Projects Day 2017–2018
Biology/Computer Science/Mathematics Clinic
Dart NeuroScience, LLC
Network Analysis and Methodology Development for Drug Discovery in Alzheimer’s Disease
Liaisons: Philip Cheung ’96, Qingying Meng, Douglas Fenger
Advisor: Eliot Bush
Students: Annalise Schweickart, Chloe Chan, Sasha Friedrich, Brendan Murran
The goal of this project, sponsored by Dart Neuro-Science, is to generate potential drug targets relating to memory and neural plasticity, focusing specifically on Alzheimer’s disease. We have developed a novel methodology built on existing network analysis algorithms to identify key genes implicated in Alzheimer’s Disease. This methodology can be used to identify potential drug targets for Alzheimer’s, and in the future might also be used towards drug discovery for other diseases.
Helix OpCo, LLC
Integrating Genetics and Wearable Devices for Discovery
Liaisons: Nicole Washington ’99, Anupreet Walia, Scott Burke ’91
Advisor: Lisa Kaczmarczyk
Students: Jasmin Rizko (PM-S), Moira Dillon (PM-F), Mahlet Melaku, Crystal Xiang
Helix is a private software platform company for personalized genomic products. The goal of our Clinic project was to integrate sequencing results from Helix and activity tracking via Fitbit, and develop a proof-of-concept to monitor these data in research studies. We built a participant monitoring dashboard and conducted IRB-approved human subject studies to demonstrate the dashboard’s capabilities while examining traits related to fitness and sleep.
Computer Science Clinic
Genetic Gameplay: Showcasing 23andMe’s Personal-Genetics API
Liaison: Arnold De Leon ’90
Advisor: Julie Medero
Students: Teal Stannard (PM), Giovani Barrios-Arciga, Elise Cassella, Jacob Rosalsky
23andMe is a bioinformatics company whose mission is to help people access, understand, and benefit from the human genome. 23andMe analyzes DNA to identify specific variations, or alleles, in order to determine ancestry and wellness traits. 23andMe makes much of this information available to third party developers through a public API. The goal of this project is to create an application which will help encourage other developers to use the public API. Therefore, the application should serve as an example of how to correctly access the public API and securely handle a user’s genetic information. Additionally, we aim to engage users while their data is being analyzed.
3D Model Integration for Agile Digital Product Development
Liaisons: Robert Dooley, Alex Kass
Advisor: Ran Libeskind-Hadas
Students: Emily Dorsey (PM), Wenbo (Tracy) Cao, Holly Mitchell, Shailee Samar, Abigail Schantz
3D asset management can pose a significant problem for Augmented and Virtual Reality (AR/VR) applications. The Harvey Mudd Clinic Team is working with Accenture Labs to make AR/VR content management easier by providing a straightforward workflow allowing users to alter their content from within existing tools. The team’s Unity plugin allows inexperienced users to understand the tradeoffs between the visual quality of their assets and app performance, and then manage that tradeoff by customizing their asset’s polygon counts.
Amazon Music Graph
Liaisons: Dr. Fabian Moerchen, Dr. Gert Lanckriet
Advisor: Robert Keller
Students: Dan Diemer, Rebekah Justice, Renata Paramastri, Amelia Sheppard (PM), Cha Suaysom
Our project focuses on creating an enhanced infrastructure to enable Amazon’s intelligent personal assistant, Alexa, to respond to a broader and deeper range of queries about music. To this end, we developed an ontology (graphical knowledge structure) for recorded music and prototyped a database-backed, text-based web interface based on the ontology, which demonstrates responses to sample queries.
Amazon Prime Now
Image-Text Classification to Correct the Amazon PrimeNow Search Experience
Liaisons: Igor von Nyssen, Al Vethamuthu
Advisor: Yekaterina Kharitonova
Students: Alex Mitchell, (PM-S), Zhepei Wang (PM-F), Kofi Sekyi-Appiah, Tina Zhu
Amazon Prime Now wants to automate the process of identifying products whose images do not match their associated titles on their website. Our team has designed and implemented a solution using various machine learning techniques to automatically identify these problematic listings.
