Our final project is complete:
For our last Animation assignment we created a simple game or experiment in Unity. I created a maze game.
When I was learning how to program a computer many years ago I loved to make mazes. Using our Commodore 64 computer I made games involving mazes and simple characters that would find their way through the mazes. I loved those games. The character moving through the maze would literally be a single character moving up, down, left, and right through a 2D maze. I thought it would be fitting if my first Unity game was also a maze game, but with more advanced graphics.
Our next assignment is to use a Multi-Layer Perceptron to study a dataset.
The dataset I selected is the commonly studied Poker Hand data. Each record contains data for 5 playing cards and a poker hand classification, such as full house or straight.
This dataset proved to be difficult to work with. It is an example of an imbalanced dataset in that the more common poker hands like two-of-a-kind are heavily represented and the less common hands like straight and flush are not.
I found that the Perceptron was able to correctly classify some poker hands very well while performing terribly for others. I suspect a very different training methodology is required to properly train a Perceptron with this dataset.
Our final project continues to progress towards our final presentation next week. Our project is in good shape and we were even able to do some user testing yesterday with some people in the lounge. I'm looking forward to tomorrow's user testing and additional feedback.
We made progress on several fronts. First, I collected much more raw pulse data and studied the data in Python. I was able to identify the shortcomings in the provided pulse sensor code and make some improvements. This is documented in my previous post. Our project uses this modified version that has noticeable improvements over the original version. It still isn't perfect but for people for whom the sensor gets a good reading, it works very well. This modified version has been shared with two other groups who are also using the pulse sensor.
Our Physical Computing final project depends on a Pulse Sensor to detect a user's heartbeat. The people at World Famous Electronics created an Arduino library for their customers to use with their sensor. The library adds a lot of value because it provides users with a well researched algorithm for using the sensor to properly detect a heartbeat. Pulse Sensor users don't have to re-invent the wheel and code their own algorithms. Writing your own algorithm to do this is difficult, and the one provided by the company is better than the one that I came up with for our midterm.
Still, the provided algorithm isn't perfect. For some people it seems to miss some heartbeats and add extra heartbeats. A fellow ITP student, Ellen, showed me that it would have odd spikes in the beats-per-minute (BPM) value. It wasn't clear why this was happening. Since I previously had been analyzing the sensor's data in Python, I came up with a plan to figure out why the Arduino code was doing this and to figure out if there was anything I could do about it. After studying the data and making some plots, I was able to make some improvements the algorithm. It still isn't perfect but my changes address many of the weaknesses of the algorithm.
The original Pulse Sensor Arduino code is available online on GitHub. I am sharing this code with my fellow students who are also using the same sensor. After our projects are complete I will submit my modified code to GitHub as a pull request to share with the rest of the community.
Camilla and I have made a lot of progress on our final project.
We have our first real enclosure:
It is done. I present to you my Animation After Effects video:
And what a challenge it was to make this.
Our second assignment in our Learning Machines class is to implement k-means clustering in Python. I've implemented this in other programming languages but not in Python. Normally I'd use scikit-learn for this but it is a worthwhile exercise to think through how to do this in Python.
Scott McCloud’s book Understanding Comics is ostensibly a book about comic books as an art form, including its history, evolution, and modern structure.
The author has much love for comics and fell in love with them as a child. I can partially relate in that when I was younger I looked forward to the Sunday newspaper and reading the comics. However, I never had an affinity for comic books and found them to be a waste of time. These days I only read Dilbert on a regular basis.