Future Internet

34 pages, 2336 KB

Open AccessArticle

An Integrated University Digital Transformation Model Combining IT Governance, Interoperability, Cloud Security Assessment and Data Analytics: The UTMACH Case in Ecuador

by Jennifer Célleri-Pacheco, Fernanda Tusa Jumbo, Oswaldo Chuquirima Camacho, Santiago Rodríguez Yánez and Javier Andrade-Garda

Future Internet 2026, 18(8), 443; https://doi.org/10.3390/fi18080443 - 20 Aug 2026

Abstract

Digital transformation in higher education requires integrated designs connecting strategy, governance, infrastructure, interoperability, applications, cybersecurity, accessibility, analytics, and continuous improvement. This study analyzes the Integrated University Digital Transformation Model implemented at Universidad Técnica de Machala, Ecuador, between 2023 and April 2026. A qualitative [...] Read more.

Digital transformation in higher education requires integrated designs connecting strategy, governance, infrastructure, interoperability, applications, cybersecurity, accessibility, analytics, and continuous improvement. This study analyzes the Integrated University Digital Transformation Model implemented at Universidad Técnica de Machala, Ecuador, between 2023 and April 2026. A qualitative embedded case study with a design-science orientation examined institutional documents, technical records, governance evidence, cloud migration reports, interoperability mechanisms, system descriptions, analytics outputs, and cloud security assessment records through thematic analysis, process tracing, and artifact evaluation. Findings showed alignment between the Strategic Information Technology Plan and institutional planning; formal IT governance and information security structures; an API- and microservices-based architecture; a staged migration of 52 institutional servers in four operational lots, with documented post-migration monitoring indicating 99.85% average server uptime and no critical incidents attributable to the migration during the monitored period; an automated and traceable admission allocation process within a broader portfolio of integrated academic–administrative systems; and dashboards supporting evidence-informed decisions. MMGSI-Cloud complemented the architecture by assessing governance capabilities, identifying improvement priorities, and linking findings to an institutional roadmap. The case indicates that university digital transformation is strengthened when technological implementation is integrated with formal governance, systematic assessment, evidence-based planning, and institutional accountability. Full article

► Show Figures

Graphical abstract

28 pages, 947 KB

Open AccessArticle

An AI Answer-Validation Method Using Agentic RAG for Datasheet Inquiry for IoT Application System Deployment

by Dezheng Kong, Nobuo Funabiki, Htoo Htoo Sandi Kyaw, I Nyoman Darma Kotama and Zihao Zhu

Future Internet 2026, 18(8), 442; https://doi.org/10.3390/fi18080442 - 19 Aug 2026

Abstract

Internet of Things (IoT) application systems are increasingly adopted in factories, shops, offices, and governments. However, building such systems using various devices and modules remains difficult for non-experts, because they must confirm specifications, communication interfaces, voltage ranges, and operating conditions from technical datasheets [...] Read more.

Internet of Things (IoT) application systems are increasingly adopted in factories, shops, offices, and governments. However, building such systems using various devices and modules remains difficult for non-experts, because they must confirm specifications, communication interfaces, voltage ranges, and operating conditions from technical datasheets before connecting devices. In previous studies, we have explored a generative AI-based answering tool for datasheet inquiry using Retrieval-Augmented Generation (RAG) for technical guidance of IoT application system deployment. However, the adopted top-kRAG pipeline often retrieves multiple related text chunks, which can cause the AI to confuse technically different specifications, such as power output voltage, signal output voltage, and input voltage range, and produce inaccurate answers. In addition, the AI may generate a hallucinated answer if the datasheet does not provide sufficient source information. In this paper, we propose an AI answer-validation method using agentic RAG for datasheet inquiry for IoT application system deployment. The method organizes datasheet information into structured specification data, including device models, field types, values, units, conditions, and source information. For question-answering, the agent coordinates structured fact query, top-k text retrieval, source checking, and rule-based compatibility comparison according to the question type. Instead of fully relying on the LLM to interpret retrieved chunks, this method adopts structured specifications and deterministic source checks before accepting the final answer. For evaluation, we constructed a dataset from 20 IoT datasheets, including 1000 question-answering tasks with three difficulty levels. Compared with conventional top-k RAG, the proposed method improved the correct answer rate from 0.686 to 0.958 for easy questions, from 0.549 to 0.969 for medium questions, and from 0.273 to 0.613 for hard questions, which confirms the effectiveness of the proposed method. Full article

(This article belongs to the Special Issue Future and Smart Internet of Things)

► Show Figures

Figure 1

41 pages, 823 KB

Open AccessArticle

Hierarchical Scheduler with Adaptive Time-Budget Reallocation for Time-Triggered Edge-Fog-Cloud Architectures

by Omar Hekal, Josepaul Paulachan, Daniel Onwuchekwa and Roman Obermaisser

Future Internet 2026, 18(8), 441; https://doi.org/10.3390/fi18080441 - 18 Aug 2026

Abstract

The lack of determinism restricts the integration of safety-critical applications into Edge–Fog–Cloud (EFC) architectures. Existing EFC schedulers are typically designed for dynamic, best-effort operation based on unmanaged resource allocation and elastic virtualization. This paradigm introduces unbounded queueing, resource contention, and timing jitter, making [...] Read more.

