Content uploaded by Sunil Kumar
Author content
All content in this area was uploaded by Sunil Kumar on Jul 16, 2021
Content may be subject to copyright.
DOI: 10.4018/IJMDWTFE.2019070103
Volume 10 • Issue 2 • July-December 2019
Copyright © 2019, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.
38
Sravanth K. Ramakuri, Vallurupalli Nageswara Rao Vignana Jyothi Institute of Engineering and Technology, India
Premkumar Chithaluru, Dept. of Systemics, School of Computer Science, University of Petroleum and Energy Studies, India
Sunil Kumar, Dept. of Cybernetics, School of Computer Science, University of Petroleum and Energy Studies, India
https://orcid.org/0000-0001-9957-5661
The human brain is the central organ of the human system. Many people in the world cannot move on
their own and can’t control things on their own. A person whose brain is active can control things using
the neuro-controlled robot car. It is interesting to all types of people to measure their concentration
and piece level of mind with the neuro sky mind wave device. One can easily control the robot’s
movements by simply blinking eyes; the robot’s speed will be according to the subject’s attention
levels. The neuro sky mind wave device digitizes brain wave signals to power the user-interface of
the computers, game, and health application. The neuro sky mind wave device will measure brain
waves from the forehead. The paper aims to control a robot using the brain-computer interface concept
without any muscular activity controlling healthcare applications directions. The brain activity is
recorded with the neuro sky mind wave device’s help, and the attention values are sent to the Arduino
with the help of the HC-05 Bluetooth module. Arduino is programmed so that if the attention values
between 0-29 and the person are relaxed, the green light will glow for the feedback.
Brain Waves, Brain-Computer Interface, EEG, Health Application, Healthcare, Neuro Sky Mind Wave Device,
Robot Car, Signal Processing
Wheelchairs have been around for a long time; over time, the design and functionality of wheelchairs
have improved with the invention of the first lightweight, collapsible and mass-produced wheelchair in
1933 by Harry Jennings and Herbert Everest serving as the introduction of the modern-day wheelchair
(Donoghue, 2002; Katona & Kovari, 2015; Morshed & Khan, 2014; Palaniappan et al., 2009; Sravanth,
Peddi, Sagar, Gupta, & Chakraborty, 2018). Further, the wheelchair has evolved with the growth and
development of technology. In addition to the traditional man power-driven wheelchair, the electric
and battery-powered wheelchair is now also available. Moreover, wheelchairs still are taken further
with the power of brain waves.
Volume 10 • Issue 2 • July-December 2019
39
The processing unit and the coordination unit, which controls the human body’s actions, is the
brain. The brain comprises billions of neurons, which are interconnected with the help of synaptic
gaps. The recognition or performance of the actions is done by the action potential generated by the
neurons, which are firing neurons. The brain generates different waves based on moods. The scientists’
research took them forward to record such brain activity, which is termed the electroencephalography
(EEG). Han Berger does the first recording of the human brain in 1924. The EEG can be done in two
different ways: an invasive method and the other is a non-invasive method. In the invasive methods,
we have to make the surgery such that the necessary electrodes which record the waves are placed
on the brain, which is placed very carefully, and it is a time taking process. On the other side, the
non-invasive involves placing the electrodes on the scalp, which is a straightforward process. In the
earlier days, the brain wave currents are observed using galvanometers, but nowadays, the technology
is advancing such that it leads a pathway to different ways of recording brain activity. Now the day
has come where we record the brain activity with a device consisting of a single dry electrode, and
these devices are wireless, which can transmit the continuous data of the brain waves. The technology
emerges in a way that the control of the machines is made possible with the brain’s help, which is
known as the brain-computer interface or brain-machine interface. The brain-computer interface’s
main thing is the brain waves, which are categorized based on the frequencies used to develop various
applications.
