Search Results (20,090)

This study investigates the methodologies for robust parameter estimation within the context of the parameters of the inverted Kumaraswamy model using data derived from step-stress partially accelerated life testing with Type-I generalized hybrid censoring. We formulate estimation procedures within both frequentist (maximum likelihood) and Bayesian frameworks, including the construction of asymptotic and credible intervals. Subsequently, we provide a formal derivation of the associated asymptotic and bootstrap confidence intervals. To address the analytical intractability of the Bayesian estimation, we employ Markov Chain Monte Carlo techniques. The proposed methods are illustrated through an illustrative example, an application to real-world precipitation data, and a simulation study. Full article

Parkinson’s disease (PD) is a progressive neurodegenerative disorder in which early detection remains a major clinical challenge due to heterogeneous motor and non-motor manifestations and the lack of reliable biomarkers. In recent years, machine learning (ML) and deep learning (DL) methods have been increasingly investigated as decision-support tools for PD screening using diverse clinical and behavioral data. This review synthesizes PD detection studies published between 2017 and 2025, systematically analyzing 32 representative works across multiple modalities, including MRI, PET, EEG, REM sleep biomarkers, voice recordings, gait signals, handwriting/drawing tasks, and finger-tapping measurements. Across the reviewed literature, high classification performance is frequently reported, with CNN-based and hybrid DL architectures achieving particularly strong results in imaging and time-series settings, while classical ML approaches such as SVM and ensemble models remain competitive for engineered feature-based datasets. However, the review also reveals major barriers to reliable translation, including small datasets, inconsistent evaluation protocols, limited external validation, and the risk of performance inflation caused by non-subject-independent data splitting. Overall, this review provides a structured and modality-oriented reference of algorithms, datasets, and performance trends, while highlighting key methodological gaps and practical priorities for developing robust and clinically deployable PD detection systems. Full article

Flood change detection from remote sensing data can be used to identify post-disaster flooded areas, providing decision support for emergency rescue and post-disaster reconstruction. Although the combination of SAR and optical images effectively addresses obscuration by clouds and rain, the inherent difference in their imaging mechanisms poses a challenge to improving the accuracy of flood area change detection. Furthermore, existing flood inundation change detection methods based on heterogeneous remote sensing imagery struggle to distinguish small ground objects within the background from the actual inundated regions. Therefore, a pseudo-Siamese hybrid dilation spiral feature network (PSiam-HDSFNet) is proposed in this paper. Firstly, the feature extraction pipeline progressively processes optical and SAR images through five-layer Enhanced Deep Residual Blocks and five-layer Residual Dense Blocks, respectively. A Hybrid Dilated Pyramid (HDP) module based on a sawtooth wave-like dilated coefficient is designed to enhance multi-scale semantics of deep features in order to selectively reinforce semantic features in flood areas and weaken the noise semantics from small ground objects. Then, a Spiral Feature Pyramid (SFP) module is designed to make the deep features of SAR and optical images more consistent in spatial structure and numerical distribution patterns, so that the features of flood areas become more prominent while the noise semantics from small ground objects are further suppressed. After that, the Galerkin-type attention with linear complexity is introduced to the decoder, rapidly reconstructing the abstract semantic information of floods into interpretable flood features. Finally, the Align OPT-SAR (AlignOS) method is designed to align SAR and optical image features, enabling subsequent flood area detection. Seven metrics are adopted in the comparison between PSiam-HDSFNet and the other 14 methods. The results indicate that PSiam-HDSFNet improves change detection accuracy by extracting and processing depth features of these two images without image domain translation, and its F1 scores are improved by 7.704%, 7.664%, 4.353%, and 1.111% in the four flood coverage categories detection tasks compared to the suboptimum. Full article

