Search Results (81)

Diagnosing skin diseases remains a clinical challenge due to the visual similarity among diverse dermatological conditions. This study presents a prototype deep learning–powered system for multi-class dermatological screening, implemented through a cloud-based architecture and accessed via a smartphone interface. A pre-trained Convolutional Neural Network (CNN), EfficientNetV2B3, was fine-tuned on a composite dataset encompassing nine disease categories. The model achieved promising performance, with an accuracy of 0.87, precision of 0.87, recall of 0.87, and an F1 score of 0.86, indicating its potential reliability for automated classification. Prototype validation was conducted using a cloud API (Google Cloud Storage + PostMan) to verify the inference pipeline and user interaction. While the current implementation demonstrates the feasibility of cloud-based dermatological screening, real-device mobile performance metrics such as latency, model size, and memory consumption remain future work. Users can capture or upload skin images, which are processed to generate preliminary diagnostic feedback, including symptom descriptions and general treatment information. While not intended to replace professional medical evaluation, the prototype serves as a proof-of-concept tool for initial screening and early intervention. This work illustrates how artificial intelligence (AI) can be harnessed in mobile health applications to expand access to dermatological care and supports broader initiatives to integrate AI into healthcare delivery. Full article

This work develops an effective platform to enhance the data collection process for researchers. The proposed platform connects researchers who need specific datasets with data curators, employing blockchain and artificial intelligence (AI) techniques. This system includes individual researcher and worker dashboards, an AI-integrated validation process, and a blockchain-based automatic payment mechanism. The AI-driven verification system evaluates the quality and correctness of a sample fraction of the collected data to ensure reliability before approving the full dataset. Payment transactions are handled using blockchain technology, which provides a transparent, secure, and tamper-resistant system. Workers are paid based on verified accuracy, and funds are transferred directly to MetaMask wallets on the blockchain. The prototype demonstrates how AI-based data validation and blockchain-based payments can be combined to support a more trustworthy and automated data collection process. This unique concept provides workers with an efficient and secure way to get paid while ensuring high-quality research data. Experimental results show that the proposed platform achieved validation accuracies of 94.5% and 95.8% with 10% and 20% sampling, respectively, during AI-based dataset verification. The Sepolia blockchain transaction was completed in approximately 12 s, with a transaction fee of 0.00042 ETH for transferring 0.001 ETH. The system handled 1000 users without lag and achieved an 88% satisfaction rate based on survey responses. Full article

This paper proposes a federated learning framework for privacy-preserving patient monitoring with lightweight blockchain anchoring. The framework keeps synthetic patient monitoring records local at each client and uses federated model aggregation to support collaborative learning without centralizing raw records. To improve traceability, the blockchain layer is specified as an anchoring mechanism that records compact evidence, including model hashes and participation metadata, rather than raw data or full model parameters. Experiments were conducted on synthetic patient monitoring data to evaluate framework behavior under non-IID client distributions, label noise, different client counts, partial client participation, and aggregation strategies. The centralized MLP baseline achieved approximately 0.89 overall accuracy but failed to detect alert cases, with 0% alert-class recall, showing that accuracy alone can be misleading in imbalanced monitoring scenarios. In the federated simulations, the model reached approximately 0.99 accuracy under clean labels, approximately 0.90 under 10% label noise, and approximately 0.70 under 30% label noise. Under a more difficult noisy, non-IID, dropout, and fixed skewed-client evaluation setting, the model stabilized at approximately 0.80 accuracy after 25 communication rounds. Client scaling from 5 to 20 clients remained stable, and FedAvg, weighted aggregation, and accuracy-trimmed robust aggregation produced similar final accuracy of approximately 0.98 in the 10-client setting. The results indicate that label quality strongly affects federated convergence, while blockchain anchoring should be interpreted as an auditability mechanism rather than a direct accuracy-improving component. This study provides a framework-level foundation for auditable federated patient monitoring in semi-trusted healthcare networks. Full article

