HUMAN MACHINE INTRACTION BASED ON

AUTHENTICATION
Aruna V,Monisha K,Monisha P,Pooja M
Assistant Professor+, Students +
+
Department of Electronics Communication Engineering,
+
SA Engineering college, Chennai,
Tamilnadu, India
arunav@saec.ac.in,kmonisha79@gmail.com,monisha020997@gmail.com,poojam3997@gmail.com.

Abstract—Body gestures are an essential part of non-
verbal communication, and probably also one of the
most natural components of human–human interaction. In
several circumstances, gestural languages can be more
effective than oral statements (e.g., when the
communication occurs at a distance). Therefore, it is not
surprising that body gestures are increasingly being
considered for biometric applications, both for
identification (i.e., recognizing an individual) and for
verification (i.e., confirming or denying the claimed
identity of an individual).Among the different kinds of
body gestures, those involving the hands are probably the
most widespread. Explicit identification and verification
based on hand gestures seem therefore viable approaches,
either as additional verification mechanisms (besides more
traditional techniques such as those exploiting PINs) or
when the identity check must take place at a distance
(e.g., in environments in which touch less procedures are
mandatory).Gesture-based methods have advantages over
other common identification and authentication
techniques, as gestures may require lower attention and
precision compared to other solutions while a wrongly
entered text password is automatically rejected, some
inaccuracy may be tolerated in a gesture code. Here we are
going to implement this Technology in the field of ATM
authentication.
Keywords—Human interaction, Communication, TM,
Security
I. INTRODUCTION
Human-machine interaction is explained as a
interaction & communication between human users with
machine, a dynamic technical system, via a HMI. Good
designs of HMI and systems have gained a important value in
many products and services in application domains such as
industrial, transportation, medical, and entertainment
systems.HMI with industries and other dynamic technical
systems has nowadays been identified as important for
process safety, quality, and efficiency. It comprises all aspects
of interaction and communication between human users and
their machines via HMI. The whole system of human users,
the human-machine interface, and the machine is the so-called
human-machine system (HMS); The term “machine”
indicates any kind of technical system including its
automation and decision support equipment and software –
and it relates to many different application domains.
The automation components of the technical system are
mentioned as supervision and control system. They interact
directly with the pure technical process. The decision making
systems are more advanced, knowledge-based functionalities
of the machine which provide advice for authorities.
The application domains include all kinds of Industrial,
Transportation, Medical field, Public service, Physically
challenged, Residential & Entertainment system. The more
conventional application domains of industrial and
transportation systems have been supplemented by application
domains from medical to entertainment systems. All
application domains profit from advancements in the
development of the HMI field. Human computer interaction
(HCI) is characterized as human interaction with those
machines by real-time constraints, as it is always the case in
HMI. Application domains which are not determined by a
dynamic process or by real-time constraints, as it is always the
case in HMI.
II. RELATED WORKS
ATM is an electronic device that is used by only
bank customers to process account credits and debits. The
users access their account through smartcard which is encoded
with user information on a magnetic strip. The strip contains
with id code that is transmitted to the bank’s central server by
modem. The users insert the card into ATMs and they have to
enter password to access the account and process their account
transactions. Another thing is PC based digital media or study
contents, these details are read only with PC or LAPTOP or
NOTEPAD or any mobile devices, normal people can easily gestures, so our proposed system no ATM card and there is no
access this but physically challenged person(paralyzed) person separate password customer hand gesture going to be work as
have problem to handle it without other’s help Paralyzed a identification and authentication. And also there is no need
person can’t handle above machines without another person’s for mouse or keyboards. So it have following advantages,
help • More secure compare to existing ATM systems
• More reliable
• No need for technical knowledge
III. PROPOSED SYSTEM • Physically challenged person also can use this
without others help.
