Natya Sathyanarayana
Natya Sathyanarayana has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Ashutosh Anand
Presidency University
2 shared publications B C Lalitha
ECE, Presidency University,Bengaluru,India
1 shared publicationChalasani Divya
ECE, Presidency University,Bengaluru,India
1 shared publication- Sanjay Sharma
Thapar Institute of Engineering and Technology
1 shared publication Tushar Dattatraya Deokar
ECE, Presidency University,Bengaluru,India
1 shared publication
Latest Publications
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 159979-160010
Quantifying Accessible Advantage in Quantum Spectral Computation: A Task-Matched, Device-Calibrated Metric With a 6G Channel-Estimation Case Study
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 159979-160010
Open AccessQuantifying Accessible Advantage in Quantum Spectral Computation: A Task-Matched, Device-Calibrated Metric With a 6G Channel-Estimation Case Study
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Comparative Study of Detection and Tracking Models for Automated Monitoring of Endangered Species
Wildlife conservation is dependent on sophisticated object detection models to identify and track species with precision. In this research, three deep learning models YOLOv5s, YOLOv8n, and YOLOv11-are evaluated and compared in detecting threatened animals such as cheetahs, jaguars, lions, tigers, and leopards. The performance of the models was measured using accuracy, precision, recall, and mean average precision (mAP50). Results show that YOLOv11 performs best in terms of accuracy and precision, while YOLOv8n shows better localization. This analysis gives insight into choosing the best-performing model for real-time wildlife tracking, supporting conservation and reducing threats to biodiversity.
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Comparative Study of Detection and Tracking Models for Automated Monitoring of Endangered Species
Wildlife conservation is dependent on sophisticated object detection models to identify and track species with precision. In this research, three deep learning models YOLOv5s, YOLOv8n, and YOLOv11-are evaluated and compared in detecting threatened animals such as cheetahs, jaguars, lions, tigers, and leopards. The performance of the models was measured using accuracy, precision, recall, and mean average precision (mAP50). Results show that YOLOv11 performs best in terms of accuracy and precision, while YOLOv8n shows better localization. This analysis gives insight into choosing the best-performing model for real-time wildlife tracking, supporting conservation and reducing threats to biodiversity.