Traffic Testing in Fully Programmable, 6.4Tbps Networks
Liaisons: Remy Chang, Vladimir Gurevich
Advisor: Geoff Kuenning
Students: E. Taylor Yates (PM), Gus Callaway, M Sangheetha Naidu, Matthew Gee
Barefoot Networks builds high-speed programmable networking devices. Our team is building a configurable network traffic tester that can handle up to 6.4Tbps of traffic–enough for every student at the Claremont Colleges to simultaneously stream 200 high-definition movies. The tester will send varying traffic patterns to the device under test, which will immediately forward the packets back to the tester. The tester will analyze packet delay, sequencing, and loss, and will gather and report relevant statistics.
Algorithmic Fairness: Using Machine Learning To Detect Disparate Impact In Geo-based Risk Modeling
Liaisons: Harrison Lynch, Allen Tam, Jing Shen
Advisor: Yi-Chieh (Jessica) Wu
Students: Daniel King (PM-S), Abby Tisdale (PM-F), Tiffany Fong, Kyra Yee
Consensus Corporation makes point-of-activation software for the sale of mobile phones. This software includes a risk prediction engine, which predicts whether or not a phone plan will be deactivated and the sale deemed fraudulent. The Consensus Clinic Team’s project is twofold: (1) improve this risk prediction engine by incorporating new features and analyzing different machine learning models and (2) detect unintended bias in the risk prediction engine.
Temporal Segmentation of Surgical Suturing
Liaisons: Anthony Jarc, Liheng Guo
Advisor: Colleen Lewis
Students: Juliet Forman, Varsha Kishore (PM), Jane Wu, Hyobin You, Angela Zhao
Intuitive Surgical specializes in minimally invasive robot-assisted surgery and they developed the da Vinci surgical system. The objective of our project is to analyze the motion of surgical instruments controlled by surgeons and video recording of surgeries by developing computational models that automatically recognize suturing activities during robot-assisted surgery. Our approach comprises machine learning and neural network architectures. These computational models could then be used to generate advanced analytics such as surgeon performance reports.
Lawrence Livermore National Laboratory
Integrating Distributed-Memory Machine Learning into Large-Scale HPC
Liaisons: Cyrus Harrison, Ming Jiang, Brian Gallagher, Matt Larsen
Advisor: Christopher Stone
Students: Amy Huang (PM), Evan Chrisinger, Jeb Bearer, Katelyn Barnes
Supercomputers provide the computing power for complex physics simulations, but these simulations require frequent manual adjustments to pre-vent run-time failures. Machine learning is a potential solution for automating this process. The LLNL clinic team is developing a machine learning model appropriate for supercomputers that can learn from the output of physics simulations as they run in real time.
Mercedes-Benz Research & Development North America
Augmented and Mixed Reality for the Driver
Liaisons: Mark Poguntke, Kavita Saney, Jeff Bertalotto
Advisor: Geoff Kuenning
Students: Aman Raghuvanshi (PM-S), Julio Medina (PM-F), Drew Summy, Meredith Simpson
The objective of this project is to explore the possibility of using augmented reality (AR) while driving a car. This entails comparing various AR headsets such as the Microsoft Hololens and the Meta 2, and building a functioning prototype that addresses a moving car use-case. The headset comparison involves testing devices in a stationary and moving vehicle, and understanding their respective development experiences. Our prototype application attempts to help drivers park more safely and precisely, and serves as a starting point for the Mercedes-Benz team for an extendable AR headset prototyping framework.
NASA AMES Research Center
Minimizing Communication in Uncertain Multi-Agent Schedules
Liaison: Dr. Jeremy Frank
Advisor: Jim Boerkoel
Students: Grace Diehl (PM), David Chu, Marina Knittel, Judy Lin, William Lloyd
Our project aims to provide NASA with new scheduling protocols for multi-agent systems (e.g., a robot team). In such systems, scheduling disturbances (due to environmental factors or equipment malfunction) may necessitate rescheduling. However, communicating new schedules to all agents can be resource intensive. Reducing rescheduling can improve the performance of multi-agent systems when communication resources are limited. Our team has designed three algorithms to minimize rescheduling, trading communication for schedule quality. Further, we developed infrastructure for testing such algorithms.
New Relic, Inc.
