Deparment of Computer Science Surrey Centre for Cyber Security University of Surrey UK Patrice Rusconi School of Psychology University of Surrey UK Human Assisted Cognitive Modelling Hybrid HumanMachine Computing HHMC 2017 ID: 659235
Download Presentation The PPT/PDF document "1 Haiyue Yuan , Shujun Li" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
1
Haiyue Yuan, Shujun LiDeparment of Computer Science, Surrey Centre for Cyber Security, University of Surrey, UKPatrice RusconiSchool of Psychology, University of Surrey, UK
Human Assisted Cognitive Modelling
Hybrid Human-Machine Computing HHMC 2017
20/21 Sep Slide2
Cognitive modelling
Emulate human behaviour (perceptual, cognitive, motor process)Predict user performance and evaluate UIGOMS (Goals, Operators, Methods, and Selection) rules, KLM (Keystroke-Level Model), CPM-GOMS, etc.
Cognitive modelling software (CogTool, SANLab-CM,
Cogulator
etc.) Facilitate the design and modelling processStill needs a fair amount of manual workDifficult to model a system with complicated UI and user interaction
2
Research Background Slide3
3
CogTool+Based on the open source software CogTool developed at Carnegie-Mellon University(semi-)automated modelling and simulations of human cognitive tasksKeep humans as a source of additional data
External Human-Generated Data
Eye tracking data
ACT-R parameters
Simulation parametersSlide4
4
Case study 1Human generated eye tracking data assisted cognitive modellingCognitive modelling an user authentication system ‘Undercover[1]’
Lab-based eye-tracking user study[2].
Reproduce some human behavioural patterns
[1]
H.Sasamoto
,
N.Christin
, and
E.Hayashi
. 2008. “Undercover: authentication usable in front of prying eyes.”, In
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
(CHI '08). ACM, New York, NY, USA, 183-192
[2]
H.Yuan
, S.Li,
P.Rusconi and N.Aljaffan, 2017, “When Eye-tracking Meets Cognitive Modeling: Applications to Cyber Security Systems,” in Human Aspects of Information Security, Privacy and Trust: 5th International Conference, HAS 2017, part of HCI International HCII 2017, Vancouver, BC, Canada, Proceedings, Lecture Notes in Computer Science, vol. 10292, pp. 251-264, 2017, Springer Slide5
5
Case study 2Fitts’ law parameter to tailor simulation processPredictive model of human movement
Parameter a and b are empirically determined
Different user group (young, old, skilled, novice
etc)Add-on software module for tapping/pointing game to gather dataSlide6
Conclusion
6
6
Keep human in the loop is important
Finalise and share the CogTool+ software
How AI can be part of the human-assisted cognitive modelling process?
Acknowledgments
COMMANDO-HUMANS
COM
putational
M
odelling and
A
utomatic
N
onintrusive
D
etection
O
f
HUM
an beh
A
viour based i
NS
ecurity
www.commando-humans.net
Funders:
Project Members:Slide7
7
7
Thank you
Any questions ?