Next Issue
Volume 15, September
Previous Issue
Volume 15, July
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
9.1
5.2
Journals
Computers
Volume 15
Issue 8
share announcement

Computers, Volume 15, Issue 8 (August 2026) – 83 articles

Cover Story (view full-size image): As UAVs evolve into airborne AI platforms for disaster response, infrastructure monitoring, and public safety, the imagery enabling rapid decisions can also expose faces, plates, private locations, and human activity. PrivEdge-VLM makes privacy a real-time systems decision. It scores region-level risk and mission relevance, transforms sensitive evidence into semantic tokens, and routes VLM reasoning across onboard, edge, or sanitized cloud paths under privacy and resource constraints. Federated LoRA with differential privacy protects adaptation, while deterministic guardrails block identity-seeking outputs. Evaluated across visual, embedding, update, and output attacks, PrivEdge-VLM shows how UAV intelligence can preserve mission value without making raw identity the price of situational awareness. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
38 pages, 23443 KB  
Article
DSCMamba-TAD-YOLOv8: A Lightweight YOLOv8-Based Model for Power Line Inspection
by Zhijiang Li and Chuan Ding
Computers 2026, 15(8), 550; https://doi.org/10.3390/computers15080550 - 21 Aug 2026
Viewed by 195
Abstract
Power line component and insulator defect detection is an important task in intelligent transmission line inspection. However, UAV-based inspection images often contain small, densely distributed targets under complex backgrounds, making it difficult for existing detectors to balance accuracy and model compactness. To address [...] Read more.
Power line component and insulator defect detection is an important task in intelligent transmission line inspection. However, UAV-based inspection images often contain small, densely distributed targets under complex backgrounds, making it difficult for existing detectors to balance accuracy and model compactness. To address these challenges, this paper proposes a lightweight YOLOv8-based detector named DSCMamba-TAD-YOLOv8. First, depthwise separable convolutions are introduced into the Neck to reduce parameters and computational cost. Second, DSCMambaNet replaces the original C2f module to enhance multi-scale feature representation by combining lightweight local feature extraction and cross-region contextual modeling. An embedded CBAM component is further integrated inside DSCMambaNet to strengthen informative channel responses and spatial regions. Finally, a Task-Aware Dynamic Detection Head, named TADetect, improves head adaptability through scale-aware and task-aware feature modulation. Experiments on the InsPLAD-det dataset show that DSCMamba-TAD-YOLOv8 achieves 91.86% Precision, 88.02% Recall, 91.83% mAP@0.5, and 74.82% mAP@0.5:0.95. Compared with YOLOv8n, the proposed model improves Precision, mAP@0.5, and mAP@0.5:0.95 by 4.09, 2.43, and 4.46 percentage points, respectively, while maintaining a comparable Recall level with a slight increase from 87.04% to 88.02%. Meanwhile, Params decrease from 3.209 M to 2.702 M and GFLOPs from 8.2 to 7.5. On the revised TPL-SOD held-out test subset, the proposed model improves Precision from 86.20% to 88.16%, mAP@0.5 from 87.09% to 88.81%, and mAP@0.5:0.95 from 68.44% to 70.13%, while Recall remains stable and slightly increases from 91.75% to 92.33%. These results demonstrate that DSCMamba-TAD-YOLOv8 improves detection accuracy and localization quality while maintaining a compact structure and stable recall performance. Full article
(This article belongs to the Section AI-Driven Innovations)
►▼ Show Figures

Figure 1

45 pages, 11067 KB  
Article
A Multi-Chain Blockchain Framework for Trusted Data Management and Efficient Traceability in Fruit and Vegetable Supply Chains
by Weiqiang Chen, Zhiyao Zhao, Haisheng Li, Jiping Xu, Chongxuan Liu and Xin Zhang
Computers 2026, 15(8), 549; https://doi.org/10.3390/computers15080549 - 21 Aug 2026
Viewed by 199
Abstract
Fruit and vegetable supply chains generate heterogeneous data across production, storage, logistics, and sales, creating challenges for trusted data sharing, privacy protection, and real-time traceability across distributed supply-chain information systems. Conventional single-chain blockchains suffer from limited scalability, data redundancy, and low retrieval efficiency, [...] Read more.
Fruit and vegetable supply chains generate heterogeneous data across production, storage, logistics, and sales, creating challenges for trusted data sharing, privacy protection, and real-time traceability across distributed supply-chain information systems. Conventional single-chain blockchains suffer from limited scalability, data redundancy, and low retrieval efficiency, making them inadequate for high-frequency full-process information management. This study proposes a multi-chain blockchain framework for trusted full-process information management of fruit and vegetable supply chains. The framework integrates traceability, enterprise, notary, and regulatory chains to support hierarchical data management and privacy isolation. A reputation-based notary node election mechanism and a threshold-signature scheme based on Shamir secret sharing are designed to enhance cross-chain security and distributed regulatory consensus. To improve retrieval efficiency, a Cuckoo-Augmented Merkle Tree (CMerkle) and a skip-list-based block index are developed. Simulation results show that all malicious nodes were restricted by the 19th round, signature aggregation required 70.16 ms in a 500-node setting, and CMerkle achieved retrieval speedups of 14.7 and 153 times at data scales of 500 and 10,000 records, respectively. The framework supports trusted data governance, real-time traceability, privacy-preserving sharing, and regulatory decision support in blockchain-enabled supply-chain information systems. Full article
►▼ Show Figures

Figure 1

20 pages, 460 KB  
Article
Climatology-Anchored Residual Learning for Spatio-Temporal Traffic Forecasting
by Leonidas Boutsikaris, George Katrilakas, Athanasios Tsadiras, Symeon Samaras and Christina Topalidou
Computers 2026, 15(8), 548; https://doi.org/10.3390/computers15080548 - 21 Aug 2026
Viewed by 317
Abstract
Graph neural networks remain challenging to apply to traffic forecasting, often failing to consistently outperform simple baselines. We observe that the strongest baseline is regime-dependent: last-value persistence dominates at short horizons on smooth freeway data, while time-of-day climatology prevails at longer horizons and [...] Read more.
Graph neural networks remain challenging to apply to traffic forecasting, often failing to consistently outperform simple baselines. We observe that the strongest baseline is regime-dependent: last-value persistence dominates at short horizons on smooth freeway data, while time-of-day climatology prevails at longer horizons and on bursty arterial networks. Rather than treating this as a limitation, we propose a learnable approach that automatically selects the optimal baseline. Our method anchors predictions to a learned, per-horizon convex blend of persistence and climatology, introducing only twelve scalar parameters. This learned anchor recovers whichever baseline is locally most effective, allowing the model to focus on capturing residual variations that neither baseline captures. We evaluate on six public benchmarks (METR-LA, PEMS-BAY, PEMS03/04/07/08) spanning traffic speed and flow data under standard 70/10/20 chronological splits with masked evaluation metrics and holiday-aware climatology. Our anchored temporal models consistently beat both baseline methods on the 12-step average across all datasets, and outperform at every horizon on five of the six benchmarks. When integrated into two strong architectures (STID and Graph WaveNet), the anchor yields substantial gains at long horizons where climatology is most informative. Notably, within our lightweight framework, learned spatial graph components do not improve accuracy and can slightly degrade performance, a finding we analyze and discuss. Full article
(This article belongs to the Special Issue Intelligent Transportation Systems: Recent Advances)
►▼ Show Figures

