For more information on current projects and step-by-step tutorials, visit my main project page
Publications and research can be found on my Google Scholar and ResearchGate pages
Interested in collaboration? Reach out to me on LinkedIn!
Repositories are grouped together by topic, so expect some duplicate links. See individual repositories for a list of associated sources (papers, libraries, repositories), and associated publications.
- Ongoing Projects
- AntennaCAT
- Optimizers and Surrogate Models
- Objective Function Benchmark Suite
- AntennaCalculator
- Papers with Repositories and Tutorials
- Machine Learning
- GUI Examples
- Licensing
- Publications
- FAQs
Primary ongoing projects:
-
The AntennaCalculationAutotuningTool, "AntennaCAT", is an ongoing open-source project to make antenna design easier by automating the design, calculation, scripting, and tuning of antennas created in several common simulation software. It is designed to be compatible with Ansys HFSS, Altair Feko, Simuleon CST, COMSOL Multiphysics, and EMPIRE. This project is currently in a private repository and will be released pending publication. If you are interested in collaboration, reach out to me on LinkedIn
-
Collaborative effort forked from Dollarhyde's, the Antenna Calculator is the internal calculator for common topologies in the AntennaCAT project. Designs are being updated as they're tested/validated.
Antenna Calculation and Autotuning (AntennaCAT) is a comprehensive implementation of machine learning to automate, evaluate, and optimize the antenna design process using EM simulation software. It utilizes a combined antenna designer and internal calculator to accelerate the CAD construction and EM simulation of several common topologies, while eliminating model disparity for automated data collection.
See the following sections:
-
L. Linkous, (LC-Linkous) (2022) AntennaCAT (Version 3.0) [source code] https://github.com/LC-Linkous/AntennaCalculationAutotuningTool
- The AntennaCAT repository linked in papers prior to 2024
- The repo is public, but code will not be public until Fall/Winter 2024
-
L. Linkous, (LC-Linkous) (2022) GeneticCAT (Version 3.0) [source code] https://github.com/LC-Linkous/GeneticCAT
- Link TBA
-
L. Linkous, “Machine Learning Assisted Optimization for Calculation and Automated Tuning of Antennas,” VCU Scholars Compass, 2024. https://scholarscompass.vcu.edu/etd/7841/ (accessed Oct. 21, 2024).
-
L. Linkous, J. Lundquist, M. Suche and E. Topsakal, "Machine Learning Assisted Hyperparameter Tuning for Optimization," 2024 IEEE INC-USNC-URSI Radio Science Meeting (Joint with AP-S Symposium), Florence, Italy, 2024, pp. 107-108, doi: 10.23919/INC-USNC-URSI61303.2024.10632482.
-
L. Linkous and E. Topsakal, "Machine Learning Assisted Optimization Methods for Automated Antenna Design," 2024 United States National Committee of URSI National Radio Science Meeting (USNC-URSI NRSM), Boulder, CO, USA, 2024, pp. 377-378, doi: 10.23919/USNC-URSINRSM60317.2024.10464597. [Online:] https://ieeexplore.ieee.org/abstract/document/10464597
-
L. Linkous, J. Lundquist and E. Topsakal, "AntennaCAT: Automated Antenna Design and Tuning Tool," 2023 IEEE USNC-URSI Radio Science Meeting (Joint with AP-S Symposium), Portland, OR, USA, 2023, pp. 89-90, doi: 10.23919/USNC-URSI54200.2023.10289238. [Online:] https://ieeexplore.ieee.org/abstract/document/10289238
-
E. Karincic, E. Topsakal, and L. Linkous. "Patch Antenna Calculations and Fabrication Made Simple for Cyber Security Research," 2023 ASEE Annual Conference & Exposition, Baltimore , Maryland, 2023, June. ASEE Conferences, 2023. [Online:] https://peer.asee.org/43974
-
L. Linkous, E. Karincic, J. Lundquist and E. Topsakal, "Automated Antenna Calculation, Design and Tuning Tool for HFSS," 2023 United States National Committee of URSI National Radio Science Meeting (USNC-URSI NRSM), Boulder, CO, USA, 2023, pp. 229-230, doi: 10.23919/USNC-URSINRSM57470.2023.10043119. [Online:] https://ieeexplore.ieee.org/abstract/document/10043119
The following are a collection of state-machine-based optimizers compatible with the AntennaCAT project. Most, if not all, have been integrated into the main AntennaCAT project. These optimizers are functional stand alone for testing and publication transparency. Some have been incorporated into other research projects or publications, which are noted on the individual README pages.
All optimizers and surrogate model examples work on state machine logic in order to incorporate substituting simulation for the objective functions in AntennaCAT.
