Lanata Antonio, Guidi Andrea, Valenza Gaetano, Baragli Paolo, Scilingo Enzo Pasquale
Annu Int Conf IEEE Eng Med Biol Soc. 2017 Jul;2017:1320-1323. doi: 10.1109/EMBC.2017.8037075.
This study focuses on the analysis of human-horse dynamic interaction using cardiovascular information exclusively. Specifically, the Information Theoretic Learning (ITL) approach has been applied to a Human-Horse Interaction paradigm, therefore accounting for the nonlinear information of the heart-heart interplay between humans and horses. Heartbeat dynamics was gathered from humans and horses during three experimental conditions: absence of interaction, visual-olfactory interaction, and brooming. Cross Information Potential, Cross Correntropy, and Correntropy Coefficient were computed to quantitatively estimate nonlinear coupling in a group of eleven subjects and one horse. Results showed a statistical significant difference on all of the three interaction phases. Furthermore, a Support Vector Machine classifier recognized the three conditions with an accuracy of 90:9%. These preliminary and encouraging results suggest that ITL analysis provides viable metrics for the quantitative evaluation of human-horse interaction.
本研究专注于仅使用心血管信息对人与马的动态交互进行分析。具体而言，信息论学习（ITL）方法已应用于人与马交互范式，从而考量了人与马之间心脏 - 心脏相互作用的非线性信息。在三种实验条件下收集了人类和马的心跳动态：无交互、视觉 - 嗅觉交互以及刷拭。计算了交叉信息势、交叉相关熵和相关熵系数，以定量估计一组11名受试者和一匹马中的非线性耦合。结果显示在所有三个交互阶段均存在统计学显著差异。此外，支持向量机分类器以90.9%的准确率识别出这三种条件。这些初步且令人鼓舞的结果表明，ITL分析为定量评估人与马的交互提供了可行的指标。
