Decoding Electroencephalography Signal Response by Stacking Ensemble Learning and Adaptive Differential Evolution
Matheus Henrique Dal Molin Ribeiro1,2, Ramon Gomes da Silva1, José Henrique Kleinubing Larcher3
1Industrial and Systems Engineering Graduate Program (PPGEPS), Pontifical Catholic University of Paraná (PUCPR), R. Imaculada Conceição 1155, Curitiba 80215-901, PR, Brazil.
Sensors (Basel, Switzerland)
|August 26, 2023
Summary
This study introduces a novel hybrid model, JADE-STACK, for analyzing complex electroencephalography (EEG) signals. The JADE-STACK model significantly improves nonlinear system identification and prediction accuracy for neural data.
Area of Science:
- Neuroscience
- Machine Learning
- Signal Processing
Background:
- Electroencephalography (EEG) signals present complex nonlinear dynamics, making accurate data modeling challenging due to noise and artifacts.
- Traditional methods struggle with the inherent nonlinearities and variability in brain activity data.
- Developing robust models is crucial for reliable neural data identification and prediction.
Purpose of the Study:
- To propose a novel hybrid framework, JADE-STACK, for nonlinear system identification using EEG signals.
- To enhance the accuracy and reliability of neural data modeling and prediction.
- To evaluate the model's performance in decoding EEG signal responses to physical perturbations.
Main Methods:
- A hybrid framework combining stacked generalization (STACK) ensemble learning with the Adaptive Differential Evolution (JADE) algorithm.
- Training five base learners: eXtreme Gradient Boosting, Gaussian Process, LASSO, Multilayer Perceptron, and Support Vector Regression.
- Utilizing JADE to optimize hyperparameters for the Cubist model, which integrates predictions from base learners.
Main Results:
- The JADE-STACK model achieved high accuracy, explaining an average of 94.50% (1-step ahead) and 67.50% (3-steps ahead) of data variability.
- Demonstrated significant improvement over existing methods, ranging from 0.6% to 161% for 1-step ahead and 43.34% for 3-steps ahead predictions.
- Outperformed individual base learners and other state-of-the-art techniques in nonlinear system identification.
Conclusions:
- The JADE-STACK model offers a powerful and accurate approach for nonlinear system identification in EEG data.
- It provides a reliable alternative for analyzing complex neural signals and developing predictive models.
- The framework's ability to handle nonlinearities and noise makes it suitable for advancing brain-computer interfaces and neurological research.
Related Concept Videos
01:35Long-term Potentiation
Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre- and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
01:25Neural Circuits
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
01:28Neuronal Communication
Neurons, the fundamental units of the brain and nervous system, communicate through complex electrochemical signals that underpin all cognitive and bodily functions. This communication is primarily facilitated by a process involving the generation and propagation of an action potential along the axon of the neuron. When the internal electrical charge of a neuron surpasses a certain threshold, an action potential is triggered. This rapid change in voltage travels swiftly along the axon to the...
01:01Neuroplasticity
Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.
01:23Storage
A schema is a mental framework that helps individuals organize and interpret information. Schemata, formed from previous experiences, influence how we process new information: how we encode it, the inferences we make, and how we retrieve it. For instance, a schema for what a typical classroom looks like might include desks, a teacher's desk, a whiteboard, and students in such an environment. This expectation helps us quickly understand and navigate new classrooms without needing to analyze each...