Matching Items (2)
Filtering by
- Creators: Petersen, Casey Alexander
- Creators: Trimble, Steve
Description
Many tasks that humans do from day to day are taken for granted in term of appreciating their true complexity. Humans are the only species on the planet that have developed such an in-depth means of auditory communication. Recreating the mechanisms in the brain that recognize speech patterns is no easy task. This paper compares and contrasts various algorithms used in modern day ASR systems, and focuses primarily on ASR systems in resource constrained environments. The Green colored blocks in Figure 1 will be focused on in greater detail throughout this paper, they are the key to building an exceptional ASR system. Deep Neural Networks (DNNs) are the clear and current leader among ASR technologies; all research in this field is currently revolving around this method. Although DNNs are very effective, many older methods of ASR are used often due to the complexities involved with DNNs; these difficulties include the large amount of hardware resources as well as development resources, such as engineers and money, required for this method.
ContributorsPetersen, Casey Alexander (Author) / Csavina, Kristine (Thesis director) / Pollat, Scott (Committee member) / Engineering Programs (Contributor) / Barrett, The Honors College (Contributor)
Created2015-12
Description
Spirometry is a type of pulmonary function test that measures the amount of air volume and the speed of air flow from a patient's breath in order to assess lung function. The goal of this project is to develop and validate a mobile spirometer technology based on a differential pressure sensor. The findings in this paper are used in a larger project that combines the features of a capnography device and a spirometer into a single mobile health unit known as the capno-spirometer. The following paper discusses the methods, experiments, and prototypes that were developed and tested in order to create a robust and accurate technology for all of the spirometry functions within the capno-spirometer. The differential pressure sensor is set up with one inlet measuring the pressure inside the spirometer tubing and the other inlet measuring the ambient pressure of the environment. The inlet measuring the inside of the tubing is very sensitive to its orientation and position with respect to the path of the air flow. It is found that taking a measurement from the center of the flow is 50% better than from the side wall. The sensor inlet is optimized at 37 mm from the mouthpiece inlet. The unit is calibrated by relating the maximum pressure sensor voltage signal to the peak expiratory flow rate (PEF) taken during a series of spirometry tests. In conclusion, this relationship is best represented as a quadratic function and a calibration equation is computed to provide a flow rate given a voltage change. The flow rates are used to calculate the four main spirometry parameters: PEF, FVC, FEV1, and FER. These methods are then referenced with the results from a commercial spirometer for validation. After validation, the pressure-based spirometry technology is proven to be both robust and accurate.
ContributorsMiller, Dylan (Author) / Forzani, Erica (Thesis advisor) / Trimble, Steve (Committee member) / Xian, Xiaojun (Committee member) / Arizona State University (Publisher)
Created2013