Multilevel ensemble model for prediction of gender and age of blackbuck using pugmarks Saini Shubham1,*, Shukla Saurabh2, Singh Jaskaran3, Rana Prashant Singh4 1Research Scholar, Department of Forensic Science, School of Bio Engineering and Bio Sciences, Lovely Professional University, Phagwara, Punjab 2Assistant Professor, Department of Forensic Science, School of Bio Engineering and Bio Sciences, Lovely Professional University, Phagwara, Punjab 3Associate Professor, Department of Forensic Science, Geeta University, Panipat, Haryana 4Associate Professor, Computer Science & Engg Department, Thapar Institute of Engg & Tech, Patiala, Punjab *Corresponding Author: Shubham Saini, Research Scholar, Department of Forensic Science, School of Bio Engineering and Bio Sciences, Lovely Professional University, Phagwara, Punjab, E-mail: shubham.forensic@gmail.com Contact : +91-7837506632
Online published on 19 December, 2023. Abstract Introduction The identification of blackbucks from their pugmarks has been a standard method for tracking wild animals for many years. Historically, manual measurements were used for pugmarks identification. However, with the advancement of technology and machine learning, it has become possible to identify blackbucks from their pugmarks with higher accuracy and efficiency. Materials and Methods In the present study, a multilevel ensemble model is proposed for the prediction of gender and age group of blackbucks from pugmarks. The proposed model uses four machine learning models to develop a multi-ensemble model. These models are selected based on their performance in similar problems, and the combination of these models provides a higher degree of accuracy than a single model. Results Proposed model showed that it reached 97% accuracy in identifying the gender and age group of blackbucks from their pugmarks. This high level of accuracy indicates the proposed model’s effectiveness and potential to be used in real- world applications. Pugmark identification is a critical tool for studying and conservating blackbucks and other wild animals. The accurate identification of blackbucks from their pugmarks provides valuable information about the size and distribution of the population, migration patterns, and other vital factors. This information is essential for effectively conserving and managing blackbucks and other wildlife. Conclusions Present study demonstrates the potential of machine learning to improve the accuracy and efficiency of pugmarks identification for blackbucks. The proposed multilevel ensemble model provides a high level of accuracy and could be used as a wildlife conservation and management tool. The study highlights the importance of using technology and machine learning for the study and conservation of wildlife and could lead to further advancements in this field. Top Keywords Wildlife Forensic, Blackbuck, Machine Learning Models, Age, Gender, Identification. Top |