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
Looking to quantify the difference between what we now know to be groups using two unique actigraphs, I calculated the average activity counts per 24 hour day and the average activity counts per minute for each subject, and then took the average of these numbers for the two groups. The results were as follows:
Phase 1 (K002-K026) : 181258 counts/day; 123 counts/minute
Phase 2 (K027-K037) : 115349 counts/day; 72 counts/minute
This demonstrates that there is likely a lower threshold for activity in the first phase vs. the second one. Looking back at the data, this is supported by higher numbers of sleep minutes being recorded in the second phase. This difference suggests that we may want to find different ways to classify sedentary activity for the two different groups.
In response to this new information, I intend to spend some more time looking at differences in activity levels between the two groups, as well as revisiting my past explorations to see if there are commonalities within the groups that I was unable to recognize. I am also going to re-create my activity and sleep over time graphs using average activity per minute instead of the sum of daily activity.
Comments
Post a Comment