In this paper, we will record the brain activity of the human brain by using a wireless wearable
EEG device with a single dry electrode, which is very comfortable and approved where no risk is
involved. To detect the blink of an eye, the thinkgear.dll file, which we will use, is with the software
MATLAB. This helps detect the blinks of a person, which is used for interfacing the more devices
and monitoring them and controlling with such states.
The device Neuro-Sky Mind-Wave headset is placed on the subject’s scalp such that the device
is used to capture the subject’s brain activity. MATLAB receives the brain signals through Bluetooth
and processes the blink detection data using the think-gear file. After blink detection, the direction is
decided and sends a command to the Arduino. Here Arduino interfaces the Bluetooth module and the
Motor driver. The command received from MATLAB through Bluetooth module to a microcontroller
is programmed for the motor driver to move according to the command’s direction. Two motors are
used for the robot in the front, back, right, and left directions. Now the subject is made to perform
blinking the eyes; the robot will move according to the direction the subject requires. This feedback
can be made input to the other devices, and we can control them.
The brain comprises billions of neurons, which are interconnected to one another with the synapses
with a gap. The electrical impulse generated in one neuron woke up all the other associated neurons in
a parallel manner such that a large amount of electrical activity is generated by the coordination of all
the neurons (Sravanth, Peddi, Sagar, Gupta, & Chakraborty, 2018). The study of such brain activity is
known as the EEG. The first brain activity was recorded by Richard canton from the animal’s brain;
later, Hans Berger was the first person to record human brain activity. The galvanometer is used in
the earlier days to measure the electrical currents.
Based on the human’s moods, the electrical activity is varied such that human brain brainwaves
are characterized into five types, i.e., Delta, Theta, Alpha, Beta, and Gamma. Delta (0.5-3.5Hz)
- these are slow waves that are generally observed when the person is in REM sleep and relaxed.
Theta (3.5-8Hz), these waves are generally observed when the person is in the meditated state or
deep sleep or when the person is in an imaginary state Alpha (8-13.5Hz) waves are observed when
the person is conscious but in the meditation state and also in the calm state. Beta (13.5 to 30Hz)
waves are observed when a person in attention and problem solving, and Gamma >30 Hz waves are
Volume 10 • Issue 2 • July-December 2019
40
observed when a person is at a high state of motor functioning abilities as shown in Table 1 (Katona
& Kovari, 2015) (Liu et al., 2010).
This process is divided into two parts: connecting the hardware and the other is software. Neurosky
Mind wave Device is a wireless device with a single dry electrode and the other hardware. Arduino
is a microcontroller and one HC-05 Bluetooth module LEDs, wires, breadboard.
The Neurosky mind wave headset costs about $100, and the battery is a single AAA battery
(Debener et al., 2012; Eason et al., 1955; Sourina et al., 2011), which gives about 8 hours run time.
It has the parts like the adjustable headband, sensor tip/arm, power switch, flexible ear arm, an ear
clip, and thinks gear chipset. The power switch is used to switch on the device, and the lights of
the led are varied, and each color and blinking having a different meaning. Table 2 shows the light,
connection status, and the respective meaning.
The adjustable band is fixed to 90 degrees, which has a sensor to be adjusted exactly to the forehead
so that the sensor’s edge should touch the forehead, which records the brain activity as shown in Figure
1. The sensor which touches the forehead senses brain activity, and the data is processed in the think
Table 1. Frequency band classification based on Brain Activity (Palaniappan et al., 2009) (Sravanth, Peddi, Sagar, Gupta, &
Chakraborty, 2018) (Katona & Kovari, 2015)
Brainwave Type Frequency Range Mental States and Conditions
Gamma wave >30 Hz Different motor functions
Beta 13.5 Hz to 30Hz Attention problem solving
Alpha 8Hz to 13.5Hz Meditation, Relaxed
Theta 3.5 Hz to 8Hz Slow-wave, Deep sleep
Delta 0.5 Hz to 3.5Hz REM sleep, Slow-wave
Figure 1. Neurosky mind wave headset
Volume 10 • Issue 2 • July-December 2019
41
gear headset; the sensor tip is used to capture the electrical signals from the forehead, and the ear clip
is used as the reference. Later these captured signals are processed in the think gear chipset, and this
data is sent to the Arduino through the HC-05 module (Barrett et al., 1976; Chithaluru, Al-Turjman,
Kumar et al, 2020; Chithaluru et al., 2019a; Chithaluru et al., 2021; Nuwer et al., 1994; Sałabun,
2014). As the Arduino we are using doesn’t have the inbuilt Bluetooth on the board, we use an extra
Bluetooth module. We use a breadboard for reducing the complexity in the connections, and we use
three types of LEDs for the indication of different states.
