Abstract
Parkinson disease (PD) is a neurodegenerative disorder which has tremor in the finger, handwriting change and so on. Tremor in the finger with PD changes the typing pattern of subjects. Keystroke dynamics-based PD detection is class-imbalanced problem due to the scarcity of PD keystroke data. To address these problems, we propose a novel multi-level ensemble learning (EL) method that incorporates adaptive data augmentation techniques to diagnose PD. Specifically, we propose adaptive data augmentation methods on three base models to solve class-imbalanced problem. Further, we propose multi-level ensemble learning method for different temporal relation between different types of free-text keystroke dynamics (free-KD). Extensive experiments on datasets demonstrate that accuracy of our proposed method is up to 99.8%. In addition, our proposed method has high generalization and robustness on both free composition and transcription tasks.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
The data used in the current study are derived from public datasets. The dataset is open access and freely available for use by researchers in the scientific community. The authors did not have any special access privileges to the dataset that others would not have.
References
Adams, W.R.: High-accuracy detection of early Parkinson’s disease using multiple characteristics of finger movement while typing. PLoS One 12(11), 0188226 (2017)
Al-Kuraishy, H.M., Jabir, M.S., Al-Gareeb, A.I., Albuhadily, A.K.: The conceivable role of prolactin hormone in parkinson disease: the same goal but with different ways. Age. Res. Rev. 102075 (2023)
Arroyo-Gallego, T., Ledesma-Carbayo, M.J., Sánchez-Ferro, A., Butterworth, I., Mendoza, C.S., Matarazzo, M., Montero, P., López-Blanco, R., Puertas-Martin, V., Trincado, R., et al.: Detection of motor impairment in Parkinson’s disease via mobile touchscreen typing. IEEE Trans. Biomed. Eng. 64(9), 1994–2002 (2017)
Batiha, G.E.-S., Al-Kuraishy, H.M., Al-Gareeb, A.I., Elekhnawy, E.: Sirt1 pathway in Parkinson’s disease: a faraway snapshot but so close. Inflammopharmacology 31(1), 37–56 (2023)
Bernardo, L.S., Damaševičius, R., Ling, S.H., Albuquerque, V.H.C., Tavares, J.M.R.: Modified squeezenet architecture for Parkinson’s disease detection based on keypress data. Biomedicines 10(11), 2746 (2022)
Chen, Z., Duan, J., Kang, L., Qiu, G.: Class-imbalanced deep learning via a class-balanced ensemble. IEEE Trans. Neural Netw. Learn. Syst. 33(10), 5626–5640 (2021)
Chen, W., Wang, Z., Xie, H., Yu, W.: Characterization of surface EMG signal based on fuzzy entropy. IEEE Trans. Neural Syst. Rehabil. Eng. 15(2), 266–272 (2007)
Chen, S., Haibo Chen, Z.Y.: Report on diagnosis, treatment, and quality of life of Parkinson’s disease patients in China 2022 (2022)
Dhir, N., Edman, M., Sanchez Ferro, A., Stafford, T., Bannard, C.: Identifying robust markers of Parkinson’s disease in typing behaviour using a CNN-LSTM network (2020)
Giancardo, L., Sanchez-Ferro, A., Arroyo-Gallego, T., Butterworth, I., Mendoza, C.S., Montero, P., Matarazzo, M., Obeso, J.A., Gray, M.L., Estépar, R.S.J.: Computer keyboard interaction as an indicator of early Parkinson’s disease. Sci. Rep. 6(1), 34468 (2016)
Goldberger, A.L., Amaral, L.A., Glass, L., Hausdorff, J.M., Ivanov, P.C., Mark, R.G., Mietus, J.E., Moody, G.B., Peng, C.-K., Stanley, H.E.: Physiobank, physiotoolkit, and physionet: components of a new research resource for complex physiologic signals. Circulation 101(23), 215–220 (2000)
Guzmán-Ponce, A., Sánchez, J.S., Valdovinos, R.M., Marcial-Romero, J.R.: Dbig-us: a two-stage under-sampling algorithm to face the class imbalance problem. Expert Syst. Appl. 168, 114301 (2021)
Hand, D.J., Christen, P., Kirielle, N.: F*: An interpretable transformation of the f-measure. Mach. Learn. 110(3), 451–456 (2021)
Hooman, O.M., Oldfield, J., Nicolaou, M.A.: Detecting early parkinson’s disease from keystroke dynamics using the tensor-train decomposition. In: 2019 27th European Signal Processing Conference (EUSIPCO), pp. 1–5. IEEE (2019)
Iakovakis, D., Hadjidimitriou, S., Charisis, V., Bostanjopoulou, S., Katsarou, Z., Klingelhoefer, L., Mayer, S., Reichmann, H., Dias, S.B., Diniz, J.A., et al.: Early parkinson’s disease detection via touchscreen typing analysis using convolutional neural networks. In: 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 3535–3538. IEEE (2019)
Iapa, A.-C., Cretu, V.-I.: Shared data set for free-text keystroke dynamics authentication algorithms (2021)
