Evolving Takagi‐Sugeno Fuzzy Systems from Streaming Data (eTS+)
Plamen Parvanov Angelov · 2010
It is a well-known fact that nowadays we are faced not only with large data sets that we need to process quickly, but with huge data streams. Special requirements are also placed by the fast-growing sector of autonomous systems, where systems that can retrain and adapt on-the-fly are needed. The author of this chapter started research work in this direction around the turn of the century, and this research culminated in proposing with Dr. D. Filev the so-called evolving Takagi-Sugeno (eTS) fuzzy system. eTS fuzzy systems can, in general, be of the multi-input-multi-output (MIMO) type. One effective online technique proposed in Angelov and Filev (2003) is based on partitioning the data space into overlapping local regions through recursive density estimation (RDE) and associating clusters to them. Once the structure of the evolving fuzzy system eTS+ is defined and established, the problem of parameter identification becomes important. Controlled Vocabulary Terms fuzzy systems; MIMO systems; Streaming media