A Self-organizing Interval Type-2 Fuzzy Neural Network for Multi-Step Time Series Prediction

2024-07-10

AI Summary

To address the challenges of high data uncertainty and the trade-off between interpretability and accuracy in multi-step time-series forecasting, this paper proposes the Self-Organizing Interval Type-2 Fuzzy Neural Network with Multi-Output capability (SOIT2FNN-MO), a novel nine-layer architecture. The method introduces three innovative components—the co-premise layer, temporal linkage layer, and rule-strength transformation layer—enabling a two-stage self-organizing learning mechanism for automatic fuzzy rule extraction and joint parameter optimization. By integrating interval type-2 fuzzy logic, deep fuzzy neural architecture, and explicit temporal dependency modeling, SOIT2FNN-MO achieves superior forecasting accuracy: improvements of 1.6%–30% over state-of-the-art methods on chaotic systems and microgrid forecasting tasks, with gains increasing under higher noise levels. Crucially, the model preserves strong interpretability—via transparent linguistic rules—and supports simultaneous multi-output prediction, thereby reconciling accuracy, robustness, and explainability in uncertain dynamic environments.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Data uncertainty is inherent in many real-world applications and poses significant challenges for accurate time series predictions. The interval type 2 fuzzy neural network (IT2FNN) has shown exceptional performance in uncertainty modelling for single-step prediction tasks. However, extending it for multi-step ahead predictions introduces further issues in uncertainty handling as well as model interpretability and accuracy. To address these issues, this paper proposes a new selforganizing interval type-2 fuzzy neural network with multiple outputs (SOIT2FNN-MO). Differing from the traditional six-layer IT2FNN, a nine-layer network architecture is developed. First, a new co-antecedent layer and a modified consequent layer are devised to improve the interpretability of the fuzzy model for multi-step time series prediction problems. Second, a new link layer is created to improve the accuracy by building temporal connections between multi-step predictions. Third, a new transformation layer is designed to address the problem of the vanishing rule strength caused by high-dimensional inputs. Furthermore, a two-stage, self-organizing learning mechanism is developed to automatically extract fuzzy rules from data and optimize network parameters. Experimental results on chaotic and microgrid prediction problems demonstrate that SOIT2FNN-MO outperforms state-of-the-art methods, by achieving a better accuracy ranging from 1.6% to 30% depending on the level of noises in data. Additionally, the proposed model is more interpretable, offering deeper insights into the prediction process.

Problem

• Handles data uncertainty in multi-step time series prediction
• Improves interpretability and accuracy of fuzzy neural networks
• Addresses vanishing rule strength in high-dimensional inputs

Innovation

• Nine-layer network architecture for multi-step prediction
• Two-stage self-organizing learning mechanism
• Improved interpretability and accuracy with new layers