I am a senior research engineer at Julia Computing, where I design next-generation tools for the Julia programming language. I received my Ph.D. from the University of Washington in Electrical Engineering, specializing in Digital Signal Processing. I also have experience in a number of related fields including low-level microcontroller programming, electromagnetics and wireless communications, high performance computing, and machine learning.
I graduated from the University of Washington with a Bachelors of Science in Electrical Engineering in 2011, and continued on directly into the graduate program, earning my Masters degree in 2014 from Prof. Les Eugene Atlas and Prof. Adrian KC Lee. My masters thesis was titled "A Fresh Look at Functional Connectivity" and proposed a new application of pre-existing mathematics toward analysis of neuroimaging signals such as those captured by electro- and magnetoencephalographic (EEG/MEG) systems.
In 2018 I graduated with my Ph.D. from the Ubiquitous Computing Laboratory studying under Prof. Shwetak Patel. My dissertation, titled "Techniques for Cough Sound Analysis" details my research into the application of deep learning to acoustic cough detection and classification. My projects page has current information on my various major projects both past and present, whereas my curriculum vitae has a more targeted selection of previous work to peruse.
I have been a core developer on the Julia language project since 2013, although I did not start working at Julia Computing until late 2018. My contributions to the project include basic infrastructure and maintenance, the design and implementation of the official OS X binary package deployment system, the design and development of the next generation cross-platform binary package compilation and deployment systems, contributions to native Julia deep learning frameworks, development of packages critical to the Julia package ecosystem such as Nettle.jl and SHA.jl, as well as innumerable bug fixes and bits of code scattered throughout the project and related efforts.
CoughSense is an ongoing research project at the University of Washington Ubiquitous Computing Laboratory on pulmonary health sensing using mobile phones as mobile cough detection and classification devices. This work is submitted for publication at IMWUT 2018, and can also be found in my Ph.D. dissertation titled Techniques for Cough Sound Analysis. This work explores the interaction between signal processing domain-specific knowledge and learning systems' ability to extract information from arbitrary inputs, as well as the specific application of such systems to cough sounds. The technology is currently part of pilot study programs deploying health sensing technologies into the homes of patients.
WiBreathe is a research project at the University of Washington Ubiquitous Computing Laboratory on remote health sensing via a system that utilizes 2.4 GHz electromagnetic signals to determine patient vital statistics such as breathing rate. This work was published at PerCom 2015 in a paper titled "WiBreathe: Estimating Respiration Rate Using Wireless Signals in Natural Settings in the Home". My main contribution was in the design and implementation of signal processing algorithms to map the received wireless signals to breathing rates. As a part of this work, we attempted to utilize pre-existing signals and wireless infrastructure, which gave me reason to build an 802.11b software decoder from scratch, something I honestly never thought I'd need to do.
SpiroSmart is a mobile phone based platform that allows for the analysis of common lung function measures (FEV1, FVC, PEF). By analyzing sound waves incident on the microphone of the mobile phone, we are capable of monitoring pulmonary ailments such as asthma, chronic obstructive pulmonary disease, and cystic fibrosis. My contributions to this project include signal processing and machine learning algorithms to estimate air flow from users' lungs across a wide range of clinical situations. This work is currently undergoing international clinical trials in partnership with a number of medical institutions.
My Master's thesis, titled "A Fresh Look at Functional Connectivity", proposed a new application of pre-existing mathematics toward analysis of neuroimaging signals such as those captured by electro- and magnetoencephalographic (EEG/MEG) systems. The work applied time-varying statistical signal processing methods toward characterizing functional connectivity in the brain of subjects performing a visual search task. This work was done as a joint research project between the Laboratory for Auditory Brain Sciences and Neuroengineering and the Interactive System Design Laboratory, at the University of Washington.
HydroSense is a pressure-based sensor that automatically determines water usage activity and flow down to the source (e.g., dishwasher, laundry, shower) from a single non-intrusive installation point. I worked on this project while I was an undergraduate, adding signal-level features to machine learning classifiers, performing experiments and collecting data in a variety of settings and building visualization platforms for real-time pressure transient classification. My contributions to the work were published in a paper titled "A Longitudinal Study of Pressure Sensing to Infer Real-World Water Usage Events in the Home" at Pervasive Computing in 2011.
I was contracted to build a realtime data collection/analysis system by Centrotherm USA for usage in their chemical engineering research. The system's fanciful name notwithstanding, I designed and implemented it to control and read off of dozens of sensors simultaneously across a variety of modalities including SOLO sensors communicating via Modbus over TCP and interfacing with Gas Chromatography and Fourier Transform Infrared Spectroscopy instrumentation. The sensor readings were streamed into a database and plotted, live, through an interactive web-based data exploration environment custom-built for this application.