The lack of determinism restricts the integration of safety-critical applications into Edge–Fog–Cloud (EFC) architectures. Existing EFC schedulers are typically designed for dynamic, best-effort operation based on unmanaged resource allocation and elastic virtualization. This paradigm introduces unbounded queueing, resource contention, and timing jitter, making standard schedulers unsuitable for hard-deadline workloads. Moreover, most approaches focus on computational placement, while communication is abstracted or treated as a secondary cost term. As a result, bounded-latency routing and deterministic task execution are rarely co-optimized under a unified timing model. This paper addresses these gaps by utilizing a managed Time-Triggered Edge–Fog–Cloud (TTEFC) architecture that supports safety-critical workloads, orchestrates IEEE Time-Sensitive Networking (TSN) for local intra-domain communication, and uses IETF Deterministic Networking (DetNet) for routed inter-domain paths. On this infrastructure, a hierarchical genetic algorithm (HGA) is proposed to jointly schedule partition-to-execution-location allocation, partition execution order, inter-partition route selection, and negotiated per-partition time budgets that act as temporal boundaries for parallel partition-level optimizers. An adaptive slack reallocation operator redistributes unused temporal slack from over-satisfied partitions to budget-violating partitions, improving feasibility convergence. Experiments on synthetic DAG workloads with 100–500 tasks compare the proposed HGA against HEFT and round-robin baselines. These baselines are included as scoped external references to contextualize the end-to-end scheduling performance of the proposed method. Ablation results show that slack reallocation improves partition-budget feasibility, reaches feasible budget assignments earlier, and produces tighter budget–makespan alignment than feedback-free and static-budget variants. An automotive-characteristic DAG case study further evaluates the method on an application-oriented workload under the same timing and communication assumptions. Full article

(This article belongs to the Special Issue Cloud Computing and Service Computing: Synergies, Innovations, and Future Directions)

► Show Figures

Figure 1

26 pages, 6578 KB

Open AccessArticle

RICO-3D: A Benchmark and Baseline Method for Semantic Segmentation of Urban Roadways

by Wided Hammedi, Olivier Hotel, Franck Roudet and David Excoffier

Future Internet 2026, 18(8), 440; https://doi.org/10.3390/fi18080440 - 18 Aug 2026

Abstract

This paper presents RICO-3D (Roadway Infrastructure in Context), a new large-scale Mobile Laser Scanning (MLS) dataset for semantic segmentation of French urban roadways, together with GA-Attention, a geometry-aware attention U-Net designed for this task. RICO-3D was acquired with a Leica Pegasus TRK300 mobile [...] Read more.

This paper presents RICO-3D (Roadway Infrastructure in Context), a new large-scale Mobile Laser Scanning (MLS) dataset for semantic segmentation of French urban roadways, together with GA-Attention, a geometry-aware attention U-Net designed for this task. RICO-3D was acquired with a Leica Pegasus TRK300 mobile mapping system across Marseille, Rennes, and Opoul-Périllos (France), and provides per-point geometry, RGB, intensity, GPS time, scan angle rank, and semantic labels for 6 classes: vegetation, road, pole, building, cable, and vehicle. The dataset contains 780,981,961 labeled points and captures realistic MLS challenges, including severe class imbalance, sparse thin structures, occlusions, and varying seasonal and weather conditions. GA-Attention combines enriched geometric descriptors, attentive local aggregation, saliency-guided downsampling, attention-gated skip fusion, and curriculum-based training within a point-based encoder-decoder framework. On RICO-3D, the proposed method achieves 83.36% overall accuracy and the best IoU for road (91.35%), pole (49.91%), and cable (56.08%), with an inference time of 8.17 s. On Toronto-3D, it reaches 82.18% overall accuracy and 56.50% mIoU. These results show the relevance of RICO-3D for infrastructure-oriented MLS segmentation and the effectiveness of GA-Attention for thin and under-represented roadway infrastructure classes. To support reproducible research, the RICO-3D dataset, source code, trained models, and evaluation scripts will be publicly available once the Orange’s legal and data-governance validation process has been completed. Full article

(This article belongs to the Special Issue Algorithms and Models for Next-Generation Vision Systems)

► Show Figures

Figure 1

20 pages, 2023 KB

Open AccessArticle

TAR-DT: A Trusted and Attack-Resilient Mechanism for Distributed DNN Training in Agentic Edge Intelligence

by Zhonghui Wu, Yunxiao Ma, Lu Lu, Han Xiao and Chao Liu

Future Internet 2026, 18(8), 439; https://doi.org/10.3390/fi18080439 - 17 Aug 2026

Abstract

As deep neural networks continue to scale and enable emerging applications such as agentic AI systems, training increasingly relies on distributed paradigms across heterogeneous edge devices. However, this shift introduces significant security challenges, particularly model poisoning attacks, which are largely underexplored in model-parallel [...] Read more.