With the development of quantum computing, classical cryptosystems (RSA, ECDSA) that ensure the security of distributed ledgers face an existential threat. This paper examines protocols for protecting personal data (PD) in blockchain, taking into account the “Harvest Now, Decrypt Later” strategy. We propose and formalize a family of protocols designed for storing and exchanging personal data in blockchain systems. The article describes in detail approaches to software implementations of smart contracts for the Ethereum (using ECIES (Elliptic Curve Integrated Encryption Scheme) and Keccak-256) and Hyperledger Fabric 2.5 (integrating NIST post-quantum standards: ML-KEM (Module-Lattice-Based Key Encapsulation Mechanism) and ML-DSA (Module-Lattice-Based Digital Signature Algorithm)) platforms based on the developed protocols. For all developed protocols, a Threat Agent Model (TAM) is presented, threat scenarios are examined, and resilience to typical attack scenarios is demonstrated. A comparative analysis of computational efficiency and overhead is conducted. The results show that using lattice cryptography provides high performance, but the 50-fold increase in signature size makes direct implementation of PQC (Post-Quantum Cryptography) in Layer 1 public networks economically unfeasible. A hybrid model and the use of Layer 2 to ensure quantum resistance are proposed. Full article

Smart-home environments require secure and reliable user authentication mechanisms to prevent unauthorized access and spoofing attacks. Traditional password- and PIN-based methods remain vulnerable to theft, replay attacks, and credential compromise. To address these challenges, this study proposes an intelligent voice-based authentication and anomaly detection framework for secure smart-home environments. The framework utilizes benchmark ASVspoof 2019 and ASVspoof 2021 datasets containing bona fide and spoofed speech samples. After preprocessing, discriminative acoustic features, including Mel-Frequency Cepstral Coefficients (MFCC) and Constant-Q Cepstral Coefficients (CQCC), are extracted and provided to a Hybrid CNN-LSTM model for speaker verification. An integrated anomaly detection module further enhances security by identifying replay, spoofing, and synthetic speech attacks. Access is granted only when the input voice is authenticated and classified as non-anomalous. Experimental results demonstrate the effectiveness of the proposed framework, achieving an overall accuracy of 97.2% and a macro-AUC of 0.972. The model also achieves low Equal Error Rates of 3.8%, 2.9%, and 2.1% across the evaluated classes, indicating robust spoof detection and anomaly generalization capabilities. These results highlight the suitability of the proposed framework for secure and intelligent smart-home access control applications. Full article

Agent-based neural models often encode transmission within neuron state updates, which can make it difficult to separately log and quantify spatial recruitment patterns, delay structure, and environment-mediated feedback effects. We present LANA (Local Adaptive Neural Agents), a dual-agent neural agent-based model in which neurons and propagating signals are represented as distinct interacting entities embedded in a dynamic environmental field. The model combines discrete leaky integrate-and-fire neuron dynamics, mobile signal agents, synaptic links with distance-dependent delays, and a bounded environment-to-neuron feedback mechanism. LANA is intended as a normalized phenomenological mesoscopic framework for mechanism-level comparison rather than as a circuit-specific biophysical reconstruction. To support interpretability and reproducibility, we report a compact internal verification block for the implemented operators, including delay propagation, environmental decay and diffusion, threshold activation, and refractory enforcement. We then compare the full LANA model against a matched neuron-only baseline and summarize spatial recruitment using first-spike maps, cumulative recruitment times, and wavefront speed as a secondary descriptive metric. Finally, we evaluate two controlled operating regimes, a resting regime (S1) and a hyperexcitable regime (S2), under fixed network size, stimulation schedule, and matched random seeds. Relative to the baseline, the full model sustains and spreads activity more effectively and provides spatially resolved recruitment summaries, including first-spike timing and cumulative recruitment measures, that are not available in the same form when transmission is represented only through neuron-level updates. Relative to S1, S2 exhibits earlier activation, higher firing activity, stronger environmental accumulation, and faster cumulative recruitment. Local and factorial sensitivity analyses further identify the parameters that most strongly govern these regime differences. Together, these results position LANA as a normalized mesoscopic and computationally tractable framework for studying how excitability, transport state dynamics, delayed coupling, and environment-mediated feedback jointly shape emergent activity in controlled simulation settings. Full article

