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

Clear all filters

190759-Thumbnail Image.png

Knowledge Distillation with Geometric Approaches for Multimodal Data Analysis

Description
This thesis presents robust and novel solutions using knowledge distillation with geometric approaches and multimodal data that can address the current challenges in deep learning, providing a comprehensive understanding of the learning process involved in knowledge distillation. Deep learning has attained significant success in various applications, such as health and…

This thesis presents robust and novel solutions using knowledge distillation with geometric approaches and multimodal data that can address the current challenges in deep learning, providing a comprehensive understanding of the learning process involved in knowledge distillation. Deep learning has attained significant success