Polymer characterization with a fuzzy classification algorithm
1994

Fuzzy Classification Algorithm for Polymer Characterization

publication Evidence: moderate

Author Information

Author(s): D. J. Ramsbottom, M. J. Adams, J. Carroll

Primary Institution: School of Applied Sciences, University of Wolverhampton

Hypothesis

Can a fuzzy c-means clustering algorithm effectively classify polymer samples based on their infra-red spectra?

Conclusion

The fuzzy c-means algorithm can classify polymer samples effectively, providing meaningful clustering without the limitations of traditional binary classification.

Supporting Evidence

  • The fuzzy c-means algorithm allows for classification of polymer samples that may consist of multiple components.
  • Principal component analysis showed that the first three components accounted for over 91% of the variance in the spectral data.
  • The method can classify unknown samples by comparing them to known data.
  • Fuzzy clustering allows for membership in multiple clusters, unlike traditional methods.

Takeaway

This study shows that a special computer program can help sort different types of plastic by looking at their unique light patterns.

Methodology

The study used a fuzzy c-means clustering algorithm to analyze infra-red spectra of polymer samples.

Limitations

The study's results may be subjective as interpreting clusters can vary based on user selection.

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication