Related Experiment Videos
A Sugeno-multiplicative neuron hybrid system trained by differential evolution algorithm for time series forecasting.
Erol Egrioglu1,2,3, Eren Bas1,2,3, Asiye Nur Yıldırım4,5,6
1Department of Data Science and Analytics, Faculty of Arts and Science, Giresun University, 28200, Giresun, Turkey.
Scientific Reports
|May 8, 2026
Summary
This study introduces a hybrid neuro-fuzzy model enhancing Sugeno systems with nonlinear multiplicative neurons for improved financial time series forecasting. The novel approach offers superior accuracy and stability, especially in volatile markets.
Area of Science:
- Artificial Intelligence
- Computational Finance
- Time Series Analysis
Background:
- Traditional Sugeno fuzzy inference systems often use linear consequents, limiting their ability to model complex nonlinear dynamics.
- Neural networks offer strong nonlinear modeling but can lack interpretability.
- Financial time series data exhibit complex, nonlinear, and volatile patterns requiring advanced forecasting techniques.
Purpose of the Study:
- To propose a novel hybrid neuro-fuzzy forecasting framework integrating Sugeno interpretability with multiplicative neuron nonlinearity.
- To enhance the representation power of Sugeno models by replacing linear consequents with nonlinear multiplicative neuron structures.
- To evaluate the proposed model's performance on real-world financial time series data.
Main Methods:
- Developed a hybrid neuro-fuzzy model combining Sugeno fuzzy inference with multiplicative neuron models.
- Employed Differential Evolution for optimizing nonlinear parameters and avoiding local minima during training.
- Evaluated the model on ERussell and ETH/USD financial time series datasets for 10, 20, and 30 steps ahead forecasting.
Main Results:
- The proposed hybrid model demonstrated superior forecasting accuracy and stability compared to classical Sugeno systems and other neural network approaches.
- Performance was validated using root mean square error (RMSE) and mean absolute percentage error (MAPE) metrics.
- The model excelled particularly in forecasting nonlinear and volatile financial time series conditions.
Conclusions:
- Structurally enhancing Sugeno consequents with nonlinear multiplicative neurons significantly improves time series forecasting capabilities.
- The hybrid neuro-fuzzy framework offers a powerful and interpretable solution for complex financial forecasting tasks.
- This approach advances the application of fuzzy systems in computational finance and machine learning.
Related Concept Videos
01:25Modeling with Differential Equations
Population dynamics can be described mathematically by considering the population size P(t) as a function of time. The rate of change of the population is then represented by the derivative of P(t). A simple assumption is that the rate of growth is proportional to the size of the population itself. This leads to an exponential growth model, where the population increases rapidly without bound. While this is a useful first approximation, it does not reflect realistic long-term...
01:29Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
01:20Separable Differential Equations
A separable differential equation is a type of first-order differential equation where the derivative dy/dx can be expressed as a product of two functions: one that depends only on x and another that depends only on y. This allows for the rearrangement of the equation so that all terms involving y are on one side, and all terms involving x are on the other. This process, known as the separation of variables, simplifies the process of solving the equation by enabling the integration of both...
01:27Linear Differential Equations
The integrating factor method provides a systematic way to solve first-order linear differential equations, especially those that cannot be handled by separation of variables. This method is particularly useful in modeling time-dependent physical systems influenced by both constant inputs and resistive forces. A common example is the motion of a car subjected to a constant engine force while experiencing air resistance proportional to its velocity.In such scenarios, Newton’s second law yields a...
01:21Differential Equations: Problem Solving
When analyzing the motion of falling objects, it is essential to consider not only the force of gravity but also the opposing force of air resistance. A practical example involves releasing a heavy test weight during a safety check on a ship. As the weight falls from rest, gravity accelerates it downward while air resistance exerts an upward force that increases with velocity. This dynamic interplay of forces is well described by differential equations, which provide a mathematical framework...
01:30Simplified Synchronous Machine Model
The Synchronous Machine Model is a fundamental tool in analyzing and ensuring the transient stability of power systems. This model simplifies the representation of a synchronous machine under balanced three-phase positive-sequence conditions, assuming constant excitation and ignoring losses and saturation. The model is pivotal for understanding the behavior of synchronous generators connected to a power grid, particularly during transient events.
In this model, each generator is connected to a...
In this model, each generator is connected to a...