Shuhan Zhong
Skip Abstract Section
Skip Supplemental Material SectionAbstract
Identifying early a person with dyslexia, a learning disorder with reading and writing, is critical for effective treatment. As accredited specialists for clinical diagnosis of dyslexia are costly and undersupplied, we research and develop a computer-assisted approach to efficiently prescreen dyslexic Chinese children so that timely resources can be channelled to those at higher risk. Previous works in this area are mostly for English and other alphabetic languages, tailored narrowly for the reading disorder, or require costly specialized equipment. To overcome that, we present DYPA, a novel DYslexia Prescreening mobile Application for Chinese children. DYPA collects multimodal data from children through a set of specially designed interactive reading and writing tests in Chinese, and comprehensively analyzes their cognitive-linguistic skills with machine learning. To better account for the dyslexia-associated features in handwritten characters, DYPA employs a deep learning based multilevel Chinese handwriting analysis framework to extract features across the stroke, radical and character levels. We have implemented and installed DYPA in tablets, and our extensive trials with more than 200 pupils in Hong Kong validate its high predictive accuracy (81.14%), sensitivity (74.27%) and specificity (82.71%).
Supplemental Material
Available for Download
zip
zhong.zip (27.6 MB)
Supplemental movie, appendix, image and software files for, DYPA: A Machine Learning Dyslexia Prescreening Mobile Application for Chinese Children
- Norah Dhafer Alqahtani, Bander Alzahrani, and Muhammad Sher Ramzan. 2023. Deep Learning Applications for Dyslexia Prediction. Applied Sciences 13, 5 (2023), 2804.Google Scholar
Cross Ref
- American Psychiatric Association. 2013. Diagnostic and Statistical Manual of Mental Disorders (fifth edition ed.). American Psychiatric Association, Washington, DC, USA. https://doi.org/10.1176/appi.books.9780890425596Google ScholarCross Ref
- Weihua An and Chao Li. 2011. Automatic matching of character strokes for computer-aided Chinese handwriting education. In Proceeding of the international conference on e-Education, entertainment and e-management. IEEE, Bali, Indonesia, 283--288.Google Scholar
- Jason L Anthony and Christopher J Lonigan. 2004. The nature of phonological awareness: Converging evidence from four studies of preschool and early grade school children. Journal of educational psychology 96, 1 (2004), 43.Google ScholarCross Ref
- Chiara Barbiero, Isabella Lonciari, Marcella Montico, Lorenzo Monasta, Roberta Penge, Claudio Vio, Patrizio Emanuele Tressoldi, Valentina Ferluga, Anna Bigoni, Alessia Tullio, et al. 2012. The submerged dyslexia iceberg: how many school children are not diagnosed? Results from an Italian study. PloS one 7, 10 (2012), e48082.Google ScholarCross Ref
- Chiara Barbiero, Marcella Montico, Isabella Lonciari, Lorenzo Monasta, Roberta Penge, Claudio Vio, Patrizio Emanuele Tressoldi, Marco Carrozzi, Anna De Petris, Anna Giulia De Cagno, et al. 2019. The lost children: The underdiagnosis of dyslexia in Italy. A cross-sectional national study. PLoS One 14, 1 (2019), e0210448.Google ScholarCross Ref
- Virginia W Berninger, Kathleen H Nielsen, Robert D Abbott, Ellen Wijsman, and Wendy Raskind. 2008. Writing problems in developmental dyslexia: Under-recognized and under-treated. Journal of school psychology 46, 1 (2008), 1--21.Google ScholarCross Ref
