information Systems) / CiteScore - Q1 (Computer Networks and Communications)
Rapid Publication: manuscripts are peer-reviewed and a first decision is provided to authors approximately 13.1 days after submission; acceptance to publication is undertaken in 2.8 days (median values for papers published in this journal in the first half of 2024).
Recognition of Reviewers: reviewers who provide timely, thorough peer-review reports receive vouchers entitling them to a discount on the APC of their next publication in any MDPI journal, in appreciation of the work done.

Impact Factor: 2.8 (2023); 5-Year Impact Factor: 3.0 (2023)

Imprint Information Journal Flyer Open Access ISSN: 1999-5903

Latest Articles

43 pages, 4383 KiB

Open AccessReview

Integrating UAVs and RISs in Future Wireless Networks: A Review and Tutorial on IoTs and Vehicular Communications

by Mohsen Eskandari and Andrey V. Savkin

Future Internet 2024, 16(12), 433; https://doi.org/10.3390/fi16120433 (registering DOI) - 21 Nov 2024

Abstract

The rapid evolution of smart cities relies heavily on advancements in wireless communication systems and extensive IoT networks. This paper offers a comprehensive review of the critical role and future potential of integrating unmanned aerial vehicles (UAVs) and reconfigurable intelligent surfaces (RISs) to enhance Internet of Vehicles (IoV) systems within beyond-fifth-generation (B5G) and sixth-generation (6G) networks. We explore the combination of quasi-optical millimeter-wave (mmWave) signals with UAV-enabled, RIS-assisted networks and their applications in urban environments. This review covers essential areas such as channel modeling and position-aware beamforming in dynamic networks, including UAVs and IoVs. Moreover, we investigate UAV navigation and control, emphasizing the development of obstacle-free trajectory designs in dense urban areas while meeting kinodynamic and motion constraints. The emerging potential of RIS-equipped UAVs (RISeUAVs) is highlighted, along with their role in supporting IoVs and in mobile edge computing. Optimization techniques, including convex programming methods and machine learning, are explored to tackle complex challenges, with an emphasis on studying computational complexity and feasibility for real-time operations. Additionally, this review highlights the integrated localization and communication strategies to enhance UAV and autonomous ground vehicle operations. This tutorial-style overview offers insights into the technical challenges and innovative solutions of the next-generation wireless networks in smart cities, with a focus on vehicular communications. Finally, future research directions are outlined. Full article

(This article belongs to the Special Issue 2024 and 2025 Feature Papers from Future Internet’s Editorial Board Members)

► Show Figures

Figure 1

16 pages, 3101 KiB

Open AccessArticle

Using Multimodal Foundation Models for Detecting Fake Images on the Internet with Explanations

by Vishnu S. Pendyala and Ashwin Chintalapati

Future Internet 2024, 16(12), 432; https://doi.org/10.3390/fi16120432 (registering DOI) - 21 Nov 2024

Abstract

Generative AI and multimodal foundation models have fueled a proliferation of fake content on the Internet. This paper investigates if foundation models help detect and thereby contain the spread of fake images. The task of detecting fake images is a formidable challenge owing to its visual nature and intricate analysis. This paper details experiments using four multimodal foundation models, Llava, CLIP, Moondream2, and Gemini 1.5 Flash, to detect fake images. Explainable AI techniques such as Local Interpretable Model-Agnostic Explanations (LIME) and removal-based explanations are used to gain insights into the detection process. The dataset used comprised real images and fake images generated by a generative artificial intelligence tool called MidJourney. Results show that the models can achieve up to a 69% accuracy rate in detecting fake images in an intuitively explainable way, as confirmed by multiple techniques and metrics. Full article

► Show Figures

Figure 1

24 pages, 1273 KiB

Open AccessArticle

Flexible Hyper-Distributed IoT–Edge–Cloud Platform for Real-Time Digital Twin Applications on 6G-Intended Testbeds for Logistics and Industry

by Maria Crespo-Aguado, Raul Lozano, Fernando Hernandez-Gobertti, Nuria Molner and David Gomez-Barquero

Future Internet 2024, 16(11), 431; https://doi.org/10.3390/fi16110431 - 20 Nov 2024

