Data Import
Data Grid Exploration
Advanced Data Plotting
Model Training
Model Selection Helper
Model Analysis
Data Import
Easily import datasets directly from your PC with a single click. Our toolbox is compatible with widely-used formats like Excel and CSV, capable of handling large datasets, including Excel files with multiple tabs for streamlined data integration.
Data Grid Exploration
Advanced Data Plotting
Intuitive Model Setup
Creating hybrid model is a breeze with our guided stepper, leading you through selecting datasets, model outputs, inputs, and neural network configurations
Model Customization and Tuning
After creation, dive into fine-tuning your model. Adjust configurations, equations, and datasets as needed.
Our Toolbox’s flexibility allows for comprehensive retraining and optimization of your models
Model Training
Train your models effortlessly. Just hit ‘start’, and our toolbox handles the complex calculations in multi-threaded mode (parallelization). Track the training progress with real-time statistics and updates on learning progress through fitting and prediction plots.
Model Selection
Leverage the model selection helper to chose which models are taken into the report section for further analysis. Manualy select the models to report according to your criteria, use the automated model preselection or a mix of both
Model Report and Analysis
Delve deeper into each report to uncover the subtleties of your models. Our platform enables plotting individual models or aggregated ones, offering average models and confidence intervals. Customize plots to suit your specific needs by simply interacting with the configuration menus (e.g., plot specific models with specific train and/or test datasets for only specific output variables) and seamlessly export them to Excel for external use
Model Export/Integration
Unlock the full potential of your machine learning models with our toolbox. Once you’ve perfected your model, it becomes entirely yours – free from royalties, ready to empower your projects or enhance third-party applications. Here’s how you can leverage your models to their fullest.
Effortlessly integrate your models with Novasign’s Digital Twin platform for advanced simulations and real-time analytics.
Dive into seamless integration with our freely accessible Novasign model API. Packaged as a Docker image, it offers HTTP REST calls for universal compatibility. With OPENAPI documentation, generating SDKs in many programming languages, including C#, Python, C++, JAVA, R, Ruby, RUST… is straightforward. We provide comprehensive guides and examples for utilizing the API across various platforms, such as C#, Python, and MATLAB, ensuring you have the tools to connect effortlessly.
# Path to ZIP file
zip_file_path = r"{Path}\ExportedHybridModel_06122023132554.zip"
# Read and encode ZIP file
with open(zip_file_path, "rb") as file:
file_bytes = file.read()
file_bytes_base64 = base64.b64encode(file_bytes).decode("utf-8")
# Instantiate Request
initate_request = InstantiateRequest(
file_bytes=file_bytes_base64,
file_name="ExportedHybridModel_06122023132554.zip",
friendly_name="My Hybrid Model",
description="My Hybrid Model Description")
# Instantiate
try:
instantiate_response = api_client.instantiate_post(instantiate_request=initate_request)
print(f"Instantiated instance: {instantiate_response.instance_id}")
except requests.exceptions.RequestException as e:
raise SystemExit(e)
% Path to ZIP file
zip_file_path = "{Path}\ExportedHybridModel_06122023132554.zip';
% Read and encode ZIP file
file = py.open(zip_file_path, 'rb');
file_bytes = file.read();
file.close();
file_bytes_base64 = py.base64.b64encode(file_bytes).decode('utf-8');
% Instantiate Request
initate_request = InstantiateRequest(pyargs(...
'file_bytes', file_bytes_base64, ...
'file_name', 'ExportedHybridModel_06122023132554.zip', ...
'friendly_name', 'My Hybrid Model', ...
'description', 'My Hybrid Model Description'));
% Instantiate
try
instantiate_response = api_client.instantiate_post(pyargs('instantiate_request', initate_request));
disp(['Instantiated instance: ', char(instantiate_response.instance_id)]);
catch e
disp(['Error: ', char(e.message)]);
end
Enhance your .NET applications by directly incorporating compiled .NET DLLs, enabling dynamic, on-the-fly integration with other .NET-based systems