Background/Objectives: Cancer remains one of the most significant challenges in modern medicine, requiring the continuous development of novel molecular scaffolds with anticancer potential that act through multiple pathways. Heterocyclic compounds incorporating indole, triazole, oxadiazole, and thiadiazine motifs have attracted considerable attention due to their diverse pharmacological activities. This study aimed to design, synthesize, and evaluate new hybrid heterocyclic systems, including 1,2,4-triazole, 1,3,4-oxadiazole, and thiadiazine motifs, targeting liver and breast cancer. Methods: A series of indolyl-based heterocyclic compounds was synthesized using efficient and environmentally friendly protocols. Indolyl-triazol-thiadiazin-6-ol 5 was prepared via solvent-free fusion of esters 2 and 3 or the corresponding acid 4. Oxadiazole derivatives were produced by reacting hydrazide intermediates with carbon disulfide. Triazole derivatives were synthesized via cylization of thiosemicarbazide 9 in aqueous KOH (4.0 N). Structural characterization was performed using Fourier Transform InfraRed (FTIR), ¹H and ¹³C NMR spectroscopy, and electron impact mass spectrometry (EIMS). Cytotoxic activity was evaluated against liver and breast cancer cell lines, and VEGFR-2 kinase inhibition was assessed for selected derivatives. Results: The synthesized compounds demonstrated notable cytotoxicity activity, with compounds 4, 5, and 9 exhibiting IC₅₀ values in the low micromolar range. Enzymatic assays revealed that compounds 4 and 9 showed strong VEGFR-2 inhibition (97.9% and 96.4%, respectively), indicating apoptosis-inducing effects. Conclusions: The synthesized indolyl-based hybrid heterocycles represent a promising chemotype with in vitro cytotoxic activity and VEGFR-2 inhibitory effects, supporting further investigation, optimization, and mechanistic studies to evaluate their potential lead for anticancer drug development. Full article

Background/Objectives: This study assesses the cost-effectiveness of integrating artificial intelligence (AI) into breast cancer screening programs in Singapore. It evaluates AI as a standalone reader and as a companion reader alongside a consultant radiologist and compares these with double reading by two radiologists to determine economic viability and impact on healthcare resource use. Methods: A Markov model compared costs and outcomes of three strategies: double reading, a hybrid AI-assisted model (radiologist plus AI), and AI-only. These were applied to biennial mammography for 10,000 women aged 50–69 years in Singapore, with a 50-year horizon. Epidemiological and cost data were sourced from Asian and local studies and standardized to 2023 values, with a 3% annual discount. Outcomes were incremental cost-effectiveness ratios (ICERs) per quality-adjusted life-year (QALY). Deterministic and probabilistic sensitivity analyses assessed uncertainty. Results: Double reading cost USD 19.18 million with 218,460.4 QALYs. The AI-companion model cost USD 18.86 million with 218,476.3 QALYs, saving USD 316,090 and gaining 15.9 QALYs. The AI-only model cost USD 20.53 million with 218,532.4 QALYs, yielding 72.0 QALYs gained and an ICER of USD 18,743 per QALY. Specificity was the most influential parameter. At a willingness-to-pay threshold of USD 50,000 per QALY, AI-only screening had >75% probability of being most cost-effective. Conclusions: AI-assisted screening was cost-saving, while AI-only was cost-effective with greater health gains but higher costs and false positives. A phased, human-in-the-loop approach offers the most economically favourable strategy for AI integration. Full article

Background: Occult lymph node metastasis (OLNM) and depth of invasion (DOI) are key determinants of elective neck dissection in clinically node-negative oral tongue squamous cell carcinoma (OTSCC), yet accurate preoperative risk stratification remains challenging. This study evaluated the diagnostic performance of artificial intelligence (AI)-based predictive models for OLNM and DOI in OTSCC. Methods: A systematic review and meta-analysis were conducted in accordance with PRISMA 2020 guidelines. A structured search of PubMed identified twelve eligible studies, nine of which provided extractable 2 × 2 contingency data for inclusion in the primary bivariate meta-analysis. One additional study modeling DOI-derived pT stage was synthesized narratively. Pooled sensitivity and specificity were estimated using a bivariate random-effects model. Heterogeneity, threshold effects, and publication bias (Deeks’ test) were assessed. Methodological quality was evaluated using QUADAS-2 supplemented by an AI-specific methodological appraisal. Results: Across nine studies included in the primary meta-analysis, pooled sensitivity was 0.679 (95% CI: 0.604–0.745) and pooled specificity was 0.762 (95% CI: 0.705–0.811), with a summary AUC of 0.786. Heterogeneity was moderate for sensitivity (I² = 41.8%) and low for specificity (I² = 23.4%), with no significant threshold effect (ρ = −0.117, p = 0.776). No significant publication bias was detected (p = 0.596). Subgroup analyses showed comparable performance between OLNM-specific and general LNM models, whereas deep learning or hybrid approaches demonstrated higher accuracy than traditional machine learning methods. Notably, only one out of nine primary studies incorporated true external validation. Conclusions: AI-based models demonstrate moderate discriminative performance for predicting LNM and DOI in OTSCC and may serve as adjunctive tools in preoperative risk stratification rather than standalone decision-makers. However, the near absence of external validation, limited calibration reporting, and lack of clinician-comparator analyses substantially constrain current clinical translation. Future research should prioritize multi-center prospective validation, systematic calibration and decision-curve analyses, and adherence to TRIPOD-AI and CLAIM reporting standards. Full article

