Call for Paper

CAE solicits original research papers for the February 2022 Edition. Last date of manuscript submission is January 31, 2022.

Read More

Keystroke Dynamics for User-Authentication on Mobile Devices using Ensemble Method

Omoyele Akinsowon. Published in Security.

Communications on Applied Electronics
Year of Publication: 2021
Publisher: Foundation of Computer Science (FCS), NY, USA
Authors: Omoyele Akinsowon

Omoyele Akinsowon. Keystroke Dynamics for User-Authentication on Mobile Devices using Ensemble Method. Communications on Applied Electronics 7(36):33-38, July 2021. BibTeX

	author = {Omoyele Akinsowon},
	title = {Keystroke Dynamics for User-Authentication on Mobile Devices using Ensemble Method},
	journal = {Communications on Applied Electronics},
	issue_date = {July 2021},
	volume = {7},
	number = {36},
	month = {Jul},
	year = {2021},
	issn = {2394-4714},
	pages = {33-38},
	numpages = {6},
	url = {},
	doi = {10.5120/cae2021652885},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}


As the days go by, the need for security keeps increasing; whether for humans, data, climate and almost everything in existence. However, despite the increase in the need to protect data, information and the corresponding devices, the Personal Identification Number (PIN) is still the most widely used approach on mobile devices. This increased requirement for protection is evidenced by various issues that continue to arise based on intrusion, theft and unlawful access to classified information. It is important to note that apart from secret-knowledge (that is PIN), biometrics and tokens are useful for security even though token seldom authenticates because it is expected to be with the authentic owner. Biometrics on the other hand makes use of the individual himself. This research sought to address the issue of securing data on mobile devices by employing some Machine Learning algorithms. The K-Nearest Neighbours (KNN), Decision Trees (DT) and Multinomial Logistic Regression (MLR) classification algorithms were used to train and test the typing patterns of several individuals who volunteered to type a static passphrase.

After carrying out the different experiments, the predictions given by Decision Trees were the most accurate of all the three base classifiers used with an accuracy value of 99.92%.


  3. Choi, M.; Lee, S.; Jo, M.; Shin, J. S. Keystroke Dynamics-Based Authentication Using Unique Keypad. Sensors 2021, 21, 2242.
  4. Banerjee, S. Woodard, D. (2012) Biometric Authentication and Identification using Keystroke Dynamics: A Survey. Journal of Pattern Recognition Research (JPRR), vol. 7, p116-139
  5. Yu Zhong and Yunbin Deng (2015), Recent Advances in User Authentication UsingKeystroke Dynamics Biometrics, DOI: 10.15579/gcsr.vol2.ch2, GCSR Vol. 2, pp. 23-40, 2015, Science Gate Publishing - Available under CC BY-NC 4.0 International License.
  6. AlsawwanAhmed, AlrashdanMaen, Al-MaatoukQusay, AbdulnabiMohamed, Veeramani, IndrianVijai, TubishatMohammad, Mosab Tayseer AlRashdan, Al-Othman Abdulaleem Z (2020), Keystroke Dynamics Analysis to Enhance Password Security of Mobile Banking Applications,
  7. Lee Hyungu, Yeon Hwang Jung, Kim Dong In, Lee Shincheol, Lee Sung-Hoon and Shin Ji Sun (2018), Security and Communication Networks, Hindawi, Volume, Article ID 2567463, 10 pages,
  8. Bhatia, Aparna & Hanmandlu Madasu (2017), Keystroke Dynamics Based Authentication Using Information Sets. Journal of Modern Physics. 08. 1557-1583. 10.4236/jmp.2017.89094.


Keystroke Dynamics, Typing Pattern, Confusion Matrix