Opening the Web Analytics Black Box with Innovations in Machine Learning, Visualization, Animation, and Big Data
Liaisons: Bill Kayser, Merlyn Albery-Speyer
Advisor: Melissa O’Neill
Students: Pratyush Kapur (PM-S), Lee Norgaard (PM-F), Alexandre Trudeau, Edward Carroll
Have you ever wondered how your website is performing? Wouldn’t it be convenient to know if your website is going to experience problems before they happen? The New Relic Clinic Team is exploring new ways to visualize website analytics data, communicate application health, and predict spikes in errors. Using animation, machine learning, and deep learning, the New Relic Clinic Team is developing innovative and unique solutions for New Relic’s customers.
Detecting Phishing Using Deep Learning Networks
Liaisons: Thomas Lynam, Mike Morris ’97
Advisor: Zach Dodds
Students: Daniel Sonner (PM), Nic Trieu, Srinidhi Srinivasan, Amberlee Baugus, Montana Roberts
Proofpoint is a leader at identifying online threats. This project seeks to more accurately classify phishing webpages based on their look, i.e., their visual rendering within a browser. The team designed, piloted, and tested software tools to support this investigation, culminating in a machine-learning pipeline that estimates the probability that a page is phishing based on its screen capture.
Securing Today’s Software-Development Pipelines
Liaisons: Corinne Druhan ’14, James Green, Bryan Trujillo ’15
Advisor: Elizabeth Sweedyk
Students: Zhenghan Zhang, Spencer Michaels, Eric Nguyen, Sarah Sedky
Our project aims to expand the capabilities of Rapid7’s security assessment platform by integrating the company’s newly-developed container assessment service into popular continuous integration tools, namely Jenkins, Bamboo, and Teamcity. Anyone developing a container with these tools can add our plugin to the build pipeline to check for vulnerabilities during each build. The plugin generates a detailed assessment report, and the user can configure rules to pass or fail the build depending on various criteria present in the assessment results.
Wood Veneer Classification and Cataloguing, Mobile
Liaisons: Ed Vander Bilt, Mark Schild, Allen Sietsema
Advisor: Katherine Breeden
Students: Brenda Castro (PM), Dalton Varney, Jessica Wang, Samantha Andow
Steelcase is looking to ensure color consistency before large purchase orders for their wood veneer furniture. In order to reduce waste due to veneer color issues, our clinic team is developing a portable veneer classification device that can verify veneer colors objectively in uncertain lighting conditions. The prototype is a mobile lightbox with an intuitive graphical user interface and a computer vision classification system.
Machine Learning on DNS Data to Discover Security Threats
Liaisons: Dave Krich, Kiran Kumar, Hal Lonas, Trung Tran, Cathy Yang
Advisor: Lisa Kaczmarczyk
Students: Julia McCarthy (PM), Anthony Romm, Reiko Tojo, Danny Wang
In this project, the goals were to aggregate DNS-level data, apply machine learning approaches to identify command and control (C&C) botnets through automated analysis of live traffic patterns, and construct a website for dynamic visualization of threats. Visualizations help the user pinpoint where botnet attacks are coming from, identify geographic hotspots for botnet activity, and find out who is at risk for infection.
High Dynamic Range Video Quality Analyzer
Liaisons: Dr. Peshala Pahalawatta, Douglas Hu ’14, Shamik Maitra ’02
Advisor: Timothy J. Tsai
Students: Justin Lauw (TL-S), Owen Morrison (TL-F), Ankoor Apte (S), Nick Draper (S), Tianyi Ma (S), Bradley Phelps (F), Hanna Ching (F), Marisol Guzman (F)
Design and prototype of High Dynamic Range/Wide Color Gamut (HDR/WCG) video analyzer tool that automates the process of detecting four artifacts: contouring, incorrect color space, clipping and noise artifacts in video content which may arise during poor conversion from legacy Standard Dynamic Range (SDR) content. Project involves designing artifact detection algorithms to detect the four artifacts in HDR videos and packaging the algorithms into an intuitive Graphical User Interface (GUI) for users to adjust algorithm parameters and view results.
