Glossary // Glossary term Technical
Feature
In signal processing and machine learning, a quantity computed from a raw signal and used as input to analysis or classification, such as mean heart rate, an HRV index or the number of skin conductance responses per minute. Feature choice encodes assumptions about which aspects of a signal matter, and different features derived from the same recording can lead to different conclusions. A feature that separates conditions in one sample may not generalise to other people or contexts. How one could reason about recording a catharsis-like change of state: signals, features, inference and context, baselines, self-report, error costs and ethics, and why every step stays uncertain. Nothing on this site measures anyone. The works the definition rests on, with the level of evidence each was appraised at. (2017). Heart rate variability and cardiac vagal tone in psychophysiological research: Recommendations for experiment planning, data analysis, and data reporting. doi:10.3389/fpsyg.2017.00213 Supports the claims that HRV indexes cardiac vagal tone and that its findings are easily misconstrued without careful design, analysis and reporting. Methods guidance, not evidence about emotion categories. (2018). Emotion fingerprints or emotion populations? A meta-analytic investigation of autonomic features of emotion categories. doi:10.1037/bul0000128 Supports the claim that autonomic effect-size patterns did not clearly distinguish one emotion category from another and varied substantially within categories. Laboratory inductions; the interpretation favours one theory of emotion.Where the site uses it
Studies behind it