The HC-05 Bluetooth module (Chithaluru, Tanwar, & Kumar, 2020; Suleiman & Fatehi, 2007;
Tong et al., 2017; Übeyli & Güler, 2004) is used to transfer the data or receive the data serially by
making the Bluetooth a slave or master, as shown in Figure 2. By default, the module is a slave. If
we want to configure, then we should follow the AT commands. The Bluetooth module’s operating
voltage is from 4v to 6v, and its range is 100m, and it follows the IEEE 802.15.1 standardized protocol.
The module comprises 6 different pins that are used for the establishment of the connection. (1) VCC,
(2) GND, (3) TxD, and RxD, (4) State, (5) Enable, and (6) Button switch.
The device requires some power supply to switch on, and for working so the Vcc is connected to
the power supply, and the ground is given to the ground pin, and the TxD is used to transmit the serial
Table 2. Mind wave device functioning (Palaniappan et al., 2009) (Chithaluru et al., 2021) (Ramakuri et al., 2019)
Function Device Display
Off Powered off The device is turned off or has no
battery
Double Blinking Blue Pairing mode The device is ready to be paired with
a device
Solid Red Unpaired The device needs to be paired with a
device
Single Blinking Blue Ready The device is waiting for a paired
device to connect
Solid Blue Connected The device is communicating with a
paired device
Double Blinking Red Low battery Check the battery function
Figure 2. Bluetooth HC-05 module
Volume 10 • Issue 2 • July-December 2019
42
data, and the RxD is used to receive the serial data, and the button switch is used for changing to the
AT mode. The module’s lead gives the status in such a way that when the led flashes continuously,
then the module is said to be on, and it is ready for pairing. A single blink of the led indicates that
the module is paired with a device and the double blink indicates the connection to the other device.
Now after setting up the module, check the status, and connect with the Arduino. Arduino is the
microcontroller board used for some dedicated tasks; it can be programmed using Arduino software.
The board here we are using is Arduino UNO, which has 14 digital input/output pins out of which
6 pins are used as the PWM outputs, and there are 6 analog pins, and it contains a USB port where
we can supply the power to the board using the USB cable as shown in Figure 3. We can supply the
power in three ways one is connecting the USB to the USB port, and the other way is connecting to
the dc power jack, and we can also make it through the Vin pin, which is on the board.
For the USB, it is 5v, and for the dc power jack, it is 7 -12 v, and for the Vin, it is 7-12 v. It contains
the reset button for resetting, and it has an IC on the board, which is ATMEGA328 (Kumar et al.,
2015; Murugappan et al., 2007; Petrantonakis & Hadjileontiadis, 2010; Prakash & Chithaluru, 2021;
Sravanth, Peddi, Sagar, Gupta, & Chakraborty, 2018) and a voltage regulator to regulate the voltage.
