ABSTRACT
METHOD AND SYSTEM FOR EVALUATION OF ONLINE TUTORIALS
The present application provides a method and system for evaluating a difficulty level of content of an online tutorial based on physiological signals. The disclosed invention uses various phFORM 2
THE PATENTS ACT, 1970 (39 of 1970) & THE PATENTS RULES, 2003
COMPLETE SPECIFICATION
(See section 10, rule 13)
1. Title of the invention: METHOD AND SYSTEM FOR EVALUATION OF ONLINE
TUTORIALS
2. Applicant(s)
NAME NATIONALITY ADDRESS
TATA CONSULTANCY Indian Nirmal Building, 9th Floor,
SERVICES LIMITED Nariman Point, Mumbai,
Maharashtra 400021, India
3. Preamble to the description
COMPLETE SPECIFICATION
The following specification describes the invention and the manner in which it is to be
performed.

FIELD OF THE INVENTION
[001] The present application generally relates to evaluating online tutorial systems (OTS). Particularly, the application provides a method and system for evaluating difficulty level of content of an online tutorial based on physiological signals.
BACKGROUND OF THE INVENTION
[002] With the advancement of internet technology, changes in the student expectations etc., online tutorial systems (OTS) are gaining huge interests. One major advantage of OTS is its availability and the students can complete the courses at their own pace. Innovative and creative tutorial contents are being designed by taking into account individual student’s abilities, needs and inclinations. In traditional classrooms, one’s participation in asking question, discussion and debate actually helps the teacher to understand the ability, attention, stress and limitations of a student. Based on these, the teacher modifies his lectures to ensure a better learning outcome.
[003] The biggest challenge is to choose a program to meet student’s expectations, needs and abilities. The prior art literature available discusses intelligent tutorial systems (ITS) for modeling students, domain, tutoring and communication. ITS uses questionnaire based approach for understanding and modeling the off-task behavior of the student however subjective measures like questionnaires or user feedback based approaches are highly biased and subject dependent.
[004] Physiological changes give a much more reliable and direct measure of the mental workload. The problems associated with the physiological measure of cognitive load are (i) the costly physiological sensors which makes mass deployment effectively impossible and (ii) correct interpretation of sensor data. Modifying the content using physiological changes ensure a better learning outcome for OTS.
[005] Moreover majority of prior art teaches methods involving wearing a large number of physiological sensors which might make the participant uncomfortable and self-conscious. Also

all these experiments are done using costly GSR, PPG, EEG setups etc. with high sampling rate which is a hindrance for mass deployment.
SUMMARY OF THE INVENTION
[006] Before the present methods, systems, and hardware enablement are described, it is to be understood that this invention is not limited to the particular systems, and methodologies described, as there can be multiple possible embodiments of the present invention which are not expressly illustrated in the present disclosure. It is also to be understood that the terminology used in the description is for the purpose of describing the particular versions or embodiments only, and is not intended to limit the scope of the present invention which will be limited only by the appended claims.
[007] The present application provides a method and system for evaluating a difficulty level of content of an online tutorial based on physiological signals.
[008] The present application provides a computer implemented method for evaluating a difficulty level of content of an online tutorial based on physiological signals, wherein said method comprises, instructing one or more users to stay in a baseline state and a learning state respectively using a user interface (204). In an embodiment a baseline is determined during the baseline state and the online tutorial is performed by the person during the learning state. Further the method comprises steps of sensing an Electroencephalograph (EEG) signal of the one or more user using an EEG sensor (224), sensing a Galvanic Skin Response (GSR) signal of the one or more user using a GSR sensor (226) and sensing a Photoplethysmogram (PPG) signal of the one or more user using a PPG sensor (228). Next according to the method disclosed herein the EEG signal, the GSR signal and the PPG signal are segmented in to a baseline interval corresponding to the baseline state, and a learning interval corresponding to the learning state using a segmentation module (210). Further the method comprises the step of calculating the cognitive load for the user by using a time-frequency based S- transform feature extraction technique to extract one or more features from the segmented EEG signal using an EEG signal processing module (212) and calculating a normalized tonic power for the user using a N point Fast Fourier Transform (FFT) on the segmented GSR signal and applying inverse FFT based on

