International Journal of Wireless and Microwave Technologies (IJWMT)
IJWMT Vol. 16, No. 3, 8 Jun. 2026
Cover page and Table of Contents: PDF (size: 1745KB)
Discrete Optimization Analysis of Ensemble Learning in Ayurvedic Dosha Classification
PDF (1745KB), PP.323-335
Views: 0 Downloads: 0
Author(s)
Index Terms
Ayurveda, Dosha classification, Machine learning, Ensemble models, Random Forest, XGBoost, Categorical data, Digital health, Personalized medicine, Questionnaire analysis
Abstract
This study introduces a unique framework that combines machine learning, and dosha profiling from Ayurveda, to improve precision, reliability, and interpretability of traditional diagnostic assessments. Four machine learning algorithms (Logistic Regression, Support Vector Machine (SVM), Random Forest, and XGBoost) were systematically investigated with a rigorous, quiz-based dataset that contained demographic, lifestyle, and physiological characteristics to classify six dosha categories (Vata, Pitta, Kapha, and their pairs). The experimental results showed a stark difference between linear and ensemble approaches. With an accuracy of 30% (F1 = 0.288), Logistic Regression provided marginal performance, suggesting there is limited separability in the overlapping patterns of health, while SVM came with an accuracy of 97.3% (F1 = 0.972) with kernel optimization. However, tree-based ensemble approaches improved predictive utility; Random Forest showed the highest overall performance (accuracy = 98.1%, F1-Macro = 0.982), with XGBoost and a Stacked Ensemble model behind (both ≈ 98%). This confirms ensemble approaches can represent the complex and nonlinear interdependencies associated with holistic wellness datasets. Interpretability analysis through feature importance ranking identified lifestyle and physiological variables—including sleep quality, appetite, emotional stability, skin texture, and digestion pattern—as the most important predictors, demonstrating a strong correlation to established Ayurvedic theory. Additionally, a desktop-based, interactive visualization was built to allow dosha prediction and wellness insights in real time. In conclusion, this work provides justification for Random Forest and XGBoost models as benchmarks for dosha classification and achieves a scientific syntheses of ancient Ayurvedic practice with contemporary machine learning. The results have important implications for the portfolio of digital Ayurvedic practice; to support data-informed personalized medicine; to foster new cross-disciplinary collaborations among ancient medicine, modern artificial intelligence and machine learning. This study compares Support Vector Machines (SVM), Random Forest (RF), and XGBoost for Ayurvedic dosha classification (Vata, Pitta, Kapha).
Cite This Paper
Rama Bhardwaj, Rakesh Kumar Saxena, "Discrete Optimization Analysis of Ensemble Learning in Ayurvedic Dosha Classification", International Journal of Wireless and Microwave Technologies(IJWMT), Vol.16, No.3, pp. 323-335, 2026. DOI:10.5815/ijwmt.2026.03.21
Reference
[1]Vayadande, K., Sukte, C. D., Bodhe, Y., Jagtap, T., Joshi, A., Joshi, P., Kadam, A., & Kadam, S. (2024). Heart disease diagnosis and diet recommendation system using Ayurvedic dosha analysis. EAI Endorsed Transactions on Internet of Things. https://doi.org/10.4108/eetiot.6016
[2]Shariff, F., Huda, L. A., Maaz, M. H. K., Zeeshan, M., & Rehman, A. (2025). Ayurvedic medicine recommendation. IRE Journals, 9(6).
[3]Kumar, S. (2024). Ayurvedic-based disease prediction and drug recommendation system. Srusti Management Review, Special Issue, 27–37.
[4]Dwivedi, J. (2025). Ayurvedic Perspective on Vata Dosha and Neurological Disorders using Machine Learning Techniques. SGS - Engineering & Sciences, 1(4). https://spast.org/techrep/article/view/5660
[5]Sil, P., Tiwari, R., Garisetti, V., Baskaran, S. P., Dhanaseelan, F. H., Srivastava, S., & Samal, A. (2026). Computational investigation of single herbal drugs in Ayurveda for diabetes and obesity using knowledge graph and network pharmacology. arXiv. https://arxiv.org/abs/2601.21643
[6]Wang, C., Wang, F., Guo, R., Liang, Y., Liu, K., & Yu, P. S. (2024). Confidence-aware fine-tuning of sequential recommendation systems via conformal prediction. arXiv Preprint arXiv:2402.08976. https://doi.org/10.48550/arXiv.2402.08976
[7]Vayadande, K., Ghadekar, P. P., Sawant, A., Shelke, M. P., Shirsath, B., Bhande, B., & Samgir, S. (2024). Identification of Ayurvedic medicinal plant using deep learning. International Journal of Intelligent Systems and Applications in Engineering, 12(15s), 678–693.
[8]Garg, S. (2021). Drug recommendation system based on sentiment analysis of drug reviews using machine learning. arXiv. https://arxiv.org/abs/2104.01113
[9]Fathi, P., & Charkari, N. M. (2024). Herb target prediction using protein complexes detection and machine learning methods in heterogeneous network. Kurdish Studies, 12(4), 65–77.
