Self-Organizing Maps
International Journal of Remote Sensing
Clustering and visualizing SOM results
IDEAL'10 Proceedings of the 11th international conference on Intelligent data engineering and automated learning
Clustering of the self-organizing map
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
In pharmaceutical technology the study of rheological behavior of powders is an important step in pre formulation of solid dosage forms. These studies, particularly the flow behavior of powders, is an exhausting and very time consuming task, which requires tools that render this process faster while maintaining accuracy. The self-organizing map (SOM) is tool in the exploratory phase of data mining. It projects data from input space to low-dimensional regular grid which may be effectively utilized to visualize and explore properties of the data. This paper applies self-organizing map and K-means in order to analyze rheological characteristics of pharmaceutical solid excipients and their binary mixtures e.q. attapulgite, a natural clay candidate to solid excipient. Self-organizing map was able to classify effectively the excipients in ordered and coherent groups and classified attapulgite as a characteristic grouping having properties far distinct from the other groups of excipients. SOM enabled a reduction of experiments via exploratory data analysis about the rheological behavior of these powders.