Gait Analysis Project
Evidence of Work
For this project we learned about the concept of gaits and were tasked with recording the gaits of a range of people, and analyze similarities between gaits. The purpose of the project was to find similarities between the gaits of individuals, and be able to predict physical attributes of individuals through a general gait model. I was tasked to work on this project with my Capstone project: Sally Cesko, Gabe Choi, and Marie Fehring. By the end of this project we had created a predictive model that considers the y acceleration of an individuals gait, and predicts that individuals height. For our model we took the average range of y acceleration from our data set and compared it with the average height of Americans.
Above is the report my group wrote up for our Gait Analysis Project, and below is the presentation we created to communicate our findings.
Content
Accelerometer: A device that measures the physical acceleration experienced by an object.
Dynamicity: In terms of gait analysis, the quantification of variations in kinematic or kinetic parameters within a step.
Gait: The stride of a human as s/he moves his/her limbs.
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.
Data Collection—The process starts with data collection using any number of strategies. Data collection might take the form of an experiment in which you conduct trials to measure the effect of one variable on another by controlling all other possible variables. The collection might be a survey of something by sampling to gather information. It is important that the survey be unbiased, random and representative of the group you are sampling. Data may already exist, eliminating the need to collect something new. In the business world, it might be historic sales, production or costs. In academia, it might be test scores. In engineering, data is collected on production processes, historical usage or environmental factors, and stress or strength measurements. Data is everywhere and often the challenge is not so much finding data as limiting it to what is relevant to study.
Data Analysis—The analysis of the collected data is a critical step. To do this, you carefully look at the collected data in an organized way, such as a table, spreadsheet or other computer application. You probably want to graph the data because trends are easier to notice in graphical format. This step is really about identifying patterns that might be present. It is possible that no strong trends are present in the data. Finding no trend is not necessarily bad; it just tells you that the variables are not related.
Mathematical Modeling—Modeling the data that was collected and analyzed is where mathematics occurs in this process. You might use a graphing calculator, computer spreadsheet or other software application to generate an equation that represents the data. These uses of technology also provide statistical measurements such as variance and correlation that can help you understand the effectiveness of your equation (model).
Reporting—The final step in this process is to report the data and model that represent it and then make predictions using the model to support decisions. If you have a model that statistically represents the data accurately, it should be possible to make fairly reliable predictions. You can present the results in tabular or graphical form, or a combination of both. Indicate your prediction by showing an extrapolation using your model and present that information as support for a decision. Be aware that any predictions made are only that—predictions. If the trend changes, your prediction will not be correct. The process of data analysis is a tool to make an educated guess about the future and not a guarantee that predictions come true.
Example graph of one trial of data we recorded and analyzed.
Reflection
Throughout this project my group worked very well with each other, and everyone ensured that the project was thorough and finished on time. Every member of our team held a great character during the entirety of the project. Everyone was respectful of others' ideas, and we all did the work that we were assigned to do. Along with the great character and attitude of the my group, our communication was also great. In our brainstorming phase of the project we all carefully listened to each others' ideas and made sure to leave room for anyone who wanted to add input or their thoughts. Even more so, our group had great communication of our findings to the class, as our presentation was concise and we had our information memorized.
While my group worked really well together throughout this project, we could have improved both our cultural competence and conscientious learning. Although the project was not directed in a way where much cultural competence could be shown, it is important to keep in mind for future projects that cultural competence is a vital skill to have. Furthermore, our group could have also proven ourselves to be better conscientious learners. Even though we were able to finish the project on time, we had to do a large portion of our work in the last few days of the time allotted for the project. Next project I want to make sure that I improve my time management and work better as a conscientious learner.