A Machine Learning Model for Interpretable PECVD Deposition Rate Prediction
Advanced Intelligent Discovery, EarlyView.This study develops six machine learning models (k‐nearest neighbors, support vector regression, decision tree, random forest, CatBoost, and backpropagation neural network) to predict SiNx deposition rates in plasma‐enhanced chemical vapor deposition using hybrid production and simulation data.
Yuxuan Zhai +8 more
wiley +1 more source
Advanced Intelligent Discovery, EarlyView.We propose a residual‐based adversarial‐gradient moving sample (RAMS) method for scientific machine learning that treats samples as trainable variables and updates them to maximize the physics residual, thereby effectively concentrating samples in inadequately learned regions.
Weihang Ouyang +4 more
wiley +1 more source
Smart Bioinspired Material‐Based Actuators: Current Challenges and Prospects
Advanced Intelligent Systems, Volume 7, Issue 3, March 2025.This work gathers, in a review style, an extensive and comprehensive literature overview on the development of autonomous actuators based on synthetic materials, bringing together valuable knowledge from several studies. Furthermore, the article identifies the fundamental principles of actuation mechanisms and defines key parameters to address the size
Alejandro Palacios +4 more
wiley +1 more source
Advanced Intelligent Systems, EarlyView.The polymerase chain reaction (PCR).Perturbation Theory and Machine Learning framework integrates perturbation theory and machine learning to classify genetic sequences, distinguishing ancient DNA from modern controls and predicting tree health from soil metagenomic data.
Jose L. Rodriguez +19 more
wiley +1 more source
AI-Based 3D Modeling Strategies for Civil Infrastructure: Quantitative Assessment of NeRF and Photogrammetry. [PDF]
Sensors (Basel)Atencio E +4 more
europepmc +1 more source
Rewiring Droplet Interface Synapses
Advanced Intelligent Systems, EarlyView.Droplet interface synapses are used to create a neuromorphic network. Voltage pulses draw the droplets into contact and enable rewiring of the network through electrowetting. Results show that the heterogeneous droplet compositions and pore‐forming molecules may be used to tune the neuromorphic properties of the device using trapped charge as a form of
Sarita Shrestha, Eric Freeman
wiley +1 more source
Correction: Yuan et al. Machine Learning Prediction Models to Evaluate the Strength of Recycled Aggregate Concrete. <i>Materials</i> 2022, <i>15</i>, 2823. [PDF]
Materials (Basel)Yuan X +6 more
europepmc +1 more source
Advanced Intelligent Systems, EarlyView.ResearchConnect is an AI‐powered platform that automates researcher profiling, interdisciplinary team formation, and early‐stage research ideation. By extracting keywords from papers and web sources, it quickly clusters researchers into coherent teams and generates collaborative ideas using large language models. Validation on NSF‐funded projects shows
Akshay Vilas Jadhav +2 more
wiley +1 more source
Molecule by Molecule Characterization of a Polymer Molecular Mass Distribution via Mass Photometry
Angewandte Chemie, EarlyView.Mass photometry (MP) was utilized to achieve label‐free, molecule‐by‐molecule measurement of the full polymer molecular mass distribution (MMD) of a synthetic polymer without the need for sample fractionation. The ability to elucidate the full MMD in minutes, as opposed to having only specific moments of the MMD acquired in hours via chromatography ...
Rachel Czerwinski +5 more
wiley +2 more sources
Correction: Castro-Muñoz et al. Merging Proline:Xylitol Eutectic Solvent in Crosslinked Chitosan Pervaporation Membranes for Enhanced Water Permeation in Dehydrating Ethanol. <i>Membranes</i> 2023, <i>13</i>, 451. [PDF]
Membranes (Basel)Castro-Muñoz R +2 more
europepmc +1 more source