Product/Service

Unscrambler® X Hierarchical Model Development Module & Engine

Improve modeling of complex data with powerful Hierarchical Modeling software. Our new software uses a powerful decision-tree approach which makes modeling of non-linear data more efficient and robust, by allowing Classification and Prediction models to be joined in a multi-level structure.

Introducing the Unscrambler® X Hierarchical Model Development Module & Engine

Improve modeling of complex data with powerful Hierarchical Modeling software. Our new software uses a powerful decision-tree approach which makes modeling of non-linear data more efficient and robust, by allowing Classification and Prediction models to be joined in a multi-level structure.

We have two new tools available:

The Hierarchical Model Development Module
This software is a plug-in to The Unscrambler® X software. It is used to develop hierarchical models and can be used for off-line data analysis.
 
The Hierarchical Model Engine
This software is designed for end-users to apply hierarchical models in real-time by integrating them into spectrometers or CAMO´s Process Pulse software.

What is a hierarchical model?
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.

Applications of Hierarchical Models
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
  • Optimizing workflows for routine at-line analysis applications
The software is 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.

Key features

  • Multivariate Projection methods (PCA, PCR, PLSR)
  • Multivariate Classification methods (SIMCA, LDA, SVM)
  • Multivariate Regression methods (MLR, PCR, PLSR)
  • 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

Hierarchical models allow a number of multivariate models to be joined using logic statements in order to arrive at a single, unique result. Most of the powerful classification, prediction or projection methods in The Unscrambler® X can be used as the building blocks.

  1. The hierarchical model is built in a top-down manner, with a global model in level 1
  2. Conditional statements about the outcome at one level define the actions to be taken on the next level
  3. Outcomes such as classification, prediction, deviation, leverage, etc. can be tested
  4. Up to 10 levels can be defined
  5. Events and alarms are set up to highlight suspect samples or stop the hierarchy