Joshua Enxing
Lecturer, Computer Science
Statistical Programmer, Phastar
BA, Boston University; MS, University of Connecticut; MS, Tufts University
What is your area of expertise?
My areas of expertise are applied mathematics, specifically data science and machine learning, parametric and non-parametric statistics, and numerical linear algebra/numerical analysis.
Please tell us about your work. Can you share any current research or recent publications?
I am currently a statistical programmer at Phastar, a contract research organization for clinical trials. I work with members of the data science team to develop machine learning algorithms/programs that autodetect associations in certain domains of clinical trial data. The goal is to promote more automatic classification of things such as serious adverse events rather than relying on clinicians to make subjective judgments. In addition to teaching at BU MET, I am also an adjunct faculty member at Bentley and Tufts universities.
How does the subject you work in apply in practice? What is its application?
Machine learning has numerous applications in many different fields. After working on clinical trials for the past two years, I am particularly interested in how machine learning algorithms can be applied to wearable health devices. I envision a future where wearable health devices can diagnose many different conditions based on different types of input data from various body systems.
In your professional pursuits, do you consciously stockpile ideas/observations that you can bring to the classroom in order to inform readings and projects, discussions of current issues, or other distinct challenges that require a practitioner’s perspective?
I feel that industry experience is essential for someone who teaches data science and machine learning. Algorithms and techniques of data analysis are great, but it’s another matter to know how to apply them to real-world data, which is often messy and unlabeled and has all other sorts of undesirable qualities.
What course(s) do you teach at MET?
I teach Introduction to Probability and Statistics (MET CS 546), Analysis of Algorithms (MET CS 566), and Data Science with Python (MET CS 677). I began facilitating Introduction to Probability almost a decade ago when I was an undergraduate at BU, and have been happily facilitating and teaching courses at MET ever since!
If you previously worked in industry, what “real-life” exercises do you bring to class?
Working in the clinical trials space, I can bring a lot of “real-world” examples to the classroom. For example, when I teach confidence intervals in any statistics-based class, I have a breadth of examples from the clinical trials field to choose from. In my more advanced statistics classes, I ask students to perform power analyses that biostatisticians in my industry perform in practice.
Is there anything else you would like to add?
I have had the pleasure of having very bright and hard-working students during my time at MET. I have really enjoyed teaching at MET for almost a decade now, and I hope to still be teaching at MET in another decade.