This collection includes most of the ASU Theses and Dissertations from 2011 to present. ASU Theses and Dissertations are available in downloadable PDF format; however, a small percentage of items are under embargo. Information about the dissertations/theses includes degree information, committee members, an abstract, supporting data or media.

In addition to the electronic theses found in the ASU Digital Repository, ASU Theses and Dissertations can be found in the ASU Library Catalog.

Dissertations and Theses granted by Arizona State University are archived and made available through a joint effort of the ASU Graduate College and the ASU Libraries. For more information or questions about this collection contact or visit the Digital Repository ETD Library Guide or contact the ASU Graduate College at gradformat@asu.edu.

Displaying 1 - 3 of 3
Filtering by

Clear all filters

161987-Thumbnail Image.png
Description
Machine learning (ML) and deep learning (DL) has become an intrinsic part of multiple fields. The ability to solve complex problems makes machine learning a panacea. In the last few years, there has been an explosion of data generation, which has greatly improvised machine learning models. But this comes with

Machine learning (ML) and deep learning (DL) has become an intrinsic part of multiple fields. The ability to solve complex problems makes machine learning a panacea. In the last few years, there has been an explosion of data generation, which has greatly improvised machine learning models. But this comes with a cost of high computation, which invariably increases power usage and cost of the hardware. In this thesis we explore applications of ML techniques, applied to two completely different fields - arts, media and theater and urban climate research using low-cost and low-powered edge devices. The multi-modal chatbot uses different machine learning techniques: natural language processing (NLP) and computer vision (CV) to understand inputs of the user and accordingly perform in the play and interact with the audience. This system is also equipped with other interactive hardware setups like movable LED systems, together they provide an experiential theatrical play tailored to each user. I will discuss how I used edge devices to achieve this AI system which has created a new genre in theatrical play. I will then discuss MaRTiny, which is an AI-based bio-meteorological system that calculates mean radiant temperature (MRT), which is an important parameter for urban climate research. It is also equipped with a vision system that performs different machine learning tasks like pedestrian and shade detection. The entire system costs around $200 which can potentially replace the existing setup worth $20,000. I will further discuss how I overcame the inaccuracies in MRT value caused by the system, using machine learning methods. These projects although belonging to two very different fields, are implemented using edge devices and use similar ML techniques. In this thesis I will detail out different techniques that are shared between these two projects and how they can be used in several other applications using edge devices.
ContributorsKulkarni, Karthik Kashinath (Author) / Jayasuriya, Suren (Thesis advisor) / Middel, Ariane (Thesis advisor) / Yu, Hongbin (Committee member) / Arizona State University (Publisher)
Created2021
153322-Thumbnail Image.png
Description
Inductors are fundamental components that do not scale well. Their physical limitations to scalability along with their inherent losses make them the main obstacle in achieving monolithic system-on-chip platform (SoCP). For past decades researchers focused on integrating magnetic materials into on-chip inductors in the quest of achieving high inductance density

Inductors are fundamental components that do not scale well. Their physical limitations to scalability along with their inherent losses make them the main obstacle in achieving monolithic system-on-chip platform (SoCP). For past decades researchers focused on integrating magnetic materials into on-chip inductors in the quest of achieving high inductance density and quality factor (QF). The state of the art on-chip inductor is made of an enclosed magnetic thin-film around the current carrying wire for maximum flux amplification. Though the integration of magnetic materials results in enhanced inductor characteristics, this approach has its own challenges and limitations especially in power applications. The current-induced magnetic field (HDC) drives the magnetic film into its saturation state. At saturation, inductance and QF drop to that of air-core inductors, eliminating the benefits of integrating magnetic materials. Increasing the current carrying capability without substantially sacrificing benefits brought on by the magnetic material is an open challenge in power applications. Researchers continue to address this challenge along with the continuous improvement in inductance and QF for RF and power applications.

In this work on-chip inductors incorporating magnetic Co-4%Zr-4%Ta -8%B thin films were fabricated and their characteristics were examined under the influence of an externally applied DC magnetic field. It is well established that spins in magnetic materials tend to align themselves in the same direction as the applied field. The resistance of the inductor resulting from the ferromagnetic film can be changed by manipulating the orientation of magnetization. A reduction in resistance should lead to decreases in losses and an enhancement in the QF. The effect of externally applied DC magnetic field along the easy and hard axes was thoroughly investigated. Depending on the strength and orientation of the externally applied field significant improvements in QF response were gained at the expense of a relative reduction in inductance. Characteristics of magnetic-based inductors degrade with current-induced stress. It was found that applying an externally low DC magnetic field across the on-chip inductor prevents the degradation in inductance and QF responses. Examining the effect of DC magnetic field on current carrying capability under low temperature is suggested.
ContributorsKhdour, Mahmoud (Author) / Yu, Hongbin (Thesis advisor) / Pan, George (Committee member) / Goryll, Michael (Committee member) / Bearat, Hamdallah (Committee member) / Arizona State University (Publisher)
Created2014
158419-Thumbnail Image.png
Description
Object detection is an interesting computer vision area that is concerned with the detection of object instances belonging to specific classes of interest as well as the localization of these instances in images and/or videos. Object detection serves as a vital module in many computer vision based applications. This work

Object detection is an interesting computer vision area that is concerned with the detection of object instances belonging to specific classes of interest as well as the localization of these instances in images and/or videos. Object detection serves as a vital module in many computer vision based applications. This work focuses on the development of object detection methods that exhibit increased robustness to varying illuminations and image quality. In this work, two methods for robust object detection are presented.

In the context of varying illumination, this work focuses on robust generic obstacle detection and collision warning in Advanced Driver Assistance Systems (ADAS) under varying illumination conditions. The highlight of the first method is the ability to detect all obstacles without prior knowledge and detect partially occluded obstacles including the obstacles that have not completely appeared in the frame (truncated obstacles). It is first shown that the angular distortion in the Inverse Perspective Mapping (IPM) domain belonging to obstacle edges varies as a function of their corresponding 2D location in the camera plane. This information is used to generate object proposals. A novel proposal assessment method based on fusing statistical properties from both the IPM image and the camera image to perform robust outlier elimination and false positive reduction is also proposed.

In the context of image quality, this work focuses on robust multiple-class object detection using deep neural networks for images with varying quality. The use of Generative Adversarial Networks (GANs) is proposed in a novel generative framework to generate features that provide robustness for object detection on reduced quality images. The proposed GAN-based Detection of Objects (GAN-DO) framework is not restricted to any particular architecture and can be generalized to several deep neural network (DNN) based architectures. The resulting deep neural network maintains the exact architecture as the selected baseline model without adding to the model parameter complexity or inference speed. Performance results provided using GAN-DO on object detection datasets establish an improved robustness to varying image quality and a higher object detection and classification accuracy compared to the existing approaches.
ContributorsPrakash, Charan Dudda (Author) / Karam, Lina (Thesis advisor) / Abousleman, Glen (Committee member) / Jayasuriya, Suren (Committee member) / Yu, Hongbin (Committee member) / Arizona State University (Publisher)
Created2020