
Arizona State University (ASU) is known for both enormous size and scale, as well as excellence in research and innovation. These attributes are embodied in the ideal of the “New American University.” ASU Library, as a partner in the New American University, has reorganized itself, completed a large-scale renovation of its main library building, and created interdisciplinary divisions of librarians and other professionals, backed up by subject “knowledge teams” that address specific research needs of faculty and students. As a result, the library has become involved in nontraditional projects across the university. This article is useful for libraries seeking to remain relevant and align themselves with institutional priorities.
Human activity recognition is the task of identifying a person’s movement from sensors in a wearable device, such as a smartphone, smartwatch, or a medical-grade device. A great method for this task is machine learning, which is the study of algorithms that learn and improve on their own with the help of massive amounts of useful data. These classification models can accurately classify activities with the time-series data from accelerometers and gyroscopes. A significant way to improve the accuracy of these machine learning models is preprocessing the data, essentially augmenting data to make the identification of each activity, or class, easier for the model. <br/>On this topic, this paper explains the design of SigNorm, a new web application which lets users conveniently transform time-series data and view the effects of those transformations in a code-free, browser-based user interface. The second and final section explains my take on a human activity recognition problem, which involves comparing a preprocessed dataset to an un-augmented one, and comparing the differences in accuracy using a one-dimensional convolutional neural network to make classifications.