Projects

Role: PI 
Funding Agency: NSF CPS
Period: Sept 2025 - Aug 2026
Collaborators: A. B. Siddique, M. Cantor, M. Segovia
Amount Awarded: $941,359 

Project Description:  Bovine Respiratory Disease (BRD) is an infection of the respiratory tract in cattle that compromises the welfare of the calf. It is estimated that BRD costs the industry $800-$900 million dollars a year. Precision technologies have the potential to monitor calves’ behavioral information to help detect diseases, such as BRD. However, the science of inferring BRD using these technologies is just at its infancy. Existing works often rely on expensive precision technologies, preventing widespread adoption. Furthermore, these approaches adopt simplistic inference solutions,  are trained and tested on individual farms, and cannot provide explainability of model predictions. To address this gap, this project develops CalfHealth, a comprehensive framework that adopts innovative sensing technologies to enable the cost-effective and explainable detection of BRD in dairy calves.  This can have profound implications for improving the profitability of farmers and calf welfare. In addition, this project will have a significant impact on the community through innovative education and outreach activities. These include: (i) field experiments and participatory workshops with relevant stakeholders, including farmers, veterinarians, companies, and consumers; (ii) interdisciplinary research experience for undergraduate and graduate students; (iii) wide dissemination of the project outcomes through high-quality publications; and (iv) demonstrations to future students at the E-Day of the College of Engineering of the University of Kentucky.

CalfHealth  is based on a novel multimodal learning framework that exploits accelerometer sensors to model calves' behavior using a fine-grained attention mechanism and fuses it with data regarding respiration rate, acquired by a Wi-Fi sensing system, through cross-attention mechanisms. To effectively adapt the detection framework to diverse farms and environmental conditions, the project adopts zero-shot and few-shot active learning approaches. Furthermore, CalfHealth enhances explainability, interaction with technology, and the ability to explore what-if scenarios. To this purpose, CalfHealth exploits language models combined with a feature attribution approach to develop an interactive chatbot for farmers. This project also accelerates the adoption of CalfHealth by using state-of-the-art economic experiments and qualitative methods to assess the behavioral and technological factors influencing farmers’ acceptance of precision technologies aimed at detecting BRD in calves. Additionally, comprehensive behavioral interventions are tested to enhance the farmer-chatbot interaction and increase farmers’ trust in CalfHealth. Finally, extensive validation on several farms is performed, including closing the loop by testing the benefit of early intervention for cattle identified by CalfHealth.

Role: Co-PI 
Funding Agency: NIFA
Period: Feb 2025 - Feb 2030
Collaborators: A. Adedeji, A. Tope, P. Vijayakumar, L. Adedokun 
Amount Awarded: $241,000

Project Description:  The food industry currently faces unprecedented challenges due to changing consumer preferences, climate change, regulatory demands and increasing need for sustainable and healthy food. The application of AI technology can provide solutions to some of these issues. However, the development of AI technologies requires a skilled workforce that can lead innovative research within the industry. There is an underrepresentation of minorities in AI, especially in Agrifood sciences, which needs to be addressed considering the pace of AI technology development. Therefore, the overall objective of this traineeship-project is to build an inclusive workforce in AI that serves the food industry. The program will provide outstanding underrepresented students with experiential learning in AI applications in food science and engineering through coursework, research projects, internship, and specialized training. Additionally, the program will include leadership and professional development training. Social impact and global engagement will also be emphasized through students’ research that touch base on global issues within the AI and food industries. 

We will emphasize diversity, equity, and inclusion, ensuring that graduates are equipped all-round to succeed in their careers. This program will contribute to the long-term sustainability of the food industry by developing a skilled workforce in AI application through leadership, social discipline, global engagement, and diversity. Project impact will be evaluated through focused-group and formal feedback system. 

Role: PI 
Funding Agency: NSF
Period: Feb 2025 - Jan 2026
Amount Awarded: $50,000

Project Description:  The purpose of this project is to plan the technical program of the 2025 National Science Foundation (NSF) Cyber-Physical Systems (CPS) Principal Investigator (PI) Meeting. The meeting is expected to take place in the Spring of 2025, in Nashville, Tennessee. The CPS PI meeting annually brings together the NSF-supported CPS Principal Investigators.  The meeting represents a unique opportunity to showcase research advancements, discuss upcoming challenges, research directions, and create new opportunities for collaborations within the CPS community. Additionally, this annual event provides a platform for CPS PIs, industry leaders, and Federal agency representatives to review recent advancements in CPS, explore emerging applications, and discuss technology challenges. Therefore, it represents a valuable opportunity for academic researchers to engage with industry and government stakeholders interested in advancing CPS research. The meeting will be in-person, but plenary sessions as well as PIs' lightning talks will be made available online to allow broader participation from researchers across academia, industry, and government.

