I am the Lead Software Developer at the Center for Health Enhancement Systems Studies (CHESS) at University of Wisconsin – Madison. I started at CHESS as a student back in 2007, worked there full-time while doing my Master’s Degree in Computer Science, and became lead software developer in 2014.

CHESS has given me many opportunities to research and build mobile, sensor, and website application systems that help patients and their families undergoing health crises. This includes working with patients undergoing substance misuse treatment, teenagers with asthma, cancer patients, caregivers of people with Alzheimer’s, and people that are simply aging.

I share CHESS’ mission, to help people. I try to do that by developing systems that empower people whether that is connecting patients undergoing life-altering treatments or research staff helping to bring technology to study participants.

I have worked with A LOT of different technologies over the years. Just a smattering include website development using PHP and the .NET framework, HTML, CSS, SCSS, Typescript, Javascript, AngularJS, Docker, MySQL, SQL, DevOps, Java for Android, Objective-C and Swift for iOS, and administrating Linux and Windows servers.

My current research interests include user and developer experience design, and applications of machine learning. Previously I worked on applications of neural networks in Chaos Theory.

In my free time, I enjoy endurance sports like triathlons, long distance running and biking. I also like reading hard sci-fi, writing fiction and research articles, learning new things, and cooking.

I also am an active member of the Friends of Military Ridge State Trail in Wisconsin. I help to maintain their website and, in 2023, set up a way to sign up members online.

For more information, please see my C.V.

Past Research Collaborations

Junho Oh of the UW-Madison Business School on research involving user-centered design

Professor J. C. Sprott of the UW-Madison Physics Department on research involving artificial neural networks and nonlinear time series analysis

  1. Using artificial neural networks to determine the lag space for mathematical systems. The lag space is any intermediate dimensions in a time series that are not used in the determination of the time series’ next step. For a system such as the weather, we are attempted to identify exactly which previous days determine today’s weather. Other places to learn about this project:
    • Our published article “Neural network method for determining embedding dimension of a time series” is available here
    • My presentation “Applications of neural networks in time-series analysis” for the Chaos and Complex Systems Seminar in April 2009. (Slides)
      • Abstract: Artificial neural networks are mathematical models that emulate biological neural systems. They have been used in classification, pattern recognition, and time-series analysis. In time-series analysis, neural networks can be used for forecasting but also to determine how many and which past values are required to predict the future. Determination of this ‘lag space’ sheds light on the nature of the dynamics and permits development of minimal models capable of replicating the dynamics. I will highlight applications of neural networks in the real world as models that classify, forecast, and analyze data while emphasizing their use in determining the lag space.
  2. Using artificial neural networks to determine the Lyapunov Spectrum of dynamical systems and our work compares neural networks to traditionally used local linear models. (Preprint)

Andrew Quanbeck from the Center for Health Enhancement Systems Studies

  1. Using social network analysis to study the organizational network of the substance abuse treatment field (Paper)

Jesse Gomer from the Center for Health Enhancement Systems Studies

  1. Assessing Alcohol Abuse Statistics Through Data Analysis Of Social Networking Sites (PDF)
Selected Research Publications
  • Adam N. Maus and Amy K. Atwood. 2015. Surveying Older Adults About a Recommender System for a Digital Library. In Proceedings of the 20th International Conference on Intelligent User Interfaces Companion (IUI Companion ’15). ACM, New York, NY, USA, 41-44.
  • Neural network method for determining embedding dimension of a time series. Communications in Nonlinear Science and Numerical Simulations. Volume 16, Issue 8, August 2011, Pages 3294-3302.
  • Evaluating Lyapunov Exponent Spectra with Neural Networks. Chaos, Solitons & Fractals. Volume 51, June 2013, Pages 13-21. Preprint (PDF)

To see a more complete list of publications, please visit https://www.researchgate.net/profile/Adam_Maus/publications