Computer Science – Clinic Program /clinic Tue, 09 Dec 2025 17:43:29 +0000 en-US hourly 1 https://wordpress.org/?v=6.9.4 Exploring the Kubernetes State Space with Graphs and Simulation /clinic/2025/exploring-the-kubernetes-state-space-with-graphs-and-simulation/ Thu, 22 May 2025 22:49:33 +0000 /clinic/2025/exploring-the-kubernetes-state-space-with-graphs-and-simulation/ Applied Computing Research Labs Computer Science/Mathematics, 2024–25

Liaison(s): David Morrison ’08
Advisor(s): Beth Trushkowsky
Students(s): Jaanvi Chopra, Saya Kim-Suzuki, Henry Merrilees (TL-F), Maximilian McKnight (TL-S), Karina Walker, Baltazar Zuniga Ruiz

The Applied Computing Research Labs (ACRL) was founded to solve distributed systems problems, particularly those involving scheduling and optimization within Kubernetes. This platform automates the management of computing tasks across many units of hardware. ACRL developed SimKube to simulate the relevant components of Kubernetes cost-effectively. The ACRL Clinic team has been tasked with encoding the Kubernetes state space as a graph to generate realistic simulation data for the Kubernetes simulator.
]]> AI’s Environmental Equation: Balancing Innovation with Sustainability /clinic/2025/ais-environmental-equation-balancing-innovation-with-sustainability/ Thu, 22 May 2025 22:48:21 +0000 /clinic/2025/ais-environmental-equation-balancing-innovation-with-sustainability/ Union of Concerned Scientists (UCS) Climate/Computer Science/ Mathematics, 2024–25

Liaison(s): Jose Pablo Ortiz-Partida
Advisor(s): Lynn Kirabo
Students(s): Taylor Backer (TL-F), Lucie Batista (TL-S), Sarah An, Emilynne Newsom, Trevor Shepherd

Aligned with the mission of the Union of Concerned Scientists—a nonprofit that puts independent science into action and advocates for a healthy, safe, and just future—this project calls for an examination of water and energy usage patterns in artificial intelligence (AI) systems through a comprehensive literature review of data center operations. The research analyzes current reporting practices regarding AI’s environmental impact and evaluates resource consumption projections. As a complement to the literature review, the Clinic team developed an interactive informational website that defines key metrics and provides context around AI infrastructure’s environmental footprint.
]]> Time-series Modeling, Analysis, Interface and Insight from Entomological Electropenetrography /clinic/2025/time-series-modeling-analysis-interface-and-insight-from-entomological-electropenetrography/ Thu, 22 May 2025 22:48:21 +0000 /clinic/2025/time-series-modeling-analysis-interface-and-insight-from-entomological-electropenetrography/ Auburn University/USDA Computer Science/Mathematics, 2024–25

Liaison(s): Elaine Backus P’19, Anastasia Cooper, Kathryn Reif
Advisor(s): Gabriel Hope
Students(s): Mehrezat Abbas (TL-F), Milo Knell, Devanshi Guglani, Lillian Vernooy, Zachary Traul (TL-S)

Researchers at the USDA and Auburn University use a technique called electropenetrography (EPG) to better understand the feeding behaviors of arthropods, in particular mosquitoes. Manual analysis of EPG data is time-consuming for our researchers, and they seek to automate the process. To help them automatically analyze this EPG data, the Clinic team created a set of machine learning models they can use through a graphical user interface.
]]> Virtual Concentration Sensor for Energy-saving Liquid Desiccant HVAC System /clinic/2025/virtual-concentration-sensor-for-energy-saving-liquid-desiccant-hvac-system/ Thu, 22 May 2025 22:48:21 +0000 /clinic/2025/virtual-concentration-sensor-for-energy-saving-liquid-desiccant-hvac-system/ Blue Frontier Climate/Computer Science/ Mathematics, 2024–25

Liaison(s): Nikhil Deshmukh, Matt Tilghman
Advisor(s): Michael Orrison
Students(s): Adia Ainsworth, Carmel Pe’er (TL), Nevaeh Thompson, Henry Trinh, Alejandro Wang

Approximately 15% of global energy consumption is used to heat and cool buildings. Blue Frontier addresses this by developing A/C technology that offers up to 90% reduction in electricity use. By using liquid desiccants, they achieve more efficient cooling and dehumidification than traditional methods. However, this requires expensive sensors, increasing upfront costs. The Clinic team is designing software-based sensors to replace the physical ones. The team is leveraging machine learning algorithms, including random forest and neural networks and physics-based models, to create these sensors, making the technology more cost-effective and scalable.
]]> Developing a Simulation Framework for International Emissions Reductions /clinic/2025/developing-a-simulation-framework-for-international-emissions-reductions/ Thu, 22 May 2025 22:48:21 +0000 /clinic/2025/developing-a-simulation-framework-for-international-emissions-reductions/ Center for Strategic and International Studies Climate/Computer Science/ Mathematics, 2024–25

Liaison(s): Joseph Majkut ’06
Advisor(s): Kaitlin Tademy
Students(s): Mildred Morales (TL-S), Sarah Lammert (TL-F), Arjun Taneja, Jack Myers, Jerry Li

