Please use this identifier to cite or link to this item:
|Title:||The evolving mamdani fuzzy inference system with fuzzy rule interpolation and extrapolation (eMFIS (FRI/E) with its applications in straddle option trading and case study of rain run off analysis||Authors:||Susanti||Keywords:||DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence||Issue Date:||2014||Abstract:||Fuzzy neural technique is often used to model dynamic data stream in the financial market and examines hypothetical cases. Hence, Fuzzy interpolation and extrapolation are required if the data is sparse, particularly in financial option trading. However, many of them do not have the learning ability. This paper extends the work of HS  with on-line learning ability. The result enables both interpolation and extrapolation to be applied in the neuro-fuzzy system algorithm in order to make inference when drift is detected or in sparse rule–based systems. This paper proposes a novel neuro-fuzzy system architecture called evolving Mamdani Fuzzy Inference System with Fuzzy Rule interpolation or Extrapolation (eMFIS (FRI/E)) that has the following advantages: 1) it is an online learning system; 2) capable of detecting and handling concept drift or shift; 3) the inference can involve multiple fuzzy rules, with each rule consisting of multiple antecedents. eMFIS (FRI/E) applies Two-staged Incremental Clustering for incremental fuzzy clustering. The Bienenstock-Cooper-Munro (BCM) is used to self-organise its rule base structure to represent the most recent knowledge of the data. eMFIS (FRI/E) uses a cluster neighbourhood age to detect the existence of the drift or shift. eMFIS (FRI/E) also applies interpolation or extrapolation when drift or shift is detected. The proposed method is compared against with those of the existing neuro-fuzzy architectures in both time-invariant and time-variant data. (eMFIS (FRI/E)) is also used for straddle option trading, market crisis analysis and the case study of rain run off analysis. The results are encouraging.||URI:||http://hdl.handle.net/10356/61931||Rights:||Nanyang Technological University||Fulltext Permission:||restricted||Fulltext Availability:||With Fulltext|
|Appears in Collections:||SCSE Student Reports (FYP/IA/PA/PI)|
Page view(s) 1280
checked on Oct 19, 2020
checked on Oct 19, 2020
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.