Evidence of Work

For this project, our main goal was to be able to create a model that can predict a variable about a person based on another variable from their gait analysis data. To study one's gait is to study the way that one walks, analyzing the various components that go into each step. To do this, our first step was to collect data for each of our group members. The data variables we collected were shoe size/foot length, leg length, total height, and then the g-forces of the x, y, and z directions while walking normally. Once we finished our data collection, we had to explore different ways to create a predictive model. It was difficult at first because we had to find two variables that had not only a correlation, but two variables where one causes the other. Our final choices were the range of the g-forces in the x direction and total height. Since we needed to use one to predict the other, we decided to have the range of g-forces in the x direction determine total height.

Once we had chosen our variables, we had to create the model. Using the data from our group members, we plotted points on a graph and drew a line connecting them. Our graphs (below) consisted of the range of g-forces on the x-axis and total height on the y-axis. From there, we found the trendline (line of best fit) for our data and that became our predictive model. We even tested a few of our classmates to look at the accuracy of our model. From the new data that we collected, we were able to determine that our predictive model works pretty well for heights that were inside the range of heights for our group, but for those outside of our range, the model would be quite inaccurate and become faulty. So we made note of that and made sure to talk about the margin of error in our written report (below) and in our presentation (also below).

Content

Vocabulary From the Unit

Gait - A pattern of limb movements made during locomotion. Human gaits are the various ways in which a human can move, either naturally or as a result of specialized training

Acceleration - Rate of change of velocity. In this project, we used an app to measure acceleration and then created graphs to compare our subjects data

Accelerometer - A device that detects acceleration and tilt. We used the accelerometer in our app measuring

G-force - G-force is a measure of acceleration

G-force Meter - A g-Force meter is able to measure the ratio of normal force to gravitational force, in three dimensions

X-Direction - Lateral axis measuring movement from right to left

Y-Direction - Vertical axis measuring movement up and down

Z-Direction - Axis measuring movement forwards and backwards

Velocity - The speed of something that is moving in one direction. In this project, it was how fast our subjects walked

Margin of Error - An amount (usually small) that is allowed for in case of miscalculation or change of circumstances

Dynamicity - In terms of gait analysis, the quantification of variations in kinematic or kinetic parameters within a step

Extrapolation - The action of estimating or concluding something by assuming that existing trends will continue or a current method will remain applicable

Metric - A quantitative indicator of a characteristic or attribute

Model - In technology, 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

Symmetry - In terms of gait analysis, the quantification of differences between left-foot and right-foot steps

Variability - In terms of gait analysis, the quantification of fluctuations from one stride to the next

Reflection

Overall for this project, I think my group and I did really well and we made a final report and model that we worked hard on and are proud of. We also had things that went well and things that could use work for our project. Two things that I think went really well were our time management and collaboration skills. For time management, we worked really effectively in the time we had to finish our project, even though we might have started slightly later than most groups. We were even able to finish our project by the original deadline, only needing to add finishing touches after that. For collaboration, we all worked together on this project and evenly split the work up to maximize efficiency. This further contributed to our outstanding time management. We made sure to organize everything we had to do carefully checking over the requirements and then dividing the work to make sure we got it done on time with good quality work.

For two things that we could work on, we could improve in our communication and work ethic skills. For communication, we had divided all of our work up, but we could have done it in a better way. Instead of one person working on a few different sections that were closely related, we all assigned random pieces to ourselves. This meant we had to do a lot of extra communicating with each other to get all of the information we needed for those parts when it could have been much easier. So for this, our actual communication wasn't the issue, just the way we went about dividing up the work. For work ethic, at times our group easily got distracted. We started on the project later than most groups, so we knew we had to work efficiently to catch up. We did end up moving relatively quickly and by working harder, we were able to finish with plenty of time left. However, if we hadn't procrastinated in the first place, we could have done it while being a little less rushed. Overall, I think our final project was a success and I'm proud of the predictive model that my group and I were able to create for this project.