This week, I worked on firmware for our wearable. I wrote code for our microcontroller, which is a WiFi-enabled Particle Photon MCU to connect to a public MQTT network and publish sensor data. I actually spent a lot of my time trying to get it to work on campus WiFi. At first, I was unable to get it to connect reliably to CMU-DEVICE, but, after futzing around with it for a couple hours, I tried out another board and it seemed to work fine.
The Photon publishes data formatted like so, in a packed byte array format:
[<4 byte little endian timestamp>, sensor value 1, sensor value 2, sensor value 3]
I hiccup I ran into is that our board cannot get a unix timestamp with millisecond accuracy, so measuring the latency of our data collection will be incredibly off and inaccurate. Might need to figure out a way around this. However, technically, this is only for measuring data for metrics, and not essential to the actual functionality of the device. So, I may need to consider the tradeoffs of taking time to fix this problem or just ignoring it and getting an inaccurate latency measure.
I also worked with Anushka to get a visualization of the sensor data working so that we can understand what kind of data we are dealing with (see video here). We have a set up with three sensors attached to a Photon that publishes data to MQTT. The webpage gets data from MQTT and displays it. I believe visualization will help guide us in what a “finger” looks like in terms of sensor data.
Additionally, I ordered the PCBs earlier this week and they should come next Tuesday (3/1). Next week, I will be working on testing and verifying that the PCBs work as intended. This will probably take up a large chunk of my time next week.
I am on track this week, but as soon as the PCBs come, I might fall behind, since they might not work… I want to get the PCBs verified before Spring Break starts.