Graphical abstract

25 pages, 3946 KB  
Article
FLVaccin: Unbalanced Hierarchical Federated Learning with Vaccination-Calibrated Adaptive Quarantine for Robust Poisoning Defense
by Tudor-Mihai David and Mihai Udrescu
Computers 2026, 15(8), 547; https://doi.org/10.3390/computers15080547 - 21 Aug 2026
Viewed by 251
Abstract
Poisoning attacks present a significant challenge for federated learning (FL), particularly when clients operate with Non-IID data and updates are transmitted through multi-tier aggregators. This paper introduces FLVaccin, a hierarchical personalized FL framework structured as an unbalanced tree. In this framework, each non-root [...] Read more.
Poisoning attacks present a significant challenge for federated learning (FL), particularly when clients operate with Non-IID data and updates are transmitted through multi-tier aggregators. This paper introduces FLVaccin, a hierarchical personalized FL framework structured as an unbalanced tree. In this framework, each non-root node both hosts local clients and aggregates shared MobileNetV2 features (FedPer), whereas the root node does not possess local data. The proposed defense integrates node-level CIFAR-100 vaccination, which calibrates depth- and round-adaptive tolerances, with per-client trend quarantine and root backbone rejection. Experimental results on CIFAR-10 with 100 clients, 25 aggregators, and Dirichlet Non-IID partitioning (α=0.5) demonstrate that the clean baseline achieves 79.9% accuracy. In contrast, unconstrained mixed attacks reduce performance to near-chance levels (20.2% k-fold). When vaccination and quarantine are enabled, 535 attack events still result in a 76.5% ± 0.4% k-fold accuracy (77.3% test), remaining within 2.6 percentage points of the clean model. These findings indicate that tree-aware, vaccination-calibrated monitoring can maintain model utility under persistent multi-vector poisoning without the need to share raw data. Full article
(This article belongs to the Section AI-Driven Innovations)
►▼ Show Figures

Figure 1

27 pages, 2725 KB  
Article
Hierarchical Graph Representation Learning for ECG Classification with Cross-Dataset Generalization
by Eman Alsaidi, Eman Omar and Basela Hasan
Computers 2026, 15(8), 546; https://doi.org/10.3390/computers15080546 - 21 Aug 2026
Viewed by 247
Abstract
In this research, we propose a graph-based approach to classify ECG signals. We model the ECG signal as a time-varying graph and examine its dynamics at two levels: intra-beat and inter-beat. The proposed framework employs a two-level graph representation of the ECG. At [...] Read more.
In this research, we propose a graph-based approach to classify ECG signals. We model the ECG signal as a time-varying graph and examine its dynamics at two levels: intra-beat and inter-beat. The proposed framework employs a two-level graph representation of the ECG. At the intra-beat level, each beat is modeled as a graph in which the P, Q, R, S, and T waves serve as nodes, and temporal distance information is incorporated into the node feature vector. At the inter-beat level, the ECG signal is represented as a graph of beats. We investigated two node representations: learnable MLP embeddings derived from handcrafted features and reduced features obtained via PCA. Unlike conventional temporal GCNs, graph attention networks (GATs), and transformers, which predominantly rely on single-level representations of ECG signals, the proposed approach builds hierarchical graph structures directly from ECG signals. The dual model was trained on 1024 ECG segments from the PTB Diagnostic ECG Database (PTBDB) and tested on 398 ECG segments from the MIT-BIH Arrhythmia Database to evaluate its performance. The results indicate that the best-performing configuration, which employs PCA-reduced node features, outperforms the other configurations tested. The model achieves a mean accuracy of 97.67% and a mean F1-score of 97.18% over five runs. Full article
►▼ Show Figures

Figure 1

15 pages, 1833 KB  
Article
Simulation-Informed Bayesian Stackelberg Defense for Multi-Stage Cyber Attacks
by Zhao Shen, Rulong He and Xiao Zhang
Computers 2026, 15(8), 545; https://doi.org/10.3390/computers15080545 - 20 Aug 2026
Viewed by 337
Abstract
We examine whether simulated attack-action evidence can inform a defender that they must commit before an attacker’s type is known. We formulate a five-stage Bayesian Stackelberg security game with five stage-specific actions per player. A Monte Carlo predictor produces type-conditioned action likelihoods on [...] Read more.
We examine whether simulated attack-action evidence can inform a defender that they must commit before an attacker’s type is known. We formulate a five-stage Bayesian Stackelberg security game with five stage-specific actions per player. A Monte Carlo predictor produces type-conditioned action likelihoods on an enterprise graph, while prediction confidence weights the next Bayesian update. The defender strategy is computed by exact follower-response enumeration and linear programming. Evaluation used a simulated 10-node enterprise network, 30 paired trials, bootstrap confidence intervals, and Holm-adjusted Wilcoxon tests. Against a fixed-prior Bayesian Strong Stackelberg Equilibrium, mean gross defense utility increased from 2.141 to 2.197. Mean attack success decreased from 0.691 to 0.686. The paired differences remained significant after multiplicity correction. Outcomes did not differ significantly from an equilibrium updated with coarse reference likelihoods, and the simulation cost reduced net utility by 0.08. Maximum follower regret and constraint violation remained at the specified numerical tolerance. Runtime remained near 0.39 s across networks of 10–100 nodes. An action/type experiment showed rapid growth as follower-response profiles increased. Exact commitment and sequential updating were feasible in the abstraction; simulation was not automatically cost-effective when a usable reference model was available. Full article
(This article belongs to the Special Issue Using New Technologies in Cyber Security Solutions (3rd Edition))
►▼ Show Figures

Figure 1

44 pages, 1508 KB  
Article
From Rule Engines to Ontologies: An OWL 2 DL Approach for Domain-Specific Evaluation Information Systems
by Borivoj Bogdanović and Siniša Nikolić
Computers 2026, 15(8), 544; https://doi.org/10.3390/computers15080544 - 20 Aug 2026
Viewed by 409
Abstract
Domain-specific information systems often maintain their data model, rule base, and application infrastructure as separate artifacts, complicating maintenance and pre-deployment verification. This study investigates whether these artifacts can be unified in a verifiable ontology-to-code pipeline without changing the expected classifications. The proposed Model-Driven [...] Read more.
Domain-specific information systems often maintain their data model, rule base, and application infrastructure as separate artifacts, complicating maintenance and pre-deployment verification. This study investigates whether these artifacts can be unified in a verifiable ontology-to-code pipeline without changing the expected classifications. The proposed Model-Driven Architecture uses the Business Application Builder framework and a Web Ontology Language 2 Description Logic ontology to represent domain structure, classification rules, and generation metadata. HermiT verifies consistency, satisfiability, and subsumption under open-world semantics before code generation. The generator produces persistence, business-logic, data-transfer, and presentation layers, while the generated Java application evaluates stored records under closed-world semantics and resolves overlapping categories using ontology-declared priorities. In a Serbian research-evaluation case study, the generated system reproduced the M30 and M33 classifications of an established Jess implementation. An internal secondary experiment generated and executed a prenatal-diagnosis application; all six runtime classifications matched the HermiT entailments and expected outcomes. The public artifact independently reproduces the ontology-level experiments but excludes the proprietary generator and generated source code. The results support the feasibility of ontology-driven generation for static-classification systems, whereas arithmetic risk computation and temporal event processing remain better suited to complementary procedural technologies. No performance superiority is claimed. Full article
►▼ Show Figures

Graphical abstract

25 pages, 5294 KB  
Article
Deep Learning-Based Indoor Localization by Using WiFi Fingerprinting and a CNN Algorithm
by Ali Fadhel Athab, Hadi Seyedarabi and Reza Afrouzian
Computers 2026, 15(8), 543; https://doi.org/10.3390/computers15080543 - 19 Aug 2026
Viewed by 264
Abstract
In this research, a new approach is proposed to accurately predict indoor three-dimensional localization based on Received Signal Strength (RSS) values. This work uses WiFi beacons to collect time-series RSS data, preprocess it, and feed it to the proposed model. The proposed model [...] Read more.
In this research, a new approach is proposed to accurately predict indoor three-dimensional localization based on Received Signal Strength (RSS) values. This work uses WiFi beacons to collect time-series RSS data, preprocess it, and feed it to the proposed model. The proposed model presents a novel architecture based on 2D convolutional neural networks, and this model employs a multitask learning approach. Hence, the model simultaneously has a classifier for floor classification and a regressor for estimating X and Y coordinates, and tries to perform accurate indoor localization even in environments with furniture and other obstacles. The proposed CNN-based model efficiently utilizes RSSI data, achieving 99.0% floor classification accuracy and 6.5 m in terms of Euclidean distance error based on coordinate estimation on the UJIIndoorLoc dataset. On the other hand, the validation results using Tampere datasets were ‘distance error (m) = 3.7868’ form localization and ‘accuracy = 98.99%’ for floor classification. Comprehensive preprocessing significantly enhances localization accuracy. Full article
►▼ Show Figures