Summary of Optimizers
Base Optimizer | Alternate version | Quantum-Inspired Optimizer |
---|---|---|
pso_python | pso_basic | pso_quantum |
cat_swarm_python | sand_cat_python | cat_swarm_quantum |
chicken_swarm_python | - | chicken_swarm_quantum |
sweep_python | *alternates in base repo | - |
bayesian optimization_python | *interchangable surrogate models included in base repo |
- |
multi_glods_python | - | - |
Summary of Surrogate Models
Objective Functions
The Objective Function Test Suite used to generate training data will be public Fall 2024
-
J. Lundquist, L. Linkous (2024) pso_python (Version 1.0) [source code] https://github.com/jonathan46000/pso_python
- pso_python by jonathan46000
- the main branch with the adaptive timestep PSO optimizer by jonathan46000
- the pso_basic branch without the timestep, for a baseline comparison by LC-Linkous
- LC-Linkous' development fork
-
L. Linkous, J. Lundquist (2024) sweep_python (Version 1.0) [source code] (https://github.com/LC-Linkous/sweep_python)
- sweep by LC-Linkous, a basic sweep optimization example compatible with AntennaCAT. Features grid search and random search.
-
L. Linkous, J. Lundquist (2024) cat_swarm_python (Version 1.0) [source code] (https://github.com/LC-Linkous/cat_swarm_python)
- cat_swarm_python by LC-Linkous,
- the main branch with traditional cat swarm optimizer by LC-Linkous
- the sand cat swarm branch by LC-Linkous
- the quantum inspired cat swarm branch with a numpy-based quantum inspired (probabilistic) approach by LC-Linkous
-
L. Linkous, J. Lundquist (2024) chicken_swarm_python (Version 1.0) [source code] (https://github.com/LC-Linkous/chicken_swarm_python)
- chicken_swarm_python by LC-Linkous
- the main branch with traditional chicken swarm optimizer by LC-Linkous
- the chicken_swarm_quantum branch with a very simple, numpy-based quantum inspired approach by LC-Linkous
-
J. Lundquist, L. Linkous (2023) multi_glods_python (Version 1.0) [source code] https://github.com/jonathan46000/multi_glods_python
- multi_glods_python by jonathan46000
- The main branch and fork are now compatible with AntennaCAT
-
L. Linkous, (LC-Linkous) (2024) Objective Function Suite (Version 1.0) https://github.com/LC-Linkous/objective_function_suite
- Objective Function Test Suite
- 50+ single, multi, and constrained objective functions compatible with the optimizer collection
This repository contains a comprehensive benchmarking framework for evaluating the performance of various optimizers in hyperparameter tuning tasks, and the ability to collect data on optimizer performance for machine learning tasks. Additional objective functions updated periodically.
It contains:
- Objective Function Library: is a collection of 50+ single objective functions, multi objective functions, and constrained objective functions formatted with work with the optimizer collection in the [Optimizers and Surrogate Models](#Optimizers and Surrogate Models) section
- Optimizer Suite: The optimizers included in this project are static versions of the optimizers integrated into the AntennaCAT software suite.
- Optimizer Performance Data Collection: Scripts for replicating the data collection method used to develop the AntennaCAT project.
- L. Linkous, (LC-Linkous) (2024) Objective Function Suite (Version 1.0) https://github.com/LC-Linkous/objective_function_suite
- Objective Function Test Suite
- Contains the objective function library, a static version of the optimizer suite (for compatibility), and scripts used in data collection.
- L. Linkous, J. Lundquist, M. Suche, and E. Topsakal, "Machine Learning Assisted Hyperparameter Tuning for Optimization," 2024 IEEE USNC-URSI Radio Science Meeting (Joint with AP-S Symposium), Florence, Italy, 2024 (TO BE PRESENTED JULY 2024) [Online:] LINK TO BE ADDED
Calculated and Previewed Microstrip Rectangular Patch Antenna
A forked GUI branch of Dollarhyde's CLI-based AntennaCalculator. This branch is a simplified version of how the AntennaCalculator is integrated into LC-Linkous' AntennaCAT project. It features some matplotlib-based graphics to help visualize the antenna topologies based on user inputs.