Iwana, B.K., Uchida, S.: An empirical survey of data augmentation for time series classification with neural networks. PLoS One 16(7), 0254841 (2021)
Kantelhardt, J.W., Zschiegner, S.A., Koscielny-Bunde, E., Havlin, S., Bunde, A., Stanley, H.E.: Multifractal detrended fluctuation analysis of nonstationary time series. Phys. A Stat. Mech. Appl. 316(1–4), 87–114 (2002)
Killourhy, K.S., Maxion, R.A.: Free vs. transcribed text for keystroke-dynamics evaluations. In: Proceedings of the 2012 workshop on learning from authoritative security experiment results, pp. 1–8 (2012)
Liu, W.-M., Yeh, C.-L., Chen, P.-W., Lin, C.-W., Liu, A.-B.: Keystroke biometrics as a tool for the early diagnosis and clinical assessment of Parkinson’s disease. Diagnostics 13(19), 3061 (2023)
Lu, X., Zhang, S., Hui, P., Lio, P.: Continuous authentication by free-text keystroke based on CNN and RNN. Comput. Secur. 96, 101861 (2020)
Mienye, I.D., Sun, Y.: Performance analysis of cost-sensitive learning methods with application to imbalanced medical data. Inform. Med. Unlocked 25, 100690 (2021)
Milne, A., Farrahi, K., Nicolaou, M.A.: Less is more: Univariate modelling to detect early Parkinson’s disease from keystroke dynamics. In: Discovery science: 21st international conference, DS 2018, Limassol, Cyprus, October 29–31, 2018, Proceedings 21, pp. 435–446. Springer (2018)
Min, O., Wei, Z., Nian, Z., Su, X.: An application of LSTM prediction model based on keystroke data. In: Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence, pp. 1–6 (2020)
Ntracha, A., Iakovakis, D., Hadjidimitriou, S., Charisis, V.S., Tsolaki, M., Hadjileontiadis, L.J.: Detection of mild cognitive impairment through natural language and touchscreen typing processing. Front. Digit. Health 2, 567158 (2020)
Pham, T.D.: Pattern analysis of computer keystroke time series in healthy control and early-stage parkinson’s disease subjects using fuzzy recurrence and scalable recurrence network features. J. Neurosci. Methods 307, 194–202 (2018)
Pincus, S.M.: Approximate entropy as a measure of system complexity. Proc. Natl. Acad. Sci. 88(6), 2297–2301 (1991)
Potekhin, V.V., Unal, O.: Detection of Parkinson’s disease using keystroke data and machine learning algorithms. Ann. DAAAM Proc. 34 (2023)
Richman, J.S., Lake, D.E., Moorman, J.R.: Sample entropy. In: Methods in Enzymology vol. 384, pp. 172–184. Elsevier (2004)
Roy, S., Roy, U., Sinha, D., Pal, R.K.: Imbalanced ensemble learning in determining Parkinson’s disease using keystroke dynamics. Expert Syst. Appl. 217, 119522 (2023)
Sun, Y., Ceker, H., Upadhyaya, S.: Shared keystroke dataset for continuous authentication. In: 2016 IEEE international workshop on information forensics and security (WIFS), pp. 1–6. IEEE (2016)
S Zeid, S., A ElKamar, R., I Hassan, S.: Fixed-text vs. free-text keystroke dynamics for user authentication. Eng. Res. J. Fac. Eng. (Shoubra) 51(1), 95–104 (2022)
Tripathi, S., Arroyo-Gallego, T., Giancardo, L.: Keystroke-dynamics for Parkinson’s disease signs detection in an at-home uncontrolled population: a new benchmark and method. IEEE Trans. Biomed. Eng. 70(1), 182–192 (2022)
Wang, T., Wang, Z., Zhang, D., Gu, T., Ni, H., Jia, J., Zhou, X., Lv, J.: Recognizing Parkinsonian gait pattern by exploiting fine-grained movement function features. ACM Trans. Intell. Syst. Technol. TIST 8(1), 1–22 (2016)
Wang, T., Zhang, D., Wang, Z., Jia, J., Ni, H., Zhou, X.: Recognizing gait pattern of Parkinson’s disease patients based on fine-grained movement function features. In: 2015 IEEE 12th Intl Conf on ubiquitous intelligence and computing and 2015 IEEE 12th Intl Conf on autonomic and trusted computing and 2015 IEEE 15th Intl Conf on scalable computing and communications and its associated workshops (UIC-ATC-ScalCom), pp. 1–10. IEEE (2015)
Zhou, Z.-H.: Ensemble Methods: Foundations and Algorithms. CRC Press (2012)
Funding
This work was partially supported by the National Science Fund for Distinguished Young Scholars (62025205), the National Natural Science Foundation of China (No. 62032020).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no Conflict of interest.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Yang, Y., Guo, B., Zhao, K. et al. MELPD-Detector: Multi-level ensemble learning method based on adaptive data augmentation for Parkinson disease detection via free-KD. CCF Trans. Pervasive Comp. Interact. (2024). https://doi.org/10.1007/s42486-024-00152-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s42486-024-00152-1