Adaptive Neuro-Fuzzy Inference System (ANFIS)-based inverse kinematics (IK) is highly accurate for trained poses but often yields approximations for unseen inputs due to non-standardized training data. This research addresses these limitations through two novel contributions designed for any generic Degrees of Freedom (DoF) serial revolute robotic arm. First, A structured training methodology is introduced using workspace decomposition and cubic path planning. Instead of random sampling, the workspace is partitioned into cubic regions where 28 unique trajectories (12 edges, 12 face diagonals, four space diagonals) connect the eight vertices using cubic polynomial interpolation. This ensures physically consistent data mirroring real world point to point (PTP) movements. Even though validated on an ABB IRB-1200 robotic arm, this modular design is inherently scalable, allowing the local cubic expertise to be extended to cover the entire reachable workspace. Second, a two-stage hybrid IK framework is proposed, where an initial ANFIS approximation is refined via Jacobian-based iterative methods. Three Hybrid Frame works were evaluated, Framework-1 (ANFIS + Jacobian Gradient), Framework-2 (ANFIS + Jacobian Pseudoinverse/Newton–Raphson), and Framework-3 (ANFIS + Damped Least Squares). The results show that all three hybrid IK frameworks achieve reliable convergence, while the DLS-based hybrid provides the best trade-off between accuracy, convergence speed, and numerical stability. This generic, analytical free architecture provides a computationally efficient solution even in a hybrid scenario, bridging the gap between offline structured training and online, real-time refinement for digital twin synchronization and industrial automation. Full article

Background/Objectives: Fundus imaging provides a detailed view of the interior surface of the eye and plays a crucial role in the early diagnosis of retinal diseases. However, automated interpretation of fundus images remains challenging due to variations in illumination, noise, and structural complexity. Methods: A novel hybrid model that integrates the Intrinsic Mode Function (IMF) filter, derived from Empirical Mode Decomposition (EMD), with a Light Convolutional Neural Network (LightCNN) for enhanced fundus image classification was proposed. The IMF filter effectively decomposes the input signal into intrinsic components, isolating high-frequency noise and preserving critical retinal patterns. These refined components are subsequently processed by the LightCNN architecture, which offers lightweight yet highly discriminative feature extraction and classification capabilities. Results: Experimental results on DIARETDB fundus datasets demonstrate that the proposed IMF + LightCNN model achieves 99.4% accuracy, 99.1% precision, 98.87% recall, and a 98.31 F1-score, significantly outperforming conventional CNN and ResNet-based models. Conclusions: Integrating advanced signal processing with lightweight deep learning improves both diagnostic accuracy and computational efficiency. This hybrid framework establishes a promising pathway for reliable and real-time clinical screening of retinal diseases. Full article

Machine learning (ML) is increasingly influencing the assessment and delivery of movement and exercise, yet its role within adapted physical activity (APA) for individuals with chronic conditions has not been comprehensively synthesized. ML-based approaches have the potential to enhance functional assessment, support individualized exercise prescription, and facilitate scalable monitoring across preventive, community-based, and long-term adapted exercise settings, particularly in populations characterized by functional heterogeneity and variable responses to exercise. The aim of this narrative review is to synthesize and critically discuss current ML applications relevant to the core professional processes of APA practice. A structured narrative review was conducted using searches in PubMed/MEDLINE, Scopus, and Web of Science, complemented by targeted searches in engineering-oriented sources to capture ML methods not consistently indexed in biomedical databases. The search covered the period in which contemporary ML approaches have been increasingly applied to human movement and exercise research and was last updated in January 2026. Evidence was synthesized thematically into application-oriented domains relevant to APA practice. ML applications in APA include markerless motion and gait analysis, wearable-sensor data processing, balance and fall-risk assessment, and functional classification. Predictive and adaptive models support individualized regulation of exercise intensity, progression, and workload, including remote and hybrid delivery models. Applications span oncology, cardiometabolic, respiratory, neuromuscular conditions, and adapted sport contexts. Ethical, legal, and governance issues, such as algorithmic bias, data privacy, and professional accountability, emerge as central considerations for safe and equitable implementation. ML represents a promising decision-support layer for APA, complementing professional expertise through enhanced assessment, personalization, and monitoring. Its effective integration requires robust validation, interpretability, and responsible governance to ensure that ML augments, rather than replaces, professional judgment in APA practice. Full article