coefficients of the N point FFT corresponding to baseline state and learning state, using a GSR signal processing module (214). The method disclosed herein further comprises calculating a heart rate (HR) and heart rate variability (HRV) using a peak to peak difference in the PPG and a standard deviation of the normal-to-normal heart beat (SDNN) on the segmented PPG signal using a PPG signal processing module (216). Lastly the difficulty of the content of the online tutorial is evaluated based on the calculated cognitive load, the calculated tonic power, the calculated HRV and a calculated baseline using an evaluation module (218).
[009] In another aspect, the present application provides a system (102) for evaluating a difficulty level of content of an online tutorial based on physiological signals; comprising a processor (202), a memory (206), operatively coupled with said processor. The system (102) further comprises an EEG sensor (224), a GSR sensor (226) and a PPG sensor (228). The input/output interface instructs a person to stay in a baseline state and carry out a trial state respectively. The task is performed by the person during the trial state. The EEG sensor senses an EEG signal of the person. The GSR sensor senses a GSR signal of the person. The PPG sensor senses a PPG signal of the user. In an embodiment the EEG signal, the GSR signal and the PPG signal are segmented in to a baseline interval corresponding to the baseline state, and a learning interval corresponding to the learning state using a segmentation module (210). The system (102) is further configured to calculate the cognitive load for the user by using a time-frequency based S- transform feature extraction technique to extract one or more features from the segmented EEG signal using an EEG signal processing module (212), calculate a normalized tonic power for the user using a N point Fast Fourier Transform (FFT) on the segmented GSR signal and applying inverse FFT based on coefficients of the N point FFT corresponding to baseline state and learning state, using a GSR signal processing module (214) and calculate a heart rate (HR) and heart rate variability (HRV) using a peak to peak difference in the PPG and a standard deviation of the normal-to-normal heart beat (SDNN) on the segmented PPG signal using a PPG signal processing module (216). Lastly the difficulty of the content of the online tutorial is evaluated by the system (102) based on the calculated cognitive load, the calculated tonic power, the calculated HRV and a calculated baseline using an evaluation module (218).

BRIEF DESCRIPTION OF THE DRAWINGS
[0010] The foregoing summary, as well as the following detailed description of preferred embodiments, are better understood when read in conjunction with the appended drawings. For the purpose of illustrating the invention, there is shown in the drawings exemplary constructions of the invention; however, the invention is not limited to the specific methods and system disclosed. In the drawings:
[0011] Figure 1: illustrates a network implementation of a system for evaluating a difficulty level of content of an online tutorial based on physiological signals, in accordance with an embodiment of the present subject matter;
[0012] Figure 2: shows block diagrams illustrating the system for evaluating a difficulty level of content of an online tutorial based on physiological signals, in accordance with an embodiment of the present subject matter;
[0013] Figure 3: show a flowchart illustrating the method for evaluating a difficulty level of content of an online tutorial based on physiological signals, in accordance with an embodiment of the present subject matter;
[0014] Figure 4A and 4B: shows a slide each of exemplary easy and difficult tutorials on SQL and NoSQL used in an exemplary implementation of the disclosed subject matter;
[0015] Figure 5: shows an experimental setup with various physiological sensors used in an exemplary implementation of the disclosed subject matter;
[0016] Figure 6: shows boxplots showing effect of sequencing for both the participant groups while analyzing the GSR signals in an exemplary implementation of the disclosed subject matter;
[0017] Figure 7 shows a Bar-plot for HRV of users for one easy and other difficult study materials in accordance with an exemplary implementation of the disclosed subject matter.