Scanning and Image Processing in a 3D Envelope
Liaisons: Noah Philips, Ph.D ’03, Gordon Alanko, Ph.D., Gordon Dobbie, Joe Kelly
Advisor: Timothy J. Tsai
Students: Patrick Scalise (TL-S), Rob Simsiman (TL-F), Peyton Holm, Zach Shattler, Rachel Perley (S), Chance Bisquera (F)
ATI Metals manufactures high performance metal products for the nuclear energy, chemical processing, and aerospace industries. ATI’s customers require parts fabricated to precise dimensions. The ATI clinic team has integrated computer vision techniques and laser rangefinders into an automated measurement system that generates a 3D model of metal components post-process on the hot rolling mill. This system will streamline ATI’s production by detecting out-of-spec parts earlier in the process, and assist process engineers in improving product consistency.
Microfluidic Chip Quality Control System Improvement
Liaisons: Atul Madhusudan, Alireza Salmanzadeh, Ph.D., Ruth Sung ’17
Advisor: Leah Mendelson
Students: Ramita Kondepudi (TL-F), Marissa Lee (TL-S), Jesus Villegas, Sati Smyth (F), Valerie Kwee (S), Russell Salazar (S)
The 2017-18 BD Biosciences Clinic Team improved a quality control (QC) system for an acoustic microfluidic chip. This chip separates white blood cells, which are of primary interest for the detection of autoimmune disorders, from the rest of blood. The QC system acquires images of flow through the chip and reports the accuracy of blood separation through image processing techniques. The team improved mechanical design and image processing components of this system to reduce manufacturing cost and processing time.
Spot Cooling in the Human Body
Liaisons: Dr. Kim Burchiel, Dr. Chris Madden, Dr. Shaun Morrison
Advisor: Erik Spjut
Students: Aurora Leeson (TL-S), Jasmine Yang (TL-F), Kyla Scott, Brenden Brown (S), Scott Montague (S), Jesus Solano (F), Angela Sun (F)
Ceremod, Inc. is a startup founded at Oregon Health & Science University to foster innovation in medical technology. The Ceremod, Inc. clinic team has modeled and designed a flexible, biocompatible subsystem to cool a small target region in the human body. The modeling results are being used in feasibility and design studies of the experimental and production devices.
City of Hope
Raman Spectrometry and Laser Ablation as a Minimally Invasive, Molecularly Guided Therapy for Cancer
Liaisons: Dr. Yuman Fong, Dr. Veronica Jones, Dr. Lily Lai, Dr. Dan Schmolze
Advisors: Phil Cha, Michael Storrie-Lombardi
Students: Ragini Kothari (TL-S), Viviana Bermúdez Reyes (TL-F), Jenny Smith, Youkang Shon, Dominique Mena
The 2017-18 COH-Raman team aimed to reduce the collection time for Raman spectra of breast tissue to 1-3 seconds. This spectral database was analyzed using machine learning algorithms to display the probability of breast cancer. The spectral analysis is driven by understanding the bio-chemical markers that are evident in each unique Raman spectrum. The team also investigated Surface Enhanced Raman Spectroscopy (SERS) to enhance the Raman spectra. Additionally, the team worked on combining Raman diagnostics with laser ablation treatment.
City of Hope
Redesigning Wireless Cameras and Smoke Evacuators for Laparoscopic Surgery
Liaisons: Dr. Kurt Melstrom, Dr. Yanghee Woo, Dr. Mustafa Raoof, Dr. Yuman Fong
Advisor: Angie Lee
Students: Lam Huynh (TL-F), Lillian Liang (TL-S), Marisa de Souza (F), Casey Gardner (F), Sabrina Chang (S), Ice Limchantra (S), Elizabeth Poss (S)
The City of Hope Wireless Clinic team is designing low-cost and wireless laparoscopic cameras and smoke evacuators. In laparoscopic surgery, smoke is a byproduct that must be evacuated because it impedes visibility and is potentially hazardous, ultimately prolonging surgery. In addition to designing the systems to be wireless, the team is incorporating recirculation of insufflated air into the smoke evacuation system and first-person view (FPV) VR technology into the camera system. With their designs, the team aims to improve visualization of the abdominal cavity during laparoscopic surgery and increase access to laparoscopic surgical tools.
