Performance Analysis of Feature Selection and Classification Methods for Predicting Dyslexia

G Vanitha; M Kasthuri

doi:10.17485/IJST/v16i33.165

Article

Performance Analysis of Feature Selection and Classification Methods for Predicting Dyslexia

VIEWS 323
PDF 98

Indian Journal of Science and Technology

DOI: 10.17485/IJST/v16i33.165

Year: 2023, Volume: 16, Issue: 33, Pages: 2663-2669

Original Article

Performance Analysis of Feature Selection and Classification Methods for Predicting Dyslexia

G Vanitha^1*, M Kasthuri²

¹Research Scholar/Associate Professor, Department of Information Technology, Bishop Heber College, Affiliated Bharathidasan University, Tiruchirappalli, 620 024, Tamil Nadu, India
²Associate Professor, Department of Computer Applications, Bishop Heber College, Affiliated Bharathidasan University, Tiruchirappalli, 620 024, Tamil Nadu, India

*Corresponding Author
Email: [email protected]

Received Date:23 January 2023, Accepted Date:28 July 2023, Published Date:08 September 2023

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Objectives: This study aims to select efficient and relevant features to detect Dyslexia with better accuracy using various Machine Learning (ML) models. Methods: A benchmark online gamified test dataset was used. Dyslexia from Kaggle used which contains 196 features. The dataset is divided as training and testing with 80-20%. Information Gain (IG), Principal Components Analysis (PCA), and Correlation Attribute Evaluation (CAE) are used to select relevant features. The performances of the selected features are evaluated using ML Classifiers models such as C 4.5, Random Forest (RF), Decision Table (DT), Logistic Regression (LR), and Support Vector Machine (SVM). Findings: Our feature selection method IG selects 192, PCA selects 195, and CAE selects 186 features out of 196 features. The selected features are tested with various above-mentioned ML classifier models. This study shows CAE with the LR classifier model well suited for select relevant features with 89.8% of accuracy. Novelty: This study presents a CAE feature selection approach with LR classifier approximately greater than 1.5 % accuracy of the existing approach of MIG, K-Best Features, and Recursive Feature Elimination in Random Forest. The proposed technique achieved improvement in accuracy.