Figure 1

26 pages, 5174 KB  
Article
A Lightweight Hybrid Graph-Neural-Network and Heuristic Framework for Practical Software Vulnerability Assessment in Production Codebases
by Ahmed M. Elalfy, Gamal A. Ebrahim and Marvy Badr Monir Mansour
Computers 2026, 15(8), 542; https://doi.org/10.3390/computers15080542 - 19 Aug 2026
Viewed by 219
Abstract
The deployment of deep-learning vulnerability detectors in production remains difficult. Models are large, false-positive rates are high, output is opaque, and a persistent gap separates benchmark performance from real-world utility. The objective of this work is to close part of that gap by [...] Read more.
The deployment of deep-learning vulnerability detectors in production remains difficult. Models are large, false-positive rates are high, output is opaque, and a persistent gap separates benchmark performance from real-world utility. The objective of this work is to close part of that gap by combining a learned detector with interpretable rules so that accuracy, efficiency, and actionability are achieved together. A hybrid framework is therefore presented in which a lightweight edge-conditioned GNN of 71,810 parameters, named FastVulnGNN, trained in 96.2 s on a single CPU core, is paired with rule-based heuristic detection for six C/C++ vulnerability classes, namely buffer overflows, format-string defects, null-pointer dereferences, double-free errors, integer overflows, and race conditions. On the MegaVul dataset, an accuracy of 71.1%, an F1 score of 0.70, and an AUC-ROC of 0.77 are obtained by the GNN component. On a production codebase of 499 files and 312,758 lines of code, the full hybrid scan completes in 5.5 s, which corresponds to about 57,000 lines per second, without any GPU hardware. Per-file risk tiers and pattern-level explanations are produced, and these are suitable for continuous-integration use. The significance of this work lies in demonstrating that a deployable, explainable detector can be assembled from compact components, and an edge-type ablation study, a cross-dataset evaluation, and a per-vulnerability analysis are reported to characterize the approach. Full article
(This article belongs to the Section AI-Driven Innovations)
►▼ Show Figures

Figure 1

22 pages, 391 KB  
Article
A New Lattice-Based Post-Quantum Digital Signature from Compact Rejection Sampling
by Pingyuan Zhang and Limin Wang
Computers 2026, 15(8), 541; https://doi.org/10.3390/computers15080541 - 19 Aug 2026
Viewed by 211
Abstract
Rejection samplings are the essential building blocks to design lattice-based digital signatures under the Fiat–Shamir paradigm. Up to now most of them have been built by Gaussian samplings or uniform samplings. Gaussian-based rejection sampling signatures such as the BLISS scheme have very short [...] Read more.
Rejection samplings are the essential building blocks to design lattice-based digital signatures under the Fiat–Shamir paradigm. Up to now most of them have been built by Gaussian samplings or uniform samplings. Gaussian-based rejection sampling signatures such as the BLISS scheme have very short signature sizes but are vulnerable to timing attacks, whereas the uniform-based rejection sampling signatures such as ML-DSA are allowed to be simply implemented but have larger signature sizes. This work intends to use a new probability distribution, rather than Gaussian or uniform distributions, to build the rejection sampling in Fiat–Shamir signatures, and aims to achieve short signature sizes while avoiding the cost of Gaussian sampling. To this end, we choose centered binomial distribution as a replacement, and build a new and compact rejection sampling that has the properties of both high-precision sampling and semi-uniform operation. As an application, we combine this rejection sampling with Lyubashevsky’s signature scheme, then propose the first lattice-based Fiat–Shamir signature scheme from centered binomial distribution. The proposed scheme not only avoids Gaussian sampling, but also is very efficient in terms of the signature sizes. Full article
►▼ Show Figures

Figure 1

30 pages, 2565 KB  
Article
Exploiting Base-Station Separability in Constrained Multiobjective Task Offloading for the Industrial Internet of Things: A Decomposition Multitasking Method with Exact Pareto-Front Synthesis
by Bingchi Sun, Haibin Zheng and Jingjing Jin
Computers 2026, 15(8), 540; https://doi.org/10.3390/computers15080540 - 19 Aug 2026
Viewed by 176
Abstract
In Industrial Internet of Things (IIoT) deployments, mobile edge computing (MEC) offloads computation-intensive tasks, a constrained biobjective problem trading time delay against energy consumption (MTOP). We show that this benchmark is exactly separable across micro base-station (MiBS) regions: its delay and energy objectives [...] Read more.
In Industrial Internet of Things (IIoT) deployments, mobile edge computing (MEC) offloads computation-intensive tasks, a constrained biobjective problem trading time delay against energy consumption (MTOP). We show that this benchmark is exactly separable across micro base-station (MiBS) regions: its delay and energy objectives are additive over regions, and the only coupling, intra-cell interference, stays within a region. Exploiting this, we propose CR-MTMEMTO-D, a structure-aware decomposition multitasking method that treats each region as an independent subtask, solves it with a feasibility-repaired NSGA-II, and reconstructs the global feasible Pareto front as the non-dominated subset of the Minkowski sum of the regional fronts, an exact composition that adds no global evaluations. Across 12 instances (45–432 variables, 20 seeds), it attains the best hypervolume and IGD on every instance (mean HV 0.9340 vs. 0.8021 for a plain NSGA-II baseline; average rank 1.00), with the margin widening as the problem scales, and it is unchanged under total-evaluation matching because every evaluation is a regional main task. A feasibility-priority acceptance gate keeps the population fully feasible. Under matched budgets, a prior cheap-task pool with bandit-controlled transfer adds no significant gain, which motivates the structural approach. Full article
►▼ Show Figures

Figure 1

35 pages, 835 KB  
Systematic Review
From Manipulation to Antidote: Mapping the Computational Capabilities of AI-Generated Synthetic Media to Health-Related Applications and Downstream Benefits
by Wellington Kanyongo and Mampilo Phahlane
Computers 2026, 15(8), 539; https://doi.org/10.3390/computers15080539 - 19 Aug 2026
Viewed by 277
Abstract
AI-generated synthetic media are evolving from tools of digital manipulation into a practical antidote for persistent challenges in digital health implementation. However, the computational capabilities that characterise these technologies, their applications and downstream health-related benefits remain fragmented and insufficiently synthesised. This systematic review [...] Read more.
AI-generated synthetic media are evolving from tools of digital manipulation into a practical antidote for persistent challenges in digital health implementation. However, the computational capabilities that characterise these technologies, their applications and downstream health-related benefits remain fragmented and insufficiently synthesised. This systematic review identified the computational capabilities that characterise AI-generated synthetic media in health, examined their applications and benefits, and developed an integrative framework linking these domains. Twenty-four studies published between 2021 and 31 May 2026 were included. Methodological quality was assessed using the Mixed Methods Appraisal Tool (MMAT) and findings were synthesised through thematic analysis. The synthesis revealed an integrated set of capabilities spanning photorealistic medical-image generation, modality-specific synthesis of clinical images and physiological signals, synthetic non-image health-data creation, preservation of statistical distributions, temporal patterns and clinical relationships, generation of diverse, novel and non-memorised samples and controlled transformation of medical and audiovisual content. Privacy-oriented synthesis and deepfake detection emerged as distinct components supporting privacy-conscious data use, clinical verification and healthcare safety. These demonstrated capabilities were linked to empirically evaluated and indicated applications, including data augmentation, AI model training, diagnostic model development, privacy-oriented health-data sharing, medical education, patient-facing communication, therapeutic support, clinical safety, health-system analytics and planning. The resulting Computational Capability–Application–Benefit (CAB) Framework conceptualises synthetic media as an evidence-graded pathway distinguishing demonstrated computational capabilities, evaluated health-related applications and reported, indicated or potential downstream benefits requiring further validation. AI-generated synthetic media, therefore, represent an emerging computational infrastructure with potential to support safer, privacy-conscious, adaptive and data-intensive healthcare. Full article
(This article belongs to the Section AI-Driven Innovations)
►▼ Show Figures