In our proposed system is worked completely based on
Paper Title Author Year Techniques Flex Sensor:
1)Understandin Yanyan 2018 In this paper
g Secure and Li and IEEE they designed This flex sensor is a variable resistor like no other. The
Usable Gestures Menguin to create their resistance of the flex sensor increases as the body of the
For Real time Xie personalized component bends. Flex sensors are available in two sizes:
Motion based 3D motion one 2.2" (5.588cm) long and another coming in at 4.5"
Authentication gesture (11.43cm) long.Left flat, these sensors will look like a 30kΩ
showing resistor. As it bends, the resistance between the two terminals
authentication will increase to as much as 70kΩ at a 90° angle.
result on the By combining the flex sensor with a static resistor to create
smart watch in a voltage divider, you can produce a variable voltage that can
real time. be read by a microcontroller’s analog-to-digital converter.
2)At Your Zaire Ali 2016,Za This paper
Fingertips: and ire Ali, proposed the A voltage divider is a simple circuit which turns a large
Considering Jamie Under position of the voltage into a smaller one. Using just two series resistors and
Finger Payton License phone to an input voltage, we can create an output voltage that is a
Distinctness in Vincent to identify the fraction of the input. Voltage dividers are one of the most
Continuous Sritapan IEEE.D finger used to fundamental circuits in electronics.
Touch-Based OI10.11 perform a
Authentication 09/SPW touch-based Arduino Uno is a microcontroller board based on the
for Mobile .2016.2 gesture. ATmega328P. It has 14 digital input/output pins (of which 6
Devices 9 can be used as PWM outputs), 6 analog inputs, a 16 MHz
3) Behavior 1536- In this paper quartz crystal, a USB connection, a power jack, an ICSP
Based Human Muham 12339(c they proposed header and a reset button. It contains everything needed to
Authentication mad )2016 BEAT, a support the microcontroller
On Touch Shazad, IEEE gesture and
Screen Devices Alex signature
Using Gestures X.Liu, based
and Signatures Arjmand authentication
Samuel scheme for
touch screen
devices.
4)Multi-touch Liwen 2014 This paper
Gesture Xu firstly
introduces
early
researches of
multi-touch
and gesture.
5) Playful User Ekaterina 2009 This paper
Interfaces Kuts provides an
review of user
interface The Arduino Uno can be programmed with the (Arduino
characteristics Software (IDE)). Select "Arduino/Genuino Uno from the
that can be Tools > Board menu (according to the microcontroller on your
considered as board).
playful.
6)A Gesture Roger 1989 This paper
Based User B.Danne ACM0- introduced a
Interface nberg 89791- system GID
Prototyping and Dale 335- support input
System Amon 3/89/00 from both a
11/0127 mouse and free
hand sensor
can track
multiple
fingers.

Experimental results:
V CONCLUSION
By using this project we can prove that the gesture is one
of the very easy and secure communication methods among
various methods in human machine interaction. There is no
need of any technical knowledge to work with these machines.
Hardware unit is dynamic one, so a same structure can used
for multiple applications in various manners. For physically
challenged persons this project make feel them as a normal
humans while accessing and authorizing devices using
gestures, For normal persons it works like an add on, which
reduce their work and time of access.
REFERENCES
[1] F. Schaub, R. Deyhle, and M. Weber, “Password
entry usability and shoulder surfing susceptibility on
different smartphone platforms,” in Proc. 11th Int.
Conf. Mobile Ubiquitous Multimedia, Ulm,
Germany,Dec. 2012, Art. no.13.
[2] De Luca et al., “Now you see me, now you don’t:
Protecting smartphone authentication from shoulder
surfers,” in Proc. SIGCHI Conf. Human Factors
Comput. Syst., Toronto, ON, Canada, May 2014,pp.
2937–2946.
[3] J. Aviv, K. Gibson, E. Mossop, M. Blaze, and J. M.
Smith, “Smudge attacks on smartphone touch
screens,” in Proc. 4th USENIX Conf.Offensive
Technol., Berkeley, CA, USA, 2010, pp. 1–7.
[4] S. Cha, S. Kwag, H. Kim, and J. H. Huh, “Boosting
the guessing attack performance on Android lock
patterns with smudge attacks,” in Proc. ACM Asia
Conf. Comput. Commun. Secur., Abu Dhabi, United
Arab Emirates, Apr. 2017, pp. 313–326.
[5] Maiti, M. Jadliwala, J. He, and I. Bilogrevic,
“(Smart)watch your taps: Side-channel keystroke
inference attacks using smartwatches,” in Proc. ACM
Int. Symp. Wearable Comput., Osaka, Japan, Sep.
