April 5, 2016

pSeven 6.6 Release

DATADVANCE development team is pleased to announce the release of pSeven 6.6, the most complete design space exploration platform up to date, for every expertise.

The newest release of pSeven is more feature-packed than ever, and is far superior even to the previous versions of pSeven in terms of capabilities it brings for every expertise. pSeven 6.6 introduces the interactive Predictive Modeling Toolkit, built on top of the powerful MACROS algorithmic core and tightly integrated into the Analyze mode, as well as a variety of long-expected feature updates and improvements, further increasing pSeven's performance, stability, and ease of use.

Predictive Modeling Toolkit, the latest addition to pSeven's wide range of data analysis and post-processing tools available in the Analyze mode, is a set of interactive tools that enables thorough data analysis, approximation model training, model validation and evaluation with high accuracy and less effort.

What makes predictive modeling and data analysis in pSeven easily available for every expertise?

  • Use all data sources you want: get your data from Excel using the updated and improved Excel import tool, read it from text files of virtually any tabular format, or load it from your pSeven project database.
  • Train your models with a click of a button! With the new SmartSelection technology implemented in the Predictive Modeling Toolkit, pSeven automatically selects the best training method and adjusts its parameters in order to train the most accurate model.
  • State-of-the-art modeling algorithms allow you to add a priori knowledge an subjective information to your data - a feature unique to pSeven. For example, you can set noise levels for data samples, or assign higher weights to important or more accurate sample points.
  • Fine-tune model builder settings: advanced users will love the amount of settings provided in the Model Builder. If you want to direct the modeling process your way, pSeven gives steering to you! Not sure where to go next? The SmartSelection technology will be your co-pilot!
  • Validate your models in a clean and intuitive way using the Model Validator tool to visualize model accuracy metrics.
  • Evaluate a model you have trained and view the results immediately, thanks to the tight integration of the Predictive Modeling Toolkit and other pSeven's data analysis tools, or add this model to a pSeven workflow automating mass calculations.
  • If you are a multitasker, pSeven is too: train multiple models, validate and evaluate them in parallel, all in the convenient multifunctional pSeven's Analyze interface.
  • Your models are yours to use wherever you want: export model code to MATLAB or C, compile it to a DLL and call it from Excel spreadsheets.
  • Automate everything you wish, even model training and export: pSeven supports approximation workflows thanks to the std.ApproxBuilder block. In pSeven 6.6 std.ApproxBuilder also received significant updates and now supports all features available in the Predictive Modeling Toolkit, including the support for incremental model training, data sample weighting and processing noisy data.

As well as all previous releases, pSeven 6.6 is aimed for higher flexibility and a wider feature set while staying backwards compatible - both in terms of program compatibility and continuing support of data analysis, optimization, and process integration methods.

  • pSeven 6.6 includes an updated robust optimization algorithm for problems that include computationally expensive objectives. Efficiency of the new method is based on more intense use of modeling capabilities, which allows optimizer to reduce the required number of objective function evaluations.
  • Updated PTC Creo integration block provides full support for integration with PTC Creo 3.0.
  • Updated SolidWorks integration block with improved error handling and higher stability.
  • Updated Python integration block with simplified import of third-party Python modules, further increasing pSeven's capabilities for scientific computing.

pSeven 6.6 also includes numerous bugfixes and stability improvements. For a detailed list of updates, please see the release changelog. You can also contact us to receive more information and pSeven updates!

LinkedIn
VK