Wind Turbine Fault Detection Through Autoencoder-Based Neural Network and FMSA by Welker Facchini Nogueira, Arthur Henrique de Andrade Melani, Gilberto Francisco Martha de Souza

“…To improve the reliability and maintainability of wind farms, this work proposes a novel hybrid fault detection approach that combines expert-driven diagnostic knowledge with data-driven modeling. The framework integrates autoencoder-based neural networks with Failure Mode and Symptoms Analysis, leveraging the strengths of both methodologies to enhance anomaly detection, feature selection, and fault localization. …”
Get full text

Integral approach to organelle profiling in human iPSC-derived cardiomyocytes enhances in vitro cardiac safety classification of known cardiotoxic compounds by Brigitta R. Szabo, Brigitta R. Szabo, Jeroen Stein, Anna Savchenko, Thomas Hutschalik, Thomas Hutschalik, Filip Van Nieuwerburgh, Tim Meese, Georgios Kosmidis, Paul G. A. Volders, Elena Matsa, Elena Matsa, Elena Matsa, Elena Matsa

“…In supervised clustering, morphological features outperformed electrophysiological data alone, and the combined data set achieved a 76% accuracy in recapitulating known clinical cardiotoxicity classifications. …”
Get full text

Marker-Less Navigation System for Anterior Cruciate Ligament Reconstruction with 3D Femoral Analysis and Arthroscopic Guidance by Shuo Wang, Weili Shi, Shuai Yang, Jiahao Cui, Qinwei Guo

“…The system’s two-stage registration framework, combining SIFT-ICP algorithms, achieves accurate alignment between preoperative models and arthroscopic views. Validation results from expert surgeons demonstrated high precision, with 71.5% of test groups achieving acceptable or excellent performance standards (mean deviation distances: 1.12–1.86 mm). …”
Get full text

Development and validation of a machine learning-based nomogram for survival prediction of patients with hilar cholangiocarcinoma after curative-intent resection by Yubo Ma, Qi Li, Zhenqi Tang, Kangpeng Li, Chen Chen, Jianjun Lei, Dong Zhang, Zhimin Geng

“…Risk factors selection was performed by five machine learning (ML) algorithms, including Least Absolute Shrinkage and Selection Operator (LASSO) Regression, Forward Stepwise Cox regression, Boruta feature selection, Random Forest and eXtreme Gradient Boosting (XGBoost). …”
Get full text

Synthesis of SBA-16 mesoporous silica from rice husk ash for removal of Rhodamine B cationic dye: Effect of hydrothermal treatment time by Shaimaa S. El-Shafey, Sohair A. Sayed Ahmed, Reham M. Aboelenin, Nady A. Fathy

“…The maximum adsorption capacity calculated from Langmuir model showed that SBA-16–48 h featuring the larger capacity of about 166.7 mg/g at pH 6. …”
Get full text

Seasonal Regional Differentiation of Human Thermal Comfort Conditions in Algeria by Salah Sahabi Abed, Andreas Matzarakis

“…This study is important since it is performed for the first time in Algeria using a deterministic approach through the calculation of PET based on the body-atmosphere energy balance using the Munich Energy-Balance Model for Individuals (MEMI). …”
Get full text

Biglycan-driven risk stratification in ZFTA-RELA fusion supratentorial ependymomas through transcriptome profiling by Konstantin Okonechnikov, David R. Ghasemi, Daniel Schrimpf, Svenja Tonn, Martin Mynarek, Jan Koster, Till Milde, Tuyu Zheng, Philipp Sievers, Felix Sahm, David T.W. Jones, Andreas von Deimling, Stefan M. Pfister, Marcel Kool, Kristian W. Pajtler, Andrey Korshunov

“…Our results indicate that integrating BGN expression (at mRNA and/or protein level) into risk stratification models may improve ST-EPN ZFTA-RELA outcome prediction. …”
Get full text

Neighborhood disadvantage and general anesthesia utilization in cesarean delivery: a retrospective analysisAJOG Global Reports at a Glance by Andrea J. Ibarra, MD, MS, Hannah Campion, MD, Cecilia Canales, MD, MS, Brittany N. Burton, Alejandro Munoz, MD, PhD, Robert S. White, MD, MS, Runjia Li, MS, Goundappa K. Balasubramani, PhD, Janet M. Catov, PhD, MS

“…The odds of receiving general anesthesia versus neuraxial anesthesia (epidural, spinal, or combined spinal-epidural) were compared using logistic regression models. Results: Of the 16,351 people with cesarean deliveries, 96.0% received neuraxial versus 4.0% general anesthesia. …”
Get full text

MetaRes-DMT-AS: A Meta-Learning Approach for Few-Shot Fault Diagnosis in Elevator Systems by Hongming Hu, Shengying Yang, Yulai Zhang, Jianfeng Wu, Liang He, Jingsheng Lei

“…Subsequent regularization via prototype networks ensures stable feature extraction. Comprehensive validation using the Case Western Reserve University bearing dataset and proprietary elevator acceleration data demonstrates the framework’s superiority: MetaRes-DMT-AS achieves state-of-the-art few-shot classification performance, surpassing benchmark models by 0.94–1.78% in overall accuracy. …”
Get full text