Figure 1

30 pages, 10969 KB  
Article
A Cloud-Based Reference Architecture and Prospective Evaluation Protocol for Integrating Business Intelligence, Extended Reality, and Learning Analytics in Health Data Science Education
by Vítor J. Sá, Paulo Veloso Gomes, João Donga, Rosalina Babo and António Marques
Computers 2026, 15(8), 538; https://doi.org/10.3390/computers15080538 - 19 Aug 2026
Viewed by 326
Abstract
The increasing complexity of healthcare data ecosystems demands educational technologies capable of supporting data-intensive learning through advanced analytics, immersive interfaces, and learning analytics. This paper presents a cloud-based reference architecture and a prospective evaluation protocol for integrating Business Intelligence (BI), Extended Reality (XR), [...] Read more.
The increasing complexity of healthcare data ecosystems demands educational technologies capable of supporting data-intensive learning through advanced analytics, immersive interfaces, and learning analytics. This paper presents a cloud-based reference architecture and a prospective evaluation protocol for integrating Business Intelligence (BI), Extended Reality (XR), and learning analytics in health data science education. The proposed architecture is informed by a systematic literature review conducted according to the PRISMA 2020 guidelines, which screened 613 records retrieved from four databases and retained 56 studies for qualitative synthesis. The review indicates that, although BI and XR technologies have independently been associated with educational benefits, empirical evidence supporting integrated educational architectures combining BI, XR, and learning analytics remains limited, particularly in health data science education. Based on these findings, the paper specifies a layered reference architecture comprising a cloud analytics engine, an immersive visualization engine, an interoperability layer, and a learning analytics pipeline designed to support adaptive and AI-assisted educational services during subsequent implementation phases. The reference architecture is partially instantiated within the curricular unit Health Data Analysis and Visualization of the Digital Health programme at the Polytechnic University of Porto, where the BI and XR components are currently deployed and used within the course, while the interoperability middleware, learning analytics infrastructure, and AI-assisted services remain under development or are specified as architectural capabilities. To support future empirical validation, the paper also defines a comprehensive prospective evaluation protocol comprising predefined outcomes, established instruments with published psychometric properties, together with an expert-developed health data literacy assessment undergoing content validation, research hypotheses, power analysis, a statistical analysis plan, and ethical and data-governance provisions. The manuscript makes four principal research contributions: (i) a cloud-based reference architecture for BI–XR integration, (ii) a computational learning analytics pipeline specification, (iii) an interoperable system design for health data science education, and (iv) a prospective evaluation protocol to guide the future validation of the proposed reference architecture. Full article
(This article belongs to the Special Issue Intelligent Educational Technologies: Core Architectures, Algorithms, and Evidence-Based Systems)
►▼ Show Figures

Figure 1

20 pages, 9197 KB  
Article
PSATM: Planar Structure Awareness-Based Texture Mapping for 3D Reconstruction of Photovoltaic Scenes
by Mingwei Cao, Zilong Wang, Ning Li and Haifeng Zhao
Computers 2026, 15(8), 537; https://doi.org/10.3390/computers15080537 - 19 Aug 2026
Viewed by 222
Abstract
In the field of 3D reconstruction for photovoltaic scenes, current texture mapping techniques frequently encounter significant texture segmentation and apparent joins in uniform plane regions, such as solar panels, because they lack geometric structural assumptions. To tackle these challenges, we introduce a new [...] Read more.
In the field of 3D reconstruction for photovoltaic scenes, current texture mapping techniques frequently encounter significant texture segmentation and apparent joins in uniform plane regions, such as solar panels, because they lack geometric structural assumptions. To tackle these challenges, we introduce a new texture-mapping strategy for 3D solar panel scene reconstruction that focuses on planar structure awareness. We term the proposed method PSATM. Initially, we suggest a global constraint and a local refinement process to incorporate clear geometric structure details. This process automatically detects and labels planar regions through a region-growing approach. Next, we integrate a planar structure-aware module into the smoothness term of the Markov Random Field (MRF) energy function. This module uses dihedral angles and plane membership to adjust label transition costs, enhancing texture coherence within planar regions and maintaining smooth transitions at genuine geometric breaks. Furthermore, we establish a boundary treatment technique relying on local geometric support. This method combines area-based weighting and normal consistency to modify erroneous labels, successfully removing small remnants and smoothing texture edges. We tested the proposed PSATM with texture patch counts and visual quality measures on actual solar panel scenes. The results indicate that the proposed PSATM considerably reduces texture segmentation errors and improves texture flow and overall visual quality compared to the existing method. Full article
►▼ Show Figures

Figure 1

41 pages, 1898 KB  
Article
Securing Cross-Chain Multisignature Execution Through Deterministic Enforcement and Explainable Anomaly Awareness
by Usman Mohyud din Chaudhary, Humaira Arshad, Muhammad Ismail Mohmand, Erum Ashraf and Waheed Ali H. M. Ghanem
Computers 2026, 15(8), 536; https://doi.org/10.3390/computers15080536 - 18 Aug 2026
Viewed by 385
Abstract
Cross-chain bridges represent one of the most damaging attack surfaces in decentralized finance, with major exploits (e.g., Ronin, Wormhole, Nomad, Multichain) arising not from broken signature schemes but from failures in proof verification, replay protection, and signer-set management, gaps that conventional threshold-signature multisignature [...] Read more.
Cross-chain bridges represent one of the most damaging attack surfaces in decentralized finance, with major exploits (e.g., Ronin, Wormhole, Nomad, Multichain) arising not from broken signature schemes but from failures in proof verification, replay protection, and signer-set management, gaps that conventional threshold-signature multisignature wallets do not address. This study presents an incident-aware multisignature architecture combining three on-chain predicates—block-height freshness windows, epoch-bound signer sets, and Merkle inclusion-proof verification—with a non-authoritative off-chain LightGBM classifier that generates SHAP-attributed risk explanations to support governance actions such as pausing, vetoing, or rotating signers, without directly blocking or approving execution. The framework was evaluated on a simulated benchmark of 78,600 Ethereum testnet transactions containing six injected anomaly classes (gas spikes, nonce jitter, malformed call data, stale intents, proof-delivery delays, and epoch-rotation replays). The LightGBM advisor achieved ROC-AUC 0.92 (95% CI [0.906, 0.926]) and F1 0.73 ([0.712, 0.749]), outperforming five baselines—logistic regression, Random Forest, XGBoost, isolation forest, and a rule-based detector—with the highest F1 (0.731) and PR-AUC (0.799), while the rule-based detector, which by construction covers only the anomaly classes addressed by the deterministic predicates, attained F1 0.282. Differences were statistically significant except for the LightGBM–XGBoost PR-AUC comparison. The deterministic layer itself is verified through 28 property-level contract tests covering all seven modeled attack objectives, with measured per-function gas costs (execute_Intent: 118,756 gas, of which 28,432 gas is Merkle-proof verification). Within this controlled setting, the results indicate that a machine learning advisor can extend anomaly-prioritization coverage beyond the scope of the deterministic predicates while leaving execution control fully deterministic. This work is presented as a controlled proof of concept: the reported metrics quantify recovery of scripted injection patterns, and validation against real-world exploit traces remains future work. Full article
(This article belongs to the Special Issue Convergence of Blockchain and AIoT: Secure and Intelligent Systems)
►▼ Show Figures

