Antenna Calculation and Autotuning Tool (AntennaCAT)
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 Release Schedule on the main project README for the immediate feature release plans.
For long-term development, feature documentation, how-to guides, and all other information,
refer to the official AntennaCAT Wiki.
Less formal information, discussion, and planning happens with the #antennacat tag .
This is the public sample of some basic encryption methods, their decryption, and an overview of cryptography. The repository includes
demos and references for further reading. It is the public half of an interactive unit on encryption being developed for an undergraduate elective
course. The full unit includes PPT slides, other Python examples, and several group assignments.
An educational sample for selecting tools and methods to get started with reverse engineering. This is the public half of the documentation
used in an undergraduate elective course. This repository provides some general methodology and a lot of references for how to get started with
reverse engineering. It is for educational use only, so (code) examples included in this repository will be focused on tool usage only.
This repository also appears below in 'Conference Projects with Code', 2024-URSI-NRSM-1265. It is a 5-part series on how to approach the analysis
of data collected from antenna design simulation. A ~30k multi-dimensional data sample is provided in the repository.
This repository features several examples of processing live video feed for point tracking and depth estimation. It uses a USB camera with dual lenses.
This is being developed into a series of examples and tutorials for a basic computer vision unit for an undergraduate course.
The tinySA device line is a series of handheld spectrum analyzers (with some generation capability). This is an unofficial, non-GUI Python API designed
to make serial interfacing a little easier. The repository uses official resources and documentation but is NOT endorsed by the official tinySA product or company.
The python package is available at https://pypi.org/project/tsapython/
This is an unofficial, non-GUI Python API designed to make serial interfacing a little easier. It is still under development and testing.
The repository uses official resources and documentation but is NOT endorsed by the official NanoVNA product or company.
This on-going collection of objective functions pulled from popular literature for testing optimizers has 60+ objective functions with
documented solution space, decision space, and objective space with Pareto Front. See README for citations.
State-Machine Based Optimizer Collection
This is an on-going collection of optimizers that integrate with the AntennaCAT project. Some are serious, some are not.
Base Optimizer:sweep_python Alternate Version: alternates in base repo
Quantum-Inspired Optimizer: N/A
Surrogate Model Version: N/A
Base Optimizer:bayesian optimization_python Alternate Version: N/A
Quantum-Inspired Optimizer: N/A
Surrogate Model Version: interchangeable surrogate model approximators included in base repo
Base Optimizer:multi_glods_python Alternate Version: N/A
Quantum-Inspired Optimizer: N/A
Surrogate Model Version: N/A
USNC-URSI 2025 NRSM Paper #1237 . Repository for code and demo featured in "Reinforcement Learning Controlled Mechanically Reconfigurable Antennas" presented at the 2025 United States National Committee of URSI National Radio Science Meeting (USNC-URSI NRSM), Boulder, CO, USA.
Repository will be updated pending publication release + with some additional tutorial material as suggested at the conference. NOTE: there have been some official hardware and firmware updates of the equipment used, so this repo is private until a rework can be done.
The Repository hosting data and select machine learning examples from the paper "Machine Learning Assisted Hyperparameter Tuning for Optimization"
presented in IEEE AP-S 2024 in Florence, Italy, July 14-19, 2024.
The Repository hosting data and select examples from the paper "Machine Learning Assisted Optimization Methods for Automated Antenna Design"
presented at the 2024 United States National Committee of URSI National Radio Science Meeting (USNC-URSI NRSM), Boulder, CO, USA., 2024.