Maritime accident analysis increasingly uses machine learning to support safety management, but many existing studies focus on single-output prediction, such as accident-occurrence probability, severity class, near-miss frequency, or one specific consequence. This study proposes a data-driven decision-support framework based on a Multi-Input Multi-Output Artificial Neural Network (MIMO-ANN) for the simultaneous prediction of multiple maritime accident consequences. A dataset of 582 recorded accident cases is constructed by integrating SafePASS project records with consequence, severity, and structural-damage information from the literature. The dataset includes 15 input variables covering ship characteristics, operational context, environmental conditions, accident type, and geographical zone and 15 consequence outputs covering structural damage, casualties, emergency-response indicators, total loss, and secondary consequence/escalation mechanisms. The ANN is trained using the Scaled Conjugate Gradient (SCG) algorithm and evaluated under different network configurations and data-partitioning strategies. The best-performing model uses 30 hidden neurons with a 60/20/20 split, achieving a correlation coefficient (R) equal to 0.9249 and a mean squared error (MSE) equal to 0.0240 for testing, and a R equal to 0.9278 and a MSE equal to 0.0231 for validation. Ten-fold cross-validation further confirms internal predictive stability, with mean testing R equal to 0.8803 ± 0.0827 and MSE equal to 0.0445 ± 0.0478. Permutation-based sensitivity analysis shows that accident type, zone, flag, natural light, environment, and visibility are key drivers of predicted consequences, whereas vessel-specific parameters have a secondary, context-dependent influence. The framework should be interpreted as predicting the relative likelihood, severity, or magnitude of accident consequences in recorded or scenario-defined accident cases, not the probability of accident occurrence. Future work should address dataset imbalance, include near-miss and nonserious records, incorporate richer AIS and metocean data, integrate exposure data, and validate the framework using independent accident datasets. Full article

Imaging of the lungs is traditionally based on chest X-ray as a first-line imaging method for lung aeration assessment. However, radiation exposure limits its use for patients in the pediatric intensive care unit. Lung ultrasonography (LUS) is a suitable alternative, but its interpretation is highly observer-dependent and requires sufficient experience and skill. We sought to develop a model based on deep learning to assist the clinician in the interpretation of LUS observations. In this retrospective, single-center, proof-of-concept study, all patients, age 0–18 years old admitted at the PICU of the Leiden University Medical Center (LUMC) between January and May 2022 who underwent an LUS were included. LUS video frames were analyzed using a deep learning tool; a conditional generative adversarial network (cGAN) was developed to generate segmentation masks containing clinical features from individual LUS frames. A total of 31 patients, with a median age of 2.5 months (IQR 0–11 months), were analyzed. A total of 98 LUS assessments and 506 4-s videos were collected. The median LUS score was 12 (IQR 8–17). The two best-performing frame-based segmentation models achieved mean Dice similarity coefficients of 0.97 ± 0.03 and 0.96 ± 0.03, with mean squared errors of 0.025 ± 0.025 and 0.030 ± 0.026, respectively. These findings demonstrate that a pediatric-specific cGAN can segment key LUS features from individual frames. However, the results derive from a small, single-center cohort with a frame-level rather than patient-level data split, and no formal clinical validation; independent, prospectively collected validation cohorts are required before any clinical implementation. Full article

