Arnab Rakshit

Followers

Following

Public Views

Uploads

Papers by Arnab Rakshit

Brain–Computer Interface for Fuzzy Position Control of a Robot Arm by Mentally Detected Magnitude and Sign of Positional Error

Lecture notes in electrical engineering, 2023

Detection and Classification of Cyber Threats in Tweets Toward Prevention

Lecture Notes in Electrical Engineering

Autonomous grasping of 3-D objects by a vision-actuated robot arm using Brain–Computer Interface

Biomedical Signal Processing and Control

Microbiome in Pulmonary Tuberculosis

Microbiome in Inflammatory Lung Diseases

Brain-Computer Interface based User Authentication System for Personal Device Security

2020 International Conference on Computer, Electrical & Communication Engineering (ICCECE), 2020

The paper proposes a novel technique of EEG induced Brain-Computer Interface system for user auth... more The paper proposes a novel technique of EEG induced Brain-Computer Interface system for user authentication of personal devices. The scheme enables a human user to lock and unlock any personal device using his/her mind generated password. A two stage security verification is employed in the scheme. In the first stage, a $3 \times 3$ spatial matrix of flickering circles will appear on the screen of which, rows are blinked randomly and user has to mentally select a row which contains his desired circle.P300 is released when the desired row is blinked. Successful selection of row is followed by the selection of a flickering circle in the desired row. Gazing at a particular flickering circle generates SSVEP brain pattern which is decoded to trace the mentally selected circle. User is able to store mentally uttered number in the selected circle, later the number with it’s spatial position will serve as the password for the unlocking phase. Here, the user is equipped with a headphone where numbers starting from zero to nine are spelled randomly. Spelled number matching with the mentally uttered number generates auditory P300 in the subject’s brain. The particular choice of mentally uttered number is detected by successful detection of auditory P300. A novel weight update algorithm of Recurrent Neural Network (RNN), based on Extended-Kalman Filter and Particle Filter is used here for classifying the brain pattern. The proposed classifier achieves the best classification accuracy of 95.6%, 86.5% and 83.5% for SSVEP, visual P300 and auditory P300 respectively.

Discriminating different color from EEG signals using Interval-Type 2 fuzzy space classifier (a neuro-marketing study on the effect of color to cognitive state)

2016 IEEE 1st International Conference on Power Electronics, Intelligent Control and Energy Systems (ICPEICES), 2016

Color perception is one of the most important cognitive features of human brain. Different colors... more Color perception is one of the most important cognitive features of human brain. Different colors lead to different cognitive activities and different mental arousal levels; as revealed by power spectral density obtained from EEG signals. As the color plays an important role in marketing and packaging industry; so neuro-marketing research; based on color stimuli is considered to be an important tool for market researcher. In order to assess the impact of each color; prime focus is to detect different colors from EEG signals. This study employs four color stimuli; e.g. red; green; yellow and blue; that were shown to various subjects and EEG signal corresponding to the mentioned stimulus was acquired. Power spectral density of each color was estimated and different activation areas of brain for each stimulus is illustrated in figures. This paper also employs an Interval-Type-II fuzzy space classifier for distinguishing between different stimuli that are considered for the concerned experiment. It is noted that classification rate is maximum for red color and minimum in case of yellow color. Precision and recall values also have been highlighted here. For detailed analysis; the performance of IT2FS classifier has been compared with other standard classifiers by Friedman Test.

Geometry Perspective Of Estimating Learning Capability Of Neural Networks

ArXiv, 2020

The paper uses statistical and differential geometric motivation to acquire prior information abo... more The paper uses statistical and differential geometric motivation to acquire prior information about the learning capability of an artificial neural network on a given dataset. The paper considers a broad class of neural networks with generalized architecture performing simple least square regression with stochastic gradient descent (SGD). The system characteristics at two critical epochs in the learning trajectory are analyzed. During some epochs of the training phase, the system reaches equilibrium with the generalization capability attaining a maximum. The system can also be coherent with localized, non-equilibrium states, which is characterized by the stabilization of the Hessian matrix. The paper proves that neural networks with higher generalization capability will have a slower convergence rate. The relationship between the generalization capability with the stability of the neural network has also been discussed. By correlating the principles of high-energy physics with the l...