Figure 1

29 pages, 2464 KB  
Article
Validate Before You Build: Exploring Pre-MVP Evidence Levels—Not Quantity—And Startup Performance in Early-Stage Software Ventures
by Frédéric Pattyn, Yannick Dillen and Peter Goetz
Computers 2026, 15(8), 535; https://doi.org/10.3390/computers15080535 - 18 Aug 2026
Viewed by 431
Abstract
Software startups operate in environments characterized by rapid change, high uncertainty, and limited resources, resulting in high failure rates and challenges such as premature scaling and cash flow mismanagement. Prior research on pre-MVP validation has largely measured activity by volume rather than by [...] Read more.
Software startups operate in environments characterized by rapid change, high uncertainty, and limited resources, resulting in high failure rates and challenges such as premature scaling and cash flow mismanagement. Prior research on pre-MVP validation has largely measured activity by volume rather than by the strength of evidence produced, leaving open whether evidence type, rather than quantity, is associated with startup performance. This study addresses that gap by investigating how early-stage software startups validate their initial idea before building their first Minimum Viable Product (MVP). Through 29 semi-structured interviews with founders from 16 software startups, pre-MVP validation activities were extracted and inductively coded into a six-level Validation Canvas spanning three validation stages identified in the literature: problem validation, problem-solution fit, and product-market fit. Startup performance was assessed through a composite ranking across funding, revenue, profitability, and runway indicators, and validation activities were analyzed thematically to derive the six evidence levels. No clear relationship was observed between the number of validation events and startup performance. Instead, stronger-performing startups tended to reach higher levels of evidence—particularly securing contingent investment commitments (Level 5) or paying customers (Level 6) before full MVP development. Level 6—paying customers before the full product exists—is identified as the strongest form of pre-MVP market evidence, as it directly validates willingness-to-pay without relying on investor confidence. In this study, product-market fit is operationalised as demonstrated commercial viability through external financial commitments rather than interest signals or free sign-ups alone. Based on these exploratory findings, the study proposes the Hierarchy of Validation: a staged, bidirectional process model in which bottom-up traversal from informal interest signals (L1) toward paying customers (L6) emerged as the primary pattern among stronger-performing startups. A top-down direction, in which experienced founders begin at higher evidence levels and work downward, is proposed as a hypothesis for future research. To our knowledge, this is among the first accounts of pre-MVP validation that differentiates strength of evidence rather than volume of activity, contributing the Hierarchy of Validation as an original, exploratory framework for early-stage software startups. These findings remain exploratory and require validation in larger and more diverse samples. Full article
(This article belongs to the Section Human–Computer Interactions)
►▼ Show Figures

Figure 1

25 pages, 6788 KB  
Article
Detection of False Stealthy Data Injection Attacks in Smart Meters Using Machine Learning and Blockchain Technology
by Mohiuddin Mehedi, Abdul Aziz Kabir, Khandakar Rabbi Ahmed, Furqaan Mujtahid, Sakib Salam Jamee and Md Nayem Rahman
Computers 2026, 15(8), 534; https://doi.org/10.3390/computers15080534 - 17 Aug 2026
Viewed by 326
Abstract
Despite the benefits associated with the use of smart meters in advanced metering infrastructure, the widespread deployment of such meters has introduced vulnerabilities that leave power systems susceptible to stealthy false data injection attacks which cannot be detected by conventional methods. In this [...] Read more.
Despite the benefits associated with the use of smart meters in advanced metering infrastructure, the widespread deployment of such meters has introduced vulnerabilities that leave power systems susceptible to stealthy false data injection attacks which cannot be detected by conventional methods. In this paper, we present a framework that combines a bidirectional long short-term memory network with an attention mechanism and a blockchain integrity layer to provide secure anomaly detection. We utilize the Smart Meter Electricity Consumption Dataset, augmented with synthetically injected anomalies, to detect abnormal consumption behavior. Experimental results demonstrate that the proposed hybrid model achieves up to 96.23% accuracy, 99.88% precision, 92.58% recall, and 96.09% F1-score, outperforming eXtreme Gradient Boosting (XGBoost), Isolation Forest, and Random Forest baselines. Confusion matrix analysis confirms minimal false positives and strong detection capability for stealthy attacks. The blockchain layer ensures immutability and trustworthiness of detection results through cryptographic hashing and consensus mechanisms with negligible overhead. The proposed framework offers a scalable, secure, and interpretable solution for defending smart grid infrastructures against complex cyberattacks. Full article
(This article belongs to the Special Issue Revolutionizing Industries: The Impact of Blockchain Technology)
►▼ Show Figures

Figure 1

38 pages, 7656 KB  
Article
DMRP: A Decentralized Mobile Reconciliation Protocol for Eventually Consistent Replication in FANETs
by Wassila Korichi, Akram Zine Eddine Boukhamla, Nadjet Azzaoui and Mohamed Chahine Ghanem
Computers 2026, 15(8), 533; https://doi.org/10.3390/computers15080533 - 17 Aug 2026
Viewed by 239
Abstract
Flying Ad Hoc Networks let unmanned aerial vehicles communicate directly, without relying on fixed ground infrastructure, in time-critical settings such as disaster response, search and rescue, border surveillance, precision agriculture, and military reconnaissance. UAV mobility, however, causes frequent topology changes and intermittent connectivity, [...] Read more.
Flying Ad Hoc Networks let unmanned aerial vehicles communicate directly, without relying on fixed ground infrastructure, in time-critical settings such as disaster response, search and rescue, border surveillance, precision agriculture, and military reconnaissance. UAV mobility, however, causes frequent topology changes and intermittent connectivity, so nodes typically store data locally and replicate it across the network to keep it available. The resulting challenge is consistency: independently evolving copies must be reconciled without a central coordinator, and strong consistency is not realistic in a network this prone to partitioning. We address this with the Decentralized Mobile Reconciliation Protocol (DMRP), which provides eventual consistency among UAV nodes with no external coordination, with convergence formally guaranteed whenever the swarm’s synchronisation graph is eventually connected. DMRP combines immediate local validation and convergence guarantees grounded in conflict-free replicated data type properties; hysteresis-based memory management with dual thresholds to cap journal storage overhead; adaptive delta or full-state synchronisation based on receiver lag; and epidemic propagation for transitive update dissemination. Energy efficiency guided the design throughout, through wireless broadcast and the avoidance of redundant transmissions. DMRP was implemented and evaluated through extensive OMNeT++/INET simulations of three-dimensional FANET scenarios. Results demonstrate that the protocol maintains a strictly bounded reconciliation journal, whereas the reference δ-CRDT log grows without bound, reducing reconciliation-journal storage by up to 75% at the largest workload evaluated, while achieving near-complete consistency after node isolation and network partitioning. Full article
(This article belongs to the Special Issue The Internet of Things—Current Trends, Applications, and Future Challenges (3rd Edition))
►▼ Show Figures

