System for real-time measurement of the activity of a cognitive function and method for calibrating such a system

A system for real-time measurement of an activity of a cognitive function of a test subject, wherein the cognitive function is a working memory, comprising:

• a subsystem for electrical signal acquisition;
• a processing unit;
• wherein the processing unit is configured for:
• a) acquiring electrical signals representing a neural activity of the test subject during an execution of a first task by the test subject, the first task being configured so that the execution of the first task by the test subject leads to different states of activity of the cognitive function of the test subject;
• b) determining signal sequences by segmenting the electrical signal acquired, and determining reference sequences by segmenting reference electrical signals, each reference electrical signal being representative of a neural activity of a reference subject during the execution of the first task by the reference subject, the reference subject being part of a first reference population;
• c) determining, by using Welch method, signal marker values from each signal sequence and determining, by using Welch method, reference marker values from each reference sequence, the signal marker values being representative of an activity state of the cognitive function of the test subject and the reference marker values being representative of an activity state of a cognitive function of a reference subject;
• d) generating copies of the signal marker values and generating copies of the reference marker values and adding noise to the copies of the signal marker values and to the copies of the reference marker values so as to produce noisy copies of the signal marker values and noisy copies of the reference marker values;
• e) constructing a classifier by automatic learning from the signal marker values, the reference marker values, and on the noisy copies of the signal marker values and noisy copies of the reference marker values, the classifier being configured to measure the activity of the cognitive function by calculating a value representing a first probability that an electrical signal representative of the neural activity of the test subject results from a predetermined activity state of the cognitive function of the test subject.