I spent all my time this week preparing for the end of the internship. I submitted a poster for admittance to the Association for Computing Machinery poster competition to be held at the Super Computing Conference in Dallas, Texas this year. Beyond that, I spent a lot of time organizing files and finishing mandatory assignments. On Monday I submitted a minute long video to a small competition for giving elevator pitches and got an honorable mention award on Thursday, which was a tie between 5th and 6th place out of 10. Not bad for one hour of recording at midnight. Thursday was the poster session for all the interns and it went fairly well. The expense of organizing the event probably wasn't worth the amount of visitors that came to participate, though. I will say that I was one of the few interns that presented their poster to Michael Stewart Witherell, the director of the lab! Now that was cool! The research poster presented at the final poster session There was a lot plan...
The beginning of this week's work was dedicated to solving some problems that came from reproducing the second experiment. With Alina's help we were able to get a much better match to the graphics from the paper, though there were still some dissimilarities. Some data was still missing and the clustering didn't always match the paper. The clustering difference can be explained by the possibility of using different parameters. Next, we worked on representing data as averages in different sized time windows. We tried examples of hour long time windows with five minute throughput averages, day long time windows with hourly throughput averages, and a window of the entire cleaned data set with daily throughput averages. This technique will become extremely useful in the future of this project. After my weekly meeting with my mentors on Thursday, I began working more directly with my project. Part of the new plan was to use PCA to determine ...
Work for the fifth week mostly focussed on writing a rough draft of the Introduction, Materials, and Methods sections of the paper required at the end of the internship. With July 4th off, this took even more time from progress directly related to my project. I did happen to use PCA on Friday for feature selection on a few subsets of data. Though I still had to think through a way of systematically choosing what would be considered the 5 most prominent features of any one subset. This leads to an arguably uninteresting post because of the lack of graphs or visuals. Though I can assure you, it would be far less interesting if I explained all the coding obstacles I went through to achieve a way to interpret PCA results.
Comments
Post a Comment