In this paper, we provide a detailed empirical comparison of three neural-based classifiers used in embedded applications. The three techniques (multi-layer Perceptrons, radial basis function networks and adaptive fuzzy systems) are compared with one another and with a classical kNN classifier. In this study, we observe that the MLP provides similar levels of performance to the RBFN, AFS land kNN) classifiers while exerting a lower computational load on the processor.
|Title of host publication||Unknown Host Publication|
|Number of pages||6|
|Publication status||Published - 2000|
|Event||SOFT COMPUTING TECHNIQUES AND APPLICATIONS - |
Duration: 1 Jan 2000 → …
|Name||ADVANCES IN SOFT COMPUTING|
|Conference||SOFT COMPUTING TECHNIQUES AND APPLICATIONS|
|Period||1/01/00 → …|
- multi-layer perceptron network
- radial basis function network
- adaptive fuzzy system
- k-nearest neighbour
- embedded system
Li, Y., Pont, MJ., Parikh, CR., & Jones, NB. (2000). Comparing the performance of three neural classifiers for use in embedded applications. In Unknown Host Publication (pp. 34-39). (ADVANCES IN SOFT COMPUTING).