Download

Decoding of Mind-Generated Pattern Locks for Security Checking Using Type-2 Fuzzy Classifier

2018 IEEE Symposium Series on Computational Intelligence (SSCI), 2018

Brain Computer Interface (BCI) aims at providing a better quality of life to people suffering fro... more Brain Computer Interface (BCI) aims at providing a better quality of life to people suffering from neuromuscular disability. This paper establishes a BCI paradigm to provide a biometric security option, used for locking and unlocking personal computers or mobile phones. Although it is primarily meant for the people with neurological disorder, its application can safely be extended for the use of normal people. The proposed scheme decodes the electroencephalogram signals liberated by the brain of the subjects, when they are engaged in selecting a sequence of dots in(6×6)2-dimensional array, representing a pattern lock. The subject, while selecting the right dot in a row, would yield a P300 signal, which is decoded later by the brain-computer interface system to understand the subject’s intention. In case the right dots in all the 6 rows are correctly selected, the subject would yield P300 signals six times, which on being decoded by a BCI system would allow the subject to access the ...

Discriminating Motor Imagery EEG signals using an improvised regularised CSP algorithm

2016 IEEE 1st International Conference on Power Electronics, Intelligent Control and Energy Systems (ICPEICES), 2016

Common Spatial Pattern is considered as one of the most efficient feature extraction methods for ... more Common Spatial Pattern is considered as one of the most efficient feature extraction methods for rehabilitative BCI paradigms. In the past many researchers have devoted their financial and intellectual resources in the said domain with an aim to regularize the concept of CSP by adding prior information in order to reach closer to the desired objective. In this paper; a novel penalty term has been introduced as an extension of one of the most popular variants of RCSP algorithms; formally termed as Weighted Tikhonov Regularized CSP. The proposed strategy has been implemented for deciphering four class Motor Imagery signals recorded from different users while performing four imagined movements of right hand and left hand. An ensemble classifier comprising of k-NN layers has been used for the classification purpose and finally; the efficiency of the proposed framework has been tested against the traditionally used standard classifiers and in each case the designed algorithm outperformed...

A Novel Hybrid Brain-Computer Interface for Robot Arm manipulation using Visual Evoked Potential

2017 Ninth International Conference on Advances in Pattern Recognition (ICAPR), 2017

This paper attempts to solve an major problem of rigorous subject training in BCI based robotics.... more This paper attempts to solve an major problem of rigorous subject training in BCI based robotics. A hybrid Brain computer interface has been established here to mentally guide a robot arm without any motor commands generated in mind. Spontaneous N200 response of human brain as a part of motion onset visual evoked potential (m VEP) is used here to detect the desired object in the environment and use of Steady state visual evoked potential (SSVEP) provides the guidance to a bedside robotic arm to reach that target object. Electroencephalographic response of ten such subjects has been used here to evaluate the efficacy of the proposed system. Recorded EEG response goes through a sequential operation of preprocessing, feature extraction and classification. For detecting N200 response of the brain, a novel EKF-Particle filter induced Neural Network classifier is also proposed which essentially outperforms the other existing classifier for N200 detection. Performance analysis of other classifiers has been given here for comparison.

Fractal analysis of EEG signals for studying the effect of cognitive stress on brain

International Journal of Biomedical Engineering and Technology, 2017

This work aims to study the development of stress in different section of brain under various men... more This work aims to study the development of stress in different section of brain under various mental stress conditions, while the brain performs variety of cognitive tasks. The cognitive tasks are designed so as to cover a wide range of brain activities, which includes puzzle solving, decision making, mathematical calculation, memorisation and recollection, correlation and matching. The purpose is to see whether different level of stresses could be developed under varied conditions. In this article we use Multifractal Detrended Fluctuation Analysis (MFDFA) to observe the different changes in different lobes of the brain. It is found that there is an effect on frontal and parietal lobes during the cognitive task. In order to confirm the results of MFDFA analysis, we also obtain topological scalp map. The features of topological scalp map are found to support the results of MFDFA.