Figure 1

26 pages, 363 KB  
Article
A Machine Learning Approach to Latent Structure Learning for Zero-Inflated Patent Keyword Count Data
by Sunghae Jun
Computers 2026, 15(8), 532; https://doi.org/10.3390/computers15080532 - 17 Aug 2026
Viewed by 249
Abstract
Patent document–keyword count data are typically high-dimensional, sparse, and dominated by zero entries, which makes it difficult to simultaneously reconstruct keyword frequencies and identify meaningful technological structures. This study proposes a machine learning approach to latent structure learning for zero-inflated patent keyword count [...] Read more.
Patent document–keyword count data are typically high-dimensional, sparse, and dominated by zero entries, which makes it difficult to simultaneously reconstruct keyword frequencies and identify meaningful technological structures. This study proposes a machine learning approach to latent structure learning for zero-inflated patent keyword count data. The proposed zero-gated latent factor model (ZG-LFM) combines nonnegative matrix factorization (NMF) with keyword-specific logistic occurrence models. NMF is used to extract interpretable document–factor and factor–keyword representations, while the occurrence gate estimates the probability that each keyword appears in a given patent document. The method was evaluated in an initial domain-specific case study using a document–keyword matrix constructed from 9434 quantum computing patent documents and 175 keywords, of which 87.60% of the entries were zero. Predictive performance was assessed using root mean squared error, mean absolute error, and the area under the receiver operating characteristic curve across different numbers of latent factors. The experimental results showed that NMF provided more accurate keyword count reconstruction, whereas the proposed model consistently achieved better discrimination between zero and nonzero keyword entries. These findings indicate that latent count reconstruction and keyword occurrence modeling provide complementary information for analyzing sparse patent data. The learned latent factors further revealed coherent quantum computing subdomains, including hybrid quantum–classical execution, quantum machine learning, quantum state measurement and error analysis, quantum cryptography, superconducting chips, quantum circuits, optical control, qubit devices, and optimization algorithms. The proposed framework therefore provides interpretable latent technology structures while improving the identification of keyword occurrence patterns in zero-inflated patent data. These findings demonstrate the feasibility of the framework within the analyzed quantum computing corpus; its generalizability across other technological domains remains to be evaluated. Full article
43 pages, 15065 KB  
Article
A Privacy-Conscious and Explainable IDS-Oriented Triage and Response Pipeline for Mobile Network Infrastructure Using Aggregated Cellular Traffic Signatures
by Özcan Dimez and Fatih Cogen
Computers 2026, 15(8), 531; https://doi.org/10.3390/computers15080531 - 16 Aug 2026
Viewed by 441
Abstract
Mobile-network operators must interpret spatial anomalies in aggregated cell-level telemetry and decide whether, where, and how to respond. This paper presents a privacy-conscious, intrusion detection system (IDS)-oriented triage and response architecture that consumes cell-level anomaly signatures and couples spatial reconstruction, short-horizon forecasting, origin [...] Read more.
Mobile-network operators must interpret spatial anomalies in aggregated cell-level telemetry and decide whether, where, and how to respond. This paper presents a privacy-conscious, intrusion detection system (IDS)-oriented triage and response architecture that consumes cell-level anomaly signatures and couples spatial reconstruction, short-horizon forecasting, origin inference, self-resolution and remaining-time estimation, adaptive gating, ETA-aware team selection, conservative redeployment, explanation, and audit logging. It is a downstream spatial-attribution and response-orchestration layer, not a packet- or flow-level attack detector. The evaluated configuration uses transparent deterministic, heuristic, and optimization-based procedures and synthetic aggregated signatures without subscriber identifiers; aggregation is treated as data minimization, not a formal privacy guarantee. Across 20 paired synthetic scenarios, the full policy reduced conditional mean response time from 37.58 to 22.86 min, total travel from 576.0 to 273.5 min, and coverage ETA from 32.28 to 26.76 min, while on-time service increased from 54.0% to 60.0%. These benefits were accompanied by lower persistent-incident coverage (91.1% to 72.1%) and a higher miss rate (8.9% to 27.9%). The inverse-origin configuration showed no repeated localization-error advantage, and conservative redeployment had only a marginal average effect. The results therefore demonstrate a configurable downstream triage trade-off under controlled synthetic conditions, not attack-classification accuracy, adversarial robustness, formal privacy, or deployment readiness. Full article
(This article belongs to the Special Issue Intelligent Systems Security: AI-Driven Approaches for Attacks, Detection & Explainability)
►▼ Show Figures

Figure 1

30 pages, 13991 KB  
Article
Hybrid Observation Source-Bias Analysis Using Explainable Machine Learning and Spatial Validation
by Gulnara Kaziyeva, Gulzira Abdikerimova, Anargul Bekenova, Saule Zhumagulovа, Gulden Murzabekova, Ainur Shekerbek, Balganym Kosherova, Shynar Turmaganbetova and Assem Aubakirova
Computers 2026, 15(8), 530; https://doi.org/10.3390/computers15080530 - 16 Aug 2026
Viewed by 246
Abstract
This study proposes a hybrid computational model for diagnosing such biases using groundwater observation data across Kazakhstan. The analytical dataset included 2402 georeferenced observations, including 492 natural springs from OpenStreetMap (OSM), 109 boreholes from OSM, and 1801 spatially filtered pseudo-absence observations. Springs and [...] Read more.
This study proposes a hybrid computational model for diagnosing such biases using groundwater observation data across Kazakhstan. The analytical dataset included 2402 georeferenced observations, including 492 natural springs from OpenStreetMap (OSM), 109 boreholes from OSM, and 1801 spatially filtered pseudo-absence observations. Springs and boreholes together formed 601 positive groundwater observations, while pseudo-absence samples represented a spatially filtered background level rather than confirmed groundwater absence. Each observation was characterized by 89 environmental predictors extracted from Google Earth Engine. The proposed hybrid observation source bias index (HOSBI) combines a normalized robust effect size based on the median absolute value of the Cliff delta, multivariate distribution divergence quantified using RBF-MMD, and spatially confirmed source distinctiveness. These components were assigned fixed weights of 0.40, 0.35, and 0.25 to emphasize statistical and distributional data while maintaining spatial validation. Spatial cross-validation achieved a balanced accuracy of 0.855 for distinguishing OSM sources from OSM wells and 0.846 for separating positive observations from background pseudo-absences. Climate showed the strongest source-related bias (HOSBI = 0.923), while Sentinel-1 SAR contributed the most to the contrast between positive and background data (HOSBI = 0.923). The proposed framework provides an interpretable and replicable preliminary assessment of source bias in heterogeneous geospatial datasets. Full article
►▼ Show Figures

Figure 1

30 pages, 17301 KB  
Article
Design, Kinematic Control, and Implementation of a LEGO-Based Drawing Robot for Lissajous Curve Generation
by Attila Körei, Szilvia Szilágyi and Ingrida Vaičiulytė
Computers 2026, 15(8), 529; https://doi.org/10.3390/computers15080529 - 14 Aug 2026
Viewed by 257
Abstract
Lissajous figures are frequently studied and widely used objects in engineering and physics. Although these patterns are usually analysed using computer simulations or oscilloscopes, such tools may limit their educational value by covering the core physical processes that generate the curves. In order [...] Read more.
Lissajous figures are frequently studied and widely used objects in engineering and physics. Although these patterns are usually analysed using computer simulations or oscilloscopes, such tools may limit their educational value by covering the core physical processes that generate the curves. In order to address these problems, the design, kinematic validation, and prototyping of a dual-axis drawing robot were carried out on the LEGO Education SPIKE Prime platform. The hardware implementation centres on a LEGO-based dual Scotch yoke mechanism, which supports precise transformation of uniform circular motion into simple harmonic motion. This setup implements the superposition of two independent simple harmonic oscillations by simultaneously moving the paper tray along the x-axis and the pen along the y-axis. High-fidelity trajectories are achieved through a 40:1 worm gear reduction, which enables precise control of the parameter configuration. The phase shift can be manually set by adjustment levers. The robot’s geometry supports discrete amplitude settings of 8, 16, and 24 mm by adjusting the crankpin position. System control is managed by Python code that synchronises motor speeds and angular displacements according to frequency ratios. The research methodology used the Double Diamond design thinking framework, structuring development into four phases: identifying historical mechanical solutions, defining pedagogical and technical classroom requirements, iteratively developing the LEGO prototype, and testing the system through representative drawing experiments. Results show that the robot can reproduce a broad range of periodic Lissajous curves with high repeatability, and that its physical outputs show strong visual and mathematical correspondence to ideal trajectories simulated in the Desmos graphing calculator. The final prototype satisfies classroom constraints, providing a transparent, low-cost, modular STEAM tool that bridges the distance between abstract parametric equations and complex mechanical implementations. Full article
(This article belongs to the Special Issue STEAM Literacy and Computational Thinking in the Digital Era)
►▼ Show Figures

