Hierarchical Modeling Software Offers Powerful Decision-tree Approach for Modeling Complex Data

Share Article

The software by CAMO makes modeling of non-linear data more efficient and robust, allowing Classification and Prediction models to be joined using multi-level modeling.

News Image
The Hierarchical Model Development Module is a plug-in to The Unscrambler® X software, used for off-line data analysis.

CAMO Software, leaders in multivariate data analysis solutions, today announced the release of two innovative new products: the Unscrambler® X Hierarchical Model Development Module, and the Unscrambler® X Hierarchical Model Engine for integration with scientific instruments such as spectrometers.

These products are designed for R&D, Production, Engineering and QA/QC environments where there is a need for developing and implementing run-time control models for process monitoring applications. It is suitable for use by production supervisors, quality assurance teams, Technical Services and control system designers.

When analyzing process or other complex data, it can be difficult to make a global prediction or classification model that predicts well in every area. Therefore, it is often necessary to refine models based on the output of initial investigations, which is usually done manually and in many steps, becoming a laborious and time-consuming process which is prone to error.

Hierarchical models join a number of multivariate models using logic statements in order to arrive at a single, unique result. This is the classic logic tree or decision tree approach, where the analysis in one step is guided by the previous step.

Hierarchical models are ideal for applications such as fermentation monitoring in biotech or food, gasoline blending in petroleum refining, reaction monitoring in chemical manufacturing, classifying and characterizing pharmaceutical raw materials or optimizing workflows for routine at-line analysis applications.

The Hierarchical Model Development Module is a plug-in to The Unscrambler® X software, used for off-line data analysis.

The Hierarchical Model Engine is designed for end-users to apply hierarchical models in real-time by integrating them into scientific instruments, and in the near-future, CAMO’s Process Pulse software. If required, further customization is available to integrate hierarchical models into control systems.

The software utilizes powerful multivariate analysis tools including Projection methods (PCA, PCR, PLSR), Classification methods (SIMCA, LDA, SVM) and Regression methods (MLR, PCR, PLSR). It accepts data in a wide range of formats, with advanced auto-pretreatment options. Alarms and warnings can be set with output in tabular format, including cell colours changing according to the alarm state, making it intuitive and easy to use for end-users.

How it works
The hierarchical model is built in a top-down manner, with a global model in level 1. Conditional statements about the outcome at one level define the actions to be taken on the next level, with the option to define up to 10 levels. Classification, prediction, deviation, leverage, Hotelling T2 and other important diagnostics are provided for making quality decisions. Events and alarms can be set up to highlight suspect samples or stop the hierarchy, and the results sent to a supervisory system for action.*

More information and a free 30-day trial of the Hierarchical Model Development Module is available at http://www.camo.com

Benefits at a glance

  •     Ideal for at-line process analysis, allowing non-normal situations to be identified and alarmed so that third-party control systems can make quality decisions*
  •     Only need to set up and validate a Hierarchical Model once, then it can be used as much as required, avoiding the time consuming process of manually developing multi-level models
  •     Once set up and validated, models can be applied across different sites and processes for use by non-experts, enabling efficient process management and technology transfer
  •     Useful if dealing with non-linear regression problems over large concentration ranges by giving a more precise analysis of the area in question
  •     Stepwise approach is ideal for complex classification problems such as raw material analysis

*may require customization

Share article on social media or email:

View article via:

Pdf Print

Contact Author

Nathan Bray
Camo
(+47) 223 963 00
Email >
Visit website