Autonomous Attachment Coupling
Liaisons: John Pfaff, Jonathan Roehrl
Advisor: Christopher Clark
Students: Aman Fatehpuria (TL-S), Jessica Lupanow (TL-F), Gabriel Rubin, Darien Joso (F), Kayla Yamada (F), David Olumese (S), Jingnan Shi (S)
The Doosan Bobcat clinic team will develop a proof of concept for autonomously driving a compact track loader to connect to a bucket attachment. Assumed starting conditions include flat, level ground and close alignment of the attachment and loader. Sensors, such as LiDAR sensors, will be used to determine the position of the vehicle with respect to the bucket. This position will be fed into the control system, which will send desired commands to the tracks on the loader.
Improved Electrically Operated Ground and Test Device (GTD)
Liaisons: Logan Weigle, Koustubh Ashtekar, Brad Leccia, Tyler Holp
Advisor: Patrick Little
Students: Lupe Carlos (TL-S), Thomas Morgan-Witts (TL-F), Kathryn Belling (F), Morgan Blevins (F), Bella Puentes (S), Matthew Huerta (S), Christopher McElroy (S)
Eaton Corp manufactures high voltage circuit breakers and related electrical safety devices. Ground and Test Devices (GTD) are used to ground the line or load side of the power bus bars for maintenance activities. The Eaton Clinic Team has been enlisted to improve design flaws in a GTD that was pulled from the market when updated standards from the Institute of Electrical and Electronics Engineers (IEEE) were released.
Improving Agricultural Water Efficiency
Liaison: Bill Jennings
Advisor: David Money Harris
Students: Kamau Waller (TL-S), Tess Despres (TL-F), Hill Balliet, Bailey Meyer, Geneva Ecola (S), Sitoë Thiam (F)
FarmX, a San Francisco startup, aims to save up to 2% of California’s water by providing precision irrigation management. The HMC FarmX clinic team improved two sensor systems: a weather station, which measures the farm’s local water cycle, and a dendrometer, which monitors tree health. These sensor systems will help FarmX provide better irrigation recommendations and alert farmers when their crops are in danger.
Georg Fischer Signet
Wireless Power and Communication for pH Sensor Networks
Liaisons: Chuck Gerner, Steve Wells, Ph.D., Kamran Afshari
Advisors: Ruye Wang (S), Brian Bryce (F)
Students: Isabel Martos-Repath (TL-S), Christine Goins (TL-F), Lauren Hu, David Kwan, Benjamin Iten (S), Kai Kaneshina (F)
Georg Fischer Signet is an engineering firm that produces flow and analytical technology. The 2017-2018 Georg Fischer Signet Clinic Team aims to design, build, and test a corrosion-proof method of internally processing and communicating pH and temperature measurements to a remote data collection network. To avoid corrosion, the project implements wireless power through inductive coupling and wireless communication through Bluetooth Low Energy. A LoRa network architecture is used to receive data from multiple units.
Optical Distortion Mapping System Development
Liaisons: Brooke Haueisen, Philip Sturman
Advisor: Kash Gokli
Students: Wenkai Qin, Sr. (TL-F), Josephine Wong, Sr. (TL-S), Enoch Yeo, Robert Gonzalez (S), Sydney Cozier, (F), Roger Hooper (F)
The GKN Aerospace Clinic Team is designing, implementing, and testing a new software system to locate and quantify optical distortions in cockpit windows, fighter jet canopies, and other aircraft transparencies. The software uses modern computer vision and data analysis tools to improve upon the industry standard for optical distortion mapping. GKN Aerospace will use our solution to prevent expensive damage on aircraft canopies and achieve higher product quality.
SERS Based Cancer Detection
Liaisons: Anita Rogacs, Jason Aronoff, Caitlin Dejong, Brian Keefe, Raghuvir Sengupta,
Advisor: Liz Orwin
Students: Michelle Lanterman (TL-F), James Palmer (TL-S), Zunyan Wang, Willis Sanchez-DuPont (S), Missy Spangler (S), Ronak Bhatia (F) Nisha Maheshwari (F)
The goal of this project is to explore the predictive diagnostic value of the complex spectra generated by metabolites adsorbed onto the HP Surface Emission Raman Spectroscopy substrates from cancerous and healthy cervical tissue in lab. The project has two primary components. The laboratory component entails cell culturing and preparation of the samples for data collection. Then when the data is collected, machine learning algorithms will be used to distinguish healthy from cancerous cell by the SERS spectra.