As deep neural networks continue to scale and enable emerging applications such as agentic AI systems, training increasingly relies on distributed paradigms across heterogeneous edge devices. However, this shift introduces significant security challenges, particularly model poisoning attacks, which are largely underexplored in model-parallel settings. To address these challenges, we propose a trusted and attack-resilient mechanism for distributed DNN training that supports both data and model parallelism. The mechanism leverages a blockchain-enabled infrastructure to ensure the tamper-resistant and auditable execution of security-critical operations. It introduces a Loss-aware Credit Evaluation mechanism to assess agent reliability based on group-level training dynamics and a Shuffling-based Isolation Mechanism to progressively cluster and isolate malicious agents across training epochs. In addition, Byzantine-tolerant aggregation (BTA) is employed to further mitigate adversarial influence during model aggregation. Extensive experiments demonstrate that the proposed mechanism achieves superior robustness and efficiency compared with state-of-the-art methods under diverse poisoning attack scenarios. Full article

(This article belongs to the Special Issue Blockchain-Empowered Internet of Agents for Trusted and Autonomous Networked Systems)

► Show Figures

Figure 1

4 pages, 142 KB

Open AccessEditorial

Virtual Reality and Metaverse: Impact on the Digital Transformation of Society—3rd Edition

by Diego Vergara

Future Internet 2026, 18(8), 438; https://doi.org/10.3390/fi18080438 - 17 Aug 2026

Abstract

Immersive technologies—including virtual reality (VR), augmented reality (AR), mixed reality (MR), extended reality (XR), and the metaverse—have undergone significant development over the past decade and are increasingly being integrated into a broad range of application domains [...] Full article

(This article belongs to the Special Issue Virtual Reality and Metaverse: Impact on the Digital Transformation of Society—3rd Edition)

40 pages, 604 KB

Open AccessArticle

Computational Jurisprudence: Verifiable Law for Machine Societies

by Vladimir Stantchev

Future Internet 2026, 18(8), 437; https://doi.org/10.3390/fi18080437 - 16 Aug 2026

Abstract

Autonomous AI agents now hold funds, delegate authority to other agents, and transact at machine speed, while the governance apparatus meant to constrain them (policies, audits, compliance) remains documentation-based and limited by human latency. Better monitoring or filtering cannot close this mismatch: compliance [...] Read more.

Autonomous AI agents now hold funds, delegate authority to other agents, and transact at machine speed, while the governance apparatus meant to constrain them (policies, audits, compliance) remains documentation-based and limited by human latency. Better monitoring or filtering cannot close this mismatch: compliance must become a runtime, compositional, proof-carrying property of computation itself. We call the resulting discipline computational jurisprudence. This article is an integrative review of the four literatures the discipline must synthesize, namely, object-capability security; verifiable, proof-carrying, and zero-knowledge computation; policy-as-code and computational law; and agentic AI with its emerging payment protocols. Each supplies a mature mechanism the others lack, and none supplies a complete normative substrate. The synthesis is organized into three pillars: (i) a delegation calculus, under which authority can only attenuate as it propagates between agents, for which we prove monotone attenuation in the conjunctive caveat fragment and exhibit a counterexample outside it; (ii) runtime compliance proofs, a three-tier evidence regime (attested, optimistic, and zero-knowledge); and (iii) sealed delegation chains with graduated attribution, reconciling capability-based privacy with the accountability adjudication requires. A case study on agentic payments grounds the architecture and evaluates three components on two platforms, with five independent executions each: local capability verification against a centralized policy decision point, enforcement on the x402 payment path, and accumulator-based revocation. What the article offers is therefore a survey, a conceptual architecture with a formal core, and a partial evaluation of three components, not a fully implemented system; a status table marks that boundary component by component. Eight open problems define the research agenda. Full article

(This article belongs to the Section Cybersecurity)

► Show Figures

Graphical abstract

17 pages, 307 KB

Open AccessArticle

The Telephone AI Paradox: How Voice Agents Can Help Counter Unwanted Telemarketing Through Role-Based Automation, Transparency, and Governance

by Eldar Sultanow, Alexander Loosley, Alina Chircu, Jonas Arnold, Timon Bayer, Emilia Bauer, Yudha Hefitra Firdaus, Stoyan Ivanov, Elisa Rofalski, Serhat Ugur and Christian Czarnecki

Future Internet 2026, 18(8), 436; https://doi.org/10.3390/fi18080436 - 14 Aug 2026

Abstract

Unwanted telemarketing calls are a persistent source of consumer frustration and a legally regulated issue in Germany. At first glance, the idea of addressing this problem with AI-based voice technology appears contradictory: why should an automated caller help restore trust in a communication [...] Read more.

