Rule-based Evolving Fuzzy System for Time Series Forecasting: New Perspectives Based on Type-2 Fuzzy Sets Measures Approach

• URL: http://arxiv.org/abs/2502.03650v1
• Date: Wed, 05 Feb 2025 22:27:20 GMT
• Title: Rule-based Evolving Fuzzy System for Time Series Forecasting: New Perspectives Based on Type-2 Fuzzy Sets Measures Approach
• Authors: Eduardo Santos de Oliveira Marques, Arthur Caio Vargas Pinto, Kaike Sa Teles Rocha Alves, Eduardo Pestana de Aguiar,
• Abstract summary: Real-world data contain uncertainty and variations that can be correlated to external variables, known as randomness. One of the existing methods to deal with this type of data is the use of the evolving Fuzzy Systems (eFSs) We propose ePL-KRLS-FSM+, an enhanced class of evolving fuzzy modeling approach that combines participatory learning (PL) with fuzzy logic and data transformation into fuzzy sets (FSs) This improvement allows to create and measure type-2 fuzzy sets for better handling uncertainties in the data, generating a model that can predict chaotic data with increased accuracy.
• Score: 0.0
• License:
• Abstract: Real-world data contain uncertainty and variations that can be correlated to external variables, known as randomness. An alternative cause of randomness is chaos, which can be an important component of chaotic time series. One of the existing methods to deal with this type of data is the use of the evolving Fuzzy Systems (eFSs), which have been proven to be a powerful class of models for time series forecasting, due to their autonomy to handle the data and highly complex problems in real-world applications. However, due to its working structure, type-2 fuzzy sets can outperform type-1 fuzzy sets for highly uncertain scenarios. We then propose ePL-KRLS-FSM+, an enhanced class of evolving fuzzy modeling approach that combines participatory learning (PL), a kernel recursive least squares method (KRLS), type-2 fuzzy logic and data transformation into fuzzy sets (FSs). This improvement allows to create and measure type-2 fuzzy sets for better handling uncertainties in the data, generating a model that can predict chaotic data with increased accuracy. The model is evaluated using two complex datasets: the chaotic time series Mackey-Glass delay differential equation with different degrees of chaos, and the main stock index of the Taiwan Capitalization Weighted Stock Index - TAIEX. Model performance is compared to related state-of-the-art rule-based eFS models and classical approaches and is analyzed in terms of error metrics, runtime and the number of final rules. Forecasting results show that the proposed model is competitive and performs consistently compared with type-1 models, also outperforming other forecasting methods by showing the lowest error metrics and number of final rules.

Related papers

• TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation [91.50296404732902]
  We introduce TabDiff, a joint diffusion framework that models all mixed-type distributions of tabular data in one model. Our key innovation is the development of a joint continuous-time diffusion process for numerical and categorical data. TabDiff achieves superior average performance over existing competitive baselines, with up to $22.5%$ improvement over the state-of-the-art model on pair-wise column correlation estimations.
  arXiv  Detail & Related papers  (2024-10-27T22:58:47Z)
• Random Models for Fuzzy Clustering Similarity Measures [0.0]
  The Adjusted Rand Index (ARI) is a widely used method for comparing hard clusterings. We propose a single framework for computing the ARI with three random models that are intuitive and explainable for both hard and fuzzy clusterings.
  arXiv  Detail & Related papers  (2023-12-16T00:07:04Z)
• Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality [84.94877848357896]
  Recent datasets expose the lack of the systematic generalization ability in standard sequence-to-sequence models. We analyze this behavior of seq2seq models and identify two contributing factors: a lack of mutual exclusivity bias and the tendency to memorize whole examples. We show substantial empirical improvements using standard sequence-to-sequence models on two widely-used compositionality datasets.
  arXiv  Detail & Related papers  (2022-11-28T17:36:41Z)
• Learning from aggregated data with a maximum entropy model [73.63512438583375]
  We show how a new model, similar to a logistic regression, may be learned from aggregated data only by approximating the unobserved feature distribution with a maximum entropy hypothesis. We present empirical evidence on several public datasets that the model learned this way can achieve performances comparable to those of a logistic model trained with the full unaggregated data.
  arXiv  Detail & Related papers  (2022-10-05T09:17:27Z)
• Multi-scale Attention Flow for Probabilistic Time Series Forecasting [68.20798558048678]
  We propose a novel non-autoregressive deep learning model, called Multi-scale Attention Normalizing Flow(MANF) Our model avoids the influence of cumulative error and does not increase the time complexity. Our model achieves state-of-the-art performance on many popular multivariate datasets.
  arXiv  Detail & Related papers  (2022-05-16T07:53:42Z)
• Accurate Prediction Using Triangular Type-2 Fuzzy Linear Regression [5.996411241086518]
  Complex calculations of type-2 fuzzy (T2F) model are simplified by reducing three dimensional type-2 fuzzy set (3DT2FS) into two dimensional interval type-2 fuzzy (2DIT2F) models. Our developed model reached the highest performance as compared to the other state-of-art techniques.
  arXiv  Detail & Related papers  (2021-09-12T08:34:14Z)
• IT2CFNN: An Interval Type-2 Correlation-Aware Fuzzy Neural Network to Construct Non-Separable Fuzzy Rules with Uncertain and Adaptive Shapes for Nonlinear Function Approximation [1.599072005190786]
  We introduce a new interval type-2 fuzzy neural network able to construct non-separable fuzzy rules with adaptive shapes. The proposed paradigm is successfully applied to real-world time-series predictions, regression problems, and nonlinear system identification.
  arXiv  Detail & Related papers  (2021-08-11T13:00:13Z)
• Deep Time Series Models for Scarce Data [8.673181404172963]
  Time series data have grown at an explosive rate in numerous domains and have stimulated a surge of time series modeling research. Data scarcity is a universal issue that occurs in a vast range of data analytics problems.
  arXiv  Detail & Related papers  (2021-03-16T22:16:54Z)
• Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encoder [59.69303945834122]
  We present a Smoothness-Inducing Sequential Variational Auto-Encoder (SISVAE) model for robust estimation and anomaly detection of time series. Our model parameterizes mean and variance for each time-stamp with flexible neural networks. We show the effectiveness of our model on both synthetic datasets and public real-world benchmarks.
  arXiv  Detail & Related papers  (2021-02-02T06:15:15Z)
• Robust Finite Mixture Regression for Heterogeneous Targets [70.19798470463378]
  We propose an FMR model that finds sample clusters and jointly models multiple incomplete mixed-type targets simultaneously. We provide non-asymptotic oracle performance bounds for our model under a high-dimensional learning framework. The results show that our model can achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-10-12T03:27:07Z)
• A Bayesian Approach with Type-2 Student-tMembership Function for T-S Model Identification [47.25472624305589]
  fuzzyc-regression clustering based on type-2 fuzzyset has been shown the remarkable results on non-sparse data. Aninnovative architecture for fuzzyc-regression model is presented and a novel student-tdistribution based membership functionis designed for sparse data modelling.
  arXiv  Detail & Related papers  (2020-09-02T05:10:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.