L293D (Chithaluru & Prakash, 2018; Chithaluru et al., 2018; Chithaluru et al., 2019b; Prakash
et al., 2019) is a motor driver that allows DC motor to drive in different directions as shown in Figure
4; it is a 16 pin IC that can control 2 DC motors in all directions. It contains an H-bridge circuit,
where two motors are controlled easily. The voltage flow is in either direction of the bridge; this is
mainly used to control the 2 DC motors. It is used in robotic applications. There are 4 input and 4
Figure 3. Arduino UNO board
Figure 4. Pin diagram of L293D
Volume 10 • Issue 2 • July-December 2019
43
output pins for l293d. The pins in the left are used to control the left motor, and the right pins are
used to control the right motor. For the motor to rotate in a clockwise direction, the input should be
Logic 1 and logic 0. There are two enable pins 1 and 9; these enable pins are to be logic 1 to enable
the motor driver. When the enable pins are low, then the driver is disabled, and output will be low.
The MATLAB software is a multi-paradigm numerical computing environment and proprietary
programming language developed by Math-works; Arduino software is the open-source software used
to write the programming logic for the Arduino. It is an IDE that is supported by Windows, Linux, Mac
OS x. The compilation of the code and uploading the code to the board is a straightforward process,
and it has features like auto indenting and brace matching, and syntax highlighting. Neuro-Sky-Mind-
wave mobile attached to the forehead, i.e., the brain’s frontal lobe detects the neural activity in the
frontal lobe of the brain. When the eye blinks, there will be a high rate of neurons striking, which
generates small amounts of current, that will be detected using the neuro-sky-mind-wave mobile and
is transferred to MATLAB through Bluetooth as shown in Figure 5.
In MATLAB using thinkgear.dll file, those small currents are mapped to the corresponding blink
strength values, for a normal blink threshold value of blink strength are 300. Therefore, when we get
a blink-strength value more than 300, eye blink got detected. Then direction is decided according
to the loop. After deciding the direction, the command is transferred to the Arduino through the
Bluetooth module. Using a motor driver, the bot will move (Chithaluru, Al-Turjman, Kumar et al,
2020) (Sravanth, Peddi, Sagar, Gupta, & Chakraborty, 2018).
The total numbers of participants are graduates from the VNR Vignana Jyothi Institute of Engineering
and technology, of which 5 male and 5 female. All the participants participated in this voluntarily,
having the aged between 18 to 25 years and are free from medication, drugs, neurological disorder,
and a head injury, which may have affected the results. After successful connections, the neuro sky
mind wave device’s establishment is with PC and HC-05 with pc. Check the port number to which
Figure 5. System block diagram
Volume 10 • Issue 2 • July-December 2019
44
it got connected because it is dynamic in the Bluetooth port number, which is not constant. Now
enter the port number in MATLAB code for serial communication. Run the code; now, we will get
the GUI (graphical user interface). The flow chart starts with event A. Firstly, it is set in a forward
direction; it will ask for a blink to move forward. If a blink is detected with blink-strength more than
300 and less than -300(amplitude), since the blink strength signal is sinusoidal, it will command
‘F’ to the Arduino through the Bluetooth module. The flowchart of the blink is shown in Figure 6.
Arduino receives a command, and the programmed motors will move according to the direction. If
the blink is not detected within 3 seconds, it will go to event A; now, the direction got updated with
the Right direction. After every cycle, the direction will be updating, and the subject can move the
robot to the required direction.
After the successful connection setup with the neuro sky mind wave device, PC, and HC-05 Bluetooth
module, the subject needs to check the direction in which he/she wants to move. If his desired direction,
for example, forward direction, he should blink the eyes, then the blink strength signal will appear. If
the blink is detected, then the robot will move in the forward direction. The following images show
different moving directions of the robot.
Figure 6. Flow chart for blink state
Volume 10 • Issue 2 • July-December 2019
45
Figure 7 shows the hardware setup containing a laptop robot with Arduino, Bluetooth module,
motor driver, and neuro sky mind wave mobile.
Figure 8 shows the raw blink strength signal and subject blinking eyes; the blink strength signal
is clearly a sinusoidal signal with maximum blink strength above 300 and minimum blink strength
less than -300.
