The Effect of Linear Discriminant Analysis and Quantum Feature Maps on QSVM Performance for Obesity Diagnosis

Year 2024, Volume: 12 Issue: 3, 206 - 213, 30.09.2024

Zeynep Özpolat , Özal Yıldırım , Murat Karabatak

https://doi.org/10.17694/bajece.1475896

Abstract

Obesity, characterized by an excessive increase in body fat, is not only a significant disease but also a condition that serves as the basis for many other illnesses. Therefore, early intervention and necessary precautions for diagnosing and treating obesity are of paramount importance. Classical machine learning algorithms are actively utilized in medical fields to expedite prediction processes. However, the increasing volume of data renders even effective classification algorithms inadequate for experts to diagnose diseases. Quantum computing-based algorithms come into play at this point, offering a new perspective in machine learning by utilizing quantum physics, which is contrary to the rules of classical physics. Dimensionality reduction techniques required for the use of quantum-based algorithms play an essential role in both classical and quantum applications. In this study, Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA), classical dimensionality reduction methods, were applied to the obesity dataset and analyzed with Quantum Support Vector Machine (QSVM) and Support Vector Machine (SVM) algorithms. To conduct QSVM studies, the comparison of three different quantum feature maps providing the qubit transformation of classical bit data is also included in this study. As a result of the analysis, it was determined that the proposed method as LDA-QSVM achieved 100% success when used with Z and Pauli X feature maps. This success, which is rare in literature studies on obesity data, emphasizes the future potential of quantum-based algorithms in obesity diagnosis and treatment.

Keywords

Obesity, Linear Discriminant Analysis, Quantum Support Vector Machine, Dimensionality Reduction, Quantum Machine Learning.