Unwanted telemarketing calls are a persistent source of consumer frustration and a legally regulated issue in Germany. At first glance, the idea of addressing this problem with AI-based voice technology appears contradictory: why should an automated caller help restore trust in a communication channel that has been damaged by aggressive outbound practices? This design-oriented case and prototype study argues that the paradox can be resolved through a different design logic. Rather than using AI to intensify persuasion, we present a role-based voice-agent architecture that constrains conversational behavior through narrow task boundaries, explicit escalation rules, and auditable data handling. The paper reports a transfer project involving FH Aachen students, Capgemini, and Fairdient GmbH. Methodologically, the work is positioned as a design-oriented case study with a prototype artifact. The contribution is threefold: first, we describe a three-agent architecture for outbound screening, consent-aware explanation, and inbound service; second, we derive governance principles for legally and ethically sensitive telephony, including transparency, bounded knowledge, privacy-preserving deployment, and human fallback; and third, we propose an evaluation framework covering conversion, compliance, hallucination control, user trust, and cost per validated outcome. The prototype does not yet claim large-scale field effectiveness. Instead, it offers a structured and empirically testable design for trustworthy voice automation in a domain where misuse, opacity, and user distrust are especially pronounced. Full article

(This article belongs to the Special Issue Human-Centered Artificial Intelligence—2nd Edition)

► Show Figures

Graphical abstract

22 pages, 18257 KB

Open AccessArticle

Deep-Learning-Based Multi-Camera Framework for Indoor Human Detection and Presence Management

by Thang Chien Vu, Dung The Nguyen, Long Quy Dinh, Mui Duc Nguyen, De Rosal Ignatius Moses Setiadi and Minh Tuan Nguyen

Future Internet 2026, 18(8), 435; https://doi.org/10.3390/fi18080435 - 13 Aug 2026

Abstract

Currently, in high-density indoor environments such as businesses and factories, managing human presence and access control remains a significant challenge. Traditional access control systems based on facial recognition or card scanning typically only record authentication events at the point of entry. Therefore, continuous [...] Read more.

Currently, in high-density indoor environments such as businesses and factories, managing human presence and access control remains a significant challenge. Traditional access control systems based on facial recognition or card scanning typically only record authentication events at the point of entry. Therefore, continuous monitoring, presence detection, or restricted area surveillance are limited. This paper proposes an integrated indoor person detection and management framework based on centralized multi-camera processing for deployment-oriented identification surveillance. The proposed framework combines SCRFD and ArcFace to perform enrollment-based face recognition and distinguish between enrolled and unknown identities. During the experimental evaluation, the facial recognition module using the SCRFD 2.5G configuration achieved a recognition accuracy of approximately 88.2%. YOLOv11n is integrated with DeepSORT to detect and continuously track individuals within the monitored area. Experimental results showed the system achieving an average processing performance of 10.6 FPS, demonstrating the feasibility of the proposed architecture for small- to medium-scale indoor surveillance applications. Additionally, this system framework integrates event-driven spatial analysis using virtual boundaries and surveillance zones to support entry/exit counting, presence monitoring, and intrusion detection in restricted areas. Experimental results demonstrate that the proposed system framework provides consistent identification monitoring performance, stable multi-object tracking capabilities, and an efficient event management mechanism for typical indoor surveillance scenarios. This work offers a centralized, deployment-oriented surveillance architecture suitable for practical indoor security management and access control applications utilizing multiple cameras. Full article

► Show Figures

Figure 1

30 pages, 2004 KB

Open AccessArticle

Enhanced Hybrid Retrieval-Augmented Model for Question Answering in High-Sensitivity Domains

by Ali Mohammed Aloqla, Reda Salama, Wajdi Alghamdi and Adnan Ahmed Abi Sen

Future Internet 2026, 18(8), 434; https://doi.org/10.3390/fi18080434 - 13 Aug 2026

Abstract

Arabic question-answering systems in high-sensitivity domains require not only accurate retrieval but also reliable evidence grounding and effective hallucination mitigation, as incorrect or unsupported responses may have serious consequences. Existing retrieval and generation approaches do not fully integrate reliable lexical retrieval, semantic understanding, [...] Read more.

Arabic question-answering systems in high-sensitivity domains require not only accurate retrieval but also reliable evidence grounding and effective hallucination mitigation, as incorrect or unsupported responses may have serious consequences. Existing retrieval and generation approaches do not fully integrate reliable lexical retrieval, semantic understanding, and evidence-based answer verification within a unified framework for these domains. To address this limitation, this study proposes an Enhanced Hybrid Retrieval-Augmented model that combines BM25-based lexical retrieval, dense semantic scoring, semi-structured metadata, domain-aware classification, source-trust and freshness indicators, and evidence-based answer verification. The model was evaluated on a corpus of 128,297 Arabic documents using 200 expert-validated questions and compared against BM25, Dense, and Classical Hybrid retrieval configurations. Expert assessment showed that the Enhanced Hybrid Model produced 198 fully grounded correct answers out of 200, achieving a grounded-correctness rate of 99.0%, compared with 96.5% for Classical Hybrid, 87.0% for BM25, and 86.5% for Dense. It also achieved the strongest answer-level Hit@5 performance, the best golden-answer ordering, and the highest dynamic mixture-based F1-score. These findings demonstrate that integrating reliable retrieval, metadata-aware ranking, and evidence-grounded answer verification can substantially improve the reliability and trustworthiness of Arabic question-answering systems in high-sensitivity domains, providing a practical foundation for future evidence-based intelligent information systems. Full article

(This article belongs to the Special Issue Advances in Intelligent Learning Systems)

► Show Figures

Figure 1

29 pages, 716 KB

Open AccessArticle

Threat Actor Attribution Applying a Tactics–Techniques–Procedures Approach: An Empirical Investigation

by Shaheen Hussain and Krassie Petrova

Future Internet 2026, 18(8), 433; https://doi.org/10.3390/fi18080433 - 13 Aug 2026

Abstract

The increasing frequency and growing impact of cyberattacks have led organizations to adopt proactive defense approaches to cybersecurity risk mitigation, especially in the case of advanced persistent threats (APTs). The correct identification of the specific malicious actors behind a cyberattack is important for [...] Read more.

