Abstract
Cerebral palsy (CP) is used to describe a group of disorders, characterized by non-progressive, but permanent damage to the developing brain that results in motor deficits, functional difficulties, sensory impairments, and cognitive impairments. AI is rapidly developing with special importance to education and healthcare. Interdisciplinary research perspectives and applications have come up as a helping hand to meet out the needs in different paradigm of Assessment and Biomedicine. At this juncture, building assessment tools for people with motor coordinate impairment is a valuable yet novel research challenge. So, authors implement a handwritten digit recognition system using optical character recognition (OCR) on dataset of CP people’s handwritten digits and based on study the problem statement is defined to detect variation in jerking hands on written to optical digits by proposing a custom convolutional neural network (CNN) architecture on the augmented dataset (CP handwritten data). The proposed research will look into a variety of design preferences for CNN-based handwritten digit recognition, including kernel size, layer count, stride size, and dilation. In addition, it evaluated the confusion matrix for maximum number prediction using various optimization algorithms. The extensive trials were conducted and obtained 85% accuracy for the CP dataset and 97% for the MNIST dataset.
Similar content being viewed by others
Data availability
Data will be shared on reasonable request.
References
Alwadkar S, Wanjari MB, Wankhede P, Mendhe D (2021) Cerebral palsy with gross developmental delay with lower respiratory infection with hypoxia-a case report. Children 1(2):3
Kim HY (2016) An investigation of the factors affecting handwriting articulation of school aged children with cerebral palsy based on the international classification of functioning, disability and health. J Phys Ther Sci 28(2):347–350
Donica DK, Goins A, Wagner L (2013) Effectiveness of handwriting readiness programs on postural control, hand control, and letter and number formation in Head Start classrooms. J Occup Therapy Schools Early Interv 6(2):81–93
Zhang J (2017) Multivariate analysis and machine learning in cerebral palsy research. Front Neurol 8:715
Proctor, K. “Speech Therapy for Cerebral Palsy” https://www.cerebralpalsyguide.com/treatment/speech-therapy/ , 2020.
Van Hoorn JF, Maathuis CG, Peters LH, Hadders-Algra MIJNA (2010) Handwriting, visuomotor integration, and neurological condition at school age. Dev Med Child Neurol 52(10):941–947
Khan A, Sohail A, Zahoora U, Qureshi AS (2020) A survey of the recent architectures of deep convolutional neural networks. Artif Intell Rev 53(8):5455–5516
Boufenar C, Kerboua A, Batouche M (2018) Investigation on deep learning for off-line handwritten Arabic character recognition. Cogn Syst Res 50:180–195
Bora MB, Daimary D, Amitab K, Kandar D (2020) Handwritten character recognition from images using CNN-ECOC. Procedia Comput Sci 167:2403–2409
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444
Chen S, Almamlook R, Gu Y, Wells L (2018) Offline handwritten digits recognition using machine learning. In: Proceedings of the international conference on industrial engineering and operations management, pp 274–286
Khan H (2017) MCS HOG features and SVM based handwritten digit recognition system. J Intell Learn Syst Appl 9(2):21–33
Tuba E, Tuba M, and Simian D (2016) Handwritten digit recognition by support vector machine optimized by bat algorithm. In: 24th Conference on computer graphics, visualization and computer vision
Kulkarni SR, Rajendran B (2018) Spiking neural networks for handwritten digit recognition—Supervised learning and network optimization. Neural Netw 103:118–127
Hamdan YB, Sathish A (2021) Construction of statistical SVM based recognition model for handwritten character recognition. J Inf Technol Digit World 3:92–107