DETAILED DESCRIPTION OF THE INVENTION
[0018] Some embodiments of this invention, illustrating all its features, will now be discussed in detail.
[0019] The words "comprising," "having," "containing," and "including," and other forms thereof, are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items.
[0020] It must also be noted that as used herein and in the appended claims, the singular forms "a," "an," and "the" include plural references unless the context clearly dictates otherwise. Although any systems and methods similar or equivalent to those described herein can be used in the practice or testing of embodiments of the present invention, the preferred, systems and methods are now described.
[0021] The disclosed embodiments are merely exemplary of the invention, which may be embodied in various forms.
[0022] The elements illustrated in the Figures inter-operate as explained in more detail below. Before setting forth the detailed explanation, however, it is noted that all of the discussion below, regardless of the particular implementation being described, is exemplary in nature, rather than limiting. For example, although selected aspects, features, or components of the implementations are depicted as being stored in memories, all or part of the systems and methods consistent with the attrition warning system and method may be stored on, distributed across, or read from other machine-readable media.
[0023] The techniques described above may be implemented in one or more computer programs executing on (or executable by) a programmable computer including any combination of any number of the following: a processor, a storage medium readable and/or writable by the processor (including, for example, volatile and non-volatile memory and/or storage elements), plurality of input units, and plurality of output devices. Program code may be applied to input

entered using any of the plurality of input units to perform the functions described and to generate an output displayed upon any of the plurality of output devices.
[0024] Each computer program within the scope of the claims below may be implemented in any programming language, such as assembly language, machine language, a high-level procedural programming language, or an object-oriented programming language. The programming language may, for example, be a compiled or interpreted programming language. Each such computer program may be implemented in a computer program product tangibly embodied in a machine-readable storage device for execution by a computer processor.
[0025] Method steps of the invention may be performed by one or more computer processors executing a program tangibly embodied on a computer-readable medium to perform functions of the invention by operating on input and generating output. Suitable processors include, by way of example, both general and special purpose microprocessors. Generally, the processor receives (reads) instructions and data from a memory (such as a read-only memory and/or a random access memory) and writes (stores) instructions and data to the memory. Storage devices suitable for tangibly embodying computer program instructions and data include, for example, all forms of non-volatile memory, such as semiconductor memory devices, including EPROM, EEPROM, and flash memory devices; magnetic disks such as internal hard disks and removable disks; magneto-optical disks; and CD-ROMs. Any of the foregoing may be supplemented by, or incorporated in, specially-designed ASICs (application-specific integrated circuits) or FPGAs (Field-Programmable Gate Arrays). A computer can generally also receive (read) programs and data from, and write (store) programs and data to, a non-transitory computer-readable storage medium such as an internal disk (not shown) or a removable disk.
[0026] Any data disclosed herein may be implemented, for example, in one or more data structures tangibly stored on a non-transitory computer-readable medium. Embodiments of the invention may store such data in such data structure(s) and read such data from such data structure(s).
[0027] The present application provides a computer implemented method and system for evaluating a difficulty level of content of an online tutorial based on physiological signals.

[0028] The present application provides a computer implemented method and system for evaluating a difficulty level of content of an online tutorial based on physiological signals. Referring now to Fig. 1, a network implementation 100 of a system 102 for evaluating a difficulty level of content of an online tutorial based on physiological signals is illustrated, in accordance with an embodiment of the present subject matter. Although the present subject matter is explained considering that the system 102 is implemented on a server, it may be understood that the system 102 may also be implemented in a variety of computing systems, such as a laptop computer, a desktop computer, a notebook, a workstation, a mainframe computer, a server, a network server, and the like. In one implementation, the system 102 may be implemented in a cloud-based environment. In another embodiment, it may be implemented as custom built hardware designed to efficiently perform the invention disclosed. It will be understood that the system 102 may be accessed by multiple users through one or more user devices 104-1, 104-2…104-N, collectively referred to as user devices 104 hereinafter, or applications residing on the user devices 104. Examples of the user devices 104 may include, but are not limited to, a portable computer, a personal digital assistant, a handheld device, and a workstation. The user devices 104 are communicatively coupled to the system 102 through a network 106.
[0029] In one implementation, the network 106 may be a wireless network, a wired network or a combination thereof. The network 106 can be implemented as one of the different types of networks, such as intranet, local area network (LAN), wide area network (WAN), the internet, and the like. The network 106 may either be a dedicated network or a shared network. The shared network represents an association of the different types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), Wireless Application Protocol (WAP), and the like, to communicate with one another. Further the network 106 may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices, and the like.
[0030] In one embodiment the present invention, referring to Fig. 2, describes a detailed working of the various components of the system 102.