Study of Carbon Black Dispersion in Polyurethane: Impact on Mechanical and Electrical Properties
Liaisons: Bin Huang, Guang Jin Li
Advisor: Nancy Lape
Students: Sarah Silcox (TL-S), Jacey Coniff (TL-F), Jordan Howard-Jennings (S), Kaitlyn Loop (S), Aliki Sarantopoulos (S), Lisa Mattson (F), Curtis Shin (F), Meily Wu Fung (F)
The HP CB Clinic Team studied polyurethane (PU)-carbon black (CB) composites as new elastomer materials for Binary Ink Developers (BIDs) on HP Indigo printing presses. The investigation focused on how CB dispersion and loading affect the mechanical and electrical properties of the composites to meet HP’s product functionality and reliability requirements. Techniques such as tensile/tear, voltage-current sweeping, and SEM imaging analysis were used for material characterization.
Lawrence Livermore National Laboratory
Data Fusion for Ubiquitous Nuclear Threat Detection
Liaisons: Simon Labov, Brandon Seilhan
Advisor: David Harris
Students: Sarah Wang (TL-F), Yashas Hegde (TL-S), Emily Lane, Arch Robison, Jordan Abrahams (S)
As part of the nuclear terrorism prevention effort at Lawrence Livermore National Laboratory (LLNL), the LLNL Clinic Team is challenged with testing and improving the performance of a “smart” network of pocket-size radiation sensors. This will be done by 1) using non-threat radiation to monitor the calibration of the sensors, 2) configuring sensors to work together to improve detection sensitivity and confidence, and 3) integrating location information of known radiation sources to reduce false alarm rates. LLNL is operated under Contract DE-AC52-07NA27344.
Meggitt Control Systems
Aerospace Wear Coatings
Liaisons: Leo Leyanna, Mark Abrams
Advisor: Gordon Krauss
Students: Kristin Lie (TL-S), Jacob Knego (TL-F), Briana Liu (S), William Teav (S), Alex Ravnik (F), Zach Goland (F), Fernando Fernandez (F)
Meggitt Control Systems is an aerospace company that produces a variety of products for extreme environments. The Meggitt clinic team was tasked with researching, testing and characterizing low-cost, environmentally friendly surface treatments to reduce wear on a butterfly bleed-air valve. These valves are used in aircraft engines and must withstand high temperatures while experiencing as little wear as possible over 50,000 cycles.
Millennium Space Systems
Iodine Propellant Feed System
Liaison: Jason Murray
Advisor: Mary Cardenas
Students: Richard Ni (TL-F), Alex Echeverria (TL-S), Christopher Strong (F), Marianna Sbordone (F), Kaitlyn Eng (S), Maggie Gelber (S)
The team designed and built an iodine feed system which stores solid iodine for a minimum of five years, and sublimates solid iodine to deliver gaseous iodine at a rate of at least 3 mg/s within 10 minutes in a zero gravity setting. The team validated this proof of concept design through rigorous thermal and structural modeling, in addition to testing the proof of concept for corrosion, leak resistance, flow control, thermal management, and propellant management.
Harmonic Gear System Replacement in Space Application Actuator
Liaisons: Jason Ro ’99, Armand Asadurian
Advisor: Philip D. Cha
Students: Luis Viorney (TL-S), Angelica Virrueta (TL-F), Giulia Castleberg (F), Alex Nunes (F), Derrick Chun (S), Jacob Garcia (S), Nate Smith (S)
Strain wave gear reduction technology has dominated the aerospace rotary transmission industry for half a century due to its simplicity, efficiency, and accuracy. Moog, Inc. has sponsored a Harvey Mudd Clinic team to develop an alternative for use in the sponsor’s satellite actuators. The team’s solution relies on hypocycloidal geometry to achieve a high reduction ratio, zero backlash, and superior performance.
