A machine learning approach to identify stochastic resonance in human perceptual thresholds

• Published in: Journal of neuroscience methods Vol. 374; p. 109559
• Main Authors: Voros, Jamie, Rise, Rachel, Sherman, Sage, Durell, Abigail, Anderson, Allison P., Clark, Torin K.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 15.05.2022
• Subjects: Classification; False positives; Humans; Logistic regression; Machine Learning; Perceptual thresholds; Stochastic Processes; Stochastic resonance (SR); White noise; False positives; White noise; Logistic regression; Perceptual thresholds; Stochastic resonance (SR); Classification
• ISSN: 0165-0270; 1872-678X; 1872-678X
• DOI: 10.1016/j.jneumeth.2022.109559

Stochastic resonance (SR) is achieved when a faint signal is improved with the addition of the appropriate amount of white noise. Perceptual thresholds are expected to follow a characteristic performance improvement curve as a function of the white noise level added (i.e., thresholds are reduced with an optimal amount of added white noise, beyond which excessive white noise is no longer beneficial). Since SR exhibition in perceptual thresholds is defined by a shape rather than a statistical difference, the presence of SR is typically identified qualitatively. The current state-of-the-art is for blinded human judges to categorize the presence of SR by visually examining data. While categorizations are made with subject data intermixed within a balanced, simulated dataset, which accounts for false positives, this method is still subjective and prone to human error. We use a logistic regression (LR) trained on engineered features in order to quantitatively classify exhibition of SR. The LR was trained on datasets simulated from a model for SR performance enhancement. We implemented the algorithmic classification process in 6 perceptual threshold test cases, informed by the literature and parameters were defined by experimental subject data. Comparison to Existing Method(s): We report algorithmic classifications of SR exhibition, considering the 6 test cases, that outperform existing subjective methods in accuracy (p < 0.05). We demonstrate that algorithmic classification can effectively identify SR in perceptual thresholds, providing a rigorous, objective, and quantitative approach to identifying the presence of SR. •To identify stochastic resonance in noisy data, we proposed using machine learning.•Machine learning was applied to 6 representative cases, demonstrating robustness.•Machine learning outperformed current subjective methods in classification accuracy.•The machine learning rigorously and objectively identifies stochastic resonance.