Hafiz Khan is a fifth year Ph.D. student in the Information Systems Department at the University of Maryland, Baltimore County (UMBC), where his doctoral work explores how sensor data from mobile devices can be used to identify different kinds of human activity using transfer learning techniques. Originally hailing from the Natore district in northern Bangladesh, Khan received his BS in Computer Science and Engineering from the Bangladesh University of Engineering and Technology (BUET).
HP: What are you working on this summer?
I’m working in the Print Adjacencies and 3D Lab to analyze 3D printer sensor data in the hope of gaining a better understanding of how various sub-systems in a 3D printer contribute to the final part quality.
HP: What can that tell you?
There are many different parameters that you can sense. Initially, I am looking at just one: variations in the temperature, which we can record with the help of an infrared thermal camera. We are measuring the temperature of an object as it is built up layer by layer. One way of analyzing why you did or didn’t get the results you wanted across that build is to compare the temperatures you record to the outcome that’s produced. So, I’m looking to correlate the temperature data with the final produced parts. Then when there are deviations from the expected quality, we can see whether the temperature differences played a role. And then if they did, we have a sense of what needs to change in order to correct the problem. Later, we will include several other sensor and firmware parameters to chase the root cause for variations in final part quality.
HP: Are there any other goals for your project?
Yes, we’re also hoping to use machine learning to build a classification system to predict final part quality. If we can recognize different part variability as being the result of specific kinds of variations in the printing process, we’ll ultimately have a higher yield process.
HP: How are things going?
I’m just a few weeks into my internship, so it’s a little early to say. At the moment, I’m busy gathering data on the temperature levels that we’ll analyze later on.
HP: How does interning at HP compare with other internships you’ve held?
I really like the environment and culture here and how we are encouraged to approach problems. You aren’t told to just go away and work on something. You are encouraged to discuss your approach and regarded more as a peer by the permanent research team. I think that helps us do better work. And the work that I’m doing is challenging but really interesting.
HP: What do you like to do when you aren’t at work or studying?
Usually, I like to play cricket, travel and do sightseeing. But right now, I have a 6 month-old baby, so he pretty much takes up all my time when I’m not at work!