This week the team had a few successes on both the hardware and software sides. On the hardware side, the parts are soldered together we are just about ready to to record data from the EMG hardware system. On the software side, basic functionality of the MyoRun game is implemented and integrated with the Mock Muscle controller. With more game objects and functionalities being implemented, optimizations wherever possible (but not too much premature optimization) is crucial and the Software side is doing memory usage optimizations in endless map generation. On the research side, we researched into the broader impacts of ouproject space, which brings in specialized information to light for our Design Review Report. Next week’s plan is to finish recording data for the EMG and finish Integration #1. We are also basically ready for our Integration #2 after we finish recording EMG data.

One major challenge is that we have shifted from recording EMG for just one person to couple more people. After discussing with class, a more generalizable product is more valuable and compelling than a overfitted one. This comes at the cost of potentially having lower accuracy rate because due to COVID condition we are simply unable to get enough sample size. Nevertheless, the consensus was that generalizable product was more compelling. This impacts our initial plan for recording.

Unexpected changes like this one is something we did plan to spend during our slack days. So we will not be experiencing any major delays. The schedule has not changed, we are still moving along in progress. We did our presentation for our Design Review presentation which can be seen here and had valuable feedbacks.

Design Review Presentation Notes:
A question that came up was what is the difference between game delay and total delay. These names sound quite similar which can be confusing, but the metric for game delay helps to isolate time required for the game to render and react to the mock muscle simulator, while total delay is measured when using actual muscle signals which must go through the classification algorithm. Identifying these metrics and risk factors will be useful in helping us to create the full system without any significant time delays.