The increasing frequency and growing impact of cyberattacks have led organizations to adopt proactive defense approaches to cybersecurity risk mitigation, especially in the case of advanced persistent threats (APTs). The correct identification of the specific malicious actors behind a cyberattack is important for the success of incident response and for the investigative work of the security operations center (SOC) team. This research explores the capabilities and limitations of a machine learning (ML) approach to identifying malicious actors and the threats they pose (threat actor attribution) based on the tactics, techniques, and procedures (TTP) observed in specific cybersecurity incidents and on the incident context (the geographical location and industry affiliation of the victims targeted in the attack). A large language model (LLM) was used to extract TTPs from the MITRE ATT&CK database of cybersecurity incidents. The experiments included modeling threat actor attribution using five ML algorithms: k-nearest neighbors (KNN), decision tree (DT), random forest (RF), support vector machine (SVM), and naïve Bayes (NB), with different methods applied for feature selection and weighting. The results indicated that model accuracy and other performance metrics were significantly improved when the input dataset included both TTP and contextual features. The KNN and SVM models produced the best performance results; the highest classification accuracy achieved was 93.19%. The outcomes of this study may be applied by cybersecurity professionals to identify malicious actors, estimate the number and types of data points that are required to adequately attribute a cyberattack to an actor, and improve the accuracy of the classification by weighting the input dataset features. Full article

(This article belongs to the Special Issue Machine Learning and Internet of Things in Industry 4.0—2nd Edition)

► Show Figures

Figure 1

22 pages, 4839 KB

Open AccessArticle

IoT-Based Automation of a Reverse-Osmosis Desalination Process in the Galápagos Islands

by José Varela-Aldás, Cristian Gallardo, Carlos Bran, Francisco Yumbla and Carolina Del-Valle-Soto

Future Internet 2026, 18(8), 432; https://doi.org/10.3390/fi18080432 - 13 Aug 2026

Abstract

Reliable drinking-water production is difficult on remote islands where brackish-water delivery is intermittent, technical personnel are scarce, and reverse-osmosis plants are manually operated. This study presents an operational characterization of an Internet of Things (IoT) retrofit deployed in Santa Cruz, Galápagos; it is [...] Read more.

Reliable drinking-water production is difficult on remote islands where brackish-water delivery is intermittent, technical personnel are scarce, and reverse-osmosis plants are manually operated. This study presents an operational characterization of an Internet of Things (IoT) retrofit deployed in Santa Cruz, Galápagos; it is not a controlled before-and-after effectiveness evaluation. An ESP32-based M5Stack Tough controller, distributed ESP-NOW sensing nodes, relay–contactor interfaces, a binary pressure permissive, and a ThingSpeak cloud layer were integrated without replacing the existing pumps and membranes. The exported primary-flow channel contained 4,603,989 numeric observations, including 500 pre-official test readings. Operational analyses used 4,603,489 numeric observations from the official monitoring period; 4,603,340 values remained after nominal-range filtering, and positive flow had a median of 12 L/min (interquartile range: 11–15 L/min). Among 332 logged high-pressure commands, 326 were preceded by a low-pressure command (98.2% unbounded command-state consistency), whereas 275 occurred within a 120 s analytical bound (82.8%). The median low-to-high command delay was 27 s (interquartile range: 11–70 s). Four organizational representatives completed a published 41-item Industry 4.0 maturity instrument before and after deployment; the self-reported overall mean was 0.26 at baseline and 1.95 post-deployment, and these results are interpreted descriptively. Energy-consumption and production data were confidential and unavailable to the authors, while water-quality variables were not measured. The contribution is therefore a long-duration, local-first legacy retrofit with auditable telemetry and explicit limitations, rather than a claim of optimized desalination performance. Full article

(This article belongs to the Special Issue Internet of Things and Cyber-Physical Systems, 3rd Edition)

► Show Figures

Figure 1

26 pages, 827 KB

Open AccessArticle

C-GUARD: Context-Adaptive Conformal Gating for Improving Robustness Against Evasive Windows PE Malware

by Muhammad Imran, Malik Al-Essa, Felice Franchini and Giuseppe Pirlo

Future Internet 2026, 18(8), 431; https://doi.org/10.3390/fi18080431 - 13 Aug 2026

Abstract

Machine Learning (ML)-based malware detectors perform exceptionally well on standard benchmarks, but their robustness to evasive malware remains fragile. On EMBER2024, strong tree-based models achieve high accuracy on clean test sets yet miss a large number of evasive Windows PE samples. Through SHAP-based [...] Read more.