[10]Ji, X., Li, Q., Liu, Z., Wu, W., Zhang, C., Sui, H., & Chen, M. (2024). Identification of active components for sports supplements: Machine learning-driven classification and cell-based validation. ACS Omega, 9(10), 11347–11355. https://doi.org/10.1021/acsomega.3c09234
[11]GunaChandra, S., Mounika, P., Yaswanth, K., & Prasad, M. K. S. R. (2024). Deep learning for medicinal plant identification and utilization: Leveraging ResNet for enhanced recognition and applications. International Refereed Journal of Engineering and Science (IRJES), 13(2), 159–165.
[12]Qian, Y., Wang, X., Cai, L., Han, J., Huang, Z., Lou, Y., et al. (2024). Model informed precision medicine of Chinese herbal medicines formulas–A multi-scale mechanistic intelligent model. Journal of Pharmaceutical Analysis, 14(4), 100914. https://doi.org/10.1016/j.jpha.2024.100914
[13]Pushpa, B. R., Rani, N. S., Chandrajith, M., Manohar, N., & Nair, S. S. K. (2024). On the importance of integrating convolution features for Indian medicinal plant species classification using hierarchical machine learning approach. Ecological Informatics, 84, 102611. https://doi.org/10.1016/j.ecoinf.2024.102611
[14]Jin, Y., Ji, W., Shi, Y., Wang, X., & Yang, X. (2023). Meta-path guided graph attention network for explainable herb recommendation. Health Information Science and Systems, 11(1), 5. https://doi.org/10.1007/s13755-023-00208-1
[15]Jin, Z., Zhang, Y., Miao, J., Yang, Y., Zhuang, Y., & Pan, Y. (2023). A knowledge-guided and traditional Chinese medicine informed approach for herb recommendation. Frontiers of Information Technology & Electronic Engineering, 24(10), 1416–1429. https://doi.org/10.1631/FITEE.2200457
[16]Yang, X., & Ding, C. (2023). SMRGAT: A traditional Chinese herb recommendation model based on a multi-graph residual attention network and semantic knowledge fusion. Journal of Ethnopharmacology, 315, 116693. https://doi.org/10.1016/j.jep.2023.116693
[17]Zhao, Z., Ren, X., Song, K., Qiang, Y., Zhao, J., Zhang, J., & Han, P. (2023). PreGenerator: TCM prescription recommendation model based on retrieval and generation method. IEEE Access, 11, 103679–103692. https://doi.org/10.1109/ACCESS.2023.3317221
[18]Bidve, P., Mishra, S., & Annapurna, J. (2023). Enhancing Ayurvedic diagnosis using multinomial Naive Bayes and K-modes clustering: An investigation into prakriti types and dosha overlapping. arXiv. https://arxiv.org/abs/2310.02920. https://doi.org/10.3390/math11163504
[19]Khatua, D., Sekh, A. A., Kutum, R., Mukherji, M., Prasher, B., & Kar, S. (2023). Classification of Ayurveda constitution types: A deep learning approach. Soft Computing, 27(9), 5309–5317. https://doi.org/10.1007/s00500-022-07653-8
[20]Patel, M., Shah, V., & Joshi, R. (2025). A decision tree-based approach for disease prediction and Ayurvedic drug recommendation. International Journal of Intelligent Systems and Applications in Engineering, 13(1), 77–89.
[21]Rao, N., Kulkarni, P., & Deshmukh, S. (2024). Status of artificial intelligence and machine learning in Indian traditional medicine. Journal of Medicinal Plants and Comparative Research, 8(3), 145–158.
[22]Sharma, K., Gupta, R., & Bansal, P. (2024). Identification of medicinal leaves and recommendation system using deep learning. International Journal of Intelligent Systems and Applications in Engineering, 12(4), 225–234.
[23]Ahmed, S., Khan, M., & Hussain, T. (2025). An automated system for medicinal plant identification and usage recommendation. International Journal of Advanced Computer Science and Applications, 16(1), 66–75.
[24]Lee, W. Y., Lee, Y., Lee, S., Kim, Y. W., & Kim, J. H. (2022). A machine learning approach for recommending herbal formulae with enhanced interpretability and applicability. Biomolecules, 12(11), 1604. https://doi.org/10.3390/biom12111604
[25]Malik, O. A., Ismail, N., Hussein,B. R., & Yahya, U. (2022). Automated real-time identification of medicinal plants species in natural environment using deep learning models—A case study from Borneo Region. Plants, 11(15), 1952. https://doi.org/10.3390/plants11151952
[26]Azadnia, R., Al-Amidi, M. M., Mohammadi, H., Cifci, M. A., Daryab, A., & Cavallo, E. (2022). An AI based approach for medicinal plant identification using deep CNN based on global average pooling. Agronomy, 12(11), 2723. https://doi.org/10.3390/agronomy12112723
[27]Joseph, A., Thomas, M., & Roy, P. (2024). HerbId: A medicinal plant identification and recommendation framework. AIP Conference Proceedings, 3122(1), 080026. https://pubs.aip.org/aip/acp/article/3122/1/080026/3298914/HerbId-A-medicinal-plant-identification-and