Tata Consultancy Services Limited

Rahul Dasharath Gavas

Debatri Chatterjee

Rajat Kumar Das

Ramesh Kumar Ramakrishnan

Arpan Pal

Balamuralidhar Purushothaman

Aniruddha Sinha

Kingshuk Chakravarty

Shreyasi Datta

Dibyanshu Jaiswal

Venkata Subramanian Viraraghavan

Mithun Basaralu Sheshachala

Pratyusha Das

Arijit Chowdhury

Arijit Sinharay

Achanna Anil Kumar

Anwesha Khasnobish

Oishee Mazumder

Girish Mariswamy Chandra

Abhijit Das

Tanushree Banerjee

Sachin Patel

Gauri Deshpande

Sanjoy Kumar Saha

Anagha Nikhil Mehrotra

Tince Varghese

Priya Singh

Ratnamala Manna

Rolif Lima

Somnath Karmakar

Uttama Lahiri

Vedraj

Arpit Vishwakarma

Anirban Chowdhury

Mithun Basaraku Sheshachala

Lalit Kumar Hissaria

This disclosure relates generally to method and system for predicting distance of gazed objects using IR camera. Eye tracking technology is widely used to study human behavior and patterns in eye movements. Existing gaze trackers focus on predicting gaze point and hardly analyzes distance of the gazed object from the gazer or directly classify region of focus. The method of the present disclosure predicts gazed objects distance using a pair of IR cameras placed on either side of a smart glass. The gaze predictor ML model predicts distance at least one gazed object positioned from eye of each subject during systematic execution of a set of tasks. From each pupillary information of each pupil a set of features are extracted which are utilized to classify the gazed object of the subject based on the distance into at least one of a near class, an intermediate class, and a far class.

Method and system for predicting distance of gazed objects using infrared (IR) camera

This disclosure relates generally to a method and system for classification of cognitive load (CL) using data obtained from wearable sensors. The disclosed method uses a multi-modal based approach using wrist-worn sensors for real time monitoring of CL in real world scenarios and improves the accuracy of detection of CL. A set of distinguishing features are selected from physiological signals received from the wrist-worn sensors. These features are used for training a classification model for classifying the CL of a patient into a no load or a high load. The set of distinguishing features are selected from domain specific features and signal property based generic features of the physiological signals. The disclosed method is used for classification of CL in scenarios such as to check how the cognitive load of a candidate varies during interviews, to assess the participants workload during online meetings and so on.

Method and system for classification of cognitive load using data obtained from wearable sensors

This disclosure relates to analyzing effect of a secondary cognitive load task on a primary executive task. Human random sequence generation is a marker to study cognitive functions and inability to generate random sequences (RS) can reveal underlying impairments. Traditionally, 'call out' or ‘write down’ procedures are used to obtain human generated numbers, wherein short term memory and number of previously generated entities visible to a subject plays a major role. Also precise trial-wise or response-wise analysis may not be possible. In the present disclosure, the human generated random numbers are digitized into RS and a cognitive load (CL) inducing task is imposed on the executive task. The CL demanding task disrupts randomization performance. Deviation from randomness, load index based on gaze data and deviation from pupillometry data of healthy subjects are provided as indicators of an interference effect imposed by the CL and thereby indicative of underlying impairments.

Analyzing effect of a secondary cognitive load task on a primary executive task

An important task in several wellness applications is detection of emotional valence from speech. Two types of features of speech signals are used to detect valence: acoustic features and text features. Acoustic features are derived from short frames of speech, while text features are derived from the text transcription. Present disclosure provides systems and methods that determine the effect of text on acoustic features. Acoustic features of speech segments carrying emotion words are to be treated differently from other segments that do not carry such words. Only specific speech segments of the input speech signal are considered based on a dictionary specific to a language to assess emotional valence. A model trained (or trained classifier) for specific language either by including the acoustic features of the emotion related words or by omitting it is used by the system for determining emotional valence in an input speech signal.

Selection of speech segments for training classifiers for detecting emotional valence from input speech signals

This disclosure relates generally to a method and system for assessment of sustained visual attention of a target. The conventional methods utilize various markers for assessment of attention, however, blink rate variability (BRV) series signal is not explored yet. In an embodiment, the disclosed method utilizes BRV series signal for assessing sustained visual attention of a target. A gaze data of the target is recorded using an eye tracker and a set of uniformly sampled BRV series signal is reconstructed from each of the BRV series. One or more frequency domain features, including pareto frequency, are extracted from the set of uniformly sampled BRV series signal. The values of frequency domain features extracted from the set of BRV series signals are compared with corresponding threshold values to determine visual sustained attention of the target.

System and method for eye-blink based assessment of sustained visual attention of a target

This disclosure relates generally to assessment of cognitive workload using breathing pattern of a person, where cognitive workload is the amount of mental effort required while doing a task. The method and system provides assessment of cognitive workload based on breathing pattern extracted from photoplethysmograph (PPG) signal, which is collected from the person using a wearable device. The PPG signal collected using the wearable device are processed in multiple stages that include breathing signal extraction to extract breathing pattern. The extracted breathing pattern is used for assessment of cognitive workload using a generated personalized training model, wherein the personalized training model is generated and dynamically updated for each person based on selection of a sub-set of breathing pattern features using feature selection and classification techniques that include maximal information coefficient (MIC) techniques. Finally based on personalized training model, the extracted breathing pattern is classified as high cognitive workload or low cognitive workload.