CSIS is an American think tank that explores “practical ideas to address the world’s greatest challenges,” one of which is climate change. One difficulty is identifying public policy interventions that will both (1) effectively reduce greenhouse gas emissions and (2) be practical to implement in today’s international economic and political environment. The CSIS Clinic team has developed a model simulating the complex and dynamic interactions of international climate policy. This model will be used in tabletop simulations, helping CSIS staff understand political strategies for advancing global climate action.
]]> Grafana Observability Optimizations /clinic/2025/grafana-observability-optimizations/ Thu, 22 May 2025 22:48:21 +0000 /clinic/2025/grafana-observability-optimizations/ CrowdStrike Computer Science/Mathematics, 2024–25

Liaison(s): Luke Hunter ’03, Thomas Fleming ’22
Advisor(s): Chun Wong
Students(s): Arushi Malik (TL-F), Lauren Parker (TL-S), Kelly Hamamoto, Christopher Nawrocki, Hayley Walters, Valentina Watson

CrowdStrike offers cybersecurity solutions that deliver superior endpoint protection, threat intelligence and rapid incident response. To help maintain a high level of service, the company uses a data visualization system that monitors trillions of metrics, providing real-time observability of performance, speed and service health. The growth of data and metrics has reached a tipping point where the current data visualization system is not used to its full potential. Important metrics have become visually lost, and the process of defining new metrics and service dashboards has become inefficient. To overcome these challenges, this project introduces enhanced functionalities that flag unused metrics, automate dashboard generation, enable simultaneous multi-cloud visualization and enhance overall operational efficiency in the data visualization system.
]]> Autonomous Mower Path Planning and Control /clinic/2025/autonomous-mower-path-planning-and-control/ Thu, 22 May 2025 22:48:21 +0000 /clinic/2025/autonomous-mower-path-planning-and-control/ Doosan Bobcat Computer Science/Mathematics, 2024–25

Liaison(s): Dylan Stokosa, Anthony Kang ’24, Jacob Huesman
Advisor(s): Ben Morris
Students(s): Gibson Friedman (TL-F), Eric Wang (TL-S), Ryan Ramos, Jacoby Lockman, Kenyatta Dumisani

Doosan Bobcat is a leader in the compact equipment industry, including lawn mowers and other grounds maintenance equipment. The 2024–2025 Bobcat Clinic team was tasked with designing, coding and implementing an autonomous path planning system for the Bobcat Zero-Turn Riding Mower, building on the work of previous Engineering Clinic teams. The final deliverable is a graphical user interface that takes in a map of an area to be mowed and produces a planned path that the mower will autonomously follow.
]]> Affordable, Personalized AI Assistance for Landmark Life Events /clinic/2025/affordable-personalized-ai-assistance-for-landmark-life-events/ Thu, 22 May 2025 22:48:21 +0000 /clinic/2025/affordable-personalized-ai-assistance-for-landmark-life-events/ DreamDAI Computer Science/Mathematics, 2024–25

Liaison(s): Emily Jerger ’17, Nabil Zaman ’15
Advisor(s): Jim Boerkoel
Students(s): Bryce Bailey (TL-S), King Osei, Savva Ignatov, Jackson King (TL-F), Dan Fonseca

DreamDAI’s Clinic project is transforming wedding planning with an AI-driven, end-to-end vendor search experience. Leveraging natural language processing, semantic search and embeddings, the system intelligently matches users with their ideal vendors. By organizing and structuring wedding vendor data, the Clinic team enabled personalized recommendations, refining user queries through vector-based similarity models. The platform integrates a Wedding Wizard, a ranking algorithm for vendor sorting and a similarity-based recommendation engine, streamlining the vendor contracting process. This innovation reduces complexity and cost, making it easier for couples to bring loved ones together for their special day.
]]> Characterizing Nocturnal Blood Pressure Changes /clinic/2025/characterizing-nocturnal-blood-pressure-changes/ Thu, 22 May 2025 22:48:21 +0000 /clinic/2025/characterizing-nocturnal-blood-pressure-changes/ Ellison Medical Institute Computer Science/Mathematics, 2024–25

Liaison(s): Xingyao Chen ’20, Dr. Andrea Armani
Advisor(s): Jamie Haddock
Students(s): Shreya Balaji (TL-F), Channing Christian, Luis Mendoza Ramirez, Adam Sage, Lydia Stone (TL-S)

Ellison Medical Institute is a research institute focused on innovative personalized healthcare treatment for cancer and cardiovascular disease. The Clinic team characterized the relationship between nocturnal blood pressure, sleep staging and cardiovascular disease risk. Team members built a web application to aggregate blood pressure and sleep stage data from select wearable devices and performed predictive risk analysis on similar data from open-source datasets.
]]> Statistical Quality Control of Intra-facility Package Processing Times /clinic/2025/statistical-quality-control-of-intra-facility-package-processing-times/ Thu, 22 May 2025 22:48:21 +0000 /clinic/2025/statistical-quality-control-of-intra-facility-package-processing-times/ FedEx Computer Science/Mathematics, 2024–25

Liaison(s): George Richardson, Stephen Lee
Advisor(s): Susan Martonosi
Students(s): Devon Tao (TL-S), Sahil Rane, Alex Martin (TL-F), Tiger Che, Forrest Bicker

FedEx Corp is a global leader in transportation, delivering over 14 million packages daily. As a package moves from its origin to its destination, it travels through a series of facilities. At any step in this process, processing delays could result in the package being delivered late. To better understand package delays at the facilities, the Clinic team leveraged Statistical Process Control methods and advanced modeling techniques. This creates a better understanding of the relationship between facility processing time and package lateness.
]]>