[0031] A system (102) for evaluating a difficulty level of content of an online tutorial based on physiological signals; comprising a processor (202), a memory (206), operatively coupled with said processor. The system (102) further comprises an EEG sensor (224), a GSR sensor (226) and a PPG sensor (228). The input/output interface instructs a person to stay in a baseline state and carry out a trial state respectively. The task is performed by the person during the trial state. The EEG sensor senses an EEG signal of the person. The GSR sensor senses a GSR signal of the person. The PPG sensor senses a PPG signal of the user.
[0032] In an embodiment the EEG signal, the GSR signal and the PPG signal are segmented in to a baseline interval corresponding to the baseline state, and a learning interval corresponding to the learning state using a segmentation module (210). The system (102) is further configured to calculate the cognitive load for the user by using a time-frequency based S- transform feature extraction technique to extract one or more features from the segmented EEG signal using an EEG signal processing module (212), calculate a normalized tonic power for the user using a N point Fast Fourier Transform (FFT) on the segmented GSR signal and applying inverse FFT based on coefficients of the N point FFT corresponding to baseline state and learning state, using a GSR signal processing module (214) and calculate a heart rate (HR) and heart rate variability (HRV) using a peak to peak difference in the PPG and a standard deviation of the normal-to-normal heart beat (SDNN) on the segmented PPG signal using a PPG signal processing module (216).
[0033] Finally the difficulty of the content of the online tutorial is evaluated by the system (102) based on the calculated cognitive load, the calculated tonic power, the calculated HRV and a calculated baseline using an evaluation module (218).
[0034] According to an implementation of the disclosed system (102) the EEG signal is used for measuring cognitive load. The cognitive load L(n), is the product of change in the peak frequency and the magnitude for both alpha and theta band compared to the baseline and is calculated using equation (1).

[0035] Brain signals are basically stochastic in nature due to its non-deterministic nature, therefore in an embodiment some statistical analysis on L(n) may be performed. The asymmetry in L(n) is measured by measuring the skewness. Further the kurtosis also measured to investigate the distribution of L(n)over the task interval. . The skewness and kurtosis are computed on N consecutive data points corresponding to a window of duration 1 second, as per equation (2).
[0036] In another embodiment tonic power is measured from the sensed GSR signal. GSR is the measure of electrical characteristics of skin. Skin conductance, controlled by sweat gland activity, gives an indication of skin psychological arousal, stress etc. A GSR signal has two components a slow varying component called tonic and a fast varying component called phasic. The components corresponding to the frequencies < 0.5 Hz are tonic components and the remaining are called phasic component. For calculation, N point Fast Fourier Transform (FFT) of the complete signal is done using equation (3), where f is signal frequency, fs sampling frequency, k = 1,2,3,..., N-1. Let at f = 0.5Hz, k = kT.
[0037] The tonic power is computed by taking the inverse FFT (IFFT) of the first kT coefficients of the FFT of the GSR signal as per equation (4) whereas the phasic component is calculated by taking IFFT of coefficients from kT+1 to N~1 as per equation (5).
[0038] Since the skin conductance and hence the tonic power varies from person to person, the calculated tonic power is normalized as per equation (6) for comparing the results across users. The entire task data was concatenated for a participant to normalize and then again crop the data corresponding to each task.

[0039] In an embodiment of the disclosed invention the PPG signal obtained from the PPG sensor is used to measure the heart rate (HR) and the heart rate variability (HRV). HRV, the variations in instantaneous HR, is derived from peak-to-peak (R-R interval) difference in the PPG. In an embodiment SDNN (standard deviation of the normal-to-normal heart beat) may be implemented to measure the HRV which is used as an indicator of mental stress.
[0040] Referring now to Fig. 3 a flow chart illustrating the method for evaluating a difficulty level of content of an online tutorial based on physiological signals is shown. The process starts at step 302 where users are instructed to stay in a baseline state and a learning state respectively. In one scenario this instruction may be given using a user interface. In an embodiment a baseline is calculated during the baseline state and the online tutorial is performed by the person during the learning state.
[0041] At the step 304 an Electroencephalograph (EEG) sensor senses the EEG signal of the users, a Galvanic skin response (GSR) sensor senses the GSR signal of the users, and a Photoplethysmogram (PPG) sensor senses the PPG signal of the user.
[0042] At the step 306 the signals are segmented in to a baseline interval corresponding to the baseline state, and a learning interval corresponding to the learning state.
[0043] At the step 308 the cognitive load for the users is calculated by using a time-frequency based S- transform feature extraction technique to extract one or more features from the segmented EEG. Further at the step 308 a normalized tonic power for the user using a N point Fast Fourier Transform (FFT) on the segmented GSR signal and applying inverse FFT based on coefficients of the N point FFT corresponding to baseline state and learning state, and a heart rate (HR) and heart rate variability (HRV) is calculated using a peak to peak difference in the PPG and a standard deviation of the normal-to-normal heart beat (SDNN) on the segmented PPG signal.

