IRO Journals
Journal of Ubiquitous Computing and Communication Technologies

Automated Detection of Parkinson’s Disease through Kinematic and Geometric Analysis of Handwritten Strokes using Deep Learning

Open Access
Published: 21 August, 2026
Pages: 299-312
  • Geetha Ramani R. , Geetha Ramani R.
    Professor, Department of Information Technology, Anna University Chennai, India
    Professor, Department of Information Technology, Anna University Chennai, India
  • Shalini K. Shalini K.
    Professor, Department of Information Technology, Anna University Chennai, India
    Professor, Department of Information Technology, Anna University Chennai, India
view PDF
view PDF

How to Cite

R., Geetha Ramani, and Shalini K. 2026. “Automated Detection of Parkinson’s Disease through Kinematic and Geometric Analysis of Handwritten Strokes Using Deep Learning”. Journal of Ubiquitous Computing and Communication Technologies 8 (3): 299-312. https://doi.org/10.36548/jucct.2026.3.009.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Parkinson’s Disease
Deep Learning
DenseNet121
Handwriting Analysis
NeuroBiomarker
Spatial Dropout

Abstract

Parkinson's Disease (PD) is a progressive brain disorder that affects human motor functions. Early Parkinson's Disease (PD) detection plays a major role in facilitating clinical treatment. Handwriting analysis has proven to be an efficient way to detect motor problems; nonetheless, traditional methods have shown poor feature representation capability and classification robustness. In this study, a novel Deep Learning (DL) model based on DenseNet121 for automated detection of PD using spiral and meander handwriting images is introduced. Image processing, hierarchical features extraction, Global Average Pooling technique to produce 2,880-dimensional feature representation, Spatial Dropout technique, and binary classification are included in the proposed methodology. Handwriting benchmark datasets such as PaHaW, HandPD, and NewHandPD are used to test the performance of the proposed framework. The experimental findings show that the presented method is able to achieve 92.8% accuracy, which implies a reliable classification of PD and healthy samples.