The calculator features the following topologies:
- Rectangular patch antenna, probe and microstrip versions
- Quarter Wave Monopole
- Half Wave Dipole
- E. Karincic, (Dollarhyde) (2022) Antenna Calculator (Version 2.0) [source code]. https://github.com/Dollarhyde/AntennaCalculator
- Antenna Calculator by Dollarhyde
- The original, command-line based AntennaCalculator
- The python-based GUI wrapper of the AntennaCalculator
- LC-Linkous' development fork
- E. Karincic, E. Topsakal, and L. Linkous. "Patch Antenna Calculations and Fabrication Made Simple for Cyber Security Research," 2023 ASEE Annual Conference & Exposition, Baltimore , Maryland, 2023, June. ASEE Conferences, 2023. [Online:] https://peer.asee.org/43974
Paper:
L. Linkous, J. Lundquist, M. Suche, and E. Topsakal, "Machine Learning Assisted Hyperparameter Tuning for Optimization," 2024 IEEE USNC-URSI Radio Science Meeting (Joint with AP-S Symposium), Florence, Italy, 2024 (TO BE PRESENTED JULY 2024) [Online:] LINK TO BE ADDED
Repository:
-
L. Linkous (LC-Linkous) (2023) PSO_datacollection (Version 1.0) [source code]. https://github.com/LC-Linkous/PSO_datacollection
- Antenna Calculator by LC-Linkous
- This is the original repository linked in publication, but it has since been renamed as other presentations have been added
-
L. Linkous (LC-Linkous) (2023) 2024-APS-URSI-3323 (Version 2.0) [source code]. https://github.com/LC-Linkous/2024-APS-URSI-3323
- 2024-APS-URSI-3323 by LC-Linkous
- Repository hosting data and select machine learning examples from publication ["Machine Learning Assisted Hyperparameter Tuning for Optimization"]
Paper:
L. Linkous and E. Topsakal, "Machine Learning Assisted Optimization Methods for Automated Antenna Design," 2024 United States National Committee of URSI National Radio Science Meeting (USNC-URSI NRSM), Boulder, CO, USA, 2024, pp. 377-378, doi: 10.23919/USNC-URSINRSM60317.2024.10464597. [Online:] https://ieeexplore.ieee.org/abstract/document/10464597
Repository:
- L. Linkous (LC-Linkous) (2023) 2024-URSI-NRSM-1265 (Version 1.0) [source code]. https://github.com/LC-Linkous/2024-URSI-NRSM-1265
- 2024-URSI-NRSM-1265 by LC-Linkous
- Repository for publication "Machine Learning Assisted Optimization Methods for Automated Antenna Design"
- Features 5 tutorials using Jupyter Notebook to process and analyze a subset of simulation data for patch antennas
Paper:
E. Karincic, E. Topsakal, and L. Linkous. "Patch Antenna Calculations and Fabrication Made Simple for Cyber Security Research," 2023 ASEE Annual Conference & Exposition, Baltimore , Maryland, 2023, June. ASEE Conferences, 2023. [Online:] https://peer.asee.org/43974
Repository:
- E. Karincic, (Dollarhyde) (2022) Antenna Calculator (Version 2.0) [source code]. https://github.com/Dollarhyde/AntennaCalculator
- Antenna Calculator by Dollarhyde
- The original, command-line based AntennaCalculator
- The python-based GUI wrapper of the AntennaCalculator
- LC-Linkous' development fork
-
A TK GUI example of realtime plotting. Mentioned previously on an old project blog, the page will be reposted.
-
A WXPython GUI example of realtime plotting. Mentioned previously on an old project blog, the page will be reposted.
The source code linked in this documentation has been released under a variety of licenses, some as requested from their original source publication, so refer to the individual READMEs of each project (and the LICENSE file) for the most accurate information.
-
L. Linkous, J. Lundquist, M. Suche, and E. Topsakal, "Machine Learning Assisted Hyperparameter Tuning for Optimization," 2024 IEEE USNC-URSI Radio Science Meeting (Joint with AP-S Symposium), Florence, Italy, 2024 (TO BE PRESENTED JULY 2024) [Online:] LINK TO BE ADDED
-
L. Linkous and E. Topsakal, "Machine Learning Assisted Optimization Methods for Automated Antenna Design," 2024 United States National Committee of URSI National Radio Science Meeting (USNC-URSI NRSM), Boulder, CO, USA, 2024, pp. 377-378, doi: 10.23919/USNC-URSINRSM60317.2024.10464597. [Online:] https://ieeexplore.ieee.org/abstract/document/10464597
-
L. Linkous, J. Lundquist and E. Topsakal, "AntennaCAT: Automated Antenna Design and Tuning Tool," 2023 IEEE USNC-URSI Radio Science Meeting (Joint with AP-S Symposium), Portland, OR, USA, 2023, pp. 89-90, doi: 10.23919/USNC-URSI54200.2023.10289238. [Online:] https://ieeexplore.ieee.org/abstract/document/10289238
-
E. Karincic, E. Topsakal, and L. Linkous. "Patch Antenna Calculations and Fabrication Made Simple for Cyber Security Research," 2023 ASEE Annual Conference & Exposition, Baltimore , Maryland, 2023, June. ASEE Conferences, 2023. [Online:] https://peer.asee.org/43974
-
L. Linkous, E. Karincic, J. Lundquist and E. Topsakal, "Automated Antenna Calculation, Design and Tuning Tool for HFSS," 2023 United States National Committee of URSI National Radio Science Meeting (USNC-URSI NRSM), Boulder, CO, USA, 2023, pp. 229-230, doi: 10.23919/USNC-URSINRSM57470.2023.10043119. [Online:] https://ieeexplore.ieee.org/abstract/document/10043119
Roughly Fall/Winter 2024. The AntennaCAT project is my PhD dissertation. Related code (such as the optimizers and sample data/tutorials) are being released periodically, but the main AntennaCAT software suite will be released after my dissertation defense.
e.g., these: L. Linkous, (LC-Linkous) (2022) AntennaCAT (Version 3.0) [source code] https://github.com/LC-Linkous/AntennaCalculationAutotuningTool
They're in IEEE format. I'm lazy and ctrl+C ctrl+V these into my references when I'm writing a paper.
e.g, others.
Let me know and I'll update them. Some repos have been renamed, or code moved, as projects have evolved to keep things readable. I try my best to update all the links, but occasionally miss one.
Yes. Soemtiems I can even ues it.