An editorial paper by scientists at the Beijing Institute of Technology, the Imperial College London, and the University of Augsburg introduced an emerging methodology named computational psychophysiology (CPP) to explore the link between the psychological quantities and the physiological quantities.
The new editorial paper, published on Sept. 1 in the journal Cyborg and Bionic Systems, showed a potential to leverage the methodology of mathematical inverse problems to interpret the fundamental mechanism of CPP by providing a formulated abstract equation, that is f(x)=y.
"It is reasonable to think that the fundamental mechanism of CPP can be validated and /or interpreted by introducing the methodology of mathematical inverse problems," explained study author Bin Hu, a professor at the Beijing Institute of Technology.
The evaluation of psychiatric diseases is of great importance for patient's mental health and to benefit clinical practice. "With the fast development of artificial intelligence, big data, wearables, and the internet of things, we can observe successful achievements in finding quantitative methods for evaluating the degree of psychiatric diseases under the guidance of CPP," said study authors. The methodologies for quantitatively solving psychophysiological inverse problems are grouped into two categories: The methodology lent form data science, and the methodology lent form the classic inverse problems of mathematical physics. The two methodologies aim to tackle two kinds of problems: The data-driven inverse problem and the knowledge-driven inverse problem. For example, the methodology based on data science can be associated with the regression problem, aiming to directly construct an approximation of the inversion mapping. Furthermore, the authors also pointed out that for the methodology based on classical inverse problems of mathematical physics, the psychological quantity is usually the antecedent cause of a physiological quantity.
Looking forward, the team provide some perspectives and outlooks for the exploration of the inverse problems. First, it is of significance to design novel paradigms in order to construct mathematical models. Second, when it comes to data, multimodal behavioural and physiological data are crucial to find out the relationship between psychological quantities and physiological measures. Third, the authors illustrate that the real psychophysiological model is dynamical, which requires the development of a novel comprehensive framework. Fourth, the noise and uncertainty of the psychophysiological system should be considered and addressed when building the models. Fifth, some specific regularisation methods need to be developed for accurate estimation of psychological quantity.
"The physics-informed neural networks can be judged as a good candidate for modelling and efficient solving of psychophysiological inverse problems," said Hu, explaining the last but not least perspective about their proposed methodologies, that is, the physics-informed methods have the capacity to require substantially less training data and result in simpler neural network structures, but with a high accuracy in real word.
Authors of the paper include Bin Hu, Kun Qian, Ye Zhang, Jian Shen, and Björn W. Schuller.
The Ministry of Science and Technology of the People's Republic of China (2021ZD0201900); the Beijing Natural Science Foundation (Key Project No. Z210001); the National Natural Science Foundation of China (No. 12171036); and the China Post-doctoral Science Foundation (Grant No. 2021M700423).
The paper, "The Inverse Problems for Computational Psychophysiology: Opinions and Insights" was published in the journal Cyborg and Bionic Systems on September 1, 2022, at DOI: https://doi.org/10.34133/2022/9850248
Reference
Authors: Bin Hu1, Kun Qian1, Ye Zhang2, Jian Shen1, and Björn W. Schuller3,4
Title of original paper: The Inverse Problems for Computational Psychophysiology: Opinions and Insights
Journal: Cyborg and Bionic Systems
DOI: 10.34133/2022/9850248
Affiliations:
- School of Medical Technology, Beijing Institute of Technology, Beijing 100081, China
- School of Mathematics and Statistics, Beijing Institute of Technology, Beijing 100081, China
- GLAM–Group on Language, Audio, & Music, Imperial College London, London SW7 2AZ, UK
- Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg 86159, Germany
A brief introduction about author.
About Prof. Bin Hu:
Bin Hu received the Ph.D. degree in computer science from the Institute of Computing Technology, Chinese Academy of Science, Beijing, China, in 1998. He is currently a Professor and the Dean of the School of Medical Technology and the Institute of Engineering Medicine, Beijing Institute of Technology, Beijing. He is also an Adjunct Professor and the former Dean of the School of Information Science and Engineering, Lanzhou University, Lanzhou, China. He is a National Distinguished Expert, the Chief Scientist of 973, as well as the National Advanced Worker in 2020. Prof. Hu is a Fellow of the Institution of Engineering and Technology (IET). He is a member of the Steering Council of the ACM China Council and the Vice-Chair of the China Committee of the International Society for Social Neuroscience. He serves as the Editor-in-Chief for IEEE Transactions on Computational Social Systems. He is also the TC Co-Chair of computational psychophysiology in the IEEE Systems, Man, and Cybernetics Society (SMC) and the TC Co-Chair of cognitive computing in IEEE SMC. He is a member of the Steering Committee of Computer Science, Chinese Ministry of Education, and the Science and Technology Commission, Chinese Ministry of Education. His awards include the 2014 China Overseas Innovation Talent Award, the 2016 Chinese Ministry of Education Technology Invention Award, the 2018 Chinese National Technology Invention Award, and the 2019 WIPO-CNIPA Golden Award for Chinese Outstanding Patented Invention. He is a Principal Investigator for large grants such as the National Transformative Technology "Early Recognition and Intervention Technology of Mental Disorders Based on Psychophysiological Multimodal Information," which have greatly promoted the development of objective, quantitative diagnosis and nondrug interventions for mental disorders.
Personal Homepage: https://orcid.org/0000-0003-3514-5413