- C. S. H. Ho, D. Chan, K. Chung, S. M. Tsang, S. H. Lee, and C. Y. C. Fong. 2015. The Hong Kong test of specific learning difficulties in reading and writing for primary school students - third edition [HKT-P (III)]. Hong Kong Specific Learning Difficulties Research Team, Hong Kong SAR, China.Google Scholar
- C. S. H. Ho, D. Chan, K. Chung, S. M. Tsang, S. H. Lee, and R. W. Y. Cheng. 2007. The Hong Kong test of specific learning difficulties in reading and writing for primary school students - second edition [HKT-P (II)]. Hong Kong Specific Learning Difficulties Research Team, Hong Kong SAR, China.Google Scholar
- David W Chan. 2002. Developmental dyslexia in Hong Kong: An overview and lessons from an international perspective. Educational Journal 30, 2 (2002), 1--20.Google Scholar
- David W Chan, Connie Suk-han Ho, Suk-man Tsang, Suk-han Lee, and Kevin KH Chung. 2007. Prevalence, gender ratio and gender differences in reading-related cognitive abilities among Chinese children with dyslexia in Hong Kong. Educational Studies 33, 2 (2007), 249--265.Google ScholarCross Ref
- Lily Chan and Terezinha Nunes. 1998. Children's understanding of the formal and functional characteristics of written Chinese. Applied psycholinguistics 19, 1 (1998), 115--131.Google Scholar
- Jierun Chen, Tianlang He, Weipeng Zhuo, Li Ma, Sangtae Ha, and S.-H. Gary Chan. 2022. TVConv: Efficient Translation Variant Convolution for Layout-Aware Visual Processing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE/CVF, New Orleans, LA, USA, 12548--12558.Google ScholarCross Ref
- Tianqi Chen and Carlos Guestrin. 2016. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (San Francisco, California, USA) (KDD '16). Association for Computing Machinery, New York, NY, USA, 785--794. https://doi.org/10.1145/2939672.2939785Google ScholarDigital Library
- cjkvi. 2022. IDS data. https://github.com/cjkvi/cjkvi-ids original-date: 2011-05-23T16:04:00Z.Google Scholar
- Laura Tomaz Da Silva, Nathalia Bianchini Esper, Duncan D Ruiz, Felipe Meneguzzi, and Augusto Buchweitz. 2020. Visual explanation for identification of the brain bases for dyslexia on fMRI data. arXiv preprint arXiv:2007.09260 (2020).Google Scholar
- Jean-François Démonet, Margot J Taylor, and Yves Chaix. 2004. Developmental dyslexia. The Lancet 363, 9419 (2004), 1451--1460.Google Scholar
- Rita Francese, Clara Monaco, and Claudia Nicoletti. 2018. An Android Application for Helping in the Identification of Children with Reading Difficulties. In Proceedings of the 4th EAI International Conference on Smart Objects and Technologies for Social Good (Bologna, Italy) (Goodtechs '18). Association for Computing Machinery, New York, NY, USA, 226--231. https://doi.org/10.1145/3284869.3284915Google ScholarDigital Library
- Jerome H Friedman. 2002. Stochastic gradient boosting. Computational statistics & data analysis 38, 4 (2002), 367--378.Google Scholar
- Sheryl M. Handler and Walter M. Fierson. 2011. Learning Disabilities, Dyslexia, and Vision. Pediatrics 127 (2011), e818 -- e856.Google ScholarCross Ref
- Andrew Howard, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang, Yukun Zhu, Ruoming Pang, Vijay Vasudevan, et al. 2019. Searching for mobilenetv3. In Proceedings of the IEEE/CVF international conference on computer vision. IEEE/CVF, Long Beach, CA, USA, 1314--1324.Google ScholarCross Ref
- Zhi-Hui Hu, Yun Xu, Liu-Sheng Huang, and Howard Leung. 2009. A Chinese Handwriting Education System with Automatic Error Detection. Journal of Software 4, 2 (April 2009), 101--107. https://doi.org/10.4304/jsw.4.2.101-107Google ScholarCross Ref
