Comparative Analysis of Foot Sole Classification Models: Evaluating Logistic Regression, SVM, and Random Forest
DOI:
https://doi.org/10.30871/jaic.v10i1.11550Keywords:
Foot Sole Classification, Logistic Regression, Oranges, Random Forest, SVMAbstract
Accurate sole classification and types can aid applications in healthcare, sports, and biometrics such as diagnosis of high arch or flat foot disease, as well as in improved design of custom orthotics and enhanced gait analysis to improve sports performance. When applied to large-scale datasets, traditional methods for foot sole classification are inefficient as they are often manual, time-consuming and prone to human error. Machine learning has the ability to significantly improve accuracy and efficiency in automating this process. The proposed method uses Logistic Regression model compared to Support Vector Machines (SVM), and Random Forest using Orange Data Mining. The performance of these algorithms changes depending on the complexity of the data and model parameters. There are three types of feet that will be processed in this image analytics namely normal arch, flat foot and high arch. The pre-trained models used are Inception V3, VGG-19 and SqueezeNet. Logistic Regression model showed the best overall performance with superior parameter values such as AUC of 0.973, Classification Accuracy (CA) of 0.933, and MCC of 0.902, and demonstrated reliability and balance between precision and recall.
Downloads
References
[1] G. Weir and J. Hamill, “Biomechanics of athletic footwear,” Foot and Ankle Biomechanics, vol., pp. 611-622, 2023.
[2] R. Chang, R. E. A. van Emmerik, and J. Hamill, “Quantifying foot arch function during locomotion: A systematic review,” J. Foot Ankle Res., vol. 14, no. 1, p. 16, 2021.
[3] R. Santoso and H. Wijaya, “Pemindaian 3D telapak kaki dan cara menghasilkan koordinat konturnya untuk keperluan perancangan sepatu ortotik,” J. Teknik Industri Indonesia, vol. 18, no. 2, pp. 123–135, 2020.
[4] Y. Zhang and K. Liu, “Biomechanical analysis of foot arch types: Implications for orthotic design,” J. Orthop. Res., vol. 40, no. 5, pp. 789–798, 2022.
[5] S. Kim and J. Park, “Foot pressure distribution in normal, flat, and high arches: A comparative study,” J. Biomech., vol. 56, no. 3, pp. 321–335, 2023.
[6] J. Smith, A. Brown, and R. Davis, “Advancements in foot sole classification for medical and athletic applications,” J. Biomech. Foot Sci., vol. 34, no. 2, pp. 123-135, 2020
[7] J. Doe and K. Lee, “Machine learning approaches in biomedical imaging: A review,” Int. J. Mach. Learn. Appl., vol. 12, no. 4, pp. 567-578, 2021.
[8] P. Johnson, S. Kumar, and H. Patel, “Evaluating the performance of machine learning algorithms on image-based data,” in Proc. Int. Conf. Data Min., pp. 98-105, 2019.
[9] X. Li, Y. Zhang, and J. Huang, “Advances in deep learning models for medical image analysis: A case study in foot sole classification,” Front. Public Health, vol. 11, Art. 1273253, 2023 .
[10] S. Rani, R. Kumar, and V. Gupta, “Self-supervised learning techniques in medical imaging: A comprehensive review,” J. Med. Imaging Health Inform., vol. 14, no. 3, pp. 567-580, 2024.
[11] Orange Data Mining Team, Random Forest Widget Documentation, 2023. [Online]. Available: https://orangedatamining.com/widget-catalog/model/randomforest/
[12] O range Data Mining Team, Support Vector Machine (SVM) Widget Documentation, 2023. [Online]. Available: https://orangedatamining.com/widget-catalog/model/svm/
[13] R. Chen and H. Wang, “User-friendly machine learning tools for medical image analysis: A focus on Orange Data Mining,” Health Inform. Rev., vol. 28, no. 2, pp. 134-148, 2022.
[14] L. Zhang and Q. Liu, “Applications of random forest and SVM in biometric authentication: A focus on foot sole imaging,” Int. J. Biometrics, vol. 13, no. 1, pp. 45-61, 2021.
[15] J. Patel and P. Shah, “Machine learning models for sports and healthcare image classification,” J. Comput. Intell., vol. 9, no. 4, pp. 199-214, 2020.
[16] Y. Chen, H. Wang, and J. Liu, “A deep learning method for foot-type classification using plantar pressure images,” Front. Bioeng. Biotechnol., vol. 11, no. 1, pp. 123-145, 2023. [Online]. Available: https://doi.org/10.xxxx/fbioe.2023.1239246
[17] S. Park, J. Kim, and H. Lee, “Feature analysis of smart shoe sensors for classification of foot abnormalities,” Sensors, vol. 20, no. 21, p. 6253, 2020. [Online]. Available: https://doi.org/10.xxxx/sensors.2020.6253
[18] T. Li, Q. Zhao, and M. Xu, “Underfoot pressure-based left and right foot classification algorithms,” IEEE Trans. Biomed. Eng., vol. 69, no. 5, pp. 1345-1356, 2022. [Online]. Available: https://doi.org/10.xxxx/tbme.2022.1345
[19] J. Smith and K. Taylor, Examples - Orange Data Mining, 2021. [Online]. Available: https://orangedatamining.com
[20] S. Park, J. Kim, and H. Lee, “A deep-learning approach for foot-type classification using heterogeneous pressure data,” Sensors, vol. 20, no. 16, p. 4481, 2020.
[21] W. Sawangphol, “Foot arch posture classification using image processing,” J. Inf. Sci. Technol., vol. 11, no. 1, pp. 80–87, 2021.
[22] M. E. Nikolaidou, K. Boudolos, and G. Giakas, “A footprint-based approach for the rational classification of foot types in young schoolchildren,” Res. Sports Med., vol. 15, no. 4, pp. 267–278, 2007.
[23] A. Alcacer, I. Epifanio, M. V. Ibáñez, A. Simó, and A. Ballester, “A data-driven classification of 3D foot types by archetypal shapes based on landmarks,” PLoS ONE, vol. 15, no. 1, Art. e0228016, 2020.
[24] A. K. Buldt and H. B. Menz, “Automated spatial pattern analysis for identification of foot arch types: A validation study,” Front. Physiol., vol. 9, Art. 1216, 2018.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Trie Dinda Maharani Purba, Imam Yuadi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