Computational research is becoming increasingly dependent on code, data, workflows, software environments and model configurations that must be preserved and understood before findings can be reproduced. The FAIR Guiding Principles have significantly improved data stewardship, but they do not by themselves provide an executable, explainable and evidence-linked mechanism for verifying computational claims. This article presents eFAIR-X, an implementation-oriented and AI-enabled extension of FAIR for interdisciplinary computational reproducibility. The framework connects publications, claims, datasets, code, workflows, environments and verification evidence through a semantic research knowledge graph. It also defines a Dashboard for Reproducibility (DfR) that reports bounded, auditable and calibratable indicators for artefact availability, metadata completeness, workflow executability, output agreement, contribution-evidence coverage, relevance longevity and originality risk. In response to the need for stronger technical precision, the model separates three issues that are often combined: FAIR principle extension, FAIR assessment and operational reproducibility verification. A browser-based proof-of-concept prototype has now been implemented and exercised using structured JSON study files to demonstrate the dashboard, knowledge-graph view, evidence table, claim-evidence mapping and validation panel. The proposed metrics are explicitly treated as provisional operational indicators that require calibration through benchmark experiments, expert agreement analysis, case-based evaluation and sensitivity testing before they can be used as decision-support evidence. The paper further specifies local and global explainability mechanisms, human contestability, knowledge-graph node and edge semantics, metadata requirements and dashboard evidence drill-downs. eFAIR-Xis therefore positioned not as a replacement for FAIR, FAIR4RS or FAIRification frameworks, but as a complementary verification-centred infrastructure for making computational reproducibility more measurable, inspectable and actionable. Full article

Artificial intelligence (AI) has become a central driver of transformation in innovation management, reshaping how organizations design strategies, develop offerings, and generate knowledge. This study examines how innovation management has evolved from the pre-ChatGPT era—characterized by analytics, automation, and decision support—to the post-ChatGPT period, marked by the widespread adoption of generative AI (GenAI) and human–AI collaboration. Using a structured literature review of Scopus-indexed studies published between 2020 and 2025, the paper identifies the following six dominant thematic dimensions of AI-enabled innovation management: strategic and business model innovation, product and service innovation, sustainability-oriented innovation, organizational agility and capabilities, human-centric innovation, and knowledge, learning, and research. The findings reveal a conceptual shift from efficiency-driven applications toward more creative, strategic, and collaborative uses of AI, with generative models acting as co-creators rather than mere analytical tools. The study contributes by synthesizing the fragmented literature into an integrative framework that captures this transition and by highlighting emerging research gaps, particularly in sustainability and human-centered innovation. Practical implications for managers and policymakers are discussed. Full article

Autonomy and trust are central concepts in sociology and psychology and are particularly relevant to the study of hybrid societies in which human and artificial agents interact. Trust is essential for effective collaboration across a wide range of contexts, and the benefits of interacting with autonomous agents for facilitating goal achievement are well established. However, the complex interplay between trust and autonomy remains insufficiently understood, especially in sensitive domains such as healthcare, where ethical values, patient safety, and inter-agent dependencies must be carefully managed. In this work, we employ a multi-agent simulation to investigate the roles of autonomy and trust in relation to patient satisfaction. Our results show that higher levels of autonomy—enabling agents to modify delegations and exploit dependencies—effectively support implicit goal discovery and can enhance explicit goal achievement. Nevertheless, such autonomy may be detrimental compared to lower levels of autonomy that only allow dependency exploitation. This effect is particularly evident in contexts with large pools of partners who lack sufficient competence but are willing to accept multiple concurrent delegations. Conversely, in environments characterized by heterogeneous trustworthiness, higher autonomy proves advantageous, as it enables agents to more effectively discover and leverage dependencies. Full article

This article proposes a mathematical model for quantitatively assessing the cyber resilience of modern blockchain platforms. Constructing the mathematical model, the authors proposed representing the architecture of a blockchain-based information system as four layers: the cryptographic algorithm layer, the blockchain core layer, the smart contract layer, and the decentralized application layer. A study of typical vulnerabilities was conducted for each layer, and a list of countermeasures to counter potential threats was proposed. Then, key elements and their impact on the system’s cyber resilience were identified. As a result, a mathematical model for assessing the cyber resilience of blockchain platforms was developed. Based on the analysis of the model, it was experimentally demonstrated that a cyber attack carried out at a lower layer affects all higher layers of the blockchain platform, and cyber resilience at the current layer can only be effectively ensured if it is ensured at the previous layer. Full article