Machine Learning (ML)-based malware detectors perform exceptionally well on standard benchmarks, but their robustness to evasive malware remains fragile. On EMBER2024, strong tree-based models achieve high accuracy on clean test sets yet miss a large number of evasive Windows PE samples. Through SHAP-based explainability, matched error comparisons, feature-family analysis, and margin diagnostics on the validation split, we identify consistent attribution and decision-margin differences between baseline true negatives and false negatives. We further show that false negatives occur at different decision depths, including both near-boundary cases and samples misclassified with high benign confidence. We propose C-GUARD, a context-adaptive conformal gated detector that preserves the optimized high-performing baseline while selectively invoking an auxiliary rescue detector on a targeted subset of baseline negative predictions. C-GUARD combines out-of-fold rescue learning to distinguish baseline false negatives from true negatives with adaptive gating under an explicit false-positive budget. A one-sided intervention rule preserves all baseline malware decisions. On the EMBER2024 standard test set, C-GUARD recovers 178 additional malware samples at the cost of 82 additional false positives. On the evasive challenge set, it recovers 17 additional evasive malware samples. Full article

(This article belongs to the Special Issue Adversarial Attacks and Cyber Security)

► Show Figures

Figure 1

35 pages, 2265 KB

Open AccessArticle

MIRA: Safety-Constrained Multi-Agent Reinforcement Learning for Joint Prescriptive Maintenance and Production Rescheduling in Industrial IoT

by Md. Ashraful Babu, Ali AlArjani and Mohamed Lahby

Future Internet 2026, 18(8), 430; https://doi.org/10.3390/fi18080430 - 13 Aug 2026

Abstract

Industrial IoT maintenance often stops at health prediction, leaving maintenance, rescheduling, safety, and communication to separate decision processes. This study presents MIRA, a safety-constrained graph-based multi-agent reinforcement learning architecture for joint prescriptive maintenance, production rescheduling, and event-triggered communication. Machine condition was estimated from [...] Read more.

Industrial IoT maintenance often stops at health prediction, leaving maintenance, rescheduling, safety, and communication to separate decision processes. This study presents MIRA, a safety-constrained graph-based multi-agent reinforcement learning architecture for joint prescriptive maintenance, production rescheduling, and event-triggered communication. Machine condition was estimated from CNC milling data using temporal convolutional models; because predictive uncertainty failed a predefined validation gate, the controller used deterministic health estimates. Evaluation covered five controllers, six simulated scenarios, and 1800 matched episodes. Relative to Graph-MAPPO, MIRA reduced operational cost by 9.38%, weighted tardiness by 28.10%, unexpected failures by 17.39%, message count by 84.98%, and transmitted data by 83.83%, while increasing on-time completion by 23.55%, without a detectable difference in corrected critical-message recall. Across the three independently trained seeds, failures, safety violations, and message count favored MIRA consistently, whereas cost and tardiness favored MIRA in two seeds. Disabling the execution shield increased safety violations from 0 to 3.56 per episode. Post-training variation in the projected-health safe-start threshold from 0.124 to 0.132 produced no safety violations and only small changes in aggregate operational outcomes. Cross-domain health transfer to PHM 2010 failed without adaptation. The results support simulator-level decision coordination, while broader replication, variable-size deployment, and factory validation remain necessary. Full article

(This article belongs to the Special Issue Distributed Intelligence for IoT and Smart Systems)

► Show Figures

Figure 1

24 pages, 1334 KB

Open AccessArticle

Pricing Diagnostic Value Under a Clinical Deadline: A Triage- Aware Truthful Auction for Semantic Medical-Image Transmission in Healthcare IoT

by Yongwen Liu, Rui Chen, Yaoli Xu and Kailai Zhou

Future Internet 2026, 18(8), 429; https://doi.org/10.3390/fi18080429 - 12 Aug 2026

Abstract

Telemedicine in emergency and remote care relays medical images from ambulances and rural clinics to a hospital edge-computing server over a congested wireless uplink. Existing work prices such transmissions per bit or per quality-of-experience; neither metric captures the clinical value of a medical [...] Read more.

Telemedicine in emergency and remote care relays medical images from ambulances and rural clinics to a hospital edge-computing server over a congested wireless uplink. Existing work prices such transmissions per bit or per quality-of-experience; neither metric captures the clinical value of a medical transmission. Diagnostic utility vanishes below a modality-specific acceptability floor rather than degrading gracefully, the deadline is determined by triage acuity rather than by the network, and a missed finding is far costlier than a false alarm. A per-bit clearing price therefore disadvantages the node that has expended local compute to produce a compact, diagnostically sufficient stream. We propose SemAuc, a triage-aware truthful mechanism for medical-image admission over a rate-splitting uplink, in which the shared semantic knowledge base rides the common stream, and case-specific residuals ride private streams. SemAuc filters tiers below the diagnostic floor and beyond the clinical deadline, reserves a regulated-price lane for life-threatening cases, and allocates remaining capacity through a single-parameter contestable auction whose bid-independent pre-selection step satisfies the conditions of Myerson’s lemma. The contestable lane is dominant-strategy truthful, individually rational, near-linear in the number of nodes, and achieves a constant-factor density-greedy welfare guarantee; the clinical lanes follow from triage policy without disturbing these properties. Diagnostic value is grounded by an offline kernel fitted on BraTS and CheXpert. On a Rayleigh-faded uplink at two hundred contending nodes, SemAuc preserves the high-acuity diagnostic service-level objective where bit-centric benchmarks fail, and tracks the offline optimum. Full article