References

• [1] T. L. Visscher and J. C. Seidell, ‘The Public Health Impact of Obesity’, Annual Review of Public Health, vol. 22, no. Volume 22, 2001, pp. 355–375, May 2001, doi: 10.1146/annurev.publhealth.22.1.355.
• [2] W. T. Cefalu et al., ‘Advances in the Science, Treatment, and Prevention of the Disease of Obesity: Reflections From a Diabetes Care Editors’ Expert Forum’, Diabetes Care, vol. 38, no. 8, pp. 1567–1582, Jul. 2015, doi: 10.2337/dc15-1081.
• [3] ‘A Survey on Machine and Deep Learning Models for Childhood and Adolescent Obesity | IEEE Journals & Magazine | IEEE Xplore’. Accessed: Mar. 26, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9627712
• [4] I. H. Sarker, ‘Machine Learning: Algorithms, Real-World Applications and Research Directions’, SN COMPUT. SCI., vol. 2, no. 3, p. 160, Mar. 2021, doi: 10.1007/s42979-021-00592-x.
• [5] M. Schuld, I. Sinayskiy, and F. Petruccione, ‘An introduction to quantum machine learning’, Contemporary Physics, vol. 56, no. 2, pp. 172–185, Apr. 2015, doi: 10.1080/00107514.2014.964942.
• [6] T. M. Khan and A. Robles-Kelly, ‘Machine Learning: Quantum vs Classical’, IEEE Access, vol. 8, pp. 219275–219294, 2020, doi: 10.1109/ACCESS.2020.3041719.
• [7] W. Ding and J. Wang, ‘A novel approach to minimum attribute reduction based on quantum-inspired self-adaptive cooperative co-evolution’, Knowledge-Based Systems, vol. 50, pp. 1–13, Sep. 2013, doi: 10.1016/j.knosys.2013.03.008.
• [8] W. Jia, M. Sun, J. Lian, and S. Hou, ‘Feature dimensionality reduction: a review’, Complex Intell. Syst., vol. 8, no. 3, pp. 2663–2693, Jun. 2022, doi: 10.1007/s40747-021-00637-x.
• [9] B. Ghojogh and M. Crowley, ‘Unsupervised and Supervised Principal Component Analysis: Tutorial’, Aug. 01, 2022, arXiv: arXiv:1906.03148. Accessed: Jun. 25, 2023. [Online]. Available: http://arxiv.org/abs/1906.03148
• [10] C. Li and B. Wang, ‘Fisher Linear Discriminant Analysis’.
• [11] E. H. Houssein, Z. Abohashima, M. Elhoseny, and W. M. Mohamed, ‘Machine learning in the quantum realm: The state-of-the-art, challenges, and future vision’, Expert Systems with Applications, vol. 194, p. 116512, May 2022, doi: 10.1016/j.eswa.2022.116512.
• [12] M. Noori et al., ‘Analog-Quantum Feature Mapping for Machine-Learning Applications’, Phys. Rev. Appl., vol. 14, no. 3, p. 034034, Sep. 2020, doi: 10.1103/PhysRevApplied.14.034034.
• [13] T. Kumar, D. Kumar, and G. Singh, ‘Brain Tumour Classification Using Quantum Support Vector Machine Learning Algorithm’, IETE Journal of Research, May 2024, Accessed: Sep. 05, 2024. [Online]. Available: https://www.tandfonline.com/doi/abs/10.1080/03772063.2023.2245350
• [14] G. Aksoy and M. Karabatak, ‘Comparison of QSVM with Other Machine Learning Algorithms on EEG Signals’, in 2023 11th International Symposium on Digital Forensics and Security (ISDFS), May 2023, pp. 1–5. doi: 10.1109/ISDFS58141.2023.10131123.
• [15] G. Aksoy, G. Cattan, S. Chakraborty, and M. Karabatak, ‘Quantum Machine-Based Decision Support System for the Detection of Schizophrenia from EEG Records’, J Med Syst, vol. 48, no. 1, p. 29, Mar. 2024, doi: 10.1007/s10916-024-02048-0.
• [16] W. E. Maouaki, T. Said, and M. Bennai, ‘Quantum Support Vector Machine for Prostate Cancer Detection: A Performance Analysis’, Mar. 12, 2024, arXiv: arXiv:2403.07856. doi: 10.48550/arXiv.2403.07856.
• [17] M. Munshi et al., ‘Quantum machine learning-based framework to detect heart failures in Healthcare 4.0’, Software: Practice and Experience, vol. 54, no. 2, pp. 168–185, 2024, doi: 10.1002/spe.3264.
• [18] Unknown, ‘Estimation of obesity levels based on eating habits and physical condition’. UCI Machine Learning Repository, 2019. doi: 10.24432/C5H31Z.
• [19] F. M. Palechor and A. D. L. H. Manotas, ‘Dataset for estimation of obesity levels based on eating habits and physical condition in individuals from Colombia, Peru and Mexico’, Data in Brief, vol. 25, p. 104344, Aug. 2019, doi: 10.1016/j.dib.2019.104344.
• [20] S. Chen, Y. Dai, X. Ma, H. Peng, D. Wang, and Y. Wang, ‘Personalized optimal nutrition lifestyle for self obesity management using metaalgorithms’, Sci Rep, vol. 12, no. 1, Art. no. 1, Jul. 2022, doi: 10.1038/s41598-022-16260-w.
• [21] C. L. Urdinez Francisco, ‘Principal Component Analysis’, in R for Political Data Science, Chapman and Hall/CRC, 2020.
• [22] L. Ali, I. Wajahat, N. Amiri Golilarz, F. Keshtkar, and S. A. C. Bukhari, ‘LDA–GA–SVM: improved hepatocellular carcinoma prediction through dimensionality reduction and genetically optimized support vector machine’, Neural Comput & Applic, vol. 33, no. 7, pp. 2783–2792, Apr. 2021, doi: 10.1007/s00521-020-05157-2.
• [23] ‘ZZFeatureMap - Qiskit 0.44.1 documentation’. Accessed: Sep. 26, 2023. [Online]. Available: https://qiskit.org/documentation/stubs/qiskit.circuit.library.ZZFeatureMap.html
• [24] ‘ZFeatureMap - Qiskit 0.44.1 documentation’. Accessed: Sep. 26, 2023. [Online]. Available: https://qiskit.org/documentation/stubs/qiskit.circuit.library.ZFeatureMap.html
• [25] ‘PauliFeatureMap’, IBM Quantum Documentation. Accessed: Sep. 26, 2023. [Online]. Available: https://docs.quantum-computing.ibm.com/api/qiskit/qiskit.circuit.library.PauliFeatureMap
• [26] S. Altares-López, A. Ribeiro, and J. J. García-Ripoll, ‘Automatic design of quantum feature maps’, Quantum Sci. Technol., vol. 6, no. 4, p. 045015, Aug. 2021, doi: 10.1088/2058-9565/ac1ab1.
• [27] S. Agnihotri, ‘Quantum Machine Learning 102 — QSVM Using Qiskit’, Medium. Accessed: Sep. 26, 2023. [Online]. Available: https://shubham-agnihotri.medium.com/quantum-machine-learning-102-qsvm-using-qiskit-731956231a54
• [28] P. Rebentrost, M. Mohseni, and S. Lloyd, ‘Quantum Support Vector Machine for Big Data Classification’, Phys. Rev. Lett., vol. 113, no. 13, p. 130503, Sep. 2014, doi: 10.1103/PhysRevLett.113.130503.
• [29] R. Zhang, J. Wang, N. Jiang, and Z. Wang, ‘Quantum support vector machine without iteration’, Information Sciences, vol. 635, pp. 25–41, Jul. 2023, doi: 10.1016/j.ins.2023.03.106.
• [30] Z. Abohashima, M. Elhosen, E. H. Houssein, and W. M. Mohamed, ‘Classification with Quantum Machine Learning: A Survey’, Jun. 22, 2020, arXiv: arXiv:2006.12270. doi: 10.48550/arXiv.2006.12270.
• [31] R. Kaur, R. Kumar, and M. Gupta, ‘Predicting risk of obesity and meal planning to reduce the obese in adulthood using artificial intelligence’, Endocrine, vol. 78, no. 3, pp. 458–469, Dec. 2022, doi: 10.1007/s12020-022-03215-4.
• [32] P. Putzel and S. Lee, ‘Blackbox Post-Processing for Multiclass Fairness’, Jan. 12, 2022, arXiv: arXiv:2201.04461. doi: 10.48550/arXiv.2201.04461.
• [33] D. D. Solomon et al., ‘Hybrid Majority Voting: Prediction and Classification Model for Obesity’, Diagnostics, vol. 13, no. 15, Art. no. 15, Jan. 2023, doi: 10.3390/diagnostics13152610.
• [34] S. Nematzadeh, F. Kiani, M. Torkamanian-Afshar, and N. Aydin, ‘Tuning hyperparameters of machine learning algorithms and deep neural networks using metaheuristics: A bioinformatics study on biomedical and biological cases’, Computational Biology and Chemistry, vol. 97, p. 107619, Apr. 2022, doi: 10.1016/j.compbiolchem.2021.107619.
• [35] D. Mckensy-Sambola, M. Á. Rodríguez-García, F. García-Sánchez, and R. Valencia-García, ‘Ontology-Based Nutritional Recommender System’, Applied Sciences, vol. 12, no. 1, Art. no. 1, Jan. 2022, doi: 10.3390/app12010143.