G. Myklebust, Norwegian Inst. of Technol., Trondheim, Norway
J.G. Solheim, Norwegian Inst. of Technol., Trondheim, Norway
E. Steen, Norwegian Inst. of Technol., Trondheim, Norway
Abstract: We present the results of parallel implementations of Kohonen's self-organizing maps using data partitioning. Two algorithms are implemented, a pure data partitioning algorithm and a combined data- and network-partitioning algorithm. The performance of the algorithms is far better for small neural networks than the performance of our previous SOM implementations. The SOM model can be used for visualization of MR images, an application with a small number of neurons. Using one of the proposed algorithms, the performance of this application is increased by over 200%. The convergence rate of the proposed algorithm and the original algorithm is shown to be similar when the frequency of the weight update is properly selected.
Index Terms:
medical image processing; self-organising feature maps; data visualisation; biomedical NMR; convergence; Kohonen's self organizing maps; data partitioning; visualization; multispectral medical images; parallel implementation; network partitioning algorithm; performance; small neural networks; MR images; convergence rate; weight update
Citation:
G. Myklebust, J.G. Solheim, E. Steen, "Speeding Up Small Sized Self Organizing Maps for Use in Visualization of Multispectral Medical Images," cbms, pp.0103, Eighth IEEE Symposium on Computer-Based Medical Systems (CBMS'95), 1995
PURCHASE ARTICLE: $19
IEEE Xplore Subscribers
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb