Improved exploration-exploitation trade-off through adaptive prioritized experience replay DOI Creative Commons
Hossein Hassani, Soodeh Nikan, Abdallah Shami

et al.

Neurocomputing, Journal Year: 2024, Volume and Issue: 614, P. 128836 - 128836

Published: Nov. 9, 2024

Language: Английский

Improving the local diagnostic explanations of diabetes mellitus with the ensemble of label noise filters DOI
Che Xu, Peng Zhu, Jiacun Wang

et al.

Information Fusion, Journal Year: 2025, Volume and Issue: unknown, P. 102928 - 102928

Published: Jan. 1, 2025

Language: Английский

Citations

5
High dimensional mislabeled learning DOI
Henry Han, Dongdong Li,

Wenbin Liu

et al.

Neurocomputing, Journal Year: 2024, Volume and Issue: 573, P. 127218 - 127218

Published: Jan. 5, 2024

Language: Английский

Citations

6
Predicting concrete strength early age using a combination of machine learning and electromechanical impedance with nano-enhanced sensors DOI

Huang Ju,

Lin Xing,

Alaa H. Ali

et al.

Environmental Research, Journal Year: 2024, Volume and Issue: 258, P. 119248 - 119248

Published: May 31, 2024

Language: Английский

Citations

3
Drug-target binding affinity prediction based on power graph and word2vec DOI Creative Commons
Jing Hu, Shuo Hu,

Minghao Xia

et al.

BMC Medical Genomics, Journal Year: 2025, Volume and Issue: 18(S1)

Published: Jan. 13, 2025

Abstract Background Drug and protein targets affect the physiological functions metabolic effects of body through bonding reactions, accurate prediction drug-protein target interactions is crucial for drug development. In order to shorten development cycle reduce costs, machine learning methods are gradually playing an important role in field drug-target interactions. Results Compared with other methods, regression-based affinity more representative binding ability. Accurate can effectively time cost retargeting new this paper, a model (WPGraphDTA) based on power graph word2vec proposed. Conclusions model, molecular features module extracted by neural network, then obtained Word2vec method. After feature fusion, they input into three full connection layers obtain value. We conducted experiments Davis Kiba datasets, experimental results showed that WPGraphDTA exhibited good performance.

Language: Английский

Citations

0
The optimised model of predicting protein‐metal ion ligand binding residues DOI Creative Commons

Caiyun Yang,

Xiuzhen Hu, Zhenxing Feng

et al.

IET Systems Biology, Journal Year: 2025, Volume and Issue: 19(1)

Published: Jan. 1, 2025

Abstract Metal ions are significant ligands that bind to proteins and play crucial roles in cell metabolism, material transport, signal transduction. Predicting the protein‐metal ion ligand binding residues (PMILBRs) accurately is a challenging task theoretical calculations. In this study, authors employed fused amino acids their derived information as feature parameters predict PMILBRs using three classical machine learning algorithms, yielding favourable prediction results. Subsequently, deep algorithm was incorporated prediction, resulting improved results for sets of Ca 2+ Mg compared previous studies. The validation matrix provided optimal model each ionic residue, exhibiting capability effectively predicting sites metal real protein chains.

Language: Английский

Citations

0
Advancements in Machine Learning Predicting Activation and Gibbs Free Energies in Chemical Reactions DOI Open Access
Guo‐Jin Cao

International Journal of Quantum Chemistry, Journal Year: 2025, Volume and Issue: 125(7)

Published: March 19, 2025

ABSTRACT Machine learning has revolutionized computational chemistry by improving the accuracy of predicting thermodynamic and kinetic properties like activation energies Gibbs free energies, accelerating materials discovery optimizing reaction conditions in both academic industrial applications. This review investigates recent strides applying advanced machine techniques, including transfer learning, for accurately within complex chemical reactions. It thoroughly provides an extensive overview pivotal methods utilized this domain, sophisticated neural networks, Gaussian processes, symbolic regression. Furthermore, prominently highlights commonly adopted frameworks, such as Chemprop, SchNet, DeepMD, which have consistently demonstrated remarkable exceptional efficiency properties. Moreover, it carefully explores numerous influential studies that notably reported substantial successes, particularly focusing on predictive performance, diverse datasets, innovative model architectures profoundly contributed to enhancing methodologies. Ultimately, clearly underscores transformative potential significantly power intricate systems, bearing considerable implications cutting‐edge theoretical research practical

Language: Английский

Citations

0
Bridging odorants and olfactory perception through machine learning: A review DOI

Zhong Risheng,

Zongliang Ji,

Shuqi Wang

et al.

Trends in Food Science & Technology, Journal Year: 2024, Volume and Issue: 153, P. 104700 - 104700

Published: Sept. 5, 2024

Language: Английский

Citations

3
A novel stochastic configuration network with enhanced feature extraction for industrial process modeling DOI
Qianjin Wang, Wei Yang, Wei Dai

et al.

Neurocomputing, Journal Year: 2024, Volume and Issue: 594, P. 127833 - 127833

Published: May 9, 2024

Language: Английский

Citations

2
Explainable machine learning for high frequency trading dynamics discovery DOI
Henry Han, Jeffrey Yi‐Lin Forrest, Jiacun Wang

et al.

Information Sciences, Journal Year: 2024, Volume and Issue: 684, P. 121286 - 121286

Published: Aug. 3, 2024

Language: Английский

Citations

2
Environmental impact evaluation using smart real-time weather monitoring systems: a systematic review DOI

Avines Panneer Selvam,

S. N. Saud

Innovative Infrastructure Solutions, Journal Year: 2024, Volume and Issue: 10(1)

Published: Dec. 26, 2024

Language: Английский

Citations

2