{"title":"The Inverse Problems for Computational Psychophysiology: Opinions and Insights","authors":"B. Hu, Kun Qian, Ye Zhang, Jian Shen, B. Schuller","doi":"10.34133/2022/9850248","DOIUrl":null,"url":null,"abstract":"Since a long time, measuring the psychological status of subjects in a quantitative paradigm is a challenging problem in the scientific community. It is known that there is not a direct way to measure the psychological quantities [1], whereas an emerging methodology, i.e., computational psychophysiology (CPP), was introduced [2]. The core idea of CPP is to explore the link between the psychological quantities and the physiological quantities, which the latter ones can be measured via ubiquitous equipment (e.g., a braincomputer interface device). Psychiatric diseases are usually accompanied by abnormal psychological status, which can be objectively quantified by psychophysiological quantities. Evaluating psychiatric diseases is of great significance for mental health. 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 (e.g., depression) under the guidance of CPP. Nevertheless, the underlying mechanisms of these engineering milestones are still “up in the air” [3]. Investigating the fundamentals of CPP is a prerequisite for strengthening our power to extend the knowledge frontiers of mental health and benefit from clinical practice. D. R. Bach et al. proposed the concept of the “psychophysiological inverse problem,” claiming that psychologists use the peripheral physiological quantities to infer psychological quantities [4]. In particular, compared to other domains (e.g., intelligent disease diagnosis), understanding the mechanism of the mind could even benefit the development of novel clinical treatment methods for psychiatric disease. Therefore, the inverse problem tool cannot only facilitate a more personalised and precised medicine but also help discover the inherited characteristics of the psychophysiology. 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. By the language of mathematical inverse problems [5], the computational psychophysiological problems can be formulated through an abstract equation,","PeriodicalId":72764,"journal":{"name":"Cyborg and bionic systems (Washington, D.C.)","volume":" ","pages":""},"PeriodicalIF":10.5000,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cyborg and bionic systems (Washington, D.C.)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.34133/2022/9850248","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}
引用次数: 2
Abstract
Since a long time, measuring the psychological status of subjects in a quantitative paradigm is a challenging problem in the scientific community. It is known that there is not a direct way to measure the psychological quantities [1], whereas an emerging methodology, i.e., computational psychophysiology (CPP), was introduced [2]. The core idea of CPP is to explore the link between the psychological quantities and the physiological quantities, which the latter ones can be measured via ubiquitous equipment (e.g., a braincomputer interface device). Psychiatric diseases are usually accompanied by abnormal psychological status, which can be objectively quantified by psychophysiological quantities. Evaluating psychiatric diseases is of great significance for mental health. 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 (e.g., depression) under the guidance of CPP. Nevertheless, the underlying mechanisms of these engineering milestones are still “up in the air” [3]. Investigating the fundamentals of CPP is a prerequisite for strengthening our power to extend the knowledge frontiers of mental health and benefit from clinical practice. D. R. Bach et al. proposed the concept of the “psychophysiological inverse problem,” claiming that psychologists use the peripheral physiological quantities to infer psychological quantities [4]. In particular, compared to other domains (e.g., intelligent disease diagnosis), understanding the mechanism of the mind could even benefit the development of novel clinical treatment methods for psychiatric disease. Therefore, the inverse problem tool cannot only facilitate a more personalised and precised medicine but also help discover the inherited characteristics of the psychophysiology. 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. By the language of mathematical inverse problems [5], the computational psychophysiological problems can be formulated through an abstract equation,