An affinity propagation algorithm base on self-tuning kernel geodesic distance

For affinity propagation algorithm, traditional Euclidean distance measure cannot fully reflect the complex spatial distribution of the data sets. We propose a self-tuning kernel geodesic distance as the similarity measure which can reflect the inherent manifold structure information effectively. Meanwhile, according to the neighborhood density of the data sets, it identifies and eliminates the influence of boundary noise effectively, the results show that the improved algorithm has higher accuracy and better robustness for data with manifold distribution, multi-scale and noise overlap.