This week for capstone I spent the majority of my time organizing the classification algorithm approach to our EMG data. A major decision factor going into this classification of the data depends on how the data is recorded. I found that if the data is recorded in a continuous stream of repeated actions, the best approach is to use wavelet transform on the data in order to identify a basis function and the scaled and shifted versions of it. This…
This week I bought a texture pack from Unity Asset Store to bring in better look and feel in to the game. The new asset contains more diverse objects to create obstacles and background. The old terrain and structure is replaced with the new texture pack. I also fixed the lighting and fog issue where distant objects are grayed out. Graying out distant object can be good as it makes the game more realistic, but previously the gray distance was…
This week the data collection process was bolstered and thanks to Tarana’s hard work in coordinating the hardware system of the EMG, we were able to collect data recorded from more than a single electrode. Last week’s milestone was collecting data from a single electrode and visualizing the signal from different recorded movements over time. This week, toward the end of the week we got data collected for all the movement collected from five electrodes on the forearm. This upcoming…
This week I created obstacles that are appropriate for the game and implemented obstacle collision using Mesh Collider in Unity. I used a planar mesh to check for collision when the character is moving straight into the obstacle. But a different implementation is required when the character tries to move left when the obstacle is there, or when the character jumps onto the obstacle. Next week’s goal is to implement gravity and jump so that the character can jump onto…
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…
This week I presented for our team’s design review presentation. 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…
This week I developed character movement and infinite terrain feature. One of the easiest way to burden the game main thread is to infinitely create roads and terrains as the character moves forward. This eventually take up large unnecessary game memory. We can clear up the issue by deleting the objects that are behind the character. Because I expect many more objects to be created at run time (coins, obstacles, etc) I decided to just move the road that is…
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…
This week I spent time furthering specifics for the data collection experimental procedure of our project. Additionally, I have been exploring common data processing techniques for classifying EMG data, specifically useful feature extraction techniques such as Wavelet Transform. I will also be presenting during the Design Review Presentation for our team next week, so I have been working on the slides and preparing the presentation. Our project is currently on track and the next step is to collect the EMG…
This week the team had a few successes on both the hardware and software sides. On the hardware side, all the parts finally arrived so we have been able to solder parts together for the EMG system. On the software side, the mock controller has been helpful in serving as an intermediate workaround to test the game while the hardware is being developed. We are a little behind schedule as we would like to collect data in order to begin…