The transition towards high-renewable power systems introduces high-dimensional nonlinearity and uncertainty, rendering traditional offline look-up table schemes prone to control mismatch against “unseen” contingencies. Meanwhile, existing response-driven approaches face a dilemma between the computational latency of physics-based optimization and the safety risks of end-to-end AI. To bridge this gap, this paper proposes a Response-Driven Optimal Emergency Control Framework that ensures both millisecond-level speed and rigorous physical constraints. First, a deep learning-based predictor is employed to extract spatiotemporal features from real-time PMU data, enabling high-fidelity prediction of stability margins. Crucially, instead of direct black-box control, the data-driven model is utilized to derive linear control sensitivities via a batch-processing perturbation mechanism. This transforms the intractable Transient Stability Constrained Optimal Power Flow (TSC-OPF) problem into a real-time solvable Linear Programming model. Case studies on a regional AC/DC hybrid grid demonstrate that the proposed framework achieves high prediction accuracy and effectively restores stability in mismatch scenarios where traditional schemes fail. Furthermore, the decision speed of the proposed method is significantly improved compared to traditional time-domain simulations, thus strictly satisfying the real-time requirements of the second line of defense. Full article

The integration of artificial intelligence (AI) into early childhood education presents both opportunities and challenges to longstanding Froebelian pedagogies, particularly regarding child agency and nature-based play. This mixed-methods study explores this tension within the Chinese context. It examines how Chinese Froebelian practitioners perceive the alignment between AI tools and core principles and investigates the strategies they employ to navigate the integration of technology with humanistic educational values. The survey results, from 50 practitioners, revealed that AI can support autonomous and holistic learning, yet significant concerns persisted regarding the displacement of sensory and nature-based experiences. Follow-up interviews uncovered a practitioner-led “dual-track integration” approach, which strategically blends physical manipulation and nature engagement with AI-enabled personalization. Through an iterative dialogue between theory and data, this study develops and refines the “dual-track integration” framework as an empirically grounded, sensitizing model. This framework offers principled strategies for hybrid learning that uphold the developmental primacy of play. Situated within the discourse on Sustainable Development Goal 4 (quality education) and Goal 10 (reduced inequalities), the analysis highlights AI’s dual potential to advance or hinder equity. By examining China’s hybrid position, which combines advanced digital infrastructure with persistent equity gaps, this research highlights the critical role of educator agency and pedagogical design in leveraging AI to advance equitable, high-quality early childhood education. Full article

This article presents a state-of-the-art review of recent advances aimed at transforming traditional Failure Mode and Effects Analysis (FMEA) into a more intelligent, data-driven, and semantically enriched process. As engineered systems grow in complexity, conventional FMEA methods, which are largely manual, document-centric, and expert-dependent, have become increasingly inadequate for addressing the demands of modern systems engineering. We examine how techniques from Artificial Intelligence (AI), including machine learning and natural language processing, can transform FMEA into a more dynamic, data-driven, intelligent, and model-integrated process by automating failure prediction, prioritisation, and knowledge extraction from operational data. In parallel, we explore the role of ontologies in formalising system knowledge, supporting semantic reasoning, improving traceability, and enabling cross-domain interoperability. The review also synthesises emerging hybrid approaches, such as ontology-informed learning and large language model integration, which further enhance explainability and automation. These developments are discussed within the broader context of Model-Based Systems Engineering (MBSE) and function modelling, showing how AI and ontologies can support more adaptive and resilient FMEA workflows. We critically analyse a range of tools, case studies, and integration strategies, while identifying key challenges related to data quality, explainability, standardisation, and interdisciplinary adoption. By leveraging AI, systems engineering, and knowledge representation using ontologies, this review offers a structured roadmap for embedding FMEA within intelligent, knowledge-rich engineering environments. Full article

