Facebook Twitter Linkedin
  home bred bred bred bred bred bred bred  
btn Academia Journal of Biotechnology
btn Journal of Business and Economic     Management
btn  Academia Journal of Medicinal Plants
btn Academia Journal of Environmental     Sciences
btn Academia Journal of Agricultural     Research
btn Academia Journal of Educational     Research
btn Academia Journal of Food Research
btn Academia Journal of Scientific     Research
btn Academia Journal of Microbiology    Research
btn  Engineering and Technology
btn Academia Journal of Pharmacy and     Pharmacology
btn Medicine and Medical Sciences


  1. Acad. J. Med. Plant.


Research Article

Academia Journal of Medicinal Plants 7(2): 036-041, February 2019
DOI: 10.15413/ajmp.2019.0106
ISSN: 2315-7720
2019 Academia Publishing


On the determination of important plants for ayurvedic formulas in Bangladesh using unsupervised machine learning approach

Accepted 24th January, 2019


Hossain M.Mofazzal1*, M. S. A. Gazi2, M. Mahbub2, A. A. P. Sayed2, S. Kanaya3 and M. Altaf-Ul-Amin3

1Department of Electronics and Telecommunication Engineering, University of Liberal Arts Bangladesh, Dhaka 1209, Bangladesh.
2Department of Electronics and Communications Engineering, East West University, Dhaka, Bangladesh.
3Graduate School of Science and Technology, Nara Institute of Science and Technology, Nara, Japan.

Ayurveda is the most ancient traditional medicine system practiced in the sub-continents including Bangladesh. It is very popular in Bangladesh because its ingredients are cheap and the production process is much simpler than Allopathic medicines. Ayurvedic medicines are usually mixtures of various herbal plants and Bangladesh is very rich in bio-diversity. It has more than five hundred (500) medicinal plants species. Ayurvedic data was collected for analysis from literature. These data contain Ayurvedic Medicine Formulas with their plants or biological ingredients, non-plant ingredients like minerals and their application on different types of diseases. In our analysis, we considered diseases like Indigestion, stomach ache, hemorrhoid and dysentery etc. Formulas from different manufacturers were presented in the data. We generated two relationship matrices with one classifying disease classes and the other being a binary matrix. The binary matrix contains formulas in rows and plants in columns. Hierarchical clustering was applied into the binary matrix data set for accumulating similar formulas included in a cluster. Using different distance/similarity measures we chose ‘Tanimoto Coefficient’ for hierarchical clustering as it gives more clusters of similar efficacies. Thereafter, we organized a three column dataset which contain formulas, classes of diseases and cluster membership ID. Finally, we found out most effective plants against corresponding diseases from this three columns data set. Our research will help Ayurvedic medicine producers and practitioners to determine the best plant for an Ayurvedic formula for a specific disease class or classes of diseases.

Key words: Plants, ayurvedic, matrix, cluster, efficacy.

This is an open access article published under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Cite this article as:
Mofazzal HM, Gazi MSA, Mahbub M, Sayed AAP, Kanaya S, Altaf-Ul-Amin M (2018). On the determination of important plants for ayurvedic formulas in Bangladesh using unsupervised machine learning approach. Acad. J. Med. Plants. 7(2): 036-041.

Copyright © 2019 Academia Publishing. All rights reserved
 Hosted by TUCOWS DOMAINS INC. Canada.