The technical program of the 2025 CPS PI meeting will focus on four highly relevant topics, namely CPS in the Age of AI, CPS and Agriculture, CPS Resilience, and CPS with Human In The Loop. The program will be built around these topics through a comprehensive set of sessions. Specifically, these will include keynotes from leaders in the research community; poster presentations and demonstrations, to showcase CPS innovations and results; reports from impactful CPS projects; and panels and workshops, to engage the audience through a stimulating presentations and discussions. The program will also include sessions on general aspects relevant to the CPS community and investigators, such as increasing Established Program to Stimulate Competitive Research (EPSCoR) participation and Research Experiences for Undergraduates (REU). Additionally, the program will provide several opportunities for researchers to network, discuss, and foster new collaborations.

Role: PI 
Funding Agency: NSF CNS
Period: Oct 2024 - Sept 2026
Collaborators: T. La Porta, T. He, D. Ionel, M. Siddique, M. Cantor
Amount Awarded: $100,000

Project Description:  Society has witnessed revolutionary growth of capabilities in data capturing, through the wide-spread deployment of Internet of Things, and intelligent analytics, through advances in Artificial Intelligence (AI). To fully realize the potential of such a transformation, this project addresses the bottleneck of bringing data and advanced analytics together. Specifically, the project?s novelties are the development of enabling technologies for integrating distributed intelligence into the network edge to support next-generation smart applications. The project's broader significance and importance are its potential to transform how high-impact application domains such as smart energy systems and smart agriculture leverage AI to open unexplored frontiers. The project also includes educational and outreach activities for graduate, undergraduate, and K-12 students, and builds new research capacity that significantly benefits the EPSCOR jurisdiction of Kentucky. 

This project has three main thrusts. The first develops techniques for the life cycle of distributed intelligence, including data curation, decentralized learning/fine-tuning, and distributed inferencing, with a focus on optimizing the efficiency in a resource-constrained edge environment and adapting to the requirements of the supported application. The second thrust analyzes exemplary applications that can benefit from edge intelligence and identifies their requirements, with an initial focus on smart energy systems and smart agriculture. The third thrust focuses on the planning activities. The objective is to engage stakeholders from the target application domains and to perform preliminary studies for evaluating candidate technologies and formulating future research questions. Activities include two in-person workshops, one held at the University of Kentucky and the other at the Pennsylvania State University, and meetings with domain experts who are potential Co-PIs in a future CISE Large proposal.

Role: Co-PI
Funding Agency: NIFA Agriculture and Food Research Initiative (AFRI)
Period: Jan 2021 - May 2026
Collaborators: J. Costa, L. Eckelkamp, S. Schexnayder
Amount Awarded: $1,000,000

Project Description:
Good animal welfare is paramount to the dairy industry, including producers, processors, distributors, and cooperatives. The development of a new, accurate, and remote welfare assessment benchmark using validated multi-variable precision dairy technologies (PDTs) has the potential to increase the sustainability of the dairy industry. PDTs allow for real-time, continuous recording of animal behavior and other animal-based outcomes at the individual animal level. Before these technologies can be useful in assessing animal welfare, predictive models and validations must first be done. Additionally, although technology may be useful to identify animal welfare concerns onfarm, dairy producers must be willing to adopt these technologies, see value and trust in these tools, and interpret the data. Concurrently, there is a risk that investment in and adoption of novel technologies may be futile if these technologies are ultimately rejected by society. Therefore, the public must be engaged to establish which aspects of these technologies may generate social acceptance or concern. Thus, our proposed integrated research and extension project aims to bridge the use of PDTs with the social aspects of animal welfare. We will develop models and validate the use of multiple, integrated technologies to predict animal welfare assessment outcomes that can be monitored remotely while simultaneously engaging dairy producers and the public in two-way conversations about the role of these technologies on-farm. Our multidisciplinary project will integrate scientific assessments of animal welfare, artificial intelligence, machine learning, dairy production knowledge, and social science to provide practical recommendations for the sustainable use of PDT on-farm.