Figure 1

34 pages, 28776 KB  
Article
Global-Local Feature-Based Rice Leaf Disease Classification Using Two-Stream Deep Neural Network Feature Fusion
by Md Nahidur Rahaman, Abdullah Al Mamun, Md. Kamal Hossen, Abdur Rouf, Tumpa Rani Shaha, Jungpil Shin, Mohd Nizam Husen and Abu Saleh Musa Miah
Computers 2026, 15(8), 528; https://doi.org/10.3390/computers15080528 - 14 Aug 2026
Viewed by 386
Abstract
Rice leaf diseases significantly affect crop health and yield potential, creating a need for accurate and timely disease diagnosis. Many existing approaches still rely on single-stream feature extraction architectures, which may limit the ability to simultaneously capture global contextual information and fine-grained disease [...] Read more.
Rice leaf diseases significantly affect crop health and yield potential, creating a need for accurate and timely disease diagnosis. Many existing approaches still rely on single-stream feature extraction architectures, which may limit the ability to simultaneously capture global contextual information and fine-grained disease characteristics. Moreover, limited interpretability and decision-support capability hinder their practical deployment in real-world rice farming. To address these limitations, we employed a framework consists of two parallel feature extraction streams designed to capture different characteristics of disease patterns. The first stream uses a Swin Transformer to learn global contextual information and long-range spatial relationships across the leaf image. The second stream employs ConvNeXt to extract local texture features, including lesion details, spots, and color variations. By combining these complementary representations, the proposed framework effectively integrates global semantic information with local disease-specific features for improved classification performance. The extracted features from the two streams are fused through concatenation followed by an attention-based feature refinement module, enabling adaptive weighting of discriminative features. The refined representation is then used by a fully connected classifier for disease prediction. To enhance model interpretability, Grad-CAM visualization is incorporated to highlight disease-relevant regions and provide visual explanations for the model decisions. Furthermore, an LLM-based advisory module is integrated as a post-diagnosis decision-support component to provide contextualized disease management information and suggestions based on the predicted disease category. The generated suggestions are intended to support, rather than replace, expert agronomic recommendations and should be validated by agricultural professionals before practical application. The proposed framework was evaluated on two rice leaf disease datasets, achieving accuracies of 99.55% and 97.06% on Dataset-1 and Dataset-2, respectively, which are higher than those reported in previous studies. Additionally, five-fold cross-validation on Dataset-1 achieved an average accuracy of 98.91% ± 0.47, demonstrating the stability of the proposed approach. Cross-dataset evaluation using nine common disease classes across both datasets achieved 90.80% accuracy, indicating improved generalization across different data distributions. The proposed framework provides an accurate and explainable approach for rice leaf disease diagnosis in smart agriculture applications. Full article
(This article belongs to the Special Issue Advances in Computer Vision: Models, Learning, and Inference)
►▼ Show Figures

Figure 1

30 pages, 1840 KB  
Article
Weak Ridge-Flow Prior-Guided Fingerprint Reconstruction Under Severe Degradation
by Haiyong Xie, Lin Wang, Yonghao Dai and Yunqian Cheng
Computers 2026, 15(8), 527; https://doi.org/10.3390/computers15080527 - 14 Aug 2026
Viewed by 243
Abstract
Fingerprint enhancement plays an important role in recovering identity-related ridge structures from degraded fingerprints. However, existing methods primarily focus on local texture restoration and may struggle to preserve ridge continuity and structural consistency under severe degradation conditions, including ridge fragmentation, diffusion blur, and [...] Read more.
Fingerprint enhancement plays an important role in recovering identity-related ridge structures from degraded fingerprints. However, existing methods primarily focus on local texture restoration and may struggle to preserve ridge continuity and structural consistency under severe degradation conditions, including ridge fragmentation, diffusion blur, and partial information loss. In this paper, we observe that degraded fingerprints may retain incomplete ridge-flow information that can provide useful structural guidance for fingerprint reconstruction. Based on this observation, we propose a conditional generative adversarial network guided by a weak ridge-flow prior (WRP-cGAN) for degraded fingerprint enhancement. The proposed method treats the estimated ridge-flow information as a weak structural prior rather than an exact structural constraint and introduces prior-conditioned feature modulation to adaptively incorporate structural cues during reconstruction. The framework is jointly optimized using adversarial, image-space reconstruction, ridge-flow orientation-consistency, and gradient-consistency losses to improve ridge continuity, structural coherence, and local detail preservation. On the NIST SD301-derived test set, the proposed method increases the median NFIQ2 score from 9 to 44, improves the minutiae-restoration F1-score from 0.2507 to 0.5426, and increases the SourceAFIS Rank-1 identification rate from 39% to 86%. An additional qualitative evaluation on FVC2004 DB1 provides preliminary evidence of cross-dataset transferability without fine-tuning. These results suggest that weak ridge-flow priors provide useful structural guidance for degraded fingerprint reconstruction and improve recognition-oriented fingerprint quality under the degradation conditions considered in this study. Full article
(This article belongs to the Section AI-Driven Innovations)
►▼ Show Figures

Figure 1

29 pages, 840 KB  
Review
Virtual Educational Agents in Immersive Virtual Reality Learning Environments: A Scoping Review of Terminology, Conceptualizations, and Taxonomy Requirements
by Panagiota Athanasiou and Emmanuel Fokides
Computers 2026, 15(8), 526; https://doi.org/10.3390/computers15080526 - 13 Aug 2026
Viewed by 363
Abstract
The growth of immersive virtual reality learning environments (IVRLEs) coincides with the emergence of numerous virtual educational agents that offer support to their users. Researchers suggested various terms to describe these agents; yet, this terminology fragmentation creates conceptual ambiguity, rendering them hard to [...] Read more.
The growth of immersive virtual reality learning environments (IVRLEs) coincides with the emergence of numerous virtual educational agents that offer support to their users. Researchers suggested various terms to describe these agents; yet, this terminology fragmentation creates conceptual ambiguity, rendering them hard to compare. The purpose of this scoping review was to map out the terms used to describe educational agents in IVRLEs and look at how they have been conceptualized, the characteristics that have been used to differentiate them, and the educational roles and associated learning functions they have. In addition, the goal was to identify the requirements for the development of a relevant taxonomy. Arksey’s and O’Malley’s methodological framework and the PRISMA Extension for Scoping Reviews were applied. Out of the 1867 articles found in the Scopus, Eric, and LearnTechLib databases, published between 2015 and 2026, 129 met the eligibility criteria. The findings revealed substantial conceptual fragmentation, with similar educational entities being described using different terminology while identical terms were frequently applied to conceptually distinct systems. Characteristics such as intelligence, embodiment, interaction modality, adaptivity, affective and social characteristics, and context awareness distinguished these agents rather than terminology alone. Advances in artificial intelligence have further blurred the boundaries of traditional categories. Overall, this review provides a theoretical foundation for future research aimed at developing more coherent conceptual frameworks and standardized approaches to the design, classification, and evaluation of virtual educational agents. Full article
(This article belongs to the Special Issue Emerging Technologies and 21st Century Learning)
►▼ Show Figures

Graphical abstract

41 pages, 29978 KB  
Article
Attention-Guided Cross-Connected Filters Convolutional Neural Network with Surrogate-Based Interpretability for Image Splicing Forgery Detection
by Aruna Srinivasan, Surabhi Narayan and Aarnav Sandeep Deshmukh
Computers 2026, 15(8), 525; https://doi.org/10.3390/computers15080525 - 13 Aug 2026
Viewed by 271
Abstract
Background: Image splicing forgery detection is one of the most challenging problems in the field of image forensics as it involves identifying and localizing suspicious regions that are created by integrating contents from one or more different sources. The accurate detection and classification [...] Read more.
Background: Image splicing forgery detection is one of the most challenging problems in the field of image forensics as it involves identifying and localizing suspicious regions that are created by integrating contents from one or more different sources. The accurate detection and classification of splicing forgery still remains a difficult task because of the existence of overlapping image regions, which makes it complex to differentiate authentic and tampered images. This overlap causes a lack of feature representation, making it difficult to precisely detect the tampering in images. Also, the decision-making process of the model is often a black box, which makes it challenging to interpret and understand the rationale behind its decisions. Methods: To address these challenges, a Convolutional Block Attention Module (CBAM)–U-Net with Cross-Connected Filters–Convolutional Neural Network (CCF-CNN) is proposed to achieve precise detection and localization of spliced regions. The CBAM enhances spatial and channel-wise attention, enabling accurate localization of forged regions. The dual-phase CCF-CNN is incorporated with cross-connected filters to differentiate between the authentic and tampered regions by extracting global and local features. Additionally, a surrogate heatmap mechanism is introduced using intermediate decoder features to generate patch-level visual explanations, enabling precise localization of the spliced regions, thereby improving the model’s transparency in decision-making. Results: The proposed CCF-CNN obtains a high accuracy of 99.84% on the CASIA 2.0 dataset and an accuracy of 95.63% on the MISD. Conclusions: Compared to traditional CNNs such as VGG, ResNet and attention-based interpretability algorithms, the proposed model obtains higher performance in terms of detection and interpretability. Full article
(This article belongs to the Section ICT Infrastructures for Cybersecurity)
►▼ Show Figures

