Results 71 to 80 of about 2,584 (186)

MSPCIFormer: A Multi‐Scale Patching Channel‐Independent Transformer for Cryptocurrency Price Forecasting

Expert Systems, Volume 43, Issue 9, September 2026.
ABSTRACT Forecasting cryptocurrency prices remains challenging due to extreme volatility, regime‐dependent dynamics, and unstable cross‐asset correlations. Statistical methods such as ARIMA and GARCH assume stationarity and linear dependence structures, making them inadequate for capturing non‐linear temporal patterns in high volatile cryptocurrency ...
Huali Zhao, Martin Crane, Marija Bezbradica   +2 more
wiley   +1 more source

Uncertainty‐Aware Machine Learning for Onset of Deep Convection: Under what Conditions Are Trigger Predictions More Reliable?

Geophysical Research Letters, Volume 53, Issue 15, 16 August 2026.
Abstract Machine Learning (ML) models have emerged as a powerful tool for predicting deep convection triggering, yet the atmospheric conditions that systematically challenge these models in detecting deep convection remain poorly understood. To diagnose such ambiguous regimes, we trained a Controlled Abstention Neural Network (CAN) that separates high‐
Ashish Bhattarai, Youtong Zheng
wiley   +1 more source

An integrated machine learning and hyperparameter optimization framework for noninvasive creatinine estimation using photoplethysmography signals

Healthcare Analytics
Frequent measurement of creatinine levels is vital for patients with chronic kidney disease. Traditional creatinine level measurement requires invasive blood test which has several disadvantages like discomfort, anxiety, panic, pain, risk of infection ...
Parama Sridevi, Zawad Arefin, Sheikh Iqbal Ahamed   +2 more
doaj   +1 more source

Estimation of pulmonary function from time‐resolved dynamic chest radiography using machine learning in patients with respiratory disease

Journal of Applied Clinical Medical Physics, Volume 27, Issue 8, August 2026.
Abstract Background Pulmonary function tests (PFTs), particularly spirometry, are the reference standard for assessing airflow limitation in respiratory diseases such as chronic obstructive pulmonary disease (COPD) and interstitial pulmonary disease.
Takehiro Shiinoki, Yuki Yuasa, Tsunahiko Hirano, Maki Asami‐Noyama, Kazuto Matsunaga, Hidekazu Tanaka   +5 more
wiley   +1 more source

Application of the Optuna-NeuralProphet model for predicting step-like landslide displacement

AIP Advances
Displacement prediction is crucial to landslide engineering monitoring and early warning. An Optuna-NeuralProphet model is proposed based on the Optuna framework and the NeuralProphet model to address the challenge of predicting step-like landslide ...
Ming Huang, Hougang Yang, Fan Yang
doaj   +1 more source

Advanced Experiment Design Strategies for Drug Development

Advanced Intelligent Discovery, Volume 2, Issue 4, August 2026.
Wang et al. analyze 592 drug development studies published between 2020 and 2024 that applied design of experiments methodologies. The review surveys both classical and emerging approaches—including Bayesian optimization and active learning—and identifies a critical gap between advanced experimental strategies and their practical adoption in ...
Fanjin Wang, Anthony Harker, Mohan Edirisinghe, Maryam Parhizkar   +3 more
wiley   +1 more source

Classification of Alzheimer's Disease Using a Hybrid Technique Integration Between CNN and Optuna Optimization

NTU Journal of Engineering and Technology
Alzheimer's Disease (AD) is considered one of the most prevalent neurological disorders, primarily affecting elderly people and adversely impacting their brain functions. This disease is characterized by the gradual deterioration of cognitive functions,
Nawzt Sadiq Jaafar Al-Bayati, Raid Rafi Omar Al-Nima   +1 more
doaj   +1 more source

Dynamic, Unconstrained Optimization of Secreted Enzyme Production in Fed‐Batch Fermentation Using Reinforcement Learning

Biotechnology and Bioengineering, Volume 123, Issue 8, Page 2024-2036, August 2026.
ABSTRACT Reinforcement learning (RL) has been used to control a wide range of dynamic processes, especially ones that are too complex to model well or have stochastic environmental perturbations. Fed‐batch fermentations are subject to changes in starting cell growth rates and process variations that can affect cell growth and secreted target production.
Sai Harish Uthravalli, Sakib Ferdous, J. Michael Hess, Nigel F. Reuel   +3 more
wiley   +1 more source

SSEL‐CPP: A SHAP‐based feature‐selection ensemble learning framework identifies molecular properties of cell‐penetrating peptides

Protein Science, Volume 35, Issue 8, August 2026.
Abstract Cell‐penetrating peptides (CPPs) facilitate the intracellular delivery of therapeutic molecules. However, their accurate identification and design remain challenging because of the complexity of their structural and physicochemical characteristics.
Chan Woo Kwon, Minjun Kwon, Shaherin Basith, Sampa Misra, Yong Eun Jang, Gwang Lee   +5 more
wiley   +1 more source

The Use of Hyperparameter Tuning in Model Classification: A Scientific Work Area Identification

JOIV: International Journal on Informatics Visualization
This research aims to investigate the effectiveness of hyperparameter tuning, particularly using Optuna, in enhancing the classification performance of machine learning models on scientific work reviews. The study focuses on automating the classification
Nadya Alinda Rahmi, Sarjon Defit, - Okfalisa   +2 more
doaj   +1 more source