2015,pp. 27–30.
[6] Wang, X. Guo, Y. Wang, Y. Chen, and B. Liu,
“Friend or foe?: Your wearable devices reveal your
personal pin,” in Proc. 11th ACM Asia Conf.
Comput. Commun. Secur., Xi’an, China, Jun. 2016,
pp. 189–200.
[7] Sarkisyan, R. Debbiny, and A. Nahapetian,
“WristSnoop: Smartphone pins prediction using
smartwatch motion sensors,” in Proc. IEEE Int.
Workshop Inf. Forensics Secur. (WIFS), Nov. 2015,
pp. 1–6.
[8] R. Song, Y. Song, Q. Dong, A. Hu, and S. Gao,
“WebLogger: Stealing your personal PINs via mobile
Web application,” in Proc. 9th Int. Conf. Wireless
Commun. Signal Process. (WCSP), Oct. 2017, pp. 1–
6.
[9] X. Liu, Z. Zhou, W. Diao, Z. Li, and K. Zhang,
“When good becomes evil: Keystroke inference with
smartwatch,” in Proc. 22nd ACM SIGSAC Conf.
Comput. Commun. Secur., Denver, CO, USA, Oct.
2015,pp. 1273–1285.
[10] ] H. Wang, T. T.-T. Lai, and R. Roy Choudhury,
“Mole: Motion leaks through smartwatch sensors,” in
Proc. 21st Annu. Int. Conf. Mobile Comput. Netw.,
Paris, France, Sep. 2015, pp. 155–166.
[11] W. He and S. Zhang, “Control design for nonlinear
flexible wings of a robotic aircraft,” IEEE Trans.
Control Syst. Technol., vol. 25, no. 1,pp. 351–357,
Jan. 2017.
[12] W. He, Z. Yan, C. Sun, and Y. Chen, “Adaptive
neural network control of a flapping wing micro
aerial vehicle with disturbance observer,” IEEE
Trans. Cybern., vol. 47, no. 10, pp. 3452–3465, Oct.
2017.
[13] W. He, T. Meng, S. Zhang, Q. Ge, and C. Sun,
“Trajectory tracking control for the flexible wings of
a micro aerial vehicle,” IEEE Trans. Syst., Man,
Cybern., Syst., vol. 99, pp. 1–14, Jul. 2017.
[14] G. Cho, J. H. Huh, J. Cho, S. Oh, Y. Song, and H.
Kim, “Syspal:System-guided pattern locks for
Android,” in Proc. IEEE Symp. Security Privacy
(SP), May 2017, pp. 338–356.
[15] E.Owusu, J. Han, S. Das, A. Perrig, and J. Zhang,
“Accessory: Password inference using
accelerometers on smartphones,” in Proc. 12th
Workshop Mobile Comput. Syst. Appl., San Diego,
CA, USA, 2012, Art. no. 9.
[16] V. Matyas and Z. Riha, “Toward reliable user
authentication through biometrics,” IEEE Security
Privacy, vol. 99, no. 3, pp. 45–49,May/Jun. 2003.
[17] Y. Song, Z. Cai, and Z.-L. Zhang, “Multi-touch
authentication using hand geometry and behavioral
information,” in Proc. IEEE Symp. Security Privacy
(SP), San Jose, CA, USA, May 2017, pp. 357–372.
[18] Shen, Y. Zhang, X. Guan, and R. A. Maxion,
“Performance analysis of touch-interaction behavior
for active smartphone authentication,”IEEE Trans.
Inf. Forensics Security, vol. 11, no. 3, pp. 498–
513,Mar. 2016.
[19] O. J. Räsänen and J. P. Saarinen, “Sequence
prediction with sparse distributed hyperdimensional
coding applied to the analysis of mobile phone use
patterns,” IEEE Trans. Neural Netw. Learn. Syst.,
vol. 27,
[20] no. 9, pp. 1878–1889, Sep. 2016.
[21] Y. Nakada, M. Wakahara, and T. Matsumoto,
“Online Bayesian learning with natural sequential
prior distribution,” IEEE Trans. Neural Netw.Learn.
Syst., vol. 25, no. 1, pp. 40–54, Jan. 2014.