Download

A hybrid brain-computer interface for closed-loop position control of a robot arm

IEEE/CAA Journal of Automatica Sinica, 2020

Brain-Computer Interfacing has currently added a new dimension in assistive robotics. Existing br... more Brain-Computer Interfacing has currently added a new dimension in assistive robotics. Existing brain-computer interfaces designed for position control applications suffer from two fundamental limitations. First, most of the existing schemes employ open-loop control, and thus are unable to track the positional errors, resulting in failures in taking necessary online corrective actions. There are traces of one or fewer works dealing with closed-loop EEG-based position control. The existing closedloop brain-induced position control schemes employ a fixed order link selection rule, which often creates a bottleneck for timeefficient control. Second, the existing brain-induced position controllers are designed to generate the position response like a traditional first-order system, resulting in a large steady-state error. This paper overcomes the above two limitations by keeping provisions for (Steady-State Visual Evoked Potential induced) link-selection in an arbitrary order as required for efficient control and also to generate a second-order response of the position-control system with gradually diminishing overshoots/undershoots to reduce steady-state errors. Besides the above, the third novelty is to utilize motor imagery and P300 signals to design the hybrid brain-computer interfacing system for the said application with gradually diminishing error-margin by speed reversal at the zero-crossings of positional errors. Experiments undertaken reveal that the steady-state error is reduced to 0.2%. The paper also provides a thorough analysis of stability of the closed-loop system performance using Root Locus technique.

Download

Electro-oculogram based digit recognition to design assitive communication system for speech disabled patients

2016 International Conference on Microelectronics, Computing and Communications (MicroCom), 2016

HCI (Human Computer Interfacing) technology is now able to provide an alternative support to the ... more HCI (Human Computer Interfacing) technology is now able to provide an alternative support to the speech disabled person who have undergone severe brain stroke or spinal cord injury. It has been presented here that amongst all bio potential signal Electro-Oculogram (EOG) signal has got the ability to represent all daily life characters which is most needed for communication. This paper is aimed to provide novel approach of rehabilitative HCI where it successfully classifies the numerical digits drawn by subject's eye movement and for achieving the result, electro-oculography sensors (dual channel) and amplifier has been designed, which is able to extract the sharp change of corneo retinal potential due to eyeball movement intended to draw a pattern (numeric digit, alphabet). The extracted signal has been processed and classified successfully with more than 90% accuracy rate and with suitable precision and sensitivity value. Here Power spectral density has been used as feature extractor and support vector machine with multilayer perceptron kernel function has been used as feature classifier. Performance of other classifiers also have been compared here. 12 healthy subjects took part in experiment and their eyeball movement signal has been acquired for distinguishing different numerical digits that are frequently needed for communication to external world.

Robotic link position control using brain computer interface

2016 International Conference on Microelectronics, Computing and Communications (MicroCom), 2016

Brain computer interfacing is a new paradigm to provide an alternative path of communication for ... more Brain computer interfacing is a new paradigm to provide an alternative path of communication for those, who have lost their sensory, motor and autonomous function limb movement from spinal cord injury or other neuronal disorder. To increase living standard of them, a thought controlled robot or robotic arm can be of great importance for their better communication to external world. This paper proposes a novel approach towards electroencephalogram based random order control of a robot manipulator. Here steady state visual evoked potential has been used to select the desired robot link and motor imagery signal has been used to control the motion of robot link. Left and Right hand motor imagery signal has been used in this purpose. Event related error potential is used for feedback purpose and to correct the positional error of link created by motor imagery. The robot link here is realigned by experimental offset. Power spectral density, common spatial pattern and moving average, have been used as feature extractor and support vector machine with linear kernel function has been used as the classifier. At first, the subject has been trained in offline experiment and then online session performance has been evaluated.

A Naïve Bayesian approach to lower limb classification from EEG signals

2016 2nd International Conference on Control, Instrumentation, Energy & Communication (CIEC), 2016

Lower limb movement decoding is the primary objective for designing Brain-computer interface (BCI... more Lower limb movement decoding is the primary objective for designing Brain-computer interface (BCI) controlled leg prosthesis. In this paper the main objective is to classify left-right leg movement directly from electroencephalography (EEG) signals by probabilistic Naive Bayesian approach. Wavelet based decomposition has been taken as feature extractor to take care of non-stationary nature of brain waves, that have been recorded from 12 healthy subjects. The proposed method achieved average accuracy of 78.33% with 11ms of execution time. Specificity, sensitivity, type 1 and type 2 error rate have also been determined for each case. Results of the classifier is compared with other standard classifiers and statistically validated by Friedman Test. Novelty of the paper lies in the fact that it considers the both frequency and spatial domain (location in time) features of EEG signal without sacrificing accuracy and very low execution time makes it feasible for real time application. It also shows the Naïve Bayes classifier with uniform prior probability is better classifier than standard Naïve Bayes classifier in recognizing left-right lower limb movement.

