Pivot Based Seed Germination Assessment (PBSGA) Pattern for Germination Quality Analysis

Authors

  • M. M. Venkata Chalapathi, M. Rudra Kumar

Abstract

Consistent demand and imperative need to improve the agricultural production outcome paves way for exploring the seed quality optimization or seed germination process management techniques. In this manuscript, the emphasis is on developing a machine learning process of seed germination classification. While there are many internal parameters that define the effectiveness of germination, the three-stage modeled approach explored in this manuscript is to classify a germination as good, bad, or moderate. Proposed model PBSGA (Pivot Based Seed Germination Assessment) is a statistical method-based assessment model proposed for dynamic assessment of each seed considered for the study, and also in classifying improvements or deterioration imperative in the model for other conditions. The model is trained over the DT classifier and is tested in two different conditions. Firstly, the model is compared to a machine learning approach proposed in a study for rice seeds quality assessment (RSGA), and in the other way between multiple baskets of same dataset from KAGGLE dataset. The experimental study of the model reveals the efficacy of proposed solution PBSGA towards identifying the right classification of the model and also in terms of ideating the sequential improvements like difference between the quality in earlier testing batch to current batches. The outcome from the experimental study refers to the potential of the model, and how more significant classification in the form of multi-class labels approach be explored in the future studies.

Published

2021-10-18

How to Cite

M. M. Venkata Chalapathi, M. Rudra Kumar. (2021). Pivot Based Seed Germination Assessment (PBSGA) Pattern for Germination Quality Analysis. Drugs and Cell Therapies in Hematology, 10(3), 468–480. Retrieved from http://www.dcth.org/index.php/journal/article/view/644

Issue

Section

Articles