[0044] Finally at the step 310 the difficulty level of the content of online tutorial is evaluated based on the calculated cognitive load, the calculated tonic power, the calculated HRV.
[0045] The following paragraphs contain experimental data from one implementation of the proposed method and system. It will be clear to a personal skilled in the art that the disclosed system and method may be implemented using various implementation.
[0046] The intention of the following paragraphs is to better explain the working of the instant method and system and should not be considered limiting the disclosure which is limited only by the following claims.
[0047] For the purpose of the experiments the style of content delivery to the users is kept unaltered. All contents are textual type with 4 slides each. However, the vocabulary, sentence complexity, text structure, are modified to make the content easy or difficult. Texts are organized in a block for a specific learning element and pictorial representations are used for better understanding of the topic. The major focus is given to the subject matter. The contents primarily cover the relational database, its challenges and emergence of NoSQL database language. A basic introduction of Structured Query Language (SQL), its challenges and comparison with NoSQL are highlighted in the easy content. The difficult content goes few levels up for the learning objectives. Sample slides used during the experiment are shown in Fig. 4. For analyzing the design of the tutorials, questionnaire-based feedback was taken from experts of NoSQL. The questionnaire included feedback on the difficulty level, information content, etc. for both the tutorials. Subject matter experts responded in a five-point Likert scale. The separation in terms of difficulty level is analyzed using the Kruskal-Wallis test as the distribution of the feedback is non-normal. As per the shared results p = 0.0013, chi-square (χ2) = 10.28, hence, the null hypothesis, that the tutorials are similar is rejected.
[0048] Referring now to Fig. 5 the experimental setup used to perform the experiment is shown. The tutorials are shown on a 17inch computer screen kept at a viewing distance of 60cm. A single lead, dry, wireless portable EEG headband from NeuroSky™ having sampling frequency of 512Hz is used. The headband is communicating with the host machine via Bluetooth. The device contains an ear clip that acts as the reference. Brain activations are measured through the

lead placed at FP1 position. The GSR sensor used in the instant experimental implementation is from eSense™ having sampling frequency of 5Hz. The device measures the skin conductance level by applying a very low amount of voltage between index finger and middle finger of the medial phalanges. The velcro electrodes have been replaced by gel-based disposable electrodes for better connectivity. The data is transferred to a phone running android operating system at runtime through an application.
[0049] At the beginning of the experiment, an instruction slide is presented for 10 sec which participants are instructed to read carefully. Next they are instructed to relax for 30sec, during which a black screen with a white fixation cross at the middle, is shown. This duration is treated as the baseline period and is used to correct the individual differences. At the end of this 30s, the learning material (either easy or difficult) is presented. Participants are said to read that attentively. There is a provision to navigate back in order to revise the content again. At the end, four multiple choice questions are shown on the material and the participants are to answer them. The questions were given to ensure that the participants actually read the tutorials. For half of the participants, the difficult content is presented first and for remaining the easy content is presented first. This is done to study the effect of sequence of difficulty level on physiological changes. A relaxation time of 15 min is given in between the two tasks.
[0050] The details of the participants performing the experiment are provided in Table 1 below. Few of the college students studied SQL in previous semester and hence have some knowledge about the tutorial topic. Depending on the knowledge on SQL, NoSQL and general programming, four groups (PG1 - PG4) were created as shown in Table 2. PG1 group was rejected since for them both the tutorials might seem to have same difficulty level. We did all further analysis considering PG2 group only.