Abstract

This paper presents the design and development of a flexible hyper-distributed IoT–Edge–Cloud computing platform for real-time Digital Twins in real logistics and industrial environments, intended as a novel living lab and testbed for future 6G applications. It expands the limited capabilities of IoT devices with extended Cloud and Edge computing functionalities, creating an IoT–Edge–Cloud continuum platform composed of multiple stakeholder solutions, in which vertical application developers can take full advantage of the computing resources of the infrastructure. The platform is built together with a private 5G network to connect machines and sensors on a large scale. Artificial intelligence and machine learning are used to allocate computing resources for real-time services by an end-to-end intelligent orchestrator, and real-time distributed analytic tools leverage Edge computing platforms to support different types of Digital Twin applications for logistics and industry, such as immersive remote driving, with specific characteristics and features. Performance evaluations demonstrated the platform’s capability to support the high-throughput communications required for Digital Twins, achieving user-experienced rates close to the maximum theoretical values, up to 552 Mb/s for the downlink and 87.3 Mb/s for the uplink in the n78 frequency band. Moreover, the platform’s support for Digital Twins was validated via QoE assessments conducted on an immersive remote driving prototype, which demonstrated high levels of user satisfaction in key dimensions such as presence, engagement, control, sensory integration, and cognitive load. Full article

(This article belongs to the Special Issue Convergence of Edge Computing and Next Generation Networking)

► Show Figures

Figure 1

Figure 1
A conceptual diagram based on the Hexa-X 6G vision of interconnected worlds [<a href="#B1-futureinternet-16-00431" class="html-bibr">1</a>], now also encompassing Digital Twins, IoT, and Edge and Cloud computing components. The physical world comprises IoT devices, sensors, and autonomous machines that collect and act on real-world data, forming the basis of cyber-physical twinning with real-time feedback. The digital world represents a virtual replica of the physical world, comprehended along the IoT-Cloud-Edge computing continuum, which facilitates data processing, AI/ML applications, and storage for large datasets. The human world includes haptic devices, user interfaces, and Human–Machine Interfaces to enable immersive interaction with both digital and physical assets. This interconnected 6G ecosystem enables Immersive Communications across worlds, supports real-time control for responsive applications, and achieves cyber-physical twinning for advanced simulations and monitoring. Full article ">Figure 2
The architecture of the proposed IoT–Edge–Cloud platform, exemplified for two sites, structured into three primary layers: IoT-Device, Edge, and Cloud. This design enables efficient communication and scalability for connected devices. The figure illustrates flexibility in application deployment, showing that applications can operate in either the Edge or Cloud layer or even span both. Each site includes a private 5G network, represented by a dotted square, which provides 5G connectivity to the IoT-Device layer. The Edge and Network Orchestration layer manages resource allocation across both sites, which are interconnected by a direct private fiber link, supporting seamless operation and coordination between the sites. Full article ">Figure 3
The hyper-distributed experimental setup, comprising two geographically distanced Edge sites for the development and validation of an IoT-to-Edge-to-Cloud platform. The architecture illustrates the distribution of essential elements, such as the 5G core location, distributed RAN components—CUs (Centralized Units), DUs (Distributed Units), and RUs (Remote Units)—and Edge Servers at both sites. Edge Site 1 and Edge Site 2 are interconnected via secure links, with dedicated firewalls and internal routers to manage network traffic. This configuration allows for real-time data processing and transmission across the IoT, Edge, and Cloud layers, supporting latency-sensitive applications and resilient network connectivity. Full article ">Figure 4
A graphical representation of maximum data rates achieved for different UE and UPF configurations for both download (DL) and upload (UL) links. Full article ">Figure 5
A comparison of the theoretical maximum data rates against the measured rates across different frequency bands (n78 and n40) for both download (DL) and upload (UL) links. Full article ">Figure 6
Edge Site 1 network architecture for an immersive remote driving application, which includes two teleoperated vehicles leveraging 5G components and Edge servers for real-time control and feedback. The connectivity is provided through outdoor and indoor 5G bands (n40 and n78, respectively). The setup includes a Cloud Robotics Platform for processing the Digital Twin information and AI-driven applications for video-based environment detection, interfacing with Edge servers for lower-latency processing. Full article ">

22 pages, 945 KiB

Open AccessReview

Resilience in the Internet of Medical Things: A Review and Case Study

by Vikas Tomer, Sachin Sharma and Mark Davis

Future Internet 2024, 16(11), 430; https://doi.org/10.3390/fi16110430 - 20 Nov 2024

