Week #9 — Paper Finalization
Sachin C -
Welcome back!
This past week, I have been busy finishing the data collection of my project and porting it into various graphs that show a clear relationship between the various controllers. Regarding that, I am glad to report that I have finished the collection and the graph analysis. All that remains for my project is finishing the paper and the presentation.
So far, for the paper, I have finished the method section and am beginning work on the results section. I don’t anticipate this taking very long at all as the data I have collected (much to my surprise and delight) is extremely clear and shows numerous useful extrapolations.
For example, (spoiler alert!) the NXP controller performs exceptionally well with a high-noise image, even better than the Raspberry Pi 5 controller. This is a surprising result as the RPi5 is a microcomputer, which should theoretically be a step ahead of all of the other controllers in this project. This phenomenon is because of the neural accelerators of the NXP controller, which are able to process the vast amounts of data the model is being fed a notch better than the general-application RPi5. The tradeoff, however, is an drastic increase in energy consumption.
This week, I intend on continuing my work regarding the results section and slowly starting to bleed into the conclusion of the paper. I also intend to get a foothold on the presentation.
Thank you for checking in!