Figure 1

20 pages, 7625 KB  
Hypothesis
Reducing Peak Load Underprediction Through Risk-Aware Upper Quantile Forecasting: A University Laboratory Case Study
by Marwa O. Al Enany, Mazen Hesham Elnahal and Amira M. Gaber
Computers 2026, 15(8), 524; https://doi.org/10.3390/computers15080524 - 13 Aug 2026
Viewed by 244
Abstract
Underprediction of high electrical demand can be more operationally consequential than an equally sized overprediction, yet standard point forecasting models are optimized primarily for average error. This case study evaluates a multivariate quantile Transformer as a safety-oriented next observation forecasting layer for a [...] Read more.
Underprediction of high electrical demand can be more operationally consequential than an equally sized overprediction, yet standard point forecasting models are optimized primarily for average error. This case study evaluates a multivariate quantile Transformer as a safety-oriented next observation forecasting layer for a university laboratory. A timestamp-level audit identified 33,374 native measurements collected from 22 April to 12 December 2024 at a median interval of approximately 10 min. The final leakage-free pipeline uses only real observations, performs the chronological split before sequence generation, fits all scalers on training data only, and rejects windows containing gaps greater than 30 min. Persistence, fixed-order SARIMA, LSTM, GRU, CNN–LSTM, and an MSE-trained Transformer were evaluated on the same 6595-sample test period. GRU achieved the best deterministic accuracy (MAE 0.017744 kW; RMSE 0.023278 kW), whereas the proposed τ = 0.90 Transformer intentionally traded point accuracy (MAE 0.033830 ± 0.001133 kW) for asymmetric risk control. Across five independent runs, it achieved a pinball loss of 0.004453 ± 0.000069 kW, empirical coverage of 87.95 ± 1.01%, and a peak underprediction rate of 26.64 ± 5.32%, compared with 72.94–100% for the conventional benchmark outputs. Additional τ = 0.75 and τ = 0.95 experiments demonstrate the expected accuracy–safety trade-off. MAPE is not used as a primary metric because near-zero loads make percentage errors unstable. The results support the proposed model as a complementary upper quantile forecasting layer for this small, dynamic facility; they do not establish general performance at feeder or system scale. Full article
(This article belongs to the Special Issue AI Applications for Smart Grid Energy Management and Industrial Electrical Systems)
►▼ Show Figures

Graphical abstract

17 pages, 6118 KB  
Article
Time-Aware Late Fusion for Multimodal Rice Growth-Rate Prediction from UAV Imagery and Weather Context
by Alaa O. Elhadi, Saad M. Darwish and Mahmoud A. Mahdi
Computers 2026, 15(8), 523; https://doi.org/10.3390/computers15080523 - 12 Aug 2026
Viewed by 332
Abstract
Accurate crop-growth estimation from unmanned aerial vehicle (UAV) imagery is important for precision agriculture, but image-only models can struggle to represent seasonal context. This study evaluates whether combining UAV imagery with weather variables and elapsed time improves continuous rice growth-rate prediction in a [...] Read more.
Accurate crop-growth estimation from unmanned aerial vehicle (UAV) imagery is important for precision agriculture, but image-only models can struggle to represent seasonal context. This study evaluates whether combining UAV imagery with weather variables and elapsed time improves continuous rice growth-rate prediction in a single-site, publicly available rice-seedling dataset spanning multiple growing seasons. A Time-Aware Late Fusion (TALF) model is introduced in which a convolutional branch encodes image features, a multilayer perceptron encodes contextual features, and the two streams are merged only at the regression head. Relative humidity, wind speed, and elapsed time are used as contextual inputs after season-aware preprocessing. Evaluation is reported on a chronological multi-season split using internal ablations rather than external generalization claims. TALF achieved a mean absolute error (MAE) of 0.031, compared with 0.1455 for the optimized image-only baseline and 0.0890 for an early-fusion image-and-weather baseline. A secondary tolerance-based metric reached 94.9% under the reported threshold. The results indicate that weather and elapsed-time context improve prediction on this dataset and that separating image and tabular encoders until the final layers is a competitive multimodal learning design under the reported protocol. Full article
(This article belongs to the Special Issue Intelligent Computing and Sensing Systems for Sustainable Precision Agriculture)
►▼ Show Figures

Graphical abstract

33 pages, 4017 KB  
Article
Energy-Efficient Distributed Flexible Job Shop Scheduling with Machine Degradation and State-Driven Imperfect Preventive Maintenance
by Li Liu, Chenhao Gu and Kaifeng Geng
Computers 2026, 15(8), 522; https://doi.org/10.3390/computers15080522 - 12 Aug 2026
Viewed by 209
Abstract
This study addresses a distributed flexible job shop scheduling problem with machine degradation and state-driven imperfect preventive maintenance, denoted as MD-SDIPM-DFJSP. A bi-objective model is developed to minimize makespan and total energy consumption by jointly optimizing job assignment, operation sequencing, machine selection, and [...] Read more.
This study addresses a distributed flexible job shop scheduling problem with machine degradation and state-driven imperfect preventive maintenance, denoted as MD-SDIPM-DFJSP. A bi-objective model is developed to minimize makespan and total energy consumption by jointly optimizing job assignment, operation sequencing, machine selection, and processing speed. The model links processing speed with processing time, power consumption, and degradation increment, and uses a unified degradation bound to represent both degradation and reliability constraints. Preventive maintenance is treated as an imperfect recovery action and is generated according to machine states and idle-window conditions. To solve the problem, a degradation-aware multi-objective memetic algorithm (DMA) is proposed, incorporating four-layer encoding, state-driven decoding, hybrid initialization, knowledge-guided neighborhood search, and a speed-based adjustment operator. Numerical experiments show that Gurobi solved the small instance to optimality with a 0% optimality gap, and the resulting schedule satisfied the modeled production, maintenance, degradation, reliability, and energy accounting requirements. Across 84 combinations of instances and factory sizes, DMA achieved the highest HV in 72 cases and the lowest IGD in 62 cases. The Wilcoxon tests further confirmed its overall advantages over the three comparison algorithms in terms of both HV and IGD. Full article
►▼ Show Figures

Figure 1

13 pages, 3231 KB  
Article
Mosquito Swarm Algorithm-Based Energy Minimization in Wireless Sensor Networks
by Amal Aabdaoui and Najlae Idrissi
Computers 2026, 15(8), 521; https://doi.org/10.3390/computers15080521 - 12 Aug 2026
Viewed by 239
Abstract
Wireless sensor networks (WSNs) are sophisticated monitoring systems that gather environmental data via wireless sensors. Numerous wireless sensors that have been placed to monitor and gather data on a particular environment make up these networks. Typically, a base station or central node wirelessly [...] Read more.
Wireless sensor networks (WSNs) are sophisticated monitoring systems that gather environmental data via wireless sensors. Numerous wireless sensors that have been placed to monitor and gather data on a particular environment make up these networks. Typically, a base station or central node wirelessly collects the data prior to analysis. As the battery in wireless sensors is both non-replaceable and non-rechargeable, it represents a key element. As a result, optimizing energy consumption in WSN has become a growing concern. One of the key challenges is consequently the creation of effective protocols for communication in WSNs. In this article, we provide a novel MSA (Mosquito Swarm Algorithm) technique for cluster formation and data routing. Simulations indicate that our proposed algorithm conserves the energy of the nodes and keeps them running for a greater number of survival rounds compared to LEACH (Low-Energy Adaptive Clustering Hierarchy) by a difference of 70.14%, PSO-R (Particle Swarm Optimization with routing) by a difference of 4.76%, and BA-R (Bat Algorithm with routing) by a difference of 2.52%. Our algorithm provides the highest throughput, surpassing LEACH by approximately 6.38%, PSO-R by almost 1%, and BA-R by 12.67%. Simulations indicate that our algorithm is highly effective at extending network longevity and increasing throughput, making it the preferred option to lower energy consumption in WSNs. Full article
(This article belongs to the Special Issue Wireless Sensor Networks in IoT)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-83
Previous Issue
Next Issue
Back to TopTop