Abstract

The Internet of Medical Things (IoMT), an extension of the Internet of Things (IoT), is still in its early stages of development. Challenges that are inherent to IoT, persist in IoMT as well. The major focus is on data transmission within the healthcare domain due to its profound impact on health and public well-being. Issues such as latency, bandwidth constraints, and concerns regarding security and privacy are critical in IoMT owing to the sensitive nature of patient data, including patient identity and health status. Numerous forms of cyber-attacks pose threats to IoMT networks, making the reliable and secure transmission of critical medical data a challenging task. Several other situations, such as natural disasters, war, construction works, etc., can cause IoMT networks to become unavailable and fail to transmit the data. The first step in these situations is to recover from failure as quickly as possible, resume the data transfer, and detect the cause of faults, failures, and errors. Several solutions exist in the literature to make the IoMT resilient to failure. However, no single approach proposed in the literature can simultaneously protect the IoMT networks from various attacks, failures, and faults. This paper begins with a detailed description of IoMT and its applications. It considers the underlying requirements of resilience for IoMT networks, such as monitoring, control, diagnosis, and recovery. This paper comprehensively analyzes existing research efforts to provide IoMT network resilience against diverse causes. After investigating several research proposals, we identify that the combination of software-defined networks (SDNs), machine learning (ML), and microservices architecture (MSA) has the capabilities to fulfill the requirements for achieving resilience in the IoMT networks. It mainly focuses on the analysis of technologies, such as SDN, ML, and MSA, separately, for meeting the resilience requirements in the IoMT networks. SDN can be used for monitoring and control, and ML can be used for anomaly detection and diagnosis, whereas MSA can be used for bringing distributed functionality and recovery into the IoMT networks. This paper provides a case study that describes the remote patient monitoring (RPM) of a heart patient in IoMT networks. It covers the different failure scenarios in IoMT infrastructure. Finally, we provide a proposed methodology that elaborates how distributed functionality can be achieved during these failures using machine learning, software-defined networks, and microservices technologies. Full article

(This article belongs to the Special Issue The Future Internet of Medical Things II)

► Show Figures

Figure 1

19 pages, 3800 KiB

Open AccessArticle

Fully Open-Source Meeting Minutes Generation Tool

by Amma Liesvarastranta Haz, Yohanes Yohanie Fridelin Panduman, Nobuo Funabiki, Evianita Dewi Fajrianti and Sritrusta Sukaridhoto

Future Internet 2024, 16(11), 429; https://doi.org/10.3390/fi16110429 - 20 Nov 2024

Abstract

With the increasing use of online meetings, there is a growing need for efficient tools that can automatically generate meeting minutes from recorded sessions. Current solutions often rely on proprietary systems, limiting adaptability and flexibility. This paper investigates whether various open-source models and methods such as audio-to-text conversion, summarization, keyword extraction, and optical character recognition (OCR) can be integrated to create a meeting minutes generation tool for recorded video presentations. For this purpose, a series of evaluations are conducted to identify suitable models. Then, the models are integrated into a system that is modular yet accurate. The utilization of an open-source approach ensures that the tool remains accessible and adaptable to the latest innovations, thereby ensuring continuous improvement over time. Furthermore, this approach also benefits organizations and individuals by providing a cost-effective and flexible alternative. This work contributes to creating a modular and easily extensible open-source framework that integrates several advanced technologies and future new models into a cohesive system. The system was evaluated on ten videos created under controlled conditions, which may not fully represent typical online presentation recordings. It showed strong performance in audio-to-text conversion with a low word-error rate. Summarization and keyword extraction were functional but showed room for improvement in terms of precision and relevance, as gathered from the users’ feedback. These results confirm the system’s effectiveness and efficiency in generating usable meeting minutes from recorded presentation videos, with room for improvement in future works. Full article

(This article belongs to the Special Issue Deep Learning and Natural Language Processing II)

► Show Figures

Figure 1

26 pages, 1394 KiB

Open AccessArticle

Fault Prediction and Reconfiguration Optimization in Smart Grids: AI-Driven Approach

by David Carrascal, Paula Bartolomé, Elisa Rojas, Diego Lopez-Pajares, Nicolas Manso and Javier Diaz-Fuentes

Future Internet 2024, 16(11), 428; https://doi.org/10.3390/fi16110428 - 20 Nov 2024

Abstract

Smart grids (SGs) are essential for the efficient and distributed management of electrical distribution networks. A key task in SG management is fault detection and subsequently, network reconfiguration to minimize power losses and balance loads. This process should minimize power losses while optimizing distribution by balancing loads across the grid. However, the current literature yields a lack of methods for efficient fault prediction and fast reconfiguration. To achieve this goal, this paper builds on DEN2DE, an adaptable routing and reconfiguration solution potentially applicable to SGs, and investigates its potential extension with AI-based fault prediction using real-world datasets and randomly generated topologies based on the IEEE 123 Node Test Feeder. The study applies models based on Machine Learning (ML) and Deep Learning (DL) techniques, specifically evaluating Random Forest (RF) and Support Vector Machine (SVM) as ML methods, and Artificial Neural Network (ANN) as a DL method, evaluating each for accuracy, precision, and recall. Results indicate that the RF model with Recursive Feature Elimination (RFECV) achieves 94.28% precision and 81.05% recall, surpassing SVM (precision 89.32%, recall 6.95%) and ANN (precision 72.17%, recall 13.49%) in fault detection accuracy and reliability. Full article