A back-propagation through time based recurrent neural network approach for classification of cognitive EEG states

2015 IEEE International Conference on Engineering and Technology (ICETECH), 2015

Decision making plays a very vital role in a person's life and hence any impairment of this a... more Decision making plays a very vital role in a person's life and hence any impairment of this ability is of great concern. Thus our study aims at designing such an experiment that will involve the task of decision making and assist in developing cognitive rehabilitation system in near future with the help of Brain Computer Interface. The brain signals are acquired using EEG (electroencephalography) and the two vital tools of BCI system, feature extraction and classification are implemented on these signals. The feature extraction is done using the time varying adaptive autoregressive algorithm. But the prime focus of this paper is the implementation of back propagation through time recurrent neural network algorithm as mental state classifier.

Application of Electrooculography to estimate word count while reading text

2016 International Conference on Systems in Medicine and Biology (ICSMB), 2016

In the process of reading evaluation, eye movement analysis plays an important role. This work pr... more In the process of reading evaluation, eye movement analysis plays an important role. This work proposes a human computer interactive system to assist children with reading disabilities to improve their reading by the analysis of eye movements. Here a system to track how many words a user reads is presented based on electrooculography technique. A laboratory developed Electrooculogram acquisition system has been used for recording the eye movements. A simple scheme is implemented to detect the words and new lines from eye movements and then count the total numbers read by the user. Results from a group of 10 volunteers show that this work successfully counts the number of words as well as the number of lines while reading a document. The results of this work are validated on ten healthy individuals. However, as the results reveal, the proposed system may be used to train and assist dyslexic or other reading disabled children.

Brain–Computer Interface for Fuzzy Position Control of a Robot Arm by Mentally Detected Magnitude and Sign of Positional Error

Lecture notes in electrical engineering, 2023

Detection and Classification of Cyber Threats in Tweets Toward Prevention

Lecture Notes in Electrical Engineering

Autonomous grasping of 3-D objects by a vision-actuated robot arm using Brain–Computer Interface

Biomedical Signal Processing and Control

Microbiome in Pulmonary Tuberculosis

Microbiome in Inflammatory Lung Diseases

Brain-Computer Interface based User Authentication System for Personal Device Security

2020 International Conference on Computer, Electrical & Communication Engineering (ICCECE), 2020

Discriminating different color from EEG signals using Interval-Type 2 fuzzy space classifier (a neuro-marketing study on the effect of color to cognitive state)

2016 IEEE 1st International Conference on Power Electronics, Intelligent Control and Energy Systems (ICPEICES), 2016

Geometry Perspective Of Estimating Learning Capability Of Neural Networks

ArXiv, 2020

Download

Decoding of Mind-Generated Pattern Locks for Security Checking Using Type-2 Fuzzy Classifier

2018 IEEE Symposium Series on Computational Intelligence (SSCI), 2018

Discriminating Motor Imagery EEG signals using an improvised regularised CSP algorithm

2016 IEEE 1st International Conference on Power Electronics, Intelligent Control and Energy Systems (ICPEICES), 2016

A Novel Hybrid Brain-Computer Interface for Robot Arm manipulation using Visual Evoked Potential

2017 Ninth International Conference on Advances in Pattern Recognition (ICAPR), 2017

Fractal analysis of EEG signals for studying the effect of cognitive stress on brain

International Journal of Biomedical Engineering and Technology, 2017

Download

A hybrid brain-computer interface for closed-loop position control of a robot arm

IEEE/CAA Journal of Automatica Sinica, 2020

Download

Electro-oculogram based digit recognition to design assitive communication system for speech disabled patients

2016 International Conference on Microelectronics, Computing and Communications (MicroCom), 2016

Robotic link position control using brain computer interface

2016 International Conference on Microelectronics, Computing and Communications (MicroCom), 2016

A Naïve Bayesian approach to lower limb classification from EEG signals

2016 2nd International Conference on Control, Instrumentation, Energy & Communication (CIEC), 2016

A back-propagation through time based recurrent neural network approach for classification of cognitive EEG states

2015 IEEE International Conference on Engineering and Technology (ICETECH), 2015

Application of Electrooculography to estimate word count while reading text

2016 International Conference on Systems in Medicine and Biology (ICSMB), 2016

Arnab Rakshit

Uploads

Papers by Arnab Rakshit

Log In