This week, I am working to get the dynamic time warping functionality into my program. The process of doing so includes re-processing the features to include the time series, putting each series back together when we construct sequences, and then performing the DTW to generate a number that will be used to compute the kNN of each sequence which can then be used for predictions with the models. The processing time of these activities has gone up significantly since we have been using five different metrics with each of the F phase datasets. I am returning to school next week, and once I've completed the DTW processing all that will remain before we put together our second paper (The date for the reach journal we would like to submit it to is October 1), I am hoping I will have time to look again into the Agglomerative Hierarchical Clustering concept, which I did not successfully complete when we explored it earlier in the summer and then changed focus to the paper. We heard back
Following our meeting with Dr. Weeks and Dr. Skornyakov, we have a list of tasks to complete to help them out with their projects, as well as some new ideas to consider in light of the difference between the first and second phase actigraphs. Dr. Skornyakov expressed interest in potentially ignoring the first night of data collected for each patient, as there is often an adjustment period associated with sleeping while wearing an unfamiliar device. To get a look at how this might affect our 'baseline' data measurements, Alexa and I are going to calculate what the difference in Coefficient of Variation will be if we choose to only consider days 2 and 3 as the baseline.
In addition, I am going to plot out the activity and sleep on the same axes minute-by-minute for the first two days so that we can have a look at how the patient is sleeping.
We are also hoping to be able to obtain a few of the phase 1 actigraphs so that Alexa and I can wear them alongside the phase 2 actigraphs and compare activity data between the two of them. We hope that this may shed more light on how we can treat the data between the two phases relative to one another. Dr. Weeks also suggested that we consider looking at the sleep/activity relationship on weekends vs. weekdays.
Comments
Post a Comment