(This article belongs to the Section Smart System Infrastructure and Applications)

► Show Figures

Figure 1

16 pages, 725 KiB

Open AccessArticle

Virtualization vs. Containerization, a Comparative Approach for Application Deployment in the Computing Continuum Focused on the Edge

by Hamish Sturley, Augustin Fournier, Andoni Salcedo-Navarro, Miguel Garcia-Pineda and Jaume Segura-Garcia

Future Internet 2024, 16(11), 427; https://doi.org/10.3390/fi16110427 - 19 Nov 2024

Abstract

With the emergence of containerization 10 years ago, we saw a compact, convenient and portable way of running apps directly concurrently with virtualization. The major difference is in the architecture. Containers share the same kernel as the guest and then do not virtualize low-layer components like the Central Processing Unit (CPU). On the one hand, they are lighter and more flexible than virtual machines (VMs). On the other hand, VMs can more precisely meet the low-layer needs and are completely autonomous systems. Nowadays, what is the best architecture to use to develop an application? In this paper, we will study the two main virtual methods of deploying this. We will compare both methods on several criteria: compatibility based on user experience and the ease of installation/deployment, scalability based on the automatic elasticity facing the workload and energy efficiency in terms of energy and computer resources. After the tests, we conclude that the containerization option is the most ecologically advantageous option in terms of energy consumption. Full article

(This article belongs to the Special Issue Scalable and Distributed Cloud Continuum Orchestration for Next-Generation IoT Applications: Latest Advances and Prospects)

► Show Figures

Figure 1

19 pages, 2662 KiB

Open AccessArticle

Identifying Persons of Interest in Digital Forensics Using NLP-Based AI

by Jonathan Adkins, Ali Al Bataineh and Majd Khalaf

Future Internet 2024, 16(11), 426; https://doi.org/10.3390/fi16110426 - 18 Nov 2024

Abstract

The field of digital forensics relies on expertise from multiple domains, including computer science, criminology, and law. It also relies on different toolsets and an analyst’s expertise to parse enormous amounts of user-generated data to find clues that help crack a case. This process of investigative analysis is often done manually. Artificial Intelligence (AI) can provide practical solutions to efficiently mine enormous amounts of data to find useful patterns that can be leveraged to investigate crimes. Natural Language Processing (NLP) is a subdomain of research under AI that deals with problems involving unstructured data, specifically language. The domain of NLP includes several tools to parse text, including topic modeling, pairwise correlation, word vector cosine distance measurement, and sentiment analysis. In this research, we propose a digital forensic investigative technique that uses an ensemble of NLP tools to identify a person of interest list based on a corpus of text. Our proposed method serves as a type of human feature reduction, where a total pool of suspects is filtered down to a short list of candidates who possess a higher correlation with the crime being investigated. Full article

► Show Figures

Figure 1

24 pages, 2020 KiB

Open AccessArticle

Enhanced Long-Range Network Performance of an Oil Pipeline Monitoring System Using a Hybrid Deep Extreme Learning Machine Model

by Abbas Kubba, Hafedh Trabelsi and Faouzi Derbel

Future Internet 2024, 16(11), 425; https://doi.org/10.3390/fi16110425 - 17 Nov 2024

Abstract

Leak detection in oil and gas pipeline networks is a climacteric and frequent issue in the oil and gas field. Many establishments have long depended on stationary hardware or traditional assessments to monitor and detect abnormalities. Rapid technological progress; innovation in engineering; and advanced technologies providing cost-effective, rapidly executed, and easy to implement solutions lead to building an efficient oil pipeline leak detection and real-time monitoring system. In this area, wireless sensor networks (WSNs) are increasingly required to enhance the reliability of checkups and improve the accuracy of real-time oil pipeline monitoring systems with limited hardware resources. The real-time transient model (RTTM) is a leak detection method integrated with LoRaWAN technology, which is proposed in this study to implement a wireless oil pipeline network for long distances. This study will focus on enhancing the LoRa network parameters, e.g., node power consumption, average packet loss, and delay, by applying several machine learning techniques in order to optimize the durability of individual nodes’ lifetimes and enhance total system performance. The proposed system is implemented in an OMNeT++ network simulator with several frameworks, such as Flora and Inet, to cover the LoRa network, which is used as the system’s network infrastructure. In order to implement artificial intelligence over the FLoRa network, the LoRa network was integrated with several programming tools and libraries, such as Python script and the TensorFlow libraries. Several machine learning algorithms have been applied, such as the random forest (RF) algorithm and the deep extreme learning machine (DELM) technique, to develop the proposed model and improve the LoRa network’s performance. They improved the LoRa network’s output performance, e.g., its power consumption, packet loss, and packet delay, with different enhancement ratios. Finally, a hybrid deep extreme learning machine model was built and selected as the proposed model due to its ability to improve the LoRa network’s performance, with perfect prediction accuracy, a mean square error of 0.75, and an exceptional enhancement ratio of 39% for LoRa node power consumption. Full article