- G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger. 2017. Densely Connected Convolutional Networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, Los Alamitos, CA, USA, 2261--2269.Google Scholar
- A Jothi Prabha and R Bhargavi. 2019. Prediction of dyslexia using machine learning --- a research travelogue. In Proceedings of the Third International Conference on Microelectronics, Computing and Communication Systems: MCCS 2018. Springer, Singapore, 23--34.Google ScholarCross Ref
- Shahriar Kaisar. 2020. Developmental dyslexia detection using machine learning techniques: A survey. ICT Express 6, 3 (2020), 181--184.Google ScholarCross Ref
- Rehman Ullah Khan, Julia Lee Ai Cheng, and Oon Yin Bee. 2018. Machine learning and Dyslexia: Diagnostic and classification system (DCS) for kids with learning disabilities. International Journal of Engineering & Technology 7, 3.18 (2018), 97--100.Google Scholar
- Pavan Kumar Varma Kothapalli, V. Rathikarani, and Gopala Krishna Murthy Nookala. 2022. A Comprehensive Survey on Predicting Dyslexia and ADHD Using Machine Learning Approaches. In Inventive Systems and Control (Lecture Notes in Networks and Systems). Springer Nature, Singapore, 105--121. https://doi.org/10.1007/978-981-19-1012-8_8Google ScholarCross Ref
- Sutie ST Lam, Ricky KC Au, Howard WH Leung, and Cecilia WP Li-Tsang. 2011. Chinese handwriting performance of primary school children with dyslexia. Research in developmental disabilities 32, 5 (2011), 1745--1756.Google Scholar
- Cecilia W.P. Li-Tsang, Agnes S.K. Wong, Howard W.H. Leung, Joyce S. Cheng, Billy H.W. Chiu, Linda F.L. Tse, and Raymond C.K. Chung. 2013. Validation of the Chinese Handwriting Analysis System (CHAS) for primary school students in Hong Kong. Research in Developmental Disabilities 34, 9 (2013), 2872--2883. https://doi.org/10.1016/j.ridd.2013.05.048Google ScholarCross Ref
- Yuhang Lin, Xuanzhi Zhang, Qingjun Huang, Laiwen Lv, Anyan Huang, Ai Li, Kusheng Wu, and Yanhong Huang. 2020. The Prevalence of Dyslexia in Primary School Children and Their Chinese Literacy Assessment in Shantou, China. International Journal of Environmental Research and Public Health 17, 19 (2020), 7140. https://doi.org/10.3390/ijerph17197140Google ScholarCross Ref
- Cheng-Lin Liu, Fei Yin, Da-Han Wang, and Qiu-Feng Wang. 2011. CASIA online and offline Chinese handwriting databases. In 2011 international conference on document analysis and recognition. IEEE Computer Society, Los Alamitos, CA, USA, 37--41.Google ScholarDigital Library
- Li Liu, Ran Tao, Wenjing Wang, Wenping You, Danling Peng, and James R Booth. 2013. Chinese dyslexics show neural differences in morphological processing. Developmental cognitive neuroscience 6 (2013), 40--50.Google Scholar
- Stephen Man Kit Lee, Hey Wing Liu, and Shelley Xiuli Tong. 2022. Identifying Chinese Children with Dyslexia Using Machine Learning with Character Dictation. Scientific Studies of Reading 0, 0 (June 2022), 1--19. https://doi.org/10.1080/10888438.2022.2088373Google ScholarCross Ref
- Catherine McBride, Ying Wang, and Leo Man-Lit Cheang. 2018. Dyslexia in Chinese. Current Developmental Disorders Reports 5, 4 (2018), 217--225.Google ScholarCross Ref
- Eric Muller. 2012. L2/12-081 Extensions to Ideographic Description Sequences, take 2. http://unicode.org/L2/L2012/12081-ids.htmlGoogle Scholar
- Roderick I Nicolson and Angela J Fawcett. 1999. Developmental dyslexia: the role of the cerebellum 1. Dyslexia 5, 3 (1999), 155--177.Google ScholarCross Ref
- Eraldo Paulesu, J-F Démonet, Ferruccio Fazio, Eamon McCrory, Valerie Chanoine, Nicky Brunswick, Stefano F Cappa, Giuseppe Cossu, Michel Habib, Chris D Frith, et al. 2001. Dyslexia: Cultural diversity and biological unity. Science 291, 5511 (2001), 2165--2167.Google Scholar