► Show Figures

Figure 1

27 pages, 21729 KB

Open AccessArticle

Industrial Internet-Oriented Unsupervised Hydro-Turbine Bearing Fault Diagnosis via Prototype-Disentangled Conditional Wasserstein Domain Adaptation

by Xueyi Li, Binghao Hu, Jiannan Dong and Zhilin Dong

Future Internet 2026, 18(8), 428; https://doi.org/10.3390/fi18080428 - 12 Aug 2026

Abstract

With the rapid development of Industrial Internet-oriented smart energy systems, hydro-turbine generator units are increasingly monitored through networked sensors, industrial communication infrastructures, and edge/cloud-based condition-monitoring platforms. These Internet-connected monitoring environments provide abundant vibration data for intelligent operation and maintenance (O&M) but also introduce [...] Read more.

With the rapid development of Industrial Internet-oriented smart energy systems, hydro-turbine generator units are increasingly monitored through networked sensors, industrial communication infrastructures, and edge/cloud-based condition-monitoring platforms. These Internet-connected monitoring environments provide abundant vibration data for intelligent operation and maintenance (O&M) but also introduce a challenging unsupervised cross-scenario diagnosis problem. Specifically, diagnostic models trained on labeled historical data may suffer severe performance degradation when deployed to unlabeled online data collected under different hydraulic conditions, rotational speeds, or operating conditions. Furthermore, existing domain adaptation methods, in their pursuit of distribution alignment, frequently overlook a critical bottleneck that limits generalization performance: inter-class entanglement. Specifically, under intense hydraulic background noise and cross-condition distribution shifts, features belonging to distinct fault types are highly susceptible to aliasing within the feature space. To overcome these issues, this paper proposes a Conditional Wasserstein Adversarial Network with Bi-level Prototype Disentanglement Regularization (CWAN-BPDR). First, a Conditional Wasserstein Adversarial Network (CWAN) is constructed by combining the smooth-gradient property of Wasserstein distance with conditional adversarial alignment, thereby achieving stable and fine-grained category-level domain adaptation. Furthermore, to alleviate the inter-class entanglement problem that may arise during cross-domain alignment, a Bi-level Prototype Disentanglement Regularization (BPDR) term is designed. By jointly implementing source–target prototype alignment and prototype–feature bidirectional alignment, BPDR explicitly suppresses inter-class confusion and enhances intra-class compactness and inter-class separability in the feature space. Experimental results on the JNU and NEFU datasets demonstrate that CWAN-BPDR achieves average diagnostic accuracies of 97.82% and 98.99%, respectively, while significantly mitigating label entanglement in challenging cross-operating-condition tasks. These results indicate that the proposed method can effectively transfer diagnostic knowledge acquired from labeled historical operating conditions to unlabeled online monitoring data. It can therefore serve as an offline-trained diagnostic module for Industrial Internet of Things-based condition-monitoring platforms in hydropower systems. Full article

(This article belongs to the Topic Digital and Smart Technologies for Industry 4.0 / 5.0)

► Show Figures

Figure 1

23 pages, 7009 KB

Open AccessArticle

LLM-Based Semantic Navigation on a Low-Cost ROS Mobile Robot: A Hybrid Edge–Cloud Architecture

by Marius-Adrian Păun, Florin Dragomir, Otilia Elena Dragomir, Eugenia Mincă and Octavian Gabriel Duca

Future Internet 2026, 18(8), 427; https://doi.org/10.3390/fi18080427 - 12 Aug 2026

Abstract

Autonomous mobile robots require robust perception and high-level reasoning to operate in complex indoor environments. While the Robot Operating System (ROS) provides a modular framework for mapping and navigation, classical pipelines lack semantic understanding and natural-language interaction. This paper presents a semantic-aware autonomous [...] Read more.

Autonomous mobile robots require robust perception and high-level reasoning to operate in complex indoor environments. While the Robot Operating System (ROS) provides a modular framework for mapping and navigation, classical pipelines lack semantic understanding and natural-language interaction. This paper presents a semantic-aware autonomous navigation framework implemented on a ROS 1 (Melodic) mobile robot equipped with a two-dimensional light detection and ranging (LiDAR) sensor and an RGB-D camera. The system integrates LiDAR-based simultaneous localization and mapping (SLAM), the ROS navigation stack (move_base), and a lightweight You Only Look Once (YOLO) object detector for real-time on-board perception, and it anchors detections into the metric map to build a semantic map. A large language model (LLM) interprets natural-language instructions and converts them into structured navigation goals. Perception and control run entirely on-board the Jetson Nano, whereas the LLM is invoked episodically as a cloud service, yielding a hybrid embedded/cloud architecture. In indoor trials over a semantic map of two object classes, the system grounded all ten multilingual commands to the correct objects at a reasoning cost of about one second, and safely rejected a command referring to an unmapped object. We present this as an in-depth single-platform case study: owing to the 4 GB memory budget, the on-board detector and the full navigation stack are time-multiplexed rather than run continuously in parallel; nonetheless, a single degraded end-to-end trial confirmed that perception, online semantic anchoring, language grounding, and navigation compose within one continuous session. The framework offers a low-cost, extensible basis for language-guided robots in smart environments. Full article