(This article belongs to the Topic Advances in Wireless and Mobile Networking)

► Show Figures

Figure 1

21 pages, 1716 KiB

Open AccessArticle

AI-Driven Neuro-Monitoring: Advancing Schizophrenia Detection and Management Through Deep Learning and EEG Analysis

by Elena-Anca Paraschiv, Lidia Băjenaru, Cristian Petrache, Ovidiu Bica and Dragoș-Nicolae Nicolau

Future Internet 2024, 16(11), 424; https://doi.org/10.3390/fi16110424 - 16 Nov 2024

Abstract

Schizophrenia is a complex neuropsychiatric disorder characterized by disruptions in brain connectivity and cognitive functioning. Continuous monitoring of neural activity is essential, as it allows for the detection of subtle changes in brain connectivity patterns, which could provide early warnings of cognitive decline or symptom exacerbation, ultimately facilitating timely therapeutic interventions. This paper proposes a novel approach for detecting schizophrenia-related abnormalities using deep learning (DL) techniques applied to electroencephalogram (EEG) data. Using an openly available EEG dataset on schizophrenia, the focus is on preprocessed event-related potentials (ERPs) from key electrode sites and applied transfer entropy (TE) analysis to quantify the directional flow of information between brain regions. TE matrices were generated to capture neural connectivity patterns, which were then used as input for a hybrid DL model, combining convolutional neural networks (CNNs) and Bidirectional Long Short-Term Memory (BiLSTM) networks. The model achieved a performant accuracy of 99.94% in classifying schizophrenia-related abnormalities, demonstrating its potential for real-time mental health monitoring. The generated TE matrices revealed significant differences in connectivity between the two groups, particularly in frontal and central brain regions, which are critical for cognitive processing. These findings were further validated by correlating the results with EEG data obtained from the Muse 2 headband, emphasizing the potential for portable, non-invasive monitoring of schizophrenia in real-world settings. The final model, integrated into the NeuroPredict platform, offers a scalable solution for continuous mental health monitoring. By incorporating EEG data, heart rate, sleep patterns, and environmental metrics, NeuroPredict facilitates early detection and personalized interventions for schizophrenia patients. Full article

(This article belongs to the Special Issue eHealth and mHealth)

► Show Figures

Figure 1

26 pages, 4934 KiB

Open AccessArticle

Capacity and Coverage Dimensioning for 5G Standalone Mixed-Cell Architecture: An Impact of Using Existing 4G Infrastructure

by Naba Raj Khatiwoda, Babu Ram Dawadi and Sashidhar Ram Joshi

Future Internet 2024, 16(11), 423; https://doi.org/10.3390/fi16110423 - 14 Nov 2024

Abstract

With the increasing demand for expected data volume daily, current telecommunications infrastructure can not meet requirements without using enhanced technologies adopted by 5G and beyond networks. Due to their diverse features, 5G technologies and services will be phenomenal in the coming days. Proper planning procedures are to be adopted to provide cost-effective and quality telecommunication services. In this paper, we planned 5G network deployment in two frequency ranges, 3.5 GHz and 28 GHz, using a mixed cell structure. We used metaheuristic approaches such as Grey Wolf Optimization (GWO), Sparrow Search Algorithm (SSA), Whale Optimization Algorithm (WOA), Marine Predator Algorithm (MPA), Particle Swarm Optimization (PSO), and Ant Lion Optimization (ALO) for optimizing the locations of remote radio units. The comparative analysis of metaheuristic algorithms shows that the proposed network is efficient in providing an average data rate of 50 Mbps, can meet the coverage requirements of at least 98%, and meets quality-of-service requirements. We carried out the case study for an urban area and another suburban area of Kathmandu Valley, Nepal. We analyzed the outcomes of 5G greenfield deployment and 5G deployment using existing 4G infrastructure. Deploying 5G networks using existing 4G infrastructure, resources can be saved up to 33.7% and 54.2% in urban and suburban areas, respectively. Full article

(This article belongs to the Topic Advances in Wireless and Mobile Networking)

► Show Figures

Figure 1

20 pages, 552 KiB

Open AccessArticle

SBNNR: Small-Size Bat-Optimized KNN Regression

by Rasool Seyghaly, Jordi Garcia, Xavi Masip-Bruin and Jovana Kuljanin

Future Internet 2024, 16(11), 422; https://doi.org/10.3390/fi16110422 - 14 Nov 2024

Abstract

Small datasets are frequent in some scientific fields. Such datasets are usually created due to the difficulty or cost of producing laboratory and experimental data. On the other hand, researchers are interested in using machine learning methods to analyze this scale of data. For this reason, in some cases, low-performance, overfitting models are developed for small-scale data. As a result, it appears necessary to develop methods for dealing with this type of data. In this research, we provide a new and innovative framework for regression problems with a small sample size. The base of our proposed method is the K-nearest neighbors (KNN) algorithm. For feature selection, instance selection, and hyperparameter tuning, we use the bat optimization algorithm (BA). Generative Adversarial Networks (GANs) are employed to generate synthetic data, effectively addressing the challenges associated with data sparsity. Concurrently, Deep Neural Networks (DNNs), as a deep learning approach, are utilized for feature extraction from both synthetic and real datasets. This hybrid framework integrates KNN, DNN, and GAN as foundational components and is optimized in multiple aspects (features, instances, and hyperparameters) using BA. The outcomes exhibit an enhancement of up to 5% in the coefficient of determination (

R^{2}

score) using the proposed method compared to the standard KNN method optimized through grid search. Full article

(This article belongs to the Special Issue Deep Learning Techniques Addressing Data Scarcity)

► Show Figures

Figure 1

13 pages, 420 KiB

Open AccessArticle

Towards a Decentralized Collaborative Framework for Scalable Edge AI

by Ahmed M. Abdelmoniem , Mona Jaber , Ali Anwar , Yuchao Zhang and Mingliang Gao

Future Internet 2024, 16(11), 421; https://doi.org/10.3390/fi16110421 - 14 Nov 2024

Abstract

Nowadays, Edge Intelligence has seen unprecedented growth in most of our daily life applications. Traditionally, most applications required significant efforts into data collection for data-driven analytics, raising privacy concerns. The proliferation of specialized hardware on sensors, wearable, mobile, and IoT devices has led to the growth of Edge Intelligence, which has become an integral part of the development cycle of most modern applications. However, scalability issues hinder their wide-scale adoption. We aim to focus on these challenges and propose a scalable decentralized edge intelligence framework. Therefore, we analyze and empirically evaluate the challenges of existing methods, and design an architecture that overcomes these challenges. The proposed approach is client-driven and model-centric, allowing models to be shared between entities in a scalable fashion. We conduct experiments over various benchmarks to show that the proposed approach presents an efficient alternative to the existing baseline method, and it can be a viable solution to scale edge intelligence. Full article

(This article belongs to the Special Issue IoT, Edge, and Cloud Computing in Smart Cities)

► Show Figures

Figure 1

16 pages, 25350 KiB

Open AccessArticle

Eye Tracking and Human Influence Factors’ Impact on Quality of Experience of Mobile Gaming

by Omer Nawaz, Siamak Khatibi, Muhammad Nauman Sheikh and Markus Fiedler

Future Internet 2024, 16(11), 420; https://doi.org/10.3390/fi16110420 - 13 Nov 2024

Abstract

Mobile gaming accounts for more than 50% of global online gaming revenue, surpassing console and browser-based gaming. The success of mobile gaming titles depends on optimizing applications for the specific hardware constraints of mobile devices, such as smaller displays and lower computational power, to maximize battery life. Additionally, these applications must dynamically adapt to the variations in network speed inherent in mobile environments. Ultimately, user engagement and satisfaction are critical, necessitating a favorable comparison to browser and console-based gaming experiences. While Quality of Experience (QoE) subjective evaluations through user surveys are the most reliable method for assessing user perception, various factors, termed influence factors (IFs), can affect user ratings of stimulus quality. This study examines human influence factors in mobile gaming, specifically analyzing the impact of user delight towards displayed content and the effect of gaze tracking. Using Pupil Core eye-tracking hardware, we captured user interactions with mobile devices and measured visual attention. Video stimuli from eight popular games were selected, with resolutions of 720p and 1080p and frame rates of 30 and 60 fps. Our results indicate a statistically significant impact of user delight on the MOS for most video stimuli across all games. Additionally, a trend favoring higher frame rates over screen resolution emerged in user ratings. These findings underscore the significance of optimizing mobile gaming experiences by incorporating models that estimate human influence factors to enhance user satisfaction and engagement. Full article

► Show Figures

Figure 1

30 pages, 1179 KiB

Open AccessReview

Advancing Additive Manufacturing Through Machine Learning Techniques: A State-of-the-Art Review

by Shaoping Xiao, Junchao Li, Zhaoan Wang, Yingbin Chen and Soheyla Tofighi

Future Internet 2024, 16(11), 419; https://doi.org/10.3390/fi16110419 - 13 Nov 2024

Abstract

In the fourth industrial revolution, artificial intelligence and machine learning (ML) have increasingly been applied to manufacturing, particularly additive manufacturing (AM), to enhance processes and production. This study provides a comprehensive review of the state-of-the-art achievements in this domain, highlighting not only the widely discussed supervised learning but also the emerging applications of semi-supervised learning and reinforcement learning. These advanced ML techniques have recently gained significant attention for their potential to further optimize and automate AM processes. The review aims to offer insights into various ML technologies employed in current research projects and to promote the diverse applications of ML in AM. By exploring the latest advancements and trends, this study seeks to foster a deeper understanding of ML’s transformative role in AM, paving the way for future innovations and improvements in manufacturing practices. Full article

► Show Figures

Figure 1

19 pages, 654 KiB

Open AccessArticle

A Methodological Approach to Securing Cyber-Physical Systems for Critical Infrastructures

by Antonello Calabrò, Enrico Cambiaso, Manuel Cheminod, Ivan Cibrario Bertolotti, Luca Durante, Agostino Forestiero, Flavio Lombardi, Giuseppe Manco, Eda Marchetti, Albina Orlando and Giuseppe Papuzzo

Future Internet 2024, 16(11), 418; https://doi.org/10.3390/fi16110418 - 12 Nov 2024

Abstract

Modern ICT infrastructures, i.e., cyber-physical systems and critical infrastructures relying on interconnected IT (Information Technology)- and OT (Operational Technology)-based components and (sub-)systems, raise complex challenges in tackling security and safety issues. Nowadays, many security controls and mechanisms have been made available and exploitable to solve specific security needs, but, when dealing with very complex and multifaceted heterogeneous systems, a methodology is needed on top of the selection of each security control that will allow the designer/maintainer to drive her/his choices to build and keep the system secure as a whole, leaving the choice of the security controls to the last step of the system design/development. This paper aims at providing a comprehensive methodological approach to design and preliminarily implement an Open Platform Architecture (OPA) to secure the cyber-physical systems of critical infrastructures. Here, the Open Platform Architecture (OPA) depicts how an already existing or under-design target system (TS) can be equipped with technologies that are modern or currently under development, to monitor and timely detect possibly dangerous situations and to react in an automatic way by putting in place suitable countermeasures. A multifaceted use case (UC) that is able to show the OPA, starting from the security and safety requirements to the fully designed system, will be developed step by step to show the feasibility and the effectiveness of the proposed methodology. Full article

(This article belongs to the Special Issue State-of-the-Art Future Internet Technology in Italy 2024–2025)

► Show Figures

Figure 1

27 pages, 3088 KiB

Open AccessArticle

Approaches to Identifying Emotions and Affections During the Museum Learning Experience in the Context of the Future Internet

by Iana Fominska, Stefano Di Tore, Michele Nappi, Gerardo Iovane, Maurizio Sibilio and Angela Gelo

Future Internet 2024, 16(11), 417; https://doi.org/10.3390/fi16110417 - 10 Nov 2024

Abstract

The Future Internet aims to revolutionize digital interaction by integrating advanced technologies like AI and IoT, enabling a dynamic and resilient network. It envisions emotionally intelligent systems that can interpret and respond to human feelings, creating immersive, empathy-driven learning experiences. This evolution aspires to form a responsive digital ecosystem that seamlessly connects technology and human emotion. This paper presents a computational model aimed at enhancing the emotional aspect of learning experiences within museum environments. The model is designed to represent and manage affective and emotional feedback, with a focus on how emotions can significantly impact the learning process in a museum context. The proposed model seeks to identify and quantify emotions during a visitor’s engagement with museum exhibits. To achieve this goal, we primarily explored the following: (i) methods and techniques for assessing and recognizing emotional responses in museum visitors, (ii) feedback management strategies based on the detection of visitors’ emotional states. Then, the methodology was tested on 1000 cases via specific questionnaire forms, along with the presentation of images and short videos, and the results of data analysis are reported. The findings contribute toward establishing a comprehensive methodology for the identification and quantification of the emotional state of museum visitors. Full article

(This article belongs to the Section Internet of Things)

► Show Figures

Figure 1

Figure 1
Emotion classes for emotivity. Full article ">Figure 2
Emotion classes for affectivity (* means to distinguish the term when referring to a passionate person who has a connotation of sensual/sexual passion for the things synonymous with love). Full article ">Figure 3
The distribution of respondents: states divided by gender, with strong orange for female and light orange for male. Full article ">Figure 4
Distribution of responses to questionnaires with respect to the different emotions. Full article ">Figure 5
Experimental results for emotive intensity with respect to the 36 questions in the questionnaires. Full article ">Figure 6
Distribution of responses to questionnaires with respect to the different affections. Full article ">Figure 7
Experimental results of affectivity intensity with respect to the 36 questions in the questionnaires. Full article ">Figure 8
Experimental results for affectivity and emotivity. Full article ">