In medical endoscopic imaging, specular reflection (SR) frequently leads to local overexposure, obscuring essential tissue information and complicating computer-aided diagnosis (CAD). Traditional convolutional neural networks (CNNs) face difficulties in modeling global illumination phenomena due to their biased local receptive fields and the inherent “object assumption.” Conversely, pure transformer models often lose high-frequency boundary details and incur substantial computational costs. To tackle these challenges, this paper introduces VDTAR-Net, a specialized framework adapted to address the unique optical characteristics of specular reflections. Building upon hybrid architectures, our contribution focuses on two core mechanisms: (1) a Cross-architecture Fusion Module (CFM) that enables deep, bidirectional information flow, allowing the Transformer’s global illumination modeling to continuously correct the CNN’s local texture biases; and (2) a Reflective-Aware Module (RAM), which explicitly integrates the physical prior of high-intensity saturation into the attention mechanism. This task-specific design significantly enhances sensitivity to boundary details in overexposed regions. We also created the first large-scale, expert-labeled cervical white light segmentation dataset, Cervix-WL-900. High-quality ground truth labels were generated through rigorous double-blind annotation and arbitration by senior experts. Experimental results show that VDTAR-Net achieves a Dice score of 92.56% and a mean Intersection over Union (mIoU) score of 87.31% on Cervix-WL-900, demonstrating superior performance compared to methods like U-Net, DeepLabv3+, SegFormer, and PSPNet. Ablation studies further confirm the substantial contributions of dual-path collaboration, CFM deep fusion, and RAM task-specific priors. VDTAR-Net provides a robust baseline for precise highlight segmentation, laying a foundation for subsequent image quality assessment, restoration, and feature decoupling in diagnostic models. Full article

The renewed interest in hydrogen peroxide-based space propulsion systems has highlighted the persistent issue of catalyst degradation during long-term operation. Although several studies have investigated the underlying causes of this phenomenon, effective regeneration techniques capable of restoring catalytic activity have not yet been clearly demonstrated. This study investigates the mechanisms responsible for performance degradation and proposes a viable regeneration strategy for palladium-based catalysts. Experimental analyses were conducted on a batch of commercial Al${}_2$O${}_3$/Pd pellets subjected to multiple firing cycles in a 10 N-class hybrid mini-thruster. Monitoring of the propulsive performance revealed a progressive decline in catalytic activity, ultimately preventing ignition of the hybrid rocket engine. To characterize the degradation mechanisms, the pellets were examined through visual inspection, static hydrogen peroxide decomposition tests, and Temperature Programmed Reduction (TPR) analysis. The results indicated significant surface oxidation of palladium, leading to reduced decomposition efficiency. A chemical regeneration procedure based on sodium borohydride (NaBH${}_4$) treatment was subsequently developed to restore catalytic performance. The regenerated pellets were tested under the same experimental conditions that had previously led to ignition failure. Their propulsive performance was then compared with both the degraded pellets and a new batch of equivalent catalysts. The results demonstrate that the regeneration process successfully restored the catalytic activity to levels comparable with the original state, enabling stable and efficient hybrid combustion. These findings confirm the role of surface oxidation in catalyst degradation and demonstrate that targeted chemical treatment can significantly extend catalyst lifetime. The proposed regeneration strategy offers a practical method to reduce costs of ground-based experimental campaigns and support the future deployment of hydrogen peroxide-based propulsion systems in space applications by providing insights into the mechanisms that can degrade the performance of palladium catalysts. Full article

The marine centrifugal pump is one of the most energy-intensive pieces of equipment in ship auxiliary machinery, and the efficient design of its hydraulic components can effectively reduce the total energy consumption of the ship system. Aiming at the complex three-dimensional twisted blade profile structure of the marine centrifugal pump, this paper optimized the clonal selection algorithm and constructed an automatic hydraulic optimization design method for the high-efficiency centrifugal pump impeller. Considering the multi-condition operation characteristics of the marine centrifugal pump, a performance test platform for the marine centrifugal pump was built, and the actual operating conditions of the model pump were tested to obtain its performance characteristics under operating conditions. The numerical simulation method was employed to capture and analyze the internal flow field and flow characteristics of the model pump. Addressing the design challenges of the marine centrifugal pump impeller, which involve multiple parameters with significant interactions, a traditional clonal selection algorithm was enhanced using a Slime Mold Algorithm, and a hybrid Clonal Selection Algorithm integrated with Slime Mold and Tangent Flight mechanisms was established. Based on the MATLAB and ANSYS platforms, an automated hydraulic optimization design framework for the centrifugal pump impeller was established. Using the optimized clonal selection algorithm, with the operational efficiency of the model pump as the optimization objective and controlling ten key geometric parameters of the blade profile through Bézier curves, the blade profile optimization design was achieved. The pump hydraulic efficiency under the rated flow condition increased by 7%. The unsteady internal flow efficiency of the optimized marine centrifugal pump was significantly improved. The blade optimization alleviated flow separation phenomena on the tangential surface of the impeller and in partial regions of the volute, reduced the flow loss area, and significantly decreased overall flow losses. Full article