Ge DY, Yao XF, Xiang WJ, Wen XJ, Liu EC (2019) Design of high accuracy detector for MNIST handwritten digit recognition based on convolutional neural network. In: 2019 12th international conference on intelligent computation technology and automation (ICICTA) pp 658–662. IEEE
Gunawan TS, Razi AF, Noor M, Kartiwi M (2018) Development of english handwritten recognition using deep neural network. Indones J Electr Eng Comput Sci 10(2):562–568
Ahlawat S, Choudhary A, Nayyar A, Singh S, Yoon B (2020) Improved handwritten digit recognition using convolutional neural networks (CNN). Sensors 20(12):3344
Mor SS, Solanki S, Gupta S, Dhingra S, Jain M, Saxena R (2019) Handwritten text recognition: with deep learning and android. Int J Eng Adv Technol 8:172–178
Sabour S, Frosst N, Hinton GE (2017) Dynamic routing between capsules. In: Proceedings of the 2007 neural information processing systems (NIPS). Long Beach, CA, USA, 4–9, pp 548–556
Dos Santos MM, da Silva Filho AG, dos Santos WP (2019) Deep convolutional extreme learning machines: filters combination and error model validation. Neurocomputing 329:359–369
Gupta S, Bansal T, Kumar M (2018) Deep learning based english handwritten character recognition. Int J Sci Res (IJSR) 7(4):1402–1404
Rahman MM, Akhand MAH, Islam S, Shill PC, Rahman MH (2015) Bangla handwritten character recognition using convolutional neural network. Int J Image Graphics Signal Process 7(8):42
Carbune V et al (2020) Fast multi-language LSTM-based online handwriting recognition. Int J Doc Anal Recogn 23(2):89–102. https://doi.org/10.1007/s10032-020-00350-4
Bonyani M, Jahangard S, Daneshmand M (2021) Persian handwritten digit, character and word recognition using deep learning. IJDAR 24:133–143. https://doi.org/10.1007/s10032-021-00368-2
Malek SA, Mesterman R, Switzer L, DiRezze B, DeVeber G, Fehlings D, Lunsky Y, Phoenix M, Gorter JW (2022) Exploring demographic, medical, and developmental determinants of adaptive behaviour in children with hemiplegic cerebral palsy. Eur J Paediatric Neurol 36:19–25
Ahmadi MN, O’Neil ME, Baque E, Boyd RN, Trost SG (2020) Machine learning to quantify physical activity in children with cerebral palsy: comparison of group, group personalized, and fully-personalized activity classification models. Sensors 20(14):3976. https://doi.org/10.3390/s20143976
Trost SG, Fragala-Pinkham M, Lennon N, O’Neil ME (2016) Decision trees for detection of activity intensity in youth with cerebral palsy. Med Sci Sports Exerc 48(5):958–966. https://doi.org/10.1249/MSS.0000000000000842
Zhang Y, Ma Y (2019) Application of supervised machine learning algorithms in the classification of sagittal gait patterns of cerebral palsy children with spastic diplegia. Comput Biol Med 106:33–39
Duran I, Stark C, Saglam A, Semmelweis A, LiobaWunram H, Spiess S, E. (2022) Artificial intelligence to improve efficiency of administration of gross motor function assessment in children with cerebral palsy. Dev Med Child Neurol 64(2):228–234
Ramadhan HH, Hussein QM, Ahmed MA (2022) Cerebral palsy prediction using CNN depending on MRI images of the brain. J Optoelectron Laser 41(8):724–733
Serpa-Andrade L, González-Delgado L, Parra-Astudillo A, Ojeda-Zamalloa I, Robles-Bykbaev V, Bunay R (2017) Design of an intelligent system for prediction and simulation of writing in children with spasticity. Int Conf Appl Human Factors Ergon. https://doi.org/10.1007/978-3-319-60483-1_58
Joseph SE, Saji MJ (2019) Effectiveness of kinesiotaping as an adjunctive therapy to improve dysgraphia in children with hemiplegic cerebral palsy. Int J Med Pharm Sci (IJMPS) 9(6):27–38
Azzam AM (2018) Efficacy of hand arches training in the improvement of dynamic tripod grasp and handwriting skills in hemiplegic CP children. IOSR J Nurs Health Sci (IOSR-JNHS) 7:84–92