(This article belongs to the Special Issue Mobile Robotics and Autonomous System)

► Show Figures

Figure 1

20 pages, 2712 KB

Open AccessArticle

An Algebra for Two-Layer Cloud Filtering: Detecting Redundancy, Shadowing, and Dominance Anomalies Across Stateless Network ACLs and Stateful Security Groups

by Thawatchai Chomsiri and Suwichai Phunsa

Future Internet 2026, 18(8), 426; https://doi.org/10.3390/fi18080426 - 11 Aug 2026

Abstract

Traffic inside a cloud Virtual Private Cloud (VPC) is filtered by two layers with fundamentally different semantics: a stateless, ordered, first-match Network ACL (NACL) and a stateful, unordered, allow-only Security Group (SG). Existing analyzers decide point-to-point reachability using satisfiability solvers, Datalog engines, or [...] Read more.

Traffic inside a cloud Virtual Private Cloud (VPC) is filtered by two layers with fundamentally different semantics: a stateless, ordered, first-match Network ACL (NACL) and a stateful, unordered, allow-only Security Group (SG). Existing analyzers decide point-to-point reachability using satisfiability solvers, Datalog engines, or binary decision diagrams, but do not identify, at the rule level, which rules are dead, redundant, or dominated, nor explain why. We provide a closed-form set algebra over the two layers. Representing each rule field by its boundaries makes a rule a hyper-rectangle and a layer a union of boxes; the effective admitted region Φ = A(N) ∩ A(G) is then a finite union of disjoint boxes computable from rule endpoints alone. We define a taxonomy of single- and cross-layer anomalies—shadowed NACL rules, dead SG rules, Φ-redundant rules, Φ-ineffective NACL allows, and layer disagreement—characterize each by a decidable region predicate, and prove an exact iff-condition for SG Φ-redundancy. A boundary-only detection algorithm is sound and complete for the exactly decidable anomaly classes, running in O((k + t)^d) time for fixed dimension d, and the disjoint box decomposition of Φ gives a minimal anomaly-free form that is unique up to merging adjacent coplanar boxes. A single-file implementation matches brute force on millions of packets, staying orders of magnitude below the worst-case bound; the parametric model extends unchanged to IPv6 and ICMP. Full article

(This article belongs to the Collection Information Systems Security)

► Show Figures

Figure 1

47 pages, 9271 KB

Open AccessReview

AI-Driven Mobility Management in 5G and 6G Wireless Networks: A Survey

by Hafiz M. Asif, Abdulraqeb Alhammadi, Naser Tarhuni and Mohammed M. Bait-Suwailam

Future Internet 2026, 18(8), 425; https://doi.org/10.3390/fi18080425 - 11 Aug 2026

Abstract

Next-generation wireless systems are becoming increasingly complex, and there is a growing need for intelligent mobility management mechanisms that can ensure service continuity while making efficient use of network resources. In 5G and future 6G networks, dense small-cell deployments, heterogeneous architectures, and highly [...] Read more.

Next-generation wireless systems are becoming increasingly complex, and there is a growing need for intelligent mobility management mechanisms that can ensure service continuity while making efficient use of network resources. In 5G and future 6G networks, dense small-cell deployments, heterogeneous architectures, and highly mobile users mean that frequent handovers (HOs), uneven traffic distribution, and variable network conditions often lead to degraded user experience, higher signalling overhead, and inefficient use of resources. Because user movement continuously redistributes traffic across cells, effective mobility management is inseparable from load balancing, and the HO process serves as the primary mechanism through which the network manages both. Recent advances in artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), offer an opportunity to transform mobility management from reactive to predictive, since data-driven solutions can forecast user movement, fine-tune HO execution, and dynamically allocate radio resources. This paper presents a comprehensive survey of AI-enabled mobility management strategies for 5G, Beyond 5G, and upcoming 6G networks, with particular attention to HO optimization and load balancing. The surveyed literature is organized around the complete lifecycle of AI-enabled mobility management, from mobility prediction and HO decision-making through parameter optimization and execution to KPI monitoring and model updating. This structure is used to classify existing frameworks according to their architectures, learning approaches, and optimization goals. The survey then examines how intelligent HO schemes address critical issues such as load balancing, interference mitigation, connection reliability, and quality-of-service maintenance, and compares conventional and AI-based methods against standardized key performance indicators for mobility robustness, resource efficiency, and service continuity. Finally, the paper discusses unresolved problems and emerging trends, including federated learning, multi-connectivity, and non-terrestrial integration, that will shape the evolution of autonomous mobility management solutions for future wireless networks. Full article

(This article belongs to the Special Issue Task Offloading and Resource Allocation for IoT in Next-Generation Networking)

► Show Figures

Figure 1

Journal Description

Future Internet

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI