Theses and Dissertations
This collection includes both ASU Theses and Dissertations, submitted by graduate students, and the Barrett, Honors College theses submitted by undergraduate students.
Displaying 1 - 2 of 2
Filtering by
- All Subjects: Smartphones
- Creators: Santello, Marco
Description
Continuous monitoring of sensor data from smart phones to identify human activities and gestures, puts a heavy load on the smart phone's power consumption. In this research study, the non-Euclidean geometry of the rich sensor data obtained from the user's smart phone is utilized to perform compressive analysis and efficient classification of human activities by employing machine learning techniques. We are interested in the generalization of classical tools for signal approximation to newer spaces, such as rotation data, which is best studied in a non-Euclidean setting, and its application to activity analysis. Attributing to the non-linear nature of the rotation data space, which involve a heavy overload on the smart phone's processor and memory as opposed to feature extraction on the Euclidean space, indexing and compaction of the acquired sensor data is performed prior to feature extraction, to reduce CPU overhead and thereby increase the lifetime of the battery with a little loss in recognition accuracy of the activities. The sensor data represented as unit quaternions, is a more intrinsic representation of the orientation of smart phone compared to Euler angles (which suffers from Gimbal lock problem) or the computationally intensive rotation matrices. Classification algorithms are employed to classify these manifold sequences in the non-Euclidean space. By performing customized indexing (using K-means algorithm) of the evolved manifold sequences before feature extraction, considerable energy savings is achieved in terms of smart phone's battery life.
ContributorsSivakumar, Aswin (Author) / Turaga, Pavan (Thesis advisor) / Spanias, Andreas (Committee member) / Papandreou-Suppappola, Antonia (Committee member) / Arizona State University (Publisher)
Created2014
Description
Telestroke networks reduce disparities in acute stroke care between metropolitan primary stroke centers and remote hospitals. Current technologies used to conduct remote patient assessments have very high start-up costs, yet they cannot consistently establish quality connection in a timely manner. Smartphgones can be used for high quality video teleconferencing (HQ-VTC). They are relatively inexpensive and widley used among healthcare providers. We aimed to study the reliability of HQ-VTC using smartphones for conducting the NIHSS. Two vascular neurologists (VNs) assessed 83 stroke patients with the NIHSS. The remote VN assessed patients using videoconferencing on a smartphone with the assistance of a bedside medical aide. The bedside VN rated patients ontemporaneously. Each VN was blinded to the other's NIHSS scores. We tested the inter-method agreement and physician satisfaction with the device. We demonstrated high total NIHSS score correlation between the methods (r=0.941, p<0.001). The mean total NIHSS scores for bedside and remote assessments were 7.3 plus or minus 7.9 and 6.7 plus or minus 7.6 with ranges of 0-30 and 0-37, respectively. Seven NIHSS categories had significantly high agreement beyond chance: LOC-questions, LOC-commands, visual fields, motor left arm, motor right arm, motor left leg, motor right leg; seven categories had moderate agreement: LOC-consciousness, best gaze, facial palsy, sensory, best language, dysarthria, extinction/inattention; one category had poor agreement: ataxia. There was high physician satisfaction with the device. The VNs rated 96% of the assessments as good or very good for "image quality," "sound quality," "ease of use," and "ability to assess subject using NIHSS," and 84% of the assesssments as good or very good for "reception in hospital." The smartphones with HQ-VTC is reliable, easy to use, and affordable for telestroke NIHSS administration. This device has high physician satisfaction. With the variety of smartphones and professional medical applications available today, the telestroke practitioner has all the tools necessary for fast clinical decision-makingby accessing electronic medial records, viewing images, and tracking patient vitals.
ContributorsVegunta, Sravanthi (Author) / Demaerschalk, Bart (Thesis director) / Santello, Marco (Committee member) / Hurlbut, Ben (Committee member) / Barrett, The Honors College (Contributor)
Created2012-05