Figure 7. Hardware setup using BCI
Figure 8. Subject of raw blink strength signal
Volume 10 • Issue 2 • July-December 2019
46
Figure 9 shows the robot containing two motors, two wheels, Arduino, a motor driver, and a
Bluetooth module.
Figure 10 indicates the forward direction of the robot. This figure contains four arrows representing
four directions forward, right, back, and left. All these directions are in the loop and execute one after
another; if the blink is not detected, it will skip the present direction and shift to the next direction.
The arrow with blue color represents ready to move in that direction. If a blink is detected, it will
turn into a green color representing that it moves in the forward direction.
Figure 11 indicates the right direction of the robot. After the forward direction, the next direction is
the right side. Here in blink strength signal, the maximum value is greater than 300, and the minimum
value is less than -300; blink is detected and turned into green color representing the robot is moving
towards the right direction.
Figure 12 indicates the reverse direction of the robot. After the right direction, the next direction
is backside. Here in blink strength signal, the maximum value is greater than 300, and the minimum
Figure 9. Subject of raw blink strength signal
Figure 10. Forward direction to the robot
Volume 10 • Issue 2 • July-December 2019
47
value is less than -300; blink is detected and turned into green color representing the robot is moving
towards the backward direction.
Figure 13 indicates the left direction of the robot. After the reverse direction, the next direction
is towards the left side. Here in blink strength signal, the maximum value is greater than 300, and the
minimum value is less than -300; thus, blink is detected and turned into a green color representing
robot is moving towards left direction.
The brain activity is recorded with the neuro sky mind wave device’s help and is transferred to the
MATLAB using Bluetooth the received signal is converted to the blink strength signal using the
think gear file. With the help of the blink strength, one can detect the blink, and then the required
command is sent to the Arduino through the Bluetooth module; thereby, motors will move according
Figure 11. Right direction to the robot
Figure 12. Reverse direction to the robot
Volume 10 • Issue 2 • July-December 2019
48
to the programmed direction in Arduino. Using this subject can control the motors, switching ON and
OFF lights and fans; this can also apply to in-Home Automation. In the future, we are implementing
using attention-based automation vehicle detection based on this automation system. It is believed
that the methods presented in this thesis would provide promising outcomes in the EEG signal eye
state classification area. Nevertheless, there are many research directions to explore; we intend to
examine the possibility of using the proposed technique to apply other biomedical signals. Moreover,
it is also a highly promising idea to apply these methods to other neurophysiologic paradigms.
Figure 13. Left direction to the robot
Volume 10 • Issue 2 • July-December 2019
49
Barrett, G., Blumhardt, L., Halliday, A. M., Halliday, E., & Kriss, A. (1976). A paradox in the lateralisation of
the visual evoked response. Nature, 261(5557), 253–255. doi:10.1038/261253a0 PMID:1272400
Chithaluru, P., Al-Turjman, F., Kumar, M., & Stephan, T. (2020). I-AREOR: An Energy-balanced Clustering
Protocol for implementing Green IoT in smart cities. Sustainable Cities and Society, 61, 102254. doi:10.1016/j.
scs.2020.102254
Chithaluru, P., & Prakash, R. (2018). Simulation on SDN and NFV models through mininet. In Innovations in
Software-Defined Networking and Network Functions Virtualization (pp. 149–174). IGI Global. doi:10.4018/978-
1-5225-3640-6.ch007
Chithaluru, P., Prakash, R., & Srivastava, S. (2018). WSN Structure Based on SDN. In Innovations in Software-
Defined Networking and Network Functions Virtualization (pp. 240–253). IGI Global. doi:10.4018/978-1-5225-
3640-6.ch011
Chithaluru, P., Tanwar, R., & Kumar, S. (2020). Cyber-Attacks and Their Impact on Real Life: What Are Real-
Life Cyber-Attacks, How Do They Affect Real Life and What Should We Do About Them? Information Security
and Optimization, 61.
