Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Regulation of organic anion transporting polypeptide 1B1 transport function by lysine deacetylase 6.

Molecular pharmacology·2026

Same author

Heat Stress in the Liver of Chicken: Insights from Keap1-Nrf2 Pathway Mediated Ferroptosis and Cuproptosis via the HO-1/FDX1/Gpx4 Axis.

Veterinary sciences·2026

Same author

The effect of press-needle therapy on postoperative nausea and vomiting in patients undergoing bronchoscopy under general anesthesia in China: a quasi-experimental study.

Frontiers in medicine·2026

Same author

Isobolographic Analysis of the Interaction Between Remimazolam and Etomidate in General Anesthesia Induction: A Prospective, Sequential Allocation Study Based on the Dixon Up-and-Down Method.

Drug design, development and therapy·2026

Same author

Bile Drainage Improves Survival in Amatoxin-induced Severe Liver Injury: A Prospective Pilot Cohort Study.

Journal of clinical and translational hepatology·2026

Same author

Formation and Characterization of (-)-Epigallocatechin Gallate-Caffeic Acid Adduct and Their Quantitative Changes during the Processing of Green Tea.

Journal of agricultural and food chemistry·2026

Same journal

Ultrasound-guided closed-loop control of magnetic hydrogel microrobots with adaptive gait switching.

Microsystems & nanoengineering·2026

Same journal

Hysteresis-aware MEMS neuromorphic networks for embedded sensing and computation.

Microsystems & nanoengineering·2026

Same journal

High-temperature electrical performance and interface adhesion performance of SiC-based Pt thin-film RTDs.

Microsystems & nanoengineering·2026

Same journal

From single cell analysis to 3D micro physiological systems: microfluidic tools integrating cancer cell targets for delineating natural killer cell biology.

Microsystems & nanoengineering·2026

Same journal

Active devices and systems for closed-loop neuromodulation.

Microsystems & nanoengineering·2026

Same journal

An automated, digital immunoassay on a microfluidic cartridge for on-demand cytokine profiling.

Microsystems & nanoengineering·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 30, 2025

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes

Published on: March 9, 2019

Deep learning for non-parameterized MEMS structural design.

Ruiqi Guo¹, Fanping Sui¹, Wei Yue¹

¹Department of Mechanical Engineering, University of California, Berkeley, CA 94720 USA.

Microsystems & Nanoengineering

|September 2, 2022

Summary

This summary is machine-generated.

Deep learning accelerates microelectromechanical systems (MEMS) design by rapidly predicting physical properties from geometric images. This data-driven approach significantly reduces simulation time for MEMS resonators, enabling faster development cycles.

Keywords:

Electrical and electronic engineering Engineering Materials science

More Related Videos

Design and Characterization Methodology for Efficient Wide Range Tunable MEMS Filters

Design and Characterization Methodology for Efficient Wide Range Tunable MEMS Filters

Published on: February 4, 2018

Fabrication of 3D Carbon Microelectromechanical Systems C-MEMS

Fabrication of 3D Carbon Microelectromechanical Systems C-MEMS

Published on: June 17, 2017

Related Experiment Videos

Last Updated: Aug 30, 2025

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes

Published on: March 9, 2019

Design and Characterization Methodology for Efficient Wide Range Tunable MEMS Filters

Design and Characterization Methodology for Efficient Wide Range Tunable MEMS Filters

Published on: February 4, 2018

Fabrication of 3D Carbon Microelectromechanical Systems C-MEMS

Fabrication of 3D Carbon Microelectromechanical Systems C-MEMS

Published on: June 17, 2017

Area of Science:

Engineering
Materials Science
Computer Science

Background:

Microelectromechanical systems (MEMS) device performance is highly sensitive to geometric design.
Traditional numerical simulations for MEMS design are time-consuming and resource-intensive.
Exploring numerous design variations is often impractical due to computational costs.

Purpose of the Study:

To develop a deep learning framework for accelerating the MEMS design cycle.
To enable rapid and accurate prediction of physical properties for diverse MEMS designs.
To reduce reliance on conventional, slow numerical simulation methods.

Main Methods:

Utilized deep neural networks (DNNs) trained on pixelated image representations of MEMS designs.
Employed a non-parameterized, topologically unconstrained approach for design representation.
Applied the DNN to predict modal frequency and quality factor of disk-shaped microscale resonators.

Main Results:

The DNN achieved high-speed prediction, being 4.6x10^3 times faster for frequency and 2.6x10^4 times faster for quality factor than finite element analysis.
Accuracies for predicted modal frequency and quality factor were 98.8% ± 1.6% and 96.8% ± 3.1%, respectively.
Up to 96.0% of computation time was saved when simultaneously predicting both properties, enabling rapid screening of thousands of designs.

Conclusions:

Deep learning offers a powerful tool to significantly accelerate MEMS design and optimization.
The proposed data-driven method facilitates experience-free structural designs for MEMS.
This approach enhances the efficiency of exploring design spaces for micro-devices.