Commercial Clustering of Indian Bamboo Species Using Machine Learning Techniques

Bamboo is a grass that grows quickly (lm/days) and is very important to India’s social, economic, and environmental growth. India has a big market for bamboo because of the gap between its imports (3,306 thousand ${\$}$) and exports (607 thousand ${\$}$) of its products. Clustering bamboo for business will be important in the near future since it can be used in over 1,000 ways and is worth USD 2.969 billion in trade. Machine learning (ML) clustering models play a vital role in achieving this task for the commercial clustering of bamboo. In this research, we have presented details of twenty commercial species of bamboo in India has been identified, and data on the 2000 bamboo species have been collected. Although many algorithms have been introduced for clustering in recent years, not on bamboo, especially on morphological data. The target of this paper is to cluster these different bamboo species based on its commercial value using various ML algorithms such as K-means, Gaussian Mixture Models (GMM), and Balance Iterative Reducing and Clustering using Hierarchies (BIRCH). Clustering comes under unsupervised learning; there is no direct accuracy count. To evaluate the performance of clustering and determine which algorithm is best for clustering, we have used other indirect performance measures such as Silhouette Score, Calinski-Harabasz Index (CHI), and the Davies-Bouldin Index (DBI). K-mean shows the highest performance measures among all the other clustering ML models, with achieve a silhouette score of 0.5126, CHI of 17315 and DBI of 0.6633.