In the past two weeks, our team has made a lot of progress on our project. During the Thanksgiving break, we achieved the milestone set in Phase III of our schedule by completing our final integration test. As the TAs had warned us early in the semester that integration would be the most challenging part, we made sure that we kept the separate parts of our project on the right trajectory by frequently integrating everything throughout the semester. This has paid off immensely, as our entire team is in sync about what components need to go where and how our project should function as a whole. 

Prior to the Thanksgiving break, Kayla had been working on feature extraction from the muscle signals, and Tarana had been working on building a framework for the support vector machine. Those two parts of the project were integrated together to make a functioning classifier, which was used to feed inputs into the game Alex had been updating and optimizing. During this time, we made some small tweaks to the game to account for quirks in the classifier and small tweaks in the classifier to account for quirks in the game, but overall the integration of our individual project components went very well.

In the following week, we made some necessary adjustments to our classifier to improve its performance such that it would meet our target metric of 80% accuracy. After smoothing out some kinks in the system we prepared for our second in class demo, and got some really helpful feedback on how we should proceed with the presentation. 

Since then, we have been making some measurements to ensure that we are within our specifications. A good example of this is our metric of having no more than 500ms of game delay. While this quantity is difficult and impractical to measure on its own, we have broken it down into the sum of its parts, by independently measuring the delay in the hardware, signals/software, and the game. This has been a little tedious but we have been able to get an accurate breakdown of what our delay looks like. Furthermore, we have been developing ways to quantify the accuracy of our classifier and measuring some hardware specification to ensure that they match what was previously defined. 

Finally, we spent the end of this week working on our Final Presentation, taking the feedback that we had received from our demo on how we should illustrate our project working. The next steps of our project include finalizing our metric measurements, finishing up our presentation, making a demo video, and writing our report.