This paper explores how semantic-space reasoning, traditionally used in computational linguistics, can be extended to tactical decision-making in team sports. Building on the analogy between texts and teams—where players act as words and collective play conveys meaning—the proposed methodology models tactical configurations as compositional semantic structures. Each player is represented as a multidimensional vector integrating technical, physical, and psychological attributes; team profiles are aggregated through contextual weighting into a higher-level semantic representation. Within this shared vector space, tactical templates such as high press, counterattack, or possession build-up are encoded analogously to linguistic concepts. Their alignment with team profiles is evaluated using vector-distance metrics, enabling the computation of tactical “fit” and opponent-exploitation potential. A Python-based prototype demonstrates how these methods can generate interpretable, dynamically adaptive strategy recommendations, accompanied by fine-grained diagnostic insights at the attribute level. Evaluation through synthetic scenarios and a pilot study with real match data establishes internal consistency and feasibility of the approach; operational validity in live coaching contexts remains an open question for future prospective validation. Beyond football, the framework offers a potentially generalizable approach for collective decision-making in team-based domains—ranging from basketball and hockey to cooperative robotics and human–AI coordination systems. The paper concludes by outlining future directions toward real-world data integration, predictive simulation, and the validation work required before operational deployment. Full article

This study investigats both emerging and existing ethical issues associated with the adoption of artificial intelligence (AI) in Africa, a region characterised by unique socio-economic and cultural complexities. Even though AI adoption is rapidly transforming and delivering substantial benefits in sectors such as healthcare, finance, agriculture, education, industry, and governance, its implementation still raises ethical concerns. These ethical issues include digital colonialism, algorithmic bias, job displacement, limited infrastructure, data scarcity, linguistic diversity, and the risk of imposing foreign values that may undermine indigenous knowledge and social cohesion. Grounded in Afro-communitarianism and stakeholder theory, which emphasises communal values such as Ubuntu and cooperative engagement among stakeholders, this desk-based research identifies these major challenges and introduces a culturally grounded framework for responsible AI adoption in Africa. The framework calls for stronger governance, capacity building, collaboration among stakeholders, and tailored strategies across multiple stakeholders to ensure AI supports Africa’s inclusive and sustainable progress. Full article

The transition to sustainable energy systems requires the development of efficient hydrokinetic technologies to increase the reliability and competitiveness of renewable energy generation. Vertical-axis H-Darrieus turbines can improve their performance through impeller channels or external flow guidance devices that modify the local mass flow distribution around the rotor. This work introduces a systematic geometric optimization framework that quantitatively evaluates the combined effect of key channel design parameters on turbine performance by employing response surface methodology (RSM) to quantify the influence of two geometric parameters of an impeller channel—specifically, the deflection angle ($\beta$) and the channel length (H)—on the turbine power coefficient ($C_p$). This approach allows for the identification of nonlinear interactions between geometric variables, which have not been explicitly addressed in previous research on impeller channels in H-Darrieus turbines. An experimental design with thirteen treatments was implemented, and numerical simulations were performed using Computational Fluid Dynamics (CFD) in ANSYS FLUENT^®. Statistical analysis of the RSM model showed that both $\beta$ and H have significant effects ($p<0.05$) on turbine performance. The model predicted an optimal configuration with $\beta$ equal to 100° and H equal to 0.2 m, corresponding to the maximum Cp achieved. These findings confirm the potential of impulse channels to improve the aerodynamic efficiency of H-Darrieus turbines and establish a quantitative basis for design optimization in hydrokinetic applications. Full article