During this project, we measured our gaits and other pieces of data—such as height, weight, leg length, speed, etc.—to identify any possible correlations. We then used our observations to determine what we could predict about someone from their gait. In the Gait Analysis Report, we detailed all of our findings, as well as our predicative model. In the Gait Analysis Micro Presentation, we then used the data from our report and condensed it to the key elements. We also utilized the opportunity to improve our data by refining our predictive model and adding more visuals to help the viewer see our findings. Our refined predictive model found that m = 0.153543307086614340L - 0.1476, where m is the average rate of change of acceleration, or jerk, and L is the leg length of the subject. The independent variable in our model is leg length, and the dependent is jerk. Our testing found this model to boast an accuracy of 98.9%.

Gait: The stride of a person as they move their limbs.

Accelerometer: A device that measures the physical acceleration an object undergoes. We used the acceleration we measured from our gaits to compare the leg length of an individual to the jerk experienced through their gait.

Model: A description of observed or predicted behavior of some system, simplified by ignoring certain details. Models allow complex systems to be understood and their behavior predicted. We used predictive models to express the conclusions we drew from our gait analyses.

Dynamicity: The quantification of variations in kinematic or kinetic parameters within a step.

Metric: A quantitative indicator of a characteristic or attribute.

Symmetry: The quantification of differences between steps taken with the left and right foot.

Variability: The quantification of fluctuations between strides.

During this project, I demonstrated good leadership ability and critical thinking. I did a good job leading by taking charge with our predictive model and corresponding graphs. I also did a good job thinking critically about how to calculate our predictive model and what data points we would need to collect.

I could have done a better job communicating with my team and collaborating. I feel I did not communicate my ideas for the predictive model as early in the process as I should have, and although my teammates had no reservations about the correlation I looked at, this may not have been the case. I also feel I could have done a better job collaborating: my group sort of delegated tasks to each individual—which is a good strategy to work effectively as a team, but we should have contributed more to each other's work as well to really utilize our combined minds to see new perspectives and provide our best work as a team.