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…
In the past two weeks, a lot of progress was made towards our final product. During the Thanksgiving break I worked with Kayla to build the classifier that would be used to interpret the muscle input signals and classify which movement it belonged to. We integrated together the feature extraction that Kayla had been working on along with the SVM model that I had been working on. Afterwards, we integrated our classifier with the game that Alex had been developing…
This week, I worked on improving the base models for making simulated data. I’ve found that the hyperbolic secant function is a great representation of the peaks in muscle movements, so I’ve been using linear combinations of that to make a good prior distribution function. I have also been familiarizing myself with scikit, a python package that has SVM support, and could help us with our classifier. Part of our project involves classification of signals, and to better aid that…
At the beginning of this week, our group did a demo of our project, and we got a lot of useful feedback. Byron suggested including simulated data as a part of our training data. This data would come from taking the ground truth of the signals from each muscle movement and adding noise to it. After receiving that advice, I worked on defining the “ground truth” signals of our data, by analyzing the output of our test data and averaging…
At the beginning of the week, we discussed ethics and how it relates to this class, which got us considering it in the context of our project. We were able to consider the ethical implications of our project and the kind of politics driving a need for it/the politics it would catalyse with its creation. Also in the beginning of the week, we met to discuss what we had learned from integration test #2, and talk about what we should…
This week we caught up to our Gantt Chart and got ourselves back on schedule by performing the first two integration tests. Using Kayla’s thoroughly researched experimental protocol, Tarana was able to record data for both a single electrode and an array of electrodes, and play the games that Alex has been working on the past few weeks. Our first integration test featured a single electrode and a very basic game that involved moving a ball around, which was designed…
This past week, I made a lot of progress on the data collection side, and was able to take the hardware system I had been working on the past couple of weeks and record data on it. To start off, I recorded data from a single electrode, as was seen in the previous update, and used that for our first integration test. This way, we were able to confirm that our communication protocols were working smoothly and in real time,…
This week substantial time was spent working on the written draft of the Project Report. It was important that we made the report as thorough as possible in order to create a good starting point for our final report. This week I began work with the data collected from a single EMG electrode for wrist flexion and extension data. Two sample trials can be seen in the image below. The data collection portion of our project is a little behind…
Early in the week, we collectively worked on putting together our progress report. We received a lot of insightful feedback from our presentation last week, and applied it both to our report and also our project going forward. In response to this feedback, we have more clearly laid out for ourselves specific implementation details. For example, we have defined exactly what data is sent between each module and how, to make integration more clear, which was suggested to us in…
This week I started off finding a way to integrate Arduino and python, such that data could be recorded in one and immediately sent to the other in real time. Using serial communication, I was able to open up a port on my computer and continuously write to it in one program and read from it in another. Once I had communication between the two programs working continuously, I wrote a python script to collect trials of pilot data. You…