16 pages, 747 KiB

Open AccessArticle

Automatically Injecting Robustness Statements into Distributed Applications

by Daniele Marletta, Alessandro Midolo and Emiliano Tramontana

Future Internet 2024, 16(11), 416; https://doi.org/10.3390/fi16110416 - 10 Nov 2024

Abstract

When developing a distributed application, several issues need to be handled, and software components should include some mechanisms to make their execution resilient when network faults, delays, or tampering occur. For example, synchronous calls represent a too-tight connection between a client requesting a service and the service itself, whereby potential network delays or temporary server overloads would keep the client side hanging, exposing it to a domino effect. The proposed approach assists developers in dealing with such issues by providing an automatic tool that enhances a distributed application using simple blocking calls and makes it robust in the face of adverse events. The proposed devised solution consists in automatically identifying the parts of the application that connect to remote services using simple synchronous calls and substituting them with a generated customized snippet of code that handles potential network delays or faults. To accurately perform the proposed transformation, the devised tool finds application code statements that are data-dependent on the results of the original synchronous calls. Then, for the dependent statements, a solution involving guarding code, proper synchronization, and timeouts is injected. We experimented with the analysis and transformation of several applications and report a meaningful example, together with the analysis of the results achieved. Full article

(This article belongs to the Special Issue Cloud Computing and High Performance Computing (HPC) Advances for Next Generation Internet)

► Show Figures

Figure 1

41 pages, 438 KiB

Open AccessReview

Recent Advancements in Federated Learning: State of the Art, Fundamentals, Principles, IoT Applications and Future Trends

by Christos Papadopoulos, Konstantinos-Filippos Kollias and George F. Fragulis

Future Internet 2024, 16(11), 415; https://doi.org/10.3390/fi16110415 - 9 Nov 2024

Abstract

Federated learning (FL) is creating a paradigm shift in machine learning by directing the focus of model training to where the data actually exist. Instead of drawing all data into a central location, which raises concerns about privacy, costs, and delays, FL allows learning to take place directly on the device, keeping the data safe and minimizing the need for transfer. This approach is especially important in areas like healthcare, where protecting patient privacy is critical, and in industrial IoT settings, where moving large numbers of data is not practical. What makes FL even more compelling is its ability to reduce the bias that can occur when all data are centralized, leading to fairer and more inclusive machine learning outcomes. However, it is not without its challenges—particularly with regard to keeping the models secure from attacks. Nonetheless, the potential benefits are clear: FL can lower the costs associated with data storage and processing, while also helping organizations to meet strict privacy regulations like GDPR. As edge computing continues to grow, FL’s decentralized approach could play a key role in shaping how we handle data in the future, moving toward a more privacy-conscious world. This study identifies ongoing challenges in ensuring model security against adversarial attacks, pointing to the need for further research in this area. Full article

(This article belongs to the Special Issue IoT Security: Threat Detection, Analysis and Defense)

► Show Figures

Figure 1

24 pages, 453 KiB

Open AccessArticle

An Effective Ensemble Approach for Preventing and Detecting Phishing Attacks in Textual Form

by Zaher Salah, Hamza Abu Owida, Esraa Abu Elsoud, Esraa Alhenawi, Suhaila Abuowaida and Nawaf Alshdaifat

Future Internet 2024, 16(11), 414; https://doi.org/10.3390/fi16110414 - 8 Nov 2024

Abstract

Phishing email assaults have been a prevalent cybercriminal tactic for many decades. Various detectors have been suggested over time that rely on textual information. However, to address the growing prevalence of phishing emails, more sophisticated techniques are required to use all aspects of emails to improve the detection capabilities of machine learning classifiers. This paper presents a novel approach to detecting phishing emails. The proposed methodology combines ensemble learning techniques with various variables, such as word frequency, the presence of specific keywords or phrases, and email length, to improve detection accuracy. We provide two approaches for the planned task; The first technique employs ensemble learning soft voting, while the second employs weighted ensemble learning. Both strategies use distinct machine learning algorithms to concurrently process the characteristics, reducing their complexity and enhancing the model’s performance. An extensive assessment and analysis are conducted, considering unique criteria designed to minimize biased and inaccurate findings. Our empirical experiments demonstrates that using ensemble learning to merge attributes in the evolution of phishing emails showcases the competitive performance of ensemble learning over other machine learning algorithms. This superiority is underscored by achieving an F1-score of 0.90 in the weighted ensemble method and 0.85 in the soft voting method, showcasing the effectiveness of this approach. Full article

► Show Figures

Figure 1