- Stratigoula Politi-Georgousi and Athanasios Drigas. 2020. Mobile Applications, An Emerging Powerful Tool for Dyslexia Screening and Intervention: A Systematic Literature Review. International Journal of Interactive Mobile Technologies (iJIM) 14, 18 (Nov. 2020), 4--17. https://doi.org/10.3991/ijim.v14i18.15315 Number: 18.Google ScholarCross Ref
- Maria Rauschenberger, Ricardo Baeza-Yates, and Luz Rello. 2019. Technologies for dyslexia. In Web Accessibility. Springer, London, 603--627. https://doi.org/10.1007/978-1-4471-7440-0_31Google ScholarCross Ref
- Maria Rauschenberger, Ricardo Baeza-Yates, and Luz Rello. 2020. Screening Risk of Dyslexia through a Web-Game Using Language-Independent Content and Machine Learning. In Proceedings of the 17th International Web for All Conference (Taipei, Taiwan) (W4A '20). Association for Computing Machinery, New York, NY, USA, Article 13, 12 pages. https://doi.org/10.1145/3371300.3383342Google ScholarDigital Library
- Maria Rauschenberger, Luz Rello, Ricardo Baeza-Yates, and Jeffrey P. Bigham. 2018. Towards Language Independent Detection of Dyslexia with a Web-Based Game. In Proceedings of the 15th International Web for All Conference (Lyon, France) (W4A '18). Association for Computing Machinery, New York, NY, USA, Article 17, 10 pages. https://doi.org/10.1145/3192714.3192816Google ScholarDigital Library
- Luz Rello, Miguel Ballesteros, Abdullah X Ali, Miquel Serra, Daniela Alarcón Sánchez, and Jeffrey P Bigham. 2016. Dytective: diagnosing risk of dyslexia with a game. In Proceedings of the 10th EAI International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth '16). ICST (Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering), Brussels, BEL, 89--96.Google ScholarCross Ref
- Luz Rello, Enrique Romero, Maria Rauschenberger, Abdullah Ali, Kristin Williams, Jeffrey P Bigham, and Nancy Cushen White. 2018. Screening dyslexia for English using HCI measures and machine learning. In Proceedings of the 2018 international conference on digital health (DH '18). Association for Computing Machinery, New York, NY, USA, 80--84. https://doi.org/10.1145/3194658.3194675Google ScholarDigital Library
- Z Rezvani, M Zare, G Žarić, M Bonte, J Tijms, MW Van der Molen, and G Fraga González. 2019. Machine learning classification of dyslexic children based on EEG local network features. BioRxiv (2019), 569996.Google Scholar
- Sara Rosenblum, Shula Parush, and Patrice L Weiss. 2003. Computerized temporal handwriting characteristics of proficient and non-proficient handwriters. The American Journal of Occupational Therapy 57, 2 (2003), 129--138.Google ScholarCross Ref
- Gerd Schulte-Körne. 2010. The prevention, diagnosis, and treatment of dyslexia. Deutsches Arzteblatt international 107 41 (2010), 718--26.Google Scholar
- scikit learn. 2023. Feature importance for gradient boosting classifier, scikit-learn. https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.GradientBoostingClassifier.html#sklearn.ensemble.GradientBoostingClassifier.feature_importances_Google Scholar
- Hua Shu, Catherine McBride-Chang, Sina Wu, and Hongyun Liu. 2006. Understanding Chinese developmental dyslexia: morphological awareness as a core cognitive construct. Journal of educational psychology 98, 1 (2006), 122.Google ScholarCross Ref
- Margaret J Snowling. 2013. Early identification and interventions for dyslexia: a contemporary view. Journal of Research in Special Educational Needs 13, 1 (2013), 7--14.Google ScholarCross Ref
- Maritzol Tenemaza, Rosa Navarrete, Erika Jaramillo, and Andrés Rodriguez. 2019. Specific Dyslexia Exploratory Test (TEDE): Two Tasks Using Augmented Reality. In Advances in Usability, User Experience and Assistive Technology, Tareq Z. Ahram and Christianne Falcão (Eds.). Springer International Publishing, Cham, 925--933.Google Scholar
- Mei Hui Tseng. 1998. Development of pencil grip position in preschool children. The Occupational Therapy Journal of Research 18, 4 (1998), 207--224.Google ScholarCross Ref
- Chi-man Tsui, Cecilia W. P. Li-Tsang, and Pui Yee Grace Lung. 2012. Dyslexia in Hong Kong: Challenges and Opportunities. IntechOpen, Hong Kong SAR, China. https://doi.org/10.5772/32929 Publication Title: Learning Disabilities.Google ScholarCross Ref
- Ivan Vajs, Vanja Ković, Tamara Papić, Andrej M Savić, and Milica M Janković. 2022. Dyslexia detection in children using eye tracking data based on VGG16 network. In 2022 30th European Signal Processing Conference (EUSIPCO). IEEE, 1601--1605.Google ScholarCross Ref
- Aryan van der Leij. 2013. Dyslexia and early intervention: what did we learn from the Dutch Dyslexia Programme? Dyslexia 19, 4 (2013), 241--255.Google ScholarCross Ref
- FungKa Yan, Fung Kwong Chiu, Chan Aidan, and Yu Yi Ching. 2021. A Digital Tool to Provide Pre-Screening to Dyslexia in Hong Kong. In 2021 IEEE International Conference on Engineering, Technology & Education (TALE). IEEE, Los Alamitos, CA, USA, 755--761.Google ScholarCross Ref
- Chunxia Zhang, Longxue Li, and Xudong Li. 2021. A Survey of Chinese Character Recognition Research Based on Deep Learning. In 2021 7th Annual International Conference on Network and Information Systems for Computers (ICNISC). IEEE, USA, 926--931.Google ScholarCross Ref
- Jianshu Zhang, Jun Du, and Lirong Dai. 2020. Radical analysis network for learning hierarchies of Chinese characters. Pattern Recognition 103 (2020), 107305.Google ScholarCross Ref
- Shuhan Zhong, Sizhe Song, Guanyao Li, and S.-H. Gary Chan. 2022. A Tree-Based Structure-Aware Transformer Decoder for Image-To-Markup Generation. In Proceedings of the 30th ACM International Conference on Multimedia (MM '22), Oct. 10--14, 2022, Lisboa, Portugal. Association for Computing Machinery, New York, NY, USA. https://doi.org/10.1145/3503161.3548424Google ScholarDigital Library
Index Terms
- DYPA: A Machine Learning Dyslexia Prescreening Mobile Application for Chinese Children
Recommendations
Prediction of Learning Disorder: A-Systematic Review
Advances in Visual InformaticsAbstractLearning Disorder refers to a number of disorder which may influence the understanding or use of verbal or nonverbal information. The most well-known types of learning disorder involve an issue with reading, writing, listening, and speaking. When ...
Character and numeral recognition for non-Indic and Indic scripts: a survey
AbstractA collection of different scripts is employed in writing languages throughout the world. Character and numeral recognition of a particular script is a key area in the field of pattern recognition. In this paper, we have presented a comprehensive ...
Geo-education as a Valuable Support to Children with Learning Difficulties
Universal Access in Human-Computer Interaction. Access to Media, Learning and Assistive EnvironmentsAbstractIn recent years, the way some subjects are now taught has changed to provide students with a thorough understanding of the dynamics and interconnections in the world, with an increasing emphasis on geography. However, so far, little has been done ...
Comments