Role: Co-PI
Funding Agency: NSF SCC
Period: Oct 2020 - Sept 2025
Collaborators: Asheesh Singh, Sajal Das, Corinne Valdivia, Peter Kyveryga
Amount Awarded: $1,515,830 (including $16,000 of REU supplements)

Project Description:
With a goal to form a community of Smart and Connected Farms (SCFs), this innovative project aims to establish a Smart Integrated Farm Network for Rural Agricultural Communities (SIRAC). The goal is to improve timely data sharing and knowledge exchange among farmers community for coordinated responses to production threats (weed, disease, insect, pest, weather), ensuring profitability. The project will develop a flexible, scalable and efficient communication infrastructure for SCFs; provide privacy-preserving data analytics across farms for community-level decision-making; establish community of practice to facilitate learning and feedback among farmers/scientists, trusted data and technology acceptance; and demonstrate economic benefit to SCFs.

The novelty of SIRAC project lies in the holistic integration of multiband dynamic spectrum access (DSA) technology for rural connectivity and community decision-making, with social translational research to address adoptability, trust, and risk preferences, and economics research to benefit farmers. Mobile crowd sensing will improve trustworthiness and decision accuracy of information spread. Fundamental contributions involve the development of novel routing algorithms, privacy-preserving machine learning techniques, and affordable communication infrastructure with unlicensed multiple spectrum bands to create SCF community for efficient data sharing. Translational research model with behavioral experiments will identify social and economic incentives for farmers/stakeholders leading to technological innovations.

The SIRAC framework has the potential to provide tremendous impacts, as it can be adapted and replicated in different rural areas. The proposed (rural) communications technology will apply to a broad range of smart and connected communities. The assessment of social and economic incentives for farmers and other stakeholders will facilitate participation in SCF network. The project will motivate next generation of scientists and farmers to contribute to smart agricultural communities with innovative solutions. Results will be disseminated via web lecture series, invited talks, a dedicated project website, participants and other communities, extension field days, conferences and workshops, and peer-reviewed journals.

The SIRAC repository will maintain computational codes, models, real world and simulation data, experimental results for two years after the project period is over. The project website will provide two levels of access: Public and Login Required. An account can be created via registration with no charge. Additionally, developed codes and simulation models will be available to the community through the Iowa State University?s digital repository. Permission will be granted to freely use and distribute the anonymized data from simulations and field experiments with due acknowledgement of the copyright notice and the authors.

Role: PI
Funding Agency: NSF CPS
Period: 2020-2025
Amount Awarded: $524,987 - including $16,000 REU supplement

Project Description:
While substantial progress has been made in the control of electric grid considering the cyber and physical characteristics, there has been a gap in the integration of smart grid research as it integrates with human behavior -- especially in interactions with energy management systems. For example residential energy consumption has been rapidly increasing during the last decades, especially in the U.S. where 2.6 trillion kilowatt-hours were consumed during 2015, and an additional 13.5% increase is expected by 2040 . Research efforts such as demand response have been made to reduce this consumption especially in smart residential environments. Concepts such as demand response have largely overlooked the complexity of human behaviors and perceptions, and recent research in the social-science domain and recent experience has challenged the effectiveness of this approach and in some instances led to an abandonment and avoidance of such concepts. The objective of this proposal is to overcome the limitations associated with state-of-the-art energy management systems by designing novel algorithms, machine learning models, and optimization techniques that specifically consider user behaviors, perceptions, and psychological processes. This revolutionary approach will unleash the full potential of smart residential environments in reducing residential energy consumption and has the potential to transform the way in which energy management systems are designed, implemented, and used by people. This project also supports innovative educational activities such as classes, real time demonstrations, coding challenges, and research experiences for high school students. The PI will also lead a cohort of students to the diversity-oriented Grace Hopper conference and teach seminars for Hispanic elementary students. Finally, a new class on Cyber-Physical-Human System will be designed and several graduate and undergraduate students will participate in the research activities.

The proposed research combines novel algorithmic, machine learning, and optimization solutions that consider previously un-examined human behaviors, perceptions, and psychological processes. Specifically, in order to enable fine grained energy monitoring, we propose novel stream-based appliance recognition algorithms for smart outlets. These algorithms learn the appliance consumption signatures and the user engagement with the system to optimize the learning process. In addition, energy saving optimization strategies are designed by considering the user perception through social-behavioral well-being models. These models learned and refined through novel machine learning algorithms based on regressograms, interpolation, and regression using user feedback provided through a smartphone. In addition, we develop optimization algorithms for energy exchange in the context of smart residential environments equipped with renewable energy generation. These algorithms match the users' demand and production, by considering and learning also their availability and preferences in the energy exchange process. The proposed research is validated through real testbeds and large-scale simulations based on real traces.