Advanced search
Start date

Classification of body/mental states for a human-machine interface based on the heart rate variability


From the earliest single-neuron recording experiments through the multivariate functional magnetic resonance imaging (fMRI), one of the predominant themes in neuroscience has been the development of brain reading approaches and human-machine interfaces (HMI). Although decades of research, in both fields, advances are unsatisfactory, far from being useful in real-life tasks. Researchers of HMI usually focus solely on brain signals obtained by electroencephalography (EEG), fMRI, or by invasive methods such as electrocorticography (ECoG). HMI, based on these signals, shows poor performance because motor behavior does not depend only on brain activity but also on the interactions of the brain with the body, including its internal organs (feedback loop). In other words, if we do not take into account the rest of the body, the relationship between behavior and neural activity is not one-to-one. Hence, a natural way to advance the development of improved HMI technology would be the inclusion of information about how the body interacts with the brain. One way to achieve this is to measure the change in interoception, i.e., the perception of the internal physiological conditions of the body. The advantage of interoception is that it can be measured by monitoring heart activity. Heart rate variability (HRV) is a global parameter that better represents the behavioral state of the body and the brain. Thus, we aim to classify body/mental states and construct a new HMI based solely on the HRV. Results obtained here may change how we do healthcare. There are attempts to monitor HRV for health-related issues. We will scaffold on them to introduce our mental state classification approach. The success of this proposal is directly associated with the development of non-invasive/low-cost HMI for people with disabilities. (AU)

Articles published in Agência FAPESP Newsletter about the research grant:
Articles published in other media outlets (0 total):
More itemsLess items

Scientific publications
(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)
GUZMAN, GROVER E. CASTRO; FUJITA, ANDRE. Convolution-based linear discriminant analysis for functional data classification. INFORMATION SCIENCES, v. 581, p. 469-478, DEC 2021. Web of Science Citations: 0.

Please report errors in scientific publications list by writing to: