Results 121 to 130 of about 4,344 (219)

On the Adversarial Robustness of Hydrological Models

Water Resources Research, Volume 62, Issue 10, October 2026.
Abstract The evaluation of hydrological models is essential for both model selection and reliability assessment. However, comparing predictions with observations alone is insufficient to fully characterize model behavior. This limitation is particularly relevant to deep learning (DL) models because of their complex internal structures.
Yang Yang, Joseph Janssen, Hoshin Gupta, Ting Fong May Chui   +3 more
wiley   +1 more source

A Self‐Supervised Framework for Space Object Behaviour Characterisation

Expert Systems, Volume 43, Issue 10, October 2026.
ABSTRACT Foundation Models, which leverage large neural networks pre‐trained on unlabelled data before fine‐tuning for specific tasks, are increasingly being applied to specialised domains. Recent examples include ClimaX for climate and Clay for satellite Earth observation, but a Foundation Model for Space Object Behavioural Analysis (SOBA) has not yet
Ian Groves, Andrew Campbell, James Fernandes, Diego Ramírez Rodríguez, Paul Murray, Massimiliano Vasile, Victoria Nockles   +6 more
wiley   +1 more source

Application of FCEEMD-TSMFDE and adaptive CatBoost in fault diagnosis of complex variable condition bearings

Scientific Reports
The mode mixing problem and inherent mode function selection bias in Fast Ensemble Empirical Mode Decomposition (FEEMD) result in ineffective extraction of fault components during the denoising stage, the loss of coarse-grained information in Multiscale ...
Min Mao, Bingwei Xu, Yuhuan Sun, Kairong Tan, Yuran Wang, Chao Zhou, Chengjiang Zhou, Jingzong Yang   +7 more
doaj   +1 more source

Predicting Nepheline Formation in Nuclear Waste Glasses Using Machine Learning With Uncertainty Quantification

International Journal of Applied Glass Science, Volume 17, Issue 4, October 2026.
ABSTRACT The vitrification of high‐level waste (HLW) into borosilicate glass is a cornerstone of nuclear waste management, yet one of the key challenges in glass formulation for high‐aluminum‐containing waste streams is the precipitation of nepheline during the canister cooling stage.
Mayra Diaz‐Acevedo, Chloe E. Curry, Xiaonan Lu, Saehwa Chong, Sarah I. Allec, John D. Vienna   +5 more
wiley   +1 more source

Optimizing Machine Learning Models for Urban Sciences: A Comparative Analysis of Hyperparameter Tuning Methods

Urban Science
Advancing urban scholarship and addressing pressing challenges such as gentrification, housing affordability, and urban sprawl require robust predictive models.
Tris Kee, Winky K.O. Ho
doaj   +1 more source

Maternal Gait as a Potential Scaffold for Rhythm Processing: A Predictive Processing Network Model

Annals of the New York Academy of Sciences, Volume 1564, Issue 1, October 2026.
We model how maternal gait during pregnancy could scaffold rhythm perception by providing synchronized auditory‐vestibular stimulation. A predictive coding network trained with paired footstep pulses and continuous vestibular waveforms learns to anticipate auditory beats and spontaneously generates vestibular predictions from sound alone—constituting ...
Matin Yousefabadi, Jonathan Cannon
wiley   +1 more source

Deep Learning Framework With Optuna-Based Hyperparameter Tuning for Predicting Dry Turning Process Performance of 42CrMo4 Steel

IEEE Access
This study presents an integrated experimental and data-driven modeling framework for predicting key machining responses such as tool wear (TW), material removal rate (MRR), and surface roughness (Ra) during dry turning of 42CrMo4 alloy steel ...
Vasanth Siva Kumar, Mogana Priya Chinnasamy, Swetha R Kumar   +2 more
doaj   +1 more source

SUPERVISED PERSIAN SPEECH EMOTION RECOGNITION USING DISTILHUBERT AND OPTUNA TUNING

Eurasian Journal of Mathematical and Computer Applications
Speech emotion recognition (SER) is recognized as a growing field with important applications in human computer interaction. In this study, attention is given to SER for the Persian language, which is regarded as a relatively underexplored domain. A lightweight ar- chitecture is introduced, in which a frozen DistilHuBERT model is used for feature ...
S Hosseini, A Ahmadianshalchi, M Houshmand   +2 more
openaire   +1 more source

KLASIFIKASI TINGKAT KEPARAHAN KECELAKAAN LALU LINTAS BERBASIS CATBOOST PADA DATA YANG TIDAK SEIMBANG MENGGUNAKAN SMOTENC DAN OPTUNA [PDF]

Traffic accidents represent a complex issue in Surabaya, having a significant impact on public safety and socio-economic loss. A primary challenge in accident severity classification modeling is the phenomenon of data imbalance, where slight injury cases
Ayatillah, Maslahatul Kaunaini
core  

Ionospheric TEC Prediction in low-latitude Indian region during geomagnetic storm periods based on XGBoost with Optuna framework and comparison with IRI-Plas 2020

This paper introduces a strong 24-hour TEC forecast model based on the Extreme Gradient Boosting (XGBoost) algorithm, implemented for GPS-based TEC data at both the IISC and Chum stations.
Kumar, S. Kishore, Jude, Andrew F., Kenisha, J., Logesh, S., Dass, Sarat C.; id_orcid, Muthukumaran, T., Mukesh, R., Kiruthiga, S., Cynthia, G.   +8 more
core   +1 more source