Method and system for assessment of cognitive workload using breathing pattern of a person

This disclosure relates generally to a Parkinson's disease detection system. Parkinson's disease is a neuro-degenerative disorder affecting motor and cognitive functions of subjects. Since symptom manifestation is limited in Parkinson's disease, identifying Parkinson's disease in the early stage is a challenging task. The present disclosure overcomes the limitations of the conventional methods for detecting Parkinson's disease by utilizing a graph theory approach. Here, each pressure sensor attached to an insole corresponding to a plurality of pressure points associated with a foot of the subject is considered as a node of a connectivity graph. The foot dynamics analysis is performed based on a metric known as mediolateral stability index and the mediolateral stability index is calculated by utilizing a betweenness centrality associated with each node of the connectivity graph. Further, the mediolateral stability index is compared with standard values to detect the intensity of the Parkinson's disease.

Method and system for detecting Parkinson's disease progression

System and method for digitized digit symbol substitution test (DSST) are disclosed. In an example, a display area of a digitized DSST device is partitioned into multiple bins. Further, a series of number symbol pairs is displayed as a lookup table on top of the display, termed as a lookup area. Furthermore, a question and answer (QA) pair corresponding to the series of number symbol pairs to an examinee in multiple trials. In addition, feature values for the QA pair are computed in each of the multiple bins in the trials, wherein the feature values comprise a response time and an accuracy of response by the examinee. Moreover, probabilities of the feature values are determined in each of the multiple bins. Also, an entropy value based on the probabilities of the feature values is computed in each of the multiple bins providing information on distribution.

System and method for digitized digit symbol substitution test

A method and system is provided for assessing the learning experience of the person by monitoring the mental state of the person. The method involves measuring the brain signal, skin conductance using GSR device, and heart rate variability using the pulse oximeter. These physiological signals are measured when the person is performing an activity such as the modified Stroop test. Once the activity is performed, an offline questionnaire is also filled by the person. Based on the comparison of the offline questionnaire and the physiological signals, a model is generated. This model is used to assess the learning experience of the person. According to another embodiment, a method is also provided for maintaining the steady flow state of a person while performing any activity.

Method and system for assessing learning experience of a person

A method and system is provided for pre-processing of an electroencephalography (EEG) signal for cognitive load measurement. The present application provides a method and system for pre-processing of electroencephalography signal for cognitive load measurement of a user, comprises of capturing the electroencephalography signal from the head of the user, detecting the plurality of system artifacts in the captured electroencephalography signal, detecting and removing noisy window from the captured electroencephalography signal, detecting an eye blink region and filtering out said detected eye blink region from the captured electroencephalography signal, utilizing the filtered electroencephalography signal for measuring the cognitive load of the user and subsequently computing different levels of mental workloads on the user using variation of spatial distribution of frontal scalp EEG electrodes for measured cognitive load.

Method and system for pre-processing of an EEG signal for cognitive load measurement

Traditional cognitive load estimation techniques rely on raw pupil size alone which is often prone to confound with changes in illumination, errors associated with sensor devices and irregular oscillations of pupil under constant light conditions. Estimation of cognitive load finds application in many domains including optimum work allocation, assessing a work environment and medical diagnosis. The present disclosure employs frequency domain analysis of pupil size variations to estimate load imposed by a cognitive task. A cognitive load metric based on power and frequency relations at mean frequency of the variation in pupil size addresses cognitive load estimation based on pupil dilation, wherein the pupil dilation is captured by employing low cost non-intrusive nearables.

Cognitive load estimation based on pupil dilation

System and method for aiding communication for subjects suffering from paralysis of muscles controlled by peripheral nervous system are disclosed. A method for aiding communication for said subjects includes capturing, from a plurality of sensors, sensor data generated based on an interaction of a subject with an interactive UI. The plurality of sensors includes one or more body-parts movement tracking sensors for tracking motion of body-parts of the subject and one or more physiological signal sensors for monitoring physiological signals generated from the subject during the interaction. A plurality of model parameters indicative of characteristics of the subject related to the interaction are determined based on the sensor data. The navigation at the interactive UI is controlled on the plurality of model parameters.

System and method for aiding communication

A method and system for determining cognitive load of a person using a modified baseline is provided. The person is asked to perform a series of activities including staying in eye closed rest state and baseline state and performing a trial state. Simultaneously, EEG signal and GSR signal of the person are captured. The EEG signal and the GSR signal are preprocessed and segmented. The EEG and GSR signals are then used to determine a first set and a second set of inactive states from the baseline interval and the rest interval. The most inactive window is then identified out of the first set of inactive states. The most inactive window is determined from the rest interval of the person. The inactive window is used as the modified baseline to measure the cognitive load of the person.

Growing community of inventors

Kolkata, India

Rahul Dasharath Gavas