Chithaluru, P., Tiwari, R., & Kumar, K. (2019a). Performance Analysis of Energy Efficient Opportunistic Routing
Protocols in Wireless Sensor Network. International Journal of Sensors, Wireless Communications and Control,
9, 1. doi:10.2174/2210327909666191026092311
Chithaluru, P., Tiwari, R., & Kumar, K. (2019b). AREOR–Adaptive ranking based energy efficient opportunistic
routing scheme in Wireless Sensor Network. Computer Networks, 162, 106863. doi:10.1016/j.comnet.2019.106863
Chithaluru, P., Tiwari, R., & Kumar, K. (2021). ARIOR: Adaptive Ranking Based Improved Opportunistic
Routing in Wireless Sensor Networks. Wireless Personal Communications, 116(1), 153–176. doi:10.1007/
s11277-020-07709-0
Debener, S., Minow, F., Emkes, R., Gandras, K., & De Vos, M. (2012). How about taking a low‐cost, small,
and wireless EEG for a walk? Psychophysiology, 49(11), 1617–1621. doi:10.1111/j.1469-8986.2012.01471.x
PMID:23013047
Donoghue, J. P. (2002). Connecting cortex to machines: Recent advances in brain interfaces. Nature Neuroscience,
5(11), 1085–1088. doi:10.1038/nn947 PMID:12403992
Eason, G., Noble, B., & Sneddon, I. N. (1955). On certain integrals of Lipschitz-Hankel type involving products
of Bessel functions. Philosophical Transactions of the Royal Society of London. Series A, Mathematical and
Physical Sciences, 247(935), 529–551. doi:10.1098/rsta.1955.0005
Katona, J., & Kovari, A. (2015). EEG-based Computer Control Interface for Brain-Machine Interaction.
International Journal of Online Engineering, 11(6), 43. doi:10.3991/ijoe.v11i6.5119
Kumar, S., Kumar, V., & Gupta, B. (2015, September). Feature Extraction from EEG Signal through one
electrode device for medical application. In 2015 1st International Conference on Next Generation Computing
Technologies (NGCT) (pp. 555-559). IEEE. doi:10.1109/NGCT.2015.7375181
Liu, Y., Sourina, O., & Nguyen, M. K. (2010, October). Real-time EEG-based human emotion recognition and
visualization. In 2010 international conference on cyberworlds (pp. 262-269). IEEE.
Morshed, B. I., & Khan, A. (2014). A brief review of brain signal monitoring technologies for BCI applications:
Challenges and prospects. Journal of Bioengineering & Biomedical Science, 4(1), 1. doi:10.4172/2155-
9538.1000128
Murugappan, M., Rizon, M., Nagarajan, R., Yaacob, S., Zunaidi, I., & Hazry, D. (2007). EEG feature extraction
for classifying emotions using FCM and FKM. International Journal of Computers and Communications, 1(2),
21-25.
Nuwer, M. R., Lehmann, D., Silva, F. L. D., Matsuoka, S., Sutherling, W., & Vibert, J. F. (1994). IFCN guidelines
for topographic and frequency analysis of EEGs and EPs. Report of an IFCN committee. Electroencephalography
and Clinical Neurophysiology, 91(1), 1–5. doi:10.1016/0013-4694(94)90011-6 PMID:7517838
Volume 10 • Issue 2 • July-December 2019
50
Palaniappan, R., Syan, C. S., & Paramesran, R. (2009). Current practices in electroencephalogram-based brain-
computer interfaces. In Encyclopedia of Information Science and Technology (2nd ed., pp. 888–901). IGI Global.
doi:10.4018/978-1-60566-026-4.ch143
Petrantonakis, P. C., & Hadjileontiadis, L. J. (2010). Emotion recognition from brain signals using hybrid
adaptive filtering and higher order crossings analysis. IEEE Transactions on Affective Computing, 1(2), 81–97.
doi:10.1109/T-AFFC.2010.7
Prakash, R., & Chithaluru, P. (2021). Active Security by Implementing Intrusion Detection and Facial Recognition.
