ProgramMaster Logo
Conference Tools for 2020 TMS Annual Meeting & Exhibition
Login
Register as a New User
Help
Submit An Abstract
Propose A Symposium
Presenter/Author Tools
Organizer/Editor Tools
About this Abstract
Meeting 2020 TMS Annual Meeting & Exhibition
Symposium Algorithm Development in Materials Science and Engineering
Presentation Title Machine Learning and Computer Vision on Classification of Carbon Nanotube and Nanofiber Structures for TEM Dataset
Author(s) Qixiang Luo, Elizabeth A. Holm, Chen Wang
On-Site Speaker (Planned) Qixiang Luo
Abstract Scope We introduce a convolutional neural networks (CNNs) based machine learning and computer vision method to classify CNTs/CNFs and other airborne particles from a TEM image dataset. The model starts with a transfer learning pipeline achieved by hypercolumn extractions on CNN fully-connected layers from both precise edges at shallow and abstract semantics at deep, followed by K-means visual dictionary for creating feature clusters. It then uses VLAD encoder to mitigate the ambiguity between feature clusters and local feature descriptors based on image retrieval, with boosting step for classifiers. The unsupervised t-SNE method was used to visualize classification performance for data cluster analysis. The method achieves 85% accuracy on full dataset and over 90% on pure nano-carbon dataset for 5-fold cross-validation. We also discuss image pre-processing with data augmentation techniques for imbalanced dataset and hierarchical recognition, to utilize a tree-like learning structure to explore attributes from generalized to specific.
Proceedings Inclusion? Planned: Supplemental Proceedings volume

OTHER PAPERS PLANNED FOR THIS SYMPOSIUM

A First Principles Multi-Cell Monte Carlo Method for Phase Prediction
A machine learning platform for the accelerated emulation of quantum mechanical computations
A multi-GPU implementation of a full-field crystal plasticity solver for efficient modeling of high-resolution microstructures
A new phase-field model with anisotropic interface width for the highly anisotropic growth of ice dendrites
A self-consistent parametric homogenization framework for fatigue in Ni-based superalloys
Advances in a phase field dislocation dynamics model to account for various gamma-surfaces of hexagonal close packed crystallography
Advancing Methods for Atomic-Scale Modeling of Heterogeneous Systems
An Active Learning Approach for the generation of force fields from DFT calculations
An atomistic framework to understand solute grain boundary segregation in a polycrystal
An improved collocation method to treat traction-free surfaces in dislocation dynamics simulations
Applying Machine Learning to Identifying Packing Defects in Amorphous Materials
Boosting the CALPHAD modeling of multi-component systems by ab initio calculations: selected case studies
Bridging the electronic, atomistic and mesoscopic scales using machine learning
Calibrating Strength Model Parameters Using Multiple Types of Data
Charting Spaces of Materials Properties
Classifying Atomic Environments by the Gromov-Wasserstein Distance
Compressive Stress-Strain curve by Simulation for Additive Manufactured Ti6Al4V Cuboctahedron Cellular Structure
Coupled Light Capture and Lattice Boltzmann Model of TiO2 Micropillars Array for Water Purification
Designing High-strength Carbon-nanotube Polymer Composites Using Machine Learning Algorithms Integrated with Molecular Dynamics Simulations
Development and validation of interatomic potential for tantalum using physically-informed artificial neural networks
Development of a Modified Embedded-Atom Method Interatomic Potential for 2D Titanium Carbides (Tin+1Cn) MXenes
Development of an Evolutionary Deep Neural Net for Materials Research
Development of Virtual Resonant Ultrasound Spectroscopy Methods for use in Quantifying Defect Content
Direct consideration of vacancies in CALPHAD modelling of zirconium carbide
Finite element simulations of grain growth with arbitrary grain boundary energy
Functional uncertainty propagation with Bayesian ensembles in molecular dynamics
Generative deep neural networks for inverse materials design using backpropagation and adaptive learning
Hierarchical Integration of Atomistically-Derived Dislocation Mobility Laws into Discrete Dislocation Dynamics Simulations
High-throughput computational design of organic-inorganic hybrid halide semiconductors beyond perovskites
Interatomic potentials as physically-informed artificial neural networks
Inverse solutions based on reduced-order process-structure-property linkages using Markov chain Monte Carlo sampling algorithms
Investigation of Fe-O and Fe-N and H-O Bond formation Process by the Molecular Dynamics Simulations
Isolated Dislocation Core Energy from First Principles Energy Density Method
Large Scale 3D Phase-Field Sintering Simulations
Machine-Learned Interatomic Potentials For Alloy Modeling and Phase Diagrams
Machine Learning and Computer Vision on Classification of Carbon Nanotube and Nanofiber Structures for TEM Dataset
Machine Learning Approaches for Improving Density Functional Tight Binding Models of Reactive Materials: Application to Astrobiolgical Materials and Surface Chemistry
Machine learning driven functionally graded material designs for mitigation of thermally induced stress
Machine Learning Exploration and Optimization of Flame Spray Pyrolysis
Material parameters identification, modeling and experimental verification of the new smart material Vacuum Packed Particles
MEAM-BO: extension of MEAM to include bond order for polymer
Methods to simulate grain boundary diffusion in bicrystals and polycrystals
Microstructure image analysis using deep convolutional neural networks
Microstructure reconstruction of additive manufactured metallic materials with Markov random fields
Modeling Yield Point Phenomenon Using a Modified Mechanical Threshold Stress Model
Molecular simulations you can trust and reproduce: The OpenKIM framework
Monte Carlo studies of EBSPs spectroscopy
Monte Carlo Study of Paired-Spin Kagome Artificial Spin Ice Lattices
Multi-scale Modeling of Solidification Microstructure during Powder Bed Fusion
Multi-scale modelling of coarsening process in the Ag-Cu alloy
New workflow for high-throughput feature extraction of deforming open cell foams
Nudged Elastic Band Method for solid-solid Transition Under Finite Deformation
Numerical Simulation for Microstructural Evolution in Solidification Process Using CFD-CA (Cellular Automata) Coupled Method
Persistent homology: Unveiling the topological features in materials data
Phase field modeling of microstructure evolution during selective laser sintering and post aging
Physically-Motivated Requirements of Machine Learning Potentials
PRISMS-Plasticity: An open-source crystal plasticity finite element software
PyMob: Software for Automated Assessment of Atomic Mobilities
Quasiparticle approach to study solute segregation at tilt grain boundaries in bcc iron.
Randomness at scale: Properties of bulk nanostructured materials from stochastic representative volume elements
Real-time analysis of diffraction data for enabling in-situ measurements
Recent Interatomic Potential Development Activities at Sandia
Reduced-order atomistic method for simulating radiation effects in metals
Relating 2D experimental information to 3D simulations using surface structure conserving 3D microstructure generation
Robust and accurate self-consistent homogenization of elasto-viscoplastic polycrystals
Scale Bridging from DFT to MD With Machine Learning
Second Nearest-Neighbor Modified Embedded-Atom Method Potential: Development, Validation and Challenges
The ReaxFF force field- application overview and new directions in accelerated dynamics, ferroelectric materials and treatment of explicit electrons.
Three-Dimensional Modeling of Growth and Motion of Dendrites Under Thermosolutal Convection
Uncertainty Propagation in CalPhaD Calculations
Uncertainty quantification for machine learning methods applied to material properties
Unraveling Exciton Dynamics in 2D Van der Waals Heterostructures
“Sintering” models and measurements: data assimilation for microstructure prediction of nylon component SLS additive manufacturing

Questions about ProgramMaster? Contact programming@programmaster.org