Unified wound diagnostic framework for wound segmentation and classification by Mustafa Alhababi, Gregory Auner, Hafiz Malik, Muteb Aljasem, Zaid Aldoulah

“…To address these gaps, we developed a unified approach that performs S&C simultaneously. For segmentation, we proposed Attention-Dense-UNet (Att-d-UNet), and for classification, we introduced a feature concatenation-based method. …”
Get full text

Detection of the Pigment Distribution of Stacked Matcha During Processing Based on Hyperspectral Imaging Technology by Qinghai He, Zhiyuan Liu, Xiaoli Li, Yong He, Zhi Lin

“…Firstly, a quantitative relationship between HSI data of tea and their pigment contents was developed based on regression analysis, and the results showed that exceptional prediction performance was achieved by the partial least squares regression (PLSR) algorithm combined with the feature band algorithm of competitive adaptive reweighting (CARS), and the R_p² values of detection models of chlorophyll a, chlorophyll b and carotenoids were 0.90465, 0.92068 and 0.62666, respectively. …”
Get full text

Physics instructors’ acceptance and implementation of generative AI by Pornrat Wattanakasiwich, Kreetha Kaewkhong, Duanghatai Katwibun

“…A mixed-method approach combining quantitative structural equation modeling (SEM) and qualitative content analysis was employed. …”
Get full text

A hybrid approach to advanced NER techniques for AI-driven water and agricultural resource management by Dong Yan, Ming Lei, Yingying Shi

“…It includes two core components: the Adaptive Representation Neural Framework (ARNF) for multiscale semantic feature encoding, and the Adaptive Task Optimization Strategy (ATOS), which dynamically balances learning priorities to enhance multitask performance in heterogeneous and resource-constrained environments.ResultsExperimental results on several benchmark datasets demonstrate that our method significantly outperforms state-of-the-art models. …”
Get full text

The influencing factors of depression among Chinese male nursing students: application of decision tree and FsQCA by Zenghui Wang, Jianxin Zhao, Hui Wang, Dongyu Song, Danjun Feng, Miao Yu, Feng Li

“…Results The trained decision tree demonstrated acceptable predictive performance (AUC = 0.78). The feature importance ranking placed self-esteem first, followed by childhood adversity, perfectionism, perceived stress, and insomnia. …”
Get full text

Encoding Holographic Data Into Synthetic Video Streams for Enhanced Microplastic Detection by Paolo Russo, Fabiana Di Ciaccio, Pasquale Santaniello, Teresa Cacace, Pierluigi Carcagni, Marco del Coco, Melania Paturzo

“…This allows the use of transformer-based video architectures, particularly TimeSformer, for spatiotemporal modeling. Experimental results demonstrate that TimeSformer achieves a classification accuracy of up to 97.91%, with compressed 8-frame inputs maintaining high performance while significantly reducing inference time (from 42 ms to 16 ms per sample). …”
Get full text

Clinical Predictors of Cognitive Impairment in a Cohort of Patients with Older Age Bipolar Disorder by Camilla Elefante, Giulio Emilio Brancati, Maria Francesca Beatino, Benedetta Francesca Nerli, Giulia D’Alessandro, Chiara Fustini, Daniela Marro, Gabriele Pistolesi, Filippo Baldacci, Roberto Ceravolo, Lorenzo Lattanzi

“…Univariate comparisons and multivariate logistic regression models were performed to investigate the associations between clinical variables and cognitive impairment. …”
Get full text

Preliminary results of the EPIDIA4Kids study on brain function in children: multidimensional ADHD-related symptomatology screening using multimodality biometry by Yanice Guigou, Alexandre Hennequin, Théo Marchand, Théo Marchand, Mouna Chebli, Lucie Isoline Pisella, Pascal Staccini, Pascal Staccini, Vanessa Douet Vannucci, Vanessa Douet Vannucci

“…Each ADHD-related measure was evaluated with each biometric using linear mixed-effects models. In contrast to neuro-assessments, only two digit-tracking features had age and sex effects (p < 0.001) among the biometrics. …”
Get full text

Design and Development of Educational Modular Mobile Robot Platform by Denis Kotarski, Petar Piljek, Tomislav Šančić

“…The proposed platform is comprehensive in terms of motion planning and modelling. Mathematical description of the non-holonomic and holonomic configuration of the robot is given, and a derived model is implemented in a software package in order to perform simulations and experiments. …”
Get full text

A Case Study on the Gas Drainage Optimization Based on the Effective Borehole Spacing in Sima Coal Mine by Ming Ji, Zhong-guang Sun, Wei Sun

“…Based on the dynamic expressions of permeability and porosity of the coal seam derived in the paper, a multiphysical field coupling numerical model of gas migration under the interaction of stress field and seepage field was established. …”
Get full text

Gut-Microbiome Signatures Predicting Response to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer: A Systematic Review by Ielmina Domilescu, Bogdan Miutescu, Florin George Horhat, Alina Popescu, Camelia Nica, Ana Maria Ghiuchici, Eyad Gadour, Ioan Sîrbu, Delia Hutanu

“…Four independent machine-learning models achieved an Area Under the Receiver Operating Characteristic curve AUROC ≥ 0.85 for pCR prediction. …”
Get full text