Bottling Line Speed Up Project
Liaisons: Damon Choate, Ian Song ’17, Alexander Mouschovias
Advisor: Ziyad Duron
Students: Jose Godinez (TL-S), Ryan Gibbs (TL-F), Arthur Reyes, Priscilla Chu (F), Deji Andrew (F), Rikki Walters (Soph.-S)
This project focuses on the P6 gallon bottle blow-molding machine at Niagara’s Corporate plant and finding physical limitations to speed increase. The team is characterizing the dynamics of the machine and finding resonant frequencies at which the machine vibrates due to its operation. By finding what is most likely to break first due to vibration, and then strengthening it, the team can safely increase the speed of operation.
Systron Donner Intertial
Embedded Neural Network for Improved Inertial Sensor Calibration and Error Compensation Algorithm
Liaisons: Bonnie Gordon ’11, Tony Rios, Emmanuel Quevy
Advisor: Tony Bright
Students: Nicholas Sakowski (TL-S), Christopher Kotcherha (TL-F), Austin Shin, Eyassu Shimelis, Aaron Lutzger (S)
The Systron Donner Inertial (SDI) clinic team has been tasked with designing, writing, and judging the performance of an improved gyroscope bias compensation algorithm. The goal of the project is to reduce rate error by a factor of 10. This goal will be reached with the assistance of statistical analysis and an embedded neural network which will allow the team to explore new causes in gyroscope bias.
Project Beluga: Perception System and State Estimation in GPS-Denied Environment
Liaisons: Jerry Hsiung ’16, Benjamin Chasnov ’16, Cyrus Huang ’16, Vaibhav Viswanathan ’17
Advisor: Anthony Bright
Students: Zayra Lobo (TL-S), Nancy Wei (TL-F), Austin Chun, Dominic Frempong, Evan Chapman (S), John Lee (S)
The Techmation Clinic team selected and implemented an acoustic beacon and hydrophones to augment an IMU in an Autonomous Underwater Vehicle (AUV). The team then used these sensors for state estimation of the AUV in a GPS-denied environment. A major part of this process was also the development of an Extended Kalman Filter, a state estimation algorithm for sensor integration, and a localization algorithm for the acoustic system.
Toyota Motor Corporation
Development of Energy Recovery Technology for Class 8 Fuel Cell Truck
Liaisons: Justin Ward, Tak Yokoo
Advisor: Okitsugu Furuya
Students: Duncan Crowley (TL-F), Sean Mahre (TL-S), Mina Berglund, Rilke Griffin, Kim Tran
The Toyota clinic project aims to investigate alternative methods of storing and utilizing energy recovered in the regenerative braking process of Toyota’s hydrogen fuel cell drayage truck. This involves researching and ideating various energy storage solutions and quantifying the amount of energy that can be recovered along several drayage routes from the Port of Los Angeles to Long Beach.
PHOSFORS (TM) Development
Liaisons: Scott Winslow, Helen Park, Markos Okihisa
Advisor: Matthew Spencer
Students: Elijah Carbonaro, Kimberly Joly (TL-F), Hamza Khan (TL-S), Trevor Fung (S), Gabriel Quiroz (S), Shiv Seetharaman (S), Lydia Sylla (F), Felipe Borja (F)
The WET Clinic team built a fleet of small aquatic robots to perform light shows. The choreography of these shows uses a computer vision system to precisely localize the pods and a multilink Bluetooth low energy system to communicate with the pods. The fleet of pods uses multi-robot trajectory planning algorithms to move in a choreographed sequence.
Liaison: Sun Kwok
Advisor: Arthur Benjamin
Students: Cade Hulse (PM), Anji Malpani, Shreyas Kadaba, Porter Adams, Ryan Haughton (S), Laurel Schy (F)
This project has aimed to uncover inefficiencies at Niagara Bottling by taking a more holistic approach to the problem of optimizing transportation processes across Niagara’s facilities. The Harvey Mudd team has investigated potential cost-reduction measures through the application of operations research and statistical methods. The end goal of this project has been to optimize total supply chain costs across facilities as well as provide invaluable business insights to Niagara.
