Illustration of a bird flying.

CNS: Energy Centric Wireless Sensor Node System for Smart Farms

Virginia Tech is broadly invested in advancing the science of precision agriculture. The SmartFarm
Innovation Network (TM) and the newly-derived Center for Advanced Innovation in Agriculture (CAIA) have
provided seed funding to establish smart farm test beds at three research farms located throughout the state
to enable the exploration of strategies to enhance usability of technology in pastoral livestock production
systems. Two team members of this proposal, Profs. Ha and White, are involved in the project and will
leverage this involvement to facilitate the activities proposed herein. Namely, we propose to develop a
wireless sensor network (WSN) system, which measures major biometrics of cattle to enhance animal
welfare monitoring and reduce labor cost. The proposed system will leverage LoRa technologies, especially
at the physical and data link layers, to enable animal care personnel to monitor the behavior and health of
cattle remotely through the Internet. The adoption of wireless technologies introduces cyberbiosecurity
vulnerabilities that can be exploited by cyber attackers aiming to disrupt the normal system operations and
functionalities. Therefore, cyberbiosecurity is also one of major design objectives of the proposed system.

Personnel

Dong Ha (PI) is a full professor with ECE at Virginia Tech and Founding Director of the MICS (Multifunctional Integrated Circuits and Systems) group consisting of four faculty members and about 30 graduate
students.

Swarun Kumar (PI) is an assistant professor at CMU and an expert on wireless networks and mobile systems. He has made key contributions in accurate RF-based indoor positioning and efficient communication in wireless local- and wide-area networks, all including large-scale deployments.

Jin-Hee Cho (Co-PI) is an associate professor in the Department of Computer Science at Virginia Tech. Her expertise is in the areas of cybersecurity, decision making, and network science. Cho has conducted research on uncertainty-aware deep learning frameworks that provide resilient learning and decision making in the presence of evasion and poisonous attack

Robin White (Co-PI) is an associate professor in the Department of Animal and Poultry Science at Virginia Tech. She has the expertise in the areas of mathematical modeling, precision agriculture, and animal nutrition. White’s research program centers on the animal / environment interface focusing on identifying strategies to enhance efficiency of pastured animal production systems.

Publications

  1. R. Kudupudi, F. Lohrabi Pour, D. S. Ha, S. S. Ha, and K. Ramezanpour, “Analysis of Deep Learning Models Towards High Performance Digital Predistortion for RF Power Amplifiers,” International Symposium on Circuits and Systems (ISCAS), 5 pages, May 2022.
  2. A. P. Damle, S. S. Ha, Z. Zhao, B. R. dos Reis, R. White, and D. S. Ha, “Power Efficient Wireless Sensor Node through Edge Intelligence,” International Symposium on Circuits and Systems (ISCAS), 5 pages, May 2022.
  3. Q. Zhang, Y. Mahajan, I.R. Chen, D. Ha, and J.H. Cho, “An Attack-Resilient and Energy-Adaptive Monitoring System for Smart Farms,” IEEE GLOBECOM, Dec. 2022
  4. A. Gadre et al., “MiLTOn: Sensing Product Integrity without Opening the Box using Non-Invasive Acoustic Vibrometry,” 2022 21st ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN), 2022, pp. 390-402, doi: 10.1109/IPSN54338.2022.00038.
  5. J. Zhang, G. Balakrishnan, S. Srinidhi, A. Bhat, S. Kumar and C. Bettinger, “NFCapsule: An Ingestible Sensor Pill for Eosinophilic Esophagitis Detection Based on Near-field Coupling”, SenSys 2022

Data Management

We have collected acceleration data from cows for classification of behaviors. The data will be released to public once our paper under review is accepted.

Multidisciplinary Research and Education

This research will provide opportunities for students who are interested in multidisciplinary research by providing seminars/workshops, short-courses, and/or involving undergraduate/graduate students on research tasks. We will involve VT’s undergraduate program providing a major in Interdisciplinary Studies (IDST), designed to provide an opportunity for students to explore multidisciplinary research. We will support and develop multidisciplinary courses through the IDST program based on the collaboration across PI/Co-PIs with various backgrounds in disciplines.

Minority and Outreach

Our research will encourage/engage students (e.g., GRAs) and faculty members (i.e., two of PI/Co-PIs are female scientists) with diverse backgrounds and from under-represented populations. In particular, we will leverage the Multicultural Academic Opportunities Program (MAOP) program at VT, and the programs on the Black Outreach Leadership (BOLT) and the Hispanic Engagement & Achievement Team (HEAT). We will also increase recruitment of under-represented students through participation in programs such as VT’s Center for Enhancement of Engineering Diversity (CEED), the McNair Program, National Center for Women and Information Technology (NCWIT), and interaction with local high schools.

Societal Impact

Our proposed project will establish an animal monitoring system, which can provide an assessment of individual animal biometrics, behavior, and location, enabling farmers to respond to this data in real time. We expect this novel data availability will facilitate improved farming practices such that farmers will be able to meet the needs of individual animals more quickly and accurately. The proposed research could be beneficial to the fields of semiconductor devices, autonomous power IoT devices, wireless communications including 5G and beyond, machine learning, statistical signal detection, and agricultural production. To the best of our knowledge, the proposed animal monitoring system has not been applied in pastured animal production. The proposed system will open a new horizon for smart farms to inspire other researchers and entrepreneurs to follow.