In Nanoelectronics, Circuits and Communication Systems (pp. 1–7). Springer. doi:10.1007/978-981-15-7486-3_1
Prakash, R., Chithaluru, P., Sharma, D., & Srikanth, P. (2019). Implementation of Trapdoor Functionality to
Two-Layer Encryption and Decryption by Using RSA-AES Cryptography Algorithms. In Nanoelectronics,
Circuits and Communication Systems (pp. 89–95). Springer. doi:10.1007/978-981-13-0776-8_8
Ramakuri, S. K., Chakraboirty, C., Peddi, A., & Gupta, B. (2019). Classification Algorithms for EEG-Based
Brain-Computer Interface: A Review. In Advanced Classification Techniques for Healthcare Analysis (pp. 52-
73). IGI Global.
Sałabun, W. (2014). Processing and spectral analysis of the raw EEG signal from the MindWave. Przeglad
Elektrotechniczny, 90(2), 169–174.
Sourina, O., Wang, Q., & Nguyen, M. K. (2011). EEG-based” serious” games and monitoring tools for pain
management. Studies in Health Technology and Informatics, 163, 606–610. PMID:21335865
Sravanth, K. R., Peddi, A., Sagar, G. S., Gupta, B., & Chakraborty, C. (2018, November). Comparison of
Attention and Meditation Based Mobile Applications by Using EEG Signals. In 2018 Global Wireless Summit
(GWS) (pp. 260-265). IEEE.
Suleiman, A. B. R., & Fatehi, T. A. H. (2007). Features extraction techniques of EEG signal for BCI applications.
Faculty of Computer and Information Engineering Department College of Electronics Engineering. University
of Mosul.
Tong, K. K., Leung, K. S., & Leung, Y. (2017, September). A system for personalized health care with ECG and
EEG signals for analysis. In 2017 International Smart Cities Conference (ISC2) (pp. 1-6). IEEE. doi:10.1109/
ISC2.2017.8090793
Übeyli, E. D., & Güler, İ. (2004). Spectral broadening of ophthalmic arterial Doppler signals using STFT and
wavelet transform. Computers in Biology and Medicine, 34(4), 345–354. doi:10.1016/S0010-4825(03)00093-3
PMID:15121004
Sravanth Kumar R. received his Master of Technology in RF and Microwave, Visakhapatnam, India in 2012 and
Ph. D in Brain-Computer Interface for Medical Applications dept of ECE from BIT Mesra, India. He has been an
Assistant Professor in Electronics and communication engineering at VNR Vignanajyothi institute of Technology,
Hyderabad, India, since July 2016. He has authored many research publications in peer-reviewed National
and International journals. He has contributed 3 book chapters. he serves as a reviewer for many National and
International journals. His research area interest is Brain-Computer Interface, bio-medical signal processing, sensor
networks, Neuro-computing, Machine Learning, and Medical/Healthcare monitoring.
Premkumar Chithaluru is a Research Scholar/Assistant Professor (SG) in the Dept. of Systemics, SoCS at the
University of Petroleum and Energy Studies (UPES), Dehradun (India). He completed his B.Tech from (JNTUH)
in CSE, M.Tech from (JNTUH) in CSE, and pursuing a Ph.D. (WSN) from UPES, Dehradun. His area of research
is WSN, QoS in Wireless Networks, Mobile Ad-hoc Networks, and Routing Techniques.
Sunil Kumar is a Research Scholar/Assistant Professor (SG) in the Dept. of Cybernetics, SoCS at the University of
Petroleum and Energy Studies (UPES), Dehradun (India). He completed his B. Tech from Kurukshetra University,
Kurukshetra in CSE, and M. Tech from MMU, Ambala in CSE. His area of research is WSN, Deep Learning, and
Data Mining.
