Past Projects
- Advisor: Mr. Will Hanley
- Sponsor: AIRC, VICEROY
- Researchers: Zac Harmeyer, David Cho, Melanie Greig, Haylee Rogers;
- Student PM: Mahima Suresh
- Majors Involved: Industrial and Systems Engineering, Cybersecurity Management and Analytics, National Security and Foreign Affairs, Political Science
The Virginia Tech mission engineering team, alongside a team from Norfolk State University, conducted research to address the U.S. military’s lack of a comprehensive approach to training and executing effects in the information environment. The Virginia Tech mission engineering team analyzed how current operational Command Operations Centers assess the information environment and made recommendations for improvement based on research of open-source tools such as Landsat Satellite Data, ChatGPT 3.5, and CrypTool through the use of the DoD Mission Engineering process. This research was aimed to inform and support the DoD in improving the holistic human-machine system of systems to rapidly sense and deliver effects in the information environment.
- Advisor: Dr. James McClure, Mr. Will Hanley
- Sponsor: SERC/Stevens Institute of Technology
- Researchers: Benji Adjepong, Brian Holahan, Pramil Patel, Nana Yaw Oteng, Richard Martinez
- Majors Involved: Engineering, Computer Science
The Edge Supercomputing for Autonomous Sensor Platforms project was focused on collecting technical requirements for the commercialization of the Autonomous Systems at Scale SBIR project with a goal of future government acquisition. The Autonomous Systems at Scale project developed a prototype for operating multi-agent systems from a single operator. The objectives for this project were to utilize Modular Open System Approach (MOSA) to analyze and advance the current prototype and to develop a plan for commercialization.
- Advisor: Dr. Paul Wach, Dr. Stephen Adams
- Sponsor: AIRC, Deloitte
- Researchers: Adi Iyer, Bhavya Shanmugam
- Majors Involved: Computer Engineering, Industrial and Systems Engineering
The Prognostic Health Management and Resilient Lifecycles project was focused on designing a sensor driven testbed to perform prognostic health management for ball bearings and creating a data model for processing and analyzing bearing data created by machine sensors. The team achieved the monitoring of the efficacy of ball bearing systems for the importance of ensuring mechanical system health by predictive health maintenance. Predictive health maintenance is a data driven method for analyzing ball bearing data to predict when quality errors would occur. The team monitored internal features (e.g. speed, rotation) and external features (e.g. temperature, motor speed) to build a predictive data driven model.
- Advisor: Dr. Paul Wach, Peter Beling, Scott Lucero
- Sponsor: AIRC
- Researchers: Cameron Curran, Michael Shi, Kaushal Betha, Sam Bresky
- Majors Involved: Computer Science, Computer Engineering
The Adoption and Use of Generative AI in Test and Evaluation project aimed to offer actionable insights into the procurement and practical utilization of LLMs for Test & Evaluation in order to ongoing strategies in adopting this emerging technology. Generative AI’s utilization and integration for Test & Evaluation purposes is an ongoing discussion within the defense sector. Critical technologies such as LLMS offer transformative promise, however, these technologies also call for new considerations spanning acquisition, security, policy, and technical domains.
- Advisor: Ms. Emma Meno
- Sponsor: AIRC, VICEROY
- Researchers: (Government Team) Sahana Sarathy, Farhan Haider, Rishab Desai, Eera Rasne, Meghana Gunda; (YAML Team) Angelie Nguyen, Lyric Austria, Yaw Uwusu Jnr, Jeriah Valencia; (PM) Stephanie Bandy
- Majors Involved: Computer Engineering, Computer Science, Finance, Cybersecurity
The CyberML: Simulating the Government in an Acquisition Process project’s goal was to configure cyber networks based on government procurement requirements, later applicable to artificial intelligence and machine learning applications. Students were divided into three teams with designated tasks; the Government Team provided the requirements and structure for the network configuration and the other two YAML Teams produced YAML files based on the requirements provided by the Government Team. The project consisted of cycles in which the Government Team would send requirements to the YAML teams, who would then return iterations with said requirements. The objective was to simulate a government procurement process between data vendors, government acquisition, and government end users. The project goal is to develop network models to eventually be used for machine-learning-based testing and evaluation, specifically for national security purposes.
- Advisor: Ms. Emma Meno
- Sponsor: AIRC, VICEROY
- Researchers: (YAML Team) Akhilesh Anand, Utsav Manandhar, Hemansh Adunoor, Justin Jiang; (PM) Aryan Vangani
- Majors Involved: Computer Engineering, Computer Science, Finance, Cybersecurity
The CyberML: Simulating the Vendors in an Acquisition Process project was designed to simulate the government acquisition process for AI/ML-based cyber training and test environments, focusing on network security applications. Advancements in the fields of artificial intelligence and machine learning have opened the door for the rapid testing and deployment of cybersecurity solutions for government needs. This team focused on making YAML files which simulated different testing environments for reinforcement learning agents as part of an acquisition pipeline for network security applications.