Claremont Locally Grown Power
Investigating Hot Spots in Photovoltaic Panels through IdealPV’s Patented Controller
Liaisons: Kent Kernahan, Devon Hartman
Advisors: Qimin Yang, Tom Donnelly (F), Peter Saeta (S), Dick Haskell (Emeritus-S)
Students: Jonathan Kupfer (TL-F), Florence Walsh (TL-S), Dallon Asnes, William Lamb, Quentin Barth (F)
Claremont Locally Grown Power is a program of CHERP Inc., (Community Home Energy Retrofit Project), a California-based 501(c)(3) non-profit social enterprise, in an exclusive licensing agreement to deploy idealPV’s patented solar technology. The clinic team is assisting CLGP in their goal of outfitting lower-to-middle income households with cheaper, safer, and more efficient solar panels by providing third-party verification and testing of the underlying idealPV technology through lab research, physics-based mathematical modeling, and prototype comparison field studies.
Sandia National Laboratories
Measuring the Permittivity of Ferroelectric Nanoparticles in an Epoxy Composite
Liaison: Dr. Todd Monson
Advisors: Albert Dato, Peter Saeta
Students: Andrew Bishop (TL-S), Richard Liu (TL-F), Alejandro Baptista, Lupe MacIntosh, Charles Dawson (F), Benjamin Lehman (S)
Barium titanate (BTO) is a ferroelectric material commonly used in capacitors because of its high bulk dielectric constant, which may be even higher in nanoparticle form. We are determining the dielectric constant of BTO nanoparticles as a function of particle size by measuring composites of BTO nanoparticles in epoxy. We’re using ball-milling alongside surfactants to reduce nanoparticle ag-glomeration, examining particle geometry using scanning electron microscopy, and using finite element analysis to extract the dielectric constant of the nanoparticles.
Kounkuey Design Initiative
Green Infrastructure Solutions for Urban Flooding in Kibera, Nairobi, Kenya
Liaisons: Chelina Odbert, Joe Mulligan, Vera Bukachi
Advisor: Ziyad Duron
Students: Isabel King (TL-F), Camille Croll (TL-S), Manu Kondapi, Andrea Vasquez (F), Eric Contee II (F), Eliana Goehring (S)
Kibera is a large informal settlement in Nairobi, Kenya where annual flash flooding causes significant health, economic, and structural problems in the community. Current drainage infrastructure consists of informal channels that are not designed to handle the volume of water that falls during large rain events. The objective of this project is to work with the community to develop practical design improvements for the existing drainage channels that can be implemented in Kibera, to improve quality of life for residents.
Address Detection in Sanborn Maps with Image Processing and OCR
Liaisons: Zachary Fisk, Paul Schiffer, Richard White
Advisor: Rachel Levy
Students: Daniel Zhang, Jeff Carney, Mehdi Drissi, Jordan Haack
Our task is to automatically detect and read the handwritten addresses from EDR’s collection of 1.2 million Sanborn maps. Sanborn maps are detailed city maps produced regularly between 1880 and 2006. We use various image processing techniques to first find the street segments, and then detect the handwritten street names and house numbers. We then run these images through our OCR model, which reliably parses connected characters that are rotated or skewed.
Creating a 3D Sound System for Paired Volumetric Video
Liaisons: Cody Gabriel, Peter Sankhagowit, Steven Xing
Advisor: Weiqing Gu
Students: Daniel Johnson (PM), Daniel Gorelik, Ross Mawhorter, Kyle Suver
Intel’s TrueView technology can reconstruct three-dimensional video at any location in a stadium using multiple video recordings. However, this system does not extend to audio. This project involves developing an approach to reconstruct game audio at any location based on microphone recordings, to combine with the existing volumetric video system. After exploring existing algorithms for sound source separation and localization, we are developing a prototype system called auVVio that extends these techniques to interactively reconstruct game sounds in 3D.
Correlation and Root Cause Detection in Bing Livesite Metrics
Liaisons: Debashish Ghosal, Gautam Dewan
Advisor: Talithia Williams
Students: Grant Belsterling, Preethi Seshadri, Zhaocheng Yi (PM)
Bing is the second most popular search engine in the United States. Bing’s Livesite Engineering team collects system performance metrics to detect incidents (outages, etc.) that negatively impact the end user experience. These incidents result in a loss of ads revenue and users. Identifying root cause of such incidents requires sifting through a lot of metrics and narrowing down the root cause to one or more key metrics. Our clinic team is working to streamline and automate this process by leveraging statistical models and methods.