Arnould C, Bleyenheuft Y, Thonnard J-L (2014) Hand functioning in Children with Cerebral Palsy. Front Neurol 5:48. https://doi.org/10.3389/fneur.2014.00048
Balaha H, HM Ali, HA Badawy (2021) Automatic recognition of handwritten Arabic characters: a comprehensive review. Neural Comput Appl 33(7):3011–3034
Tiwari P, Qian J, Li Q, Wang B, Gupta D, Khanna A, de Albuquerque VHC (2018) Detection of subtype blood cells using deep learning. Cogn Syst Res 52:1036–1044
Cui H, Bai J (2019) A new hyperparameters optimization method for convolutional neural networks. Pattern Recogn Lett 125:828–834
Kandel I, Castelli M (2020) The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset. ICT express 6(4):312–315
Mustapha A, Mohamed L, Ali K (2021) Comparative study of optimization techniques in deep learning: application in the ophthalmology field. In: Journal of physics: conference series (Vol 1743, No. 1, p 012002). IOP Publishing
Valova I, Harris C, Mai T, Gueorguieva N (2020) Optimization of convolutional neural networks for imbalanced set classification. Procedia Comput Sci 176:660–669
ShanWei C, LiWang S, Foo NT, Ramli DA (2021) A CNN based handwritten numeral recognition model for four arithmetic operations. Procedia Comput Sci 192:4416–4424
Husnain M, Saad Missen MM, Mumtaz S, Jhanidr MZ, Coustaty M, Muzzamil Luqman M, Sang Choi G (2019) Recognition of Urdu handwritten characters using convolutional neural network. Appl Sci 9(13):2758
Garg A, Gupta D, Saxena S, Sahadev PP (2019) Validation of random dataset using an efficient CNN model trained on MNIST handwritten dataset. In: 6th International conference on signal processing and integrated networks (SPIN) 602–606. IEEE, March
Baldominos A, Saez Y, Isasi P (2018) Evolutionary convolutional neural networks: an application to handwriting recognition. Neurocomputing 283:38–52
Chooi SL, Ghafar ASA (2011) Handwritten character recognition using convolutional neural network. Progress Eng Appl Technol 2(1):593–611
Saqib N, Haque KF, Yanambaka VP, Abdelgawad A (2022) Convolutional-neural-network- based handwritten character recognition. An Approach Massive Multisource Data 15:129. https://doi.org/10.3390/a15040129
Acknowledgements
We thank Mr. C. Shanthakumar (Director, The Spastics Society of Tiruchirappalli, Tamil Nadu, India.) for providing permission for data collection. We thank Mr. B. Balachandar (physiotherapist, The spastics Society of Tiruchirapalli, Tamil Nadu, India.) and his team for giving information about cerebral palsy people. We also thank all CP people who gave their time and effort for enabling data collection and their parents and special teachers.
Author information
Authors and Affiliations
Contributions
KM collected data, developed core idea, implemented the model and conducted experiments, and wrote the entire manuscript. USR analyzed and verified the results, and reviewed the manuscript. BJ verified the results and reviewed the manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The author does not have any conflict of interest.
Ethical approval
Hereby, I Dr U Srinivasulu Reddy consciously assure that the manuscript entitled “An Improved custom CNN model for adaptive Recognition of Cerebral Palsy People’s Handwritten Digits in Assessment” is not currently being considered for publication elsewhere.
Consent to participate
Informed consent was obtained from all individual participants included in the study.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
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
Muthureka, K., Srinivasulu Reddy, U. & Janet, B. An improved customized CNN model for adaptive recognition of cerebral palsy people’s handwritten digits in assessment. Int J Multimed Info Retr 12, 23 (2023). https://doi.org/10.1007/s13735-023-00291-8
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13735-023-00291-8