Modeling Modeling Toolbox for bioprocesses

Unleash the power of advanced machine learning with our Hybrid Model Toolbox. This standalone application, effortlessly installable on your PC, revolutionizes how you create, train, and evaluate hybrid models.

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

Once imported, datasets are displayed in a responsive data grid, offering immediate insight into your data. The grid not only provides a comprehensive view but also highlights any import errors, allowing for quick rectification and analysis.

Advanced Data Plotting

Explore your data with our sophisticated plotting tools. Automatically split runs in a dataset, hide or highlight specific series, and plot variables against each other to uncover correlations. Our flexible plotting options include overlaying plots in the same figure, creating side-by-side figures, customizing axes and titles, plots with transparencies to compare overlayed figures, exporting in various formats

Run Splitting

When dataset contains multiple runs, splitting is provided out of the box, being able to visualize your runs as independent time series without pre-processing them.
Dynamic Selection

Select variable of interest with the simple selectors. Plot variables against time axis or other variables to explore visual correlations
Multiplot

Plot multiple times in the same active figure, overlaying plots within one.
Flexible Export Options

Export generated figures to PDF, SVG, PNG, C#, Text...
Customizable View

Setup figure axes, titles, legends, margins...

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

Integrative

Models that predict outcomes over time by integrating successive predictions, ideal for scenarios where continuous monitoring and forecasting are essential
Autoregressive

Models that use their previous outputs as inputs for future predictions, enhancing their forecasting accuracy, especially in time-dependent scenarios.
Mass Balances

Models capable of automatically adjusting for changes in mass or concentration due to additions or removals in a system, ensuring accurate mass conservation
Custom ANN

Flexible neural networks where you can tailor inputs, hidden layers, transfer functions, and even individual neuron connections, offering a high degree of control and customization
Bootstrapping

Models trained on various distributions of training, validation, and testing data sets, increasing robustness and reducing overfitting
Mechanistic

Models that combine the predictability of parametric models with the adaptability of non-parametric neural networks, suitable for applications needing both mechanistic understanding and predictive power

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.

No Resource Utilization

0%

Utilizing All Your Resources

0%

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.

Digital Twin
Robust API Connectivity
NET Ecosystem Integration

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.

Python
Matlab

				
					
# 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

Signup and Download!