Author: Mira Holford
HolfordM_5
Final Thoughts
Overall, I thought this class was a wonderful experience. I believe the most important piece in making this class so enjoyable was the fact that we were given substantial freedom on what we were to work on. I don’t think I have ever worked so hard in such a concentrated period of time on a project I was so passionate about.
During the class, I was a bit annoyed with other projects that I felt were taking time from the main patient project. However, looking back, I recognize that just because I wasn’t as interested in some of the other projects doesn’t mean I didn’t benefit from them. This is especially true for the reverse engineering project. As someone who had never worked in Solidworks, there was a horribly steep learning curve and the experience was often frustrating. But now I feel much better equipped to take on projects with this new skill in my pocket.
I will write more later, as of right now I am trying to finish everything by the 5 o’clock deadline.
-Mira
HolfordM_4
Today was all about perfecting the trembling algorithm. We have gotten to the point where we can rule out all sorts of daily tasks that seem similar to trembling: chopping vegetables, blowdrying hair, and typing (among others). These all leave subtle traces in the data that allow octave to distinguish them from trembling. As this is a public forum, I will not go into any further detail.
The last thing to sort out is how to distinguish shivering from trembling. This becomes quite difficult as the two are extremely similar motions. It is also difficult to capture genuine shivering data to run tests on. This is an issue I tend to address with research as opposed to comparing data. Although the motion is the same, there may be differences in duration or intensity that could be picked up.
Anyway, that is an issue for tomorrow. We have made such good progress on the algorithm and entire hardware system — I’m pretty pumped to present nonetheless.
-Mira
HolfordM_3
Kate and I are working to develop a device capable of detecting hypoglycemic trembling. We have gone about this task by programming a Raspberry Pi to read in and analyze accelerometer data. It is our thinking that hypoglycemia causes such a distinct trembling that it will leave a unique signature in the data.
In reality, this task is a bit more tricky. It’s funny that as a human we can look at someone trembling and someone chopping vegetables, and immediately know the difference. However, all the Raspberry Pi receives is three components of an acceleration vector, with absolutely no context.
We have tried to develop an algorithm to distinguish this trembling using two main routes. Firstly, we are doing research and reading papers to see if there is any “theory” we can apply. For example, metabolic tremors occur at 8-12 hertz, so we can calculate the Fourier transform and look at the frequency domain. Secondly, we are gathering data from our patient and simulating data ourselves to see if there is anything that can be discerned by trial and error.
Ultimately, saying “yes, this is trembling,” is not the hard part. It is eliminating the false positives that occur when other regular motions are picked up as similar to trembling.
Luckily, after countless hours of frustration, I [sort of ] finished the CAD assignment, so I should be able to dedicate a good amount of time to this algorithm in the coming days.
-Mira
HolfordM_ 2
I’ve always tried to stay as far away from drawing as possible, simply because it is so embarrassing. I have always felt shame when I look at things that I have drawn. It is as though I am missing some sort of link between my eyes and my hand, because I can have something right in front of me yet not be able to capture its form on paper at all.
I recognize that the ability to sketch is important, and the recent lesson in visualization was a great lesson on how to deal with this shortcoming. Through this exercise, I have found a technique that will allow me to accurately draw things that physically exist, and will provide a solid starting point for things that do not.
First, I took a picture of the object in question (my doorway). I changed the picture to black and white because I was concerned only about the outline of shapes, not color.
Then, I printed out this image to completely take up an 8 1/2 by 11 piece of paper. I taped this image to a glass table. I turned on a flash light and placed it facing upward under the glass table, such that it shown through the piece of paper.
Now, I was in a position to place a blank sheet of paper atop the printed image and locate reference points, or trace the image.
This same effect can be achieved by putting the two sheets of paper and taping them to a window on a sunny day.
This may not be perfect for every set of circumstances, but it is certainly a nice place to start.
-Mira
HolfordM_1
I’ve been thinking a great deal about the concept of “improving one’s diet”. I constantly hear people say that they need to “eat better” or “eat healthier”, but what does that really mean? I understand that in most cases a salad is probably better than a donut, but does there exist an “objectively healthiest diet”. I don’t think so. I believe that the nutritional value of any one food is directly related to how the body metabolizes and uses it, and what else the person in question has eaten. Anyways….
For the purposes of my partner, I am going to define a healthy diet as a balanced diet. This means 2500 calories a day, with a 50:20:30 carbohydrate to protein to fat ratio. I will calculate the two following metrics:
- net calories = calories consumed – calorie goal
- macro distance = sqrt((50-%carbs)^2 + (20-%protein)^2 + (30-%fat)^2)
Now, I have no data on my partner, but in the coming days I will. After seeing what he has been eating, I will reassess whether or not this is an appropriate goal.
Hopefully, I will be able to create a system that leaves my partner feeling self confidant and full of energy, so that he can get the most out of each and every day.
-Mira
BME Design 