-
101
Knowledge- and Model-Driven Deep Reinforcement Learning for Efficient Federated Edge Learning: Single- and Multi-Agent Frameworks
Published 2025-01-01“…To address these challenges, we propose knowledge/model-driven single-agent and multi-agent deep reinforcement learning (DRL) frameworks. …”
Get full text
Article -
102
-
103
Revolutionizing Clear-Sky Humidity Profile Retrieval with Multi-Angle-Aware Networks for Ground-Based Microwave Radiometers
Published 2025-01-01“…Here, we present a novel retrieval algorithm called AngleNet, a groundbreaking deep-learning model that leverages multi-angle BT observation from ground-based microwave radiometers (MWRs). …”
Get full text
Article -
104
-
105
CryoSCAPE: Scalable immune profiling using cryopreserved whole blood for multi-omic single cell and functional assays
Published 2025-01-01“…We present CryoSCAPE (Cryopreservation for Scalable Cellular And Proteomic Exploration), a scalable method for immune studies of human PBMC with multi-omic single cell assays using direct cryopreservation of whole blood. …”
Get full text
Article -
106
Deep attention model for arrhythmia signal classification based on multi-objective crayfish optimization algorithmic variational mode decomposition
Published 2025-02-01“…Moreover, Bayesian optimization was carried out to fine-tune the hyperparameters batch size, learning rate, epochs, and momentum. …”
Get full text
Article -
107
spCLUE: a contrastive learning approach to unified spatial transcriptomics analysis across single-slice and multi-slice data
Published 2025-06-01“…We introduce spCLUE, a comprehensive framework combining multi-view graph network, contrastive learning, attention mechanisms, and a batch prompting module to learn informative spot representations and integrate data from both aligned and unaligned samples. spCLUE outperforms nine single-slice and seven multi-slice methods when tested on diverse datasets and reveals biologically relevant domains across different tissues and conditions. spCLUE offers a powerful solution to spatial domain analysis and integration in spatial transcriptomics, enabling more accurate and interpretable studies of tissue organization.…”
Get full text
Article -
108
-
109
Research on Development Status and Implementation Path of Wind-Solar-Water-Thermal-Energy Storage Multi-Energy Complementary Demonstration Project
Published 2023-06-01“…This paper summarized the connotation construction principles of multi-energy complementarity, detailed the development status and existing problems of the first batch of multi-energy complementarity demonstration projects, and analyzed in detail the development paths of different modes of multi-energy complementarity projects. …”
Get full text
Article -
110
A multi task learning framework using DeBERTa and BWO optimization for enhancing long term english vocabulary memory
Published 2025-07-01“…BWO is used to dynamically adjust the key hyperparameters of the DeBERTa model, such as the learning rate, batch size, and loss weight, to keep it in the optimal state at different learning stages. …”
Get full text
Article -
111
-
112
-
113
Multi-Biofuel Production Under Controlled and Noncontrolled pH Conditions by a Glucose-Adapted <i>Enterobacter cloacae</i>
Published 2025-06-01“…Batch cultures were performed in 1 dm<sup>3</sup> bioreactors, controlling the pH at 5.5, 6.5, 7.5, and 9.2. …”
Get full text
Article -
114
Investigation of Toy Parts Produced Using Injection Molding and FDM and Selection of the Best Manufacturing Method: A Multi-Criteria Approach
Published 2025-06-01“…Cost analysis indicated that injection molding is economically viable only when production exceeds 735 pieces, while FDM becomes more attractive for smaller batches due to its low initial cost. A multi-criteria decision-making analysis using the TOPSIS method was conducted to integrate technical and economic factors. …”
Get full text
Article -
115
-
116
-
117
-
118
Deep-EFNet: An Optimized EfficientNetB0 Architecture With Dual Regularization for Scalable Multi-Class Brain Tumor Classification in MRI
Published 2025-01-01“…These enhancements include batch normalization layers for stable training, dropout and L2 regularization mechanisms for preventing overfitting, and a hierarchical dense layer structure for improved feature representation. …”
Get full text
Article -
119
Performance evaluation of aminated multi-walled carbon nanotubes incorporated with green synthesized iron nanoparticles for toxic dyes sequestration from textile wastewater
Published 2025-06-01“…This study evaluates the performance of aminated multi-walled carbon nanotubes (AM-MWCNTs) integrated with zerovalent iron nanoparticles (ZVI) synthesized using cashew leaf (Anacardium occidentale) extract (AM-MWCNTs@ZVI) for the removal of Congo Red (CR) and Methylene Blue (MB) dyes from textile industrial wastewater. …”
Get full text
Article -
120