References

  1. Bergamino, Maurizio, Elizabeth G. Keeling, Nicola J. Ray, Antonella Macerollo, Monty Silverdale, and Ashley M. Stokes. "Structural Connectivity and Brain Network Analyses in Parkinson's Disease: A Cross-Sectional and Longitudinal Study." Frontiers in Neurology 2023, vol. 14: 1137780.
  2. Akgüller, Ömer, Mehmet Ali Balcı, and Gabriela Cioca. "Functional Brain Network Disruptions in Parkinson’s Disease: Insights from Information Theory and Machine Learning." Diagnostics, 2024, vol. 14, no. 23: 2728.
  3. Ge, Shaoyun, Jun Liu, Yongfeng Jia, Zihan Li, Jianwei Wang, and Min Wang. "Topological Alteration of the Brain Structural Network in Parkinson’s Disease With Apathy." Brain Research Bulletin 2024, vol. 208: 110899.
  4. Naz, Saeeda, Iqra Kamran, Sarah Gul, Fazle Hadi, and Fahmi Khalifa. "Multi-Model Fusion of Cnns For Identification of Parkinson’s Disease using Handwritten Samples." IEEE Access 2023, vol. 11: 135600-135608.
  5. Lamba, Rohit, Pooja Rani, Ravi Kumar Sachdeva, and Priyanka Bathla. "Advances in Artificial Intelligence for Parkinson’s Disease Detection: A Decade Of Machine Learning and Deep Learning Insights." Neural Computing and Applications 2026, vol. 38, no. 12: 502.
  6. Allebawi, Mohammed F., Thameur Dhieb, Islem Jarraya, Mohamed Neji, Nouha Farhat, Khadija Moalla, Tarek M. Hamdani, Mariem Damak, Chokri Mhiri, and Adel M. Alimi. "Early Parkinson’s Disease Detection from Offline Hand-Drawing Based on Squeezenet and Tinysiamese Network." Multimedia Tools and Applications 2026, vol. 85, no. 4: 282.
  7. Sivaranjini, S., and C. M. Sujatha. "Deep Learning-Based Diagnosis of Parkinson’s Disease using Convolutional Neural Network." Multimedia Tools and Applications 2020, vol. 79, no. 21: 15467-15479.
  8. Islam, M.A., Majumder, M.Z.H., Hussein, M.A., Hossain, K.M. and Miah, M.S., "A Review of Machine Learning and Deep Learning Algorithms for Parkinson's Disease Detection using Handwriting And Voice Datasets." Heliyon, 2024, vol 10, no. 3: e25469
  9. Aldhyani, Theyazn HH, Abdullah H. Al-Nefaie, and Deepika Koundal. "Modeling and diagnosis Parkinson disease by using hand drawing: deep learning model." AIMS Mathematics 2024, vol. 9, no. 3: 6850-6877.
  10. Taleb, Catherine, Laurence Likforman-Sulem, Chafic Mokbel, and Maha Khachab. "Detection of Parkinson’s disease from handwriting using deep learning: a comparative study." Evolutionary Intelligence 2023, vol. 16, no. 6: 1813-1824.
  11. Dogan, Yahya. "An innovative approach for parkinson’s disease diagnosis using CNN, NCA, and SVM." Neural Computing and Applications 2024, vol. 36, no. 32: 20089-20110.
  12. Liang, Huaixin, Tao Zhang, Lin Li, Bo Liu, Bin Liu, Chen Shi, and BaoHong Mi. "Transfer Learning from Vision Transformer to Parkinson's Disease Offline Handwriting Detection." In 11th International Conference on Behavioural and Social Computing, IEEE 2024: 1-7.
  13. Rohini Phaneendra Kumari, G., M. Ravi Kanth, and M. V. Kamal. "Parkinson’s disease early detection using hybrid attentive CNN-transformer model." Neural Computing and Applications, 2025, vol. 37, no. 32: 26523-26543.
  14. Özdemir, Esra Yüzgeç, and Fatih Özyurt. "Elasticnet-Based Vision Transformers for early detection of Parkinson’s disease." Biomedical Signal Processing and Control 2025, vol. 101:107198.
  15. Pechetti, Sukanya, and Battula Srinivasa Rao. "Optimized MobileNetV3: a deep learningbased Parkinson’s disease classification using fused images." PeerJ Computer Science 2023, vol. 9: e1702.
  16. Raajasree, K., and R. Jaichandran. "Enhanced EfficientNet-Extended Multimodal Parkinson’s disease classification with Hybrid Particle Swarm and Grey Wolf Optimizer." Scientific Reports 2025, vol. 15, no. 1: 33857.
  17. Sangeetha, S., and B. Umarani. "MRI image-based Parkinson’s disease classification using Deep Maxout fuzzy EfficientNet." Biomedical Signal Processing and Control 2025, vol. 103: 107416.
  18. P. Drotár, J. Mekyska, I. Rektorová, L. Masarová, Z. Smékal, and M. Faundez-Zanuy, "Evaluation of handwriting kinematics and pressure for differential diagnosis of Parkinson's disease," Artificial Intelligence in Medicine 2016, vol. 67: 39-46. Available: https://bdalab.utko.fekt.vut.cz/
  19. M. A. Pereira, M. O. A. Mansour, A. X. Falcão, J. P. Papa, and C. R. Pereira, "A public dataset for Parkinson's disease handwriting analysis (HandPD)," São Paulo State University (UNESP), Brazil, 2016. Available: https://wwwp.fc.unesp.br/~papa/pub/datasets/Handpd/
  20. M. A. Pereira, J. P. Papa, A. X. Falcão, and C. R. Pereira, "NewHandPD: An online and offline handwriting dataset for Parkinson's disease diagnosis using a biometric smart pen," São Paulo State University (UNESP), Brazil, 2016. Available: https://wwwp.fc.unesp.br/~papa/pub/datasets/Handpd/