Method and system for assessing learning experience of a person

A system for assessing the learning experience of a person, the system comprising:

• a console configured to be used by the person to perform a task;
• a keyboard in connection with the console, the keyboard configured to be used by the person by pressing a plurality of keys in response to the task;
• an electroencephalogram (EEG) device for measuring brain activity of the person, wherein the brain activity indicates a skill-challenge balance of the person;
• a GSR sensing device for sensing galvanic skin response (GSR) of the person to measure a skin conductance of the person by applying a constant voltage to skin of the person through two electrodes and detecting the current passing through the skin, wherein the GSR is an electro-dermal response where the skin conductance level changes with a state of sweat glands in presence of stressful, likeable events, and wherein the GSR is characterized by phasic and tonic components that contain information associated with specific physiological aspects of brain states and are calculated by taking inverse transform of Fourier coefficients, wherein the GSR indicates the concentration of the person;
• a pulse oximeter wearable on the index finger for sensing photo-plethysmogram (PPG) signal, the PPG signal is being used to measure heart rate variability (HRV) of the person, wherein the HRV is calculated in three time domain HRV parameters namely Root mean square of successive differences between adjacent NN intervals, Standard deviation of successive differences between adjacent NN intervals, Successive difference between NN Intervals, wherein the HRV indicates a stress level of the person;
• a questionnaire configured to be filled by the person after completing the task, to have an indication of the person's perception of flow and boredom;
• a processor configured to generate an output comprising he EEG signal depicting brain activity of the person, the GSR characterized by phasic and tonic components that contain information associated with specific physiological aspects of brain states depicting the concentration of the person and the HRV calculated in three time domain HRV parameters namely Root mean square of successive differences between adjacent NN intervals, Standard deviation of successive differences between adjacent NN intervals, Successive difference between NN Intervals depicting the stress level of the person as input;
• and
• compare, the generated output with a predefined model using a two state Markov chain with distance Dk, wherein the distance metric Dk gives an estimate on the overall experience of the person related to boredom and flow and is used to assess the learning experience of the person, and wherein the predefined model is configured to be used to assess the learning experience of the person on whether they enter flow state during the learning process, and wherein comparison is performed by deriving state transition probabilities for the learning session.

A non-transitory computer-readable medium having embodied thereon a computer program for assessing the learning experience of a person, a method comprising:

• asking the person to perform a task for a predefined time period, wherein the task is performed using a keyboard;
• recording a pattern of a plurality of keys pressed on the keyboard during the predefined time period while performing the task;
• measuring brain activity of the person by sensing an electroencephalogram (EEG) signal using an EEG device during the predefined time period;
• sensing galvanic skin response (GSR) of the person using a GSR sensing device to measure a skin conductance of the person by applying a constant voltage to skin of the person through two electrodes and detecting the current passing through the skin during the predefined time period, wherein the GSR is an electro-dermal response where the skin conductance changes with a state of sweat glands in presence of stressful, likeable events, and wherein the GSR is characterized by phasic and tonic components that contain information associated with specific physiological aspects of brain states and are calculated by taking inverse transform of Fourier coefficients, wherein the GSR indicates the concentration of the person;
• measuring heart rate variability (HRV) of the person, using a pulse oximeter wearable on the index finger for sensing a photo-plethysmogram (PPG) signal during the predefined time period, wherein the HRV is calculated in three time domain HRV parameters namely Root mean square of successive differences between adjacent NN intervals, Standard deviation of successive differences between adjacent NN intervals, Successive difference between NN Intervals, wherein the HRV indicates a stress level of the person;
• acquiring psychological experience of the person using a questionnaire filled by the person after performing the task to have an indication of their perception of flow and boredom;
• generating by a processor an output comprising the EEG signal depicting brain activity of the person, the GSR characterized by phasic and tonic components that contain information associated with specific physiological aspects of brain states depicting the concentration of the person and the HRV calculated in three time domain HRV parameters namely Root mean square of successive differences between adjacent NN intervals, Standard deviation of successive differences between adjacent NN intervals, Successive difference between NN Intervals depicting the stress level of the person as input;
• and
• comparing by the processor, the generated output with a predefined model using a two state Markov chain with distance Dk, wherein the distance metric Dk gives an estimate on the overall experience of the person related to boredom and flow and is used to assess the learning experience of the person, and wherein the predefined model is configured to be used to assess the learning experience of the person on whether they enter flow state during the learning process, and wherein comparison is performed by deriving state transition probabilities for the learning session.