Keywords: Machine Learning; Feature selection; Classification; Dyslexia

References

Dyslexia at a glance . 2014. Available from: https://dyslexiaida.org/dyslexia-at-a-glance/
Dyslexia association of India . 2023. Available from: https://www.dyslexiaindia.org.in/what-dyslexia2.html/
Zauderer S. Dyslexia statistics & facts: How many people have Dyslexia? Crossrivertherapy.com. Cross River Therapy. 2023. Available from: https://www.crossrivertherapy.com/research/dyslexia-statistics
Hmimdi AEE, Ward LM, Palpanas T, Kapoula Z. Predicting Dyslexia and Reading Speed in Adolescents from Eye Movements in Reading and Non-Reading Tasks: A Machine Learning Approach. Brain Sciences. 2021;11(10):1337. Available from: http://dx.doi.org/10.3390/brainsci11101337
Alqahtani ND, Alzahrani B, Ramzan MS. Deep Learning Applications for Dyslexia Prediction. Applied Sciences. 2023;13(5):2804. Available from: http://dx.doi.org/10.3390/app13052804
Prabha J, Bhargavi A. Prediction of dyslexia from eye movements using machine learning. IETE Journal of Research. 2022;68(2):814–837. Available from: http://dx.doi.org/10.1080/03772063.2019.1622461
Man K, Lee S, Liu HW, Tong SX. Identifying Chinese children with dyslexia using machine learning with character dictation. Scientific Studies of Reading. 2023;27(1):82–100. Available from: http://dx.doi.org/10.1080/10888438.2022.2088373
Jan TG, Khan SM. A Systematic Review of Research Dimensions Towards Dyslexia Screening Using Machine Learning. Journal of The Institution of Engineers (India): Series B. 2023;104(2):511–522. Available from: http://dx.doi.org/10.1007/s40031-023-00853-8
Asvestopoulou T, Manousaki V, Psistakis A, Smyrnakis I, Andreadakis V, Aslanides IM. Screening tool for dyslexia using machine learning. ARXIV. 2019. Available from: http://dx.doi.org/10.48550/ARXIV.1903.06274
Szalma J, Weiss B. Data-Driven Classification of Dyslexia Using Eye-Movement Correlates of Natural Reading. In: ACM Symposium on Eye Tracking Research and Applications. (Vol. 2020) ACM. 2020.
Raatikainen P, Hautala J, Loberg O, Kärkkäinen T, Leppänen P, Nieminen P. Detection of developmental dyslexia with machine learning using eye movement data. Array. 2021;12:100087. Available from: http://dx.doi.org/10.1016/j.array.2021.100087
Bommert A, Sun X, Bischl B, Rahnenführer J, Lang M. Benchmark for filter methods for feature selection in high-dimensional classification data. Computational Statistics & Data Analysis. 2020;143:106839. Available from: https://doi.org/10.1016/j.csda.2019.106839
Oliaee A, Mohebbi M, Shirani S, Rostami R. Extraction of discriminative features from EEG signals of dyslexic children; before and after the treatment. Cognitive Neurodynamics. 2022;16(6):1249–1259. Available from: http://dx.doi.org/10.1007/s11571-022-09794-2
Rello L, Baeza-Yates R, Ali A, Bigham JP, Serra MP. Predicting risk of dyslexia with an online gamified test. PLOS ONE. 2020;15(12):e0241687. Available from: http://dx.doi.org/10.1371/journal.pone.0241687
Dataset. Kaggle Repository. Available from: https://doi.org/10.34740/kaggle/dsv/1617514
Alyasiri OM, Cheah NN, Abasi AK, Al-Janabi OM. Wrapper and Hybrid Feature Selection Methods Using Metaheuristic Algorithms for English Text Classification: A Systematic Review. IEEE Access. 2022;10:39833–39852. Available from: http://dx.doi.org/10.1109/access.2022.3165814
Shankar S, Ashokkumar G, Vinayakumar P, Ghosh R, Mansoor U, WWS. An embedded-based weighted feature selection algorithm for classifying web document. Wireless Communications and Mobile Computing. 2020;p. 1–10. Available from: https://doi.org/10.1155/2020/8879054
N A, MB R, HM EH, I A, M R. An efficient machine learning-based feature optimization model for the detection of dyslexia. 2023. Available from: http://dx.doi.org/10.1155/2022/8491753
Chakraborty V, Sundaram M. Machine learning algorithms for prediction of dyslexia using eye movement. Journal of Physics: Conference Series. 2020;1427(1):012012. Available from: https://doi.org/10.1088/1742-6596/1427/1/012012
Devi MS, Kumar VD, Brezulianu A, Geman O, Arif M. A Novel Blunge Calibration Intelligent Feature Classification Model for the Prediction of Hypothyroid Disease. PMCID. 2023. Available from: https://doi.org/10.3390/s23031128
Jan TG, Khan SM. An effective feature selection and classification technique based on ensemble learning for dyslexia detection. 2023. Available from: https://doi.org/10.1007/978-981-19-1844-5_32
Raatikainen P, Hautala J, Loberg O, Kärkkäinen T, Leppänen P, Nieminen P. Detection of developmental dyslexia with machine learning using eye movement data. Array. 2021;12:100087. Available from: http://dx.doi.org/10.1016/j.array.2021.100087
Radzi SFM, Hassan MS, Radzi MAHM. Comparison of classification algorithms for predicting autistic spectrum disorder using WEKA modeler. BMC Medical Informatics and Decision Making. 2022;22(1):306. Available from: http://dx.doi.org/10.1186/s12911-022-02050-x

Copyright

© 2023 Vanitha & Kasthuri. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)