Follow the Flow exploits the potential of state-of-the-art machine learning for the analysis of physiological signals. In this implementation of artificial intelligence, the perceived level of arousal and valence of the situation will be paired with the physiological activation of the subject (creating a supervised learning model). After that, the machine will learn how to classify the data stream of physiological activation, discovering which signals and features are the fundamentals for the differentiation. An innovative methodology is then presented to understand the shortest time and least amount of data required to recognize flow: different machine learning approaches will be implemented to differentiate the potentialities of different time spans. This methodology permits to follow directly the stream of flow, divided into small epochs, the duration of which is chosen based on the best time/performance ratio.

Sajno, E., Riva, G., Follow the Flow: Artificial Intelligence and Machine Learning for Achieving Optimal Performance, <<CYBERPSYCHOLOGY, BEHAVIOR AND SOCIAL NETWORKING>>, 2022; 25 (7): 476-477. [doi:10.1089/cyber.2022.29251.ceu] [https://hdl.handle.net/10807/229451]

Follow the Flow: Artificial Intelligence and Machine Learning for Achieving Optimal Performance

Sajno, Elena;Riva, Giuseppe
2022

Abstract

Follow the Flow exploits the potential of state-of-the-art machine learning for the analysis of physiological signals. In this implementation of artificial intelligence, the perceived level of arousal and valence of the situation will be paired with the physiological activation of the subject (creating a supervised learning model). After that, the machine will learn how to classify the data stream of physiological activation, discovering which signals and features are the fundamentals for the differentiation. An innovative methodology is then presented to understand the shortest time and least amount of data required to recognize flow: different machine learning approaches will be implemented to differentiate the potentialities of different time spans. This methodology permits to follow directly the stream of flow, divided into small epochs, the duration of which is chosen based on the best time/performance ratio.
2022
Inglese
Sajno, E., Riva, G., Follow the Flow: Artificial Intelligence and Machine Learning for Achieving Optimal Performance, <<CYBERPSYCHOLOGY, BEHAVIOR AND SOCIAL NETWORKING>>, 2022; 25 (7): 476-477. [doi:10.1089/cyber.2022.29251.ceu] [https://hdl.handle.net/10807/229451]
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10807/229451
Citazioni
  • ???jsp.display-item.citation.pmc??? 0
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 2
social impact