From Age (yrs) Educational background Number
Research lab 25-35 Bachelor degree in engineering 20
Engineering College 18-22 Pursuing bachelor degree 20

Non engineering students 18-22 Pursuing Masters in CS 20
Table 1. Distribution of participants from colleges and research lab

Group SQL NoSQL Database Students Professionals
PG1 √ √ √ × ×
PG2 √ × √ 30 17
PG3 × × √ 3 3
PG4 × × × 7 0
Table 2. Grouping of participants based on background knowledge
[0051] In order to analyze the EEG signal, NeuroSky™ reported attention values (on a scale of 1 to 100) are used for baseline correction. According to the manual, a values of 40-60, are treated as the neutral value. Analysis of the experimental data found that these limits vary from person to person. Hence the median of the entire baseline interval of an individual was calculated and
used that as the neutral attention level. Next Lwskew and LwKurt were evaluated using equation
(2). The analysis is done in windows of duration 1 sec. The percentage accuracy using kurtosis (K), skewness (S) for various conditions are listed in Table 3 below.

Subjects Accuracy without any constraints Accuracy with time constraints Accuracy without Back button

K S K S K S
Students 56 48 75 66.67 75 66.67
Professionals 64.28 64.28 83.3 83.3 83.3 83.3
Table 3. Accuracy (%) of cognitive load detection for various conditions
0052] The easy and difficult tutorial contents are expected to impart low and high cognitive
oad respectively. If this is fulfilled, then the detection is treated as accurate. Further time
constraints were applied on the recorded data. A back button was introdued to investigate the

effect of split attention. In online learning, the split attention of the learner is avoided by reducing the need to scroll back and forth between webpages. The tutorials were presented in slides, so scrolling back and forth corresponds to using back/forward button. Results show that avoiding back button improves the overall results. While using back button, new information are processed while holding the information from some other part. The accuracy of cognitive load detection is low for the participants who have used the back/forward button and didn’t reflect enough difference between the tutorials.
[0053] Further while analyzing GSR data Normalized tonic power for both the tutorials (easy and difficult) are calculated using equation (5). For overall accuracy a similar approach as adopted for analysis of EEG signals was used. If the tonic power while reading the difficult content is higher than that for the easy content, then it is treated as accurate detection of the stress level. The results are shown in Table 4. Also the effect of sequence of presentation was analyzed and the results of ANOVA analysis are shown in Fig. 6. The plot shows that if easy material is presented first, then we get better separation for tutorials. Reverse trend is observed for students for high-low sequence.
[0054] In order to analyze the PPG data and calculate HR and HRV data, the PPG signal is normalized and shifted to zero mean. Subsequently a band pass filter (0.5 - 5 Hz) is used to remove the high frequency components. Finally, peak detection is used to calculate the n-n interval. HRV is also calculated using SDNN. The PPG data for 21 participants are very noisy hence rejected. Fig. 7 shows HRV for 15 participants. Results show that 9 participants have higher HRV during easy tutorial (t1) compared to difficult (t2) indicating 67% accuracy.
[0055] On analysis of the results the EEG based cognitive load gives 83% accuracy considering usage of no back buttons, GSR based analysis provides 90% accuracy and HRV based analysis provides 67% accuracy and this data together is used to evaluate the different online tutorial content and categorize the content as easy or difficult.

I/We Claim:
1. A method for evaluating a difficulty level of content of an online tutorial based on physiological signals, the method comprising processor implemented steps of:
instructing one or more users to stay in a baseline state and a learning state respectively using a user interface (204), wherein a baseline is determined during the baseline state and the online tutorial is performed by the person during the learning state;
sensing an Electroencephalograph (EEG) signal of the one or more user using an EEG sensor (224);
sensing a Galvanic Skin Response (GSR) signal of the one or more user using a GSR sensor (226);
sensing a Photoplethysmogram (PPG) signal of the one or more user using a PPG sensor (228);
segmenting the EEG signal, the GSR signal and the PPG signal in to a baseline interval corresponding to the baseline state, and a learning interval corresponding to the learning state using a segmentation module (210);
calculating the cognitive load for the user by using a time-frequency based S-transform feature extraction technique to extract one or more features from the segmented EEG signal using an EEG signal processing module (212);
calculating a normalized tonic power for the user using a N point Fast Fourier Transform (FFT) on the segmented GSR signal and applying inverse FFT based on coefficients of the N point FFT corresponding to baseline state and learning state, using a GSR signal processing module (214);
calculating a heart rate (HR) and heart rate variability (HRV) using a peak to peak difference in the PPG and a standard deviation of the normal-to-normal heart beat (SDNN) on the segmented PPG signal using a PPG signal processing module (216); and
evaluating the difficulty of the content of the online tutorial based on the calculated cognitive load, the calculated tonic power, the calculated HRV and a calculated baseline using an evaluation module (218).

2. The method according to claim 1 further comprising of sub dividing the EEG signal, the GSR signal and the PPG signal into windows of 1 second duration using the segmentation module (210).
3. The method according to claim 1 wherein statistical analysis is performed on the calculated cognitive load to measure skewness and kurtosis, using the EEG signal processing module (212).
4. The method according to claim 1 wherein calculating the normalized tonic power using the GSR signal processing module (214) comprises:
applying N point FFT on the sensed GSR signal;
calculating a tonic and a phasic component by applying inverse FFT based on the resulting coefficients of the N point FFT corresponding to baseline state and learning state;
calculating a normalized tonic power by concatenating the entire learning state data for each of the one or more users and cropping the data corresponding to each task.
5. The method according to claim 1 wherein the EEG sensor, the GSR sensor, the PPG sensor are wearable devices worn by the user at the time of performing the online tutorial.
6. A system (102) for evaluating a difficulty level of an online tutorial based on physiological signals; comprising a processor (202), a memory (206), operatively coupled with said processor, the system comprising:
a user interface (204) configured to instruct one or more user to stay in a baseline state and a learning state respectively, wherein a baseline is calculated during the baseline state and the online tutorial is performed by the person during the learning state;
an EEG sensor (224) configured to sense an EEG signal of the one or more user;
a GSR sensor (226) configured to sense a GSR signal of the one or more user;
a PPG sensor (228) configured to sense a PPG signal of the one or more user;

a segmentation module (210) configured to segment the EEG signal, the GSR signal and the PPG signal in to a baseline interval corresponding to the baseline state, and a learning interval corresponding to the learning state;
an EEG signal processing module (212) configured to calculate the cognitive load for the user by using a time-frequency based S- transform feature extraction technique to extract one or more features from the segmented EEG signal;
a GSR signal processing module (214) configured to calculate a normalized tonic power for the user using a N point Fast Fourier Transform (FFT) on the sensed GSR signal and then applying inverse FFT based on coefficients of the N point FFT corresponding to baseline state and learning state;
a PPG signal processing module (216) configured to calculate a heart rate (HR) and heart rate variability (HRV) using a peak to peak difference in the PPG and a standard deviation of the normal-to-normal heart beat (SDNN) on the segmented PPG signal; and
an evaluation module (218) configured to evaluating the difficulty level of the content of online tutorial based on the calculated cognitive load, the calculated tonic power, the calculated HRV and the calculated baseline.
7. The system according to claim 6 wherein the segmentation module (210) is configured to sub dividing the EEG signal, the GSR signal and the PPG signal into windows of 1 second duration.
8. The system according to claim 6 wherein the EEG signal processing module (212) is further configured to perform statistical analysis on the calculated cognitive load to measure skewness and kurtosis
9. The system according to claim 6 wherein the GSR signal processing module (214) is configured to:
apply N point FFT on the sensed GSR signal;
calculate a tonic and a phasic component by applying inverse FFT based on the resulting coefficients of the N point FFT corresponding to baseline state and learning state;

calculate a normalized tonic power by concatenating the entire learning state data for each of the one or more users and cropping the data corresponding to each task.
10. The system according to claim 6 the EEG sensor, the GSR sensor, the PPG sensor are wearable devices worn by the one or more user at the time of performing the online tutorial.
ysiological signals like brain signals, galvanic skin response, pulse-oximeter signals, for evaluating online tutorials in terms of difficulty levels. A baseline is determined for the users taking the test during a baseline state. Electroencephalograph (EEG), Photoplethysmogram (PPG) and (Galvanic skin response) GSR signals are sensed while the users perform an online tutorial during a learning state using low cost sensors and the result is analyzed vis-à-vis the calculated baseline to evaluate an online tutorial.