-
11061
Enhancing Wind Turbine Power Output Estimation Using Causal Inference and Adaptive Neuro-Fuzzy Inference System ANFIS
Published 2025-04-01“…To meet the demand for renewable energy at the lowest cost, wind energy became the target of machine learning algorithms and was employed to predict the output power of wind turbines. …”
Get full text
Article -
11062
The Hydrodynamic Performance of a Vertical-Axis Hydro Turbine with an Airfoil Designed Based on the Outline of a Sailfish
Published 2025-06-01“…Through Latin hypercube experimental design combined with optimization algorithms, four key geometric variables governing the airfoil’s hydrodynamic characteristics were systematically analyzed. …”
Get full text
Article -
11063
DEVELOPMENT OF METHODOLOGY FOR DESIGNING TESTABLE COMPONENT STRUCTURE OF DISCIPLINARY COMPETENCE
Published 2015-03-01“…The research findings can help promoting learning efficiency increase, a choice of adequate control devices, accuracy of assessment, and also efficient use of personnel, temporal and material resources of higher education institutions. Proposed algorithms, methods and approaches to procedure of control results organization and realization of developed competences and its components can be used as methodical base while designing the computerassisted system for educational process management and quality supervision of graduates’ competences. …”
Get full text
Article -
11064
Infrared Small Target Detection Based on Double Gray-Values Descend Angle Contrast Measure
Published 2025-01-01“…Experimental evaluations were conducted on four publicly available datasets, comparing our proposed approach with seven existing algorithms. The results demonstrate that our method facilitates rapid detection of small targets affected by salt noise within complex backgrounds while exhibiting exceptional detection capabilities and real-time performance. …”
Get full text
Article -
11065
Deep Learning Network Selection and Optimized Information Fusion for Enhanced COVID-19 Detection: A Literature Review
Published 2025-07-01“…Recent developments in COVID-19 diagnosis involve constructing expansive multi-noise information sets while creating clinical process-oriented AI algorithms and implementing distributed learning protocols for securing information security and system stability. …”
Get full text
Article -
11066
A Comparative Study of Data-Driven Prognostic Approaches under Training Data Deficiency
Published 2024-09-01“…In industrial system health management, prognostics play a crucial role in ensuring safety and enhancing system availability. While the data-driven approach is the most common for this purpose, they often face challenges due to insufficient training data. …”
Get full text
Article -
11067
Solar radiation prediction: A multi-model machine learning and deep learning approach
Published 2025-05-01“…This study demonstrates that RNN excels in short-term predictions, while GBR is more effective for long-term forecasts. …”
Get full text
Article -
11068
Precise application of water and fertilizer to crops: challenges and opportunities
Published 2024-12-01“…Precision water and fertilizer application technologies have emerged as crucial innovations in sustainable agriculture, addressing the pressing need to enhance crop yield and quality while optimizing resource use and minimizing environmental impacts. …”
Get full text
Article -
11069
Multi-model machine learning framework for lung cancer risk prediction: A comparative analysis of nine classifiers with hybrid and ensemble approaches using behavioral and hematolo...
Published 2025-08-01“…Performance measures (accuracy, sensitivity, specificity, F1-score, AUC) identify quantitative differences: GB had the best F1-scores (0.953) and NB had the second-best F1-score (0.945), while GB had the best sensitivity (99.1 %). The KNN-AB hybrid model reported the highest accuracy with 99.5 %, while RF reported the highest AUC with a value of 0.92. …”
Get full text
Article -
11070
Development of time to event prediction models using federated learning
Published 2025-05-01“…However, performing centralized pooling of multiple data sources, while protecting each patients’ sensitive data, can require a cumbersome process involving many institutional bodies. …”
Get full text
Article -
11071
Fraud Detection in Privacy Preserving Health Insurance System Using Blockchain Technology
Published 2025-08-01“…Privacy is preserved using cryptographic techniques such as secure hashing and anonymous credentials, which ensure that sensitive patient information remains confidential throughout the claim process. Smart contract algorithms are utilized in two scenarios: patient‐submitted claims and healthcare provider‐submitted claims, ensuring accurate processing and validation while detecting fraudulent activities such as duplicate claims, inflated medical bills, billing for unprovided services, falsifying patient records, and submitting claims for nonexistent treatments. …”
Get full text
Article -
11072
A secure medical image encryption technique based on DNA cryptography with elliptic curves
Published 2025-06-01“…With progress in imaging technologies and biomedical processing algorithms, the amount of image data increases rapidly. …”
Get full text
Article -
11073
Enhancing Privacy in IoT-Enabled Digital Infrastructure: Evaluating Federated Learning for Intrusion and Fraud Detection
Published 2025-05-01“…To address these issues, federated learning (FL) using a flower framework is utilized to protect the privacy of individual organizations while still collaborating through separate models to create a unified global model. …”
Get full text
Article -
11074
Exploring happiness factors with explainable ensemble learning in a global pandemic.
Published 2025-01-01“…The greatest happiness principle posits that morality is determined by pleasure, aiming for a society where individuals are content and free from suffering. While happiness factors vary, some are universally recognized. …”
Get full text
Article -
11075
Redefining customer connections in the UAE’s digital era: A study on emerging technological synergies
Published 2025-06-01“…Ethical concerns, including data privacy and algorithmic bias, received a mean score of 3.75, while sustainability challenges, such as e-waste and energy consumption, scored the lowest (mean = 3.20, SD = 0.85). …”
Get full text
Article -
11076
Proactive Data Placement in Heterogeneous Storage Systems via Predictive Multi-Objective Reinforcement Learning
Published 2025-01-01“…The system incorporates a sophisticated reward mechanism that balances performance gains against migration overhead, while employing prioritized experience replay and adaptive learning rates to handle non-stationary workload characteristics. …”
Get full text
Article -
11077
Modality-based Modeling with Data Balancing and Dimensionality Reduction for Early Stunting Detection
Published 2025-04-01“…Unimodal modeling uses tabular or image data alone, while multimodal modeling combines both before classification. …”
Get full text
Article -
11078
A novel Hadamard matrix based hybrid compressive sensing technique for enhancing energy efficiency and network longevity
Published 2025-02-01“…The simulation results also reveal that the proposed strategy can reduce energy costs while ensuring reliable performance. Furthermore, the strategy can be easily implemented with existing hardware, making it a viable option for WSNs.…”
Get full text
Article -
11079
Dynamic Monitoring and Precision Fertilization Decision System for Agricultural Soil Nutrients Using UAV Remote Sensing and GIS
Published 2025-07-01“…Real-time data processing algorithms enable rapid updates of soil nutrient status, while a time-series dynamic model captures seasonal variations and crop growth stage influences, improving prediction accuracy (RMSE reductions of 43–70% for nitrogen, phosphorus, and potassium compared to conventional laboratory-based methods and satellite NDVI approaches). …”
Get full text
Article -
11080
FLIP: A Novel Feedback Learning-Based Intelligent Plugin Towards Accuracy Enhancement of Chinese OCR
Published 2025-07-01“…The plugin’s modular design enables seamless integration without requiring modifications to existing OCR algorithms, while its feedback mechanism adapts to domain-specific terminology and user preferences. …”
Get full text
Article