AI TECHNIQUES FOR IDENTIFICATION AND STUDY OF MEDICINAL PLANTS: A REVIEW

Abstract

Medicinal plants have been integral to human health for centuries, offering a wealth of bioactive compounds with therapeutic potential. However, their identification and study pose significant challenges due to the vast number of species, morphological similarities, and the need for expert knowledge. Traditional methods are time-consuming and often require specialized skills. With the advent of artificial intelligence (AI), particularly machine learning, there is a growing opportunity to streamline and enhance the processes involved in medicinal plant research. This review explores the application of AI techniques, focusing on machine learning and deep learning, in the identification and study of medicinal plants. By synthesizing recent research, this paper highlights how AI can address key challenges in this field, the combination of machine learning algorithms and multi-source data analysis facilitates a comprehensive analysis and aids in the effective evaluation of the quality of medicinal plants. Deep learning and Convolutional Neural Networks (CNNs); Product Decision Rule (PDR); EfficientNet-B1-based deep learning model; Direct Ensemble Classifier for Imbalanced Multiclass Learning (DECIML) are among the prominent machine learning tools used to identify medicinal plants based on their leaf textural features in an ensemble manner are used to compare their performance accuracies over this data. Also, Artificial Neural Networks, Deep Neural Networks, Neuro-fuzzy Logic have eased the time required in classical experimental strategy and paved a pathway for understanding from accurate species recognition to predicting bioactive compound biosynthesis, thereby paving the way for more efficient drug discovery and conservation efforts.