A 13.2k-parameter dilated 1D CNN classifies 18 affective touch gestures on a plush toy with 75% random-split and 85% leave-one-subject-out accuracy, with estimated 20 Hz operation on an ESP32.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Design and Validation of a Lightweight 1D CNN for Affective Touch Classification in Soft Plush Companions
A 13.2k-parameter dilated 1D CNN classifies 18 affective touch gestures on a plush toy with 75% random-split and 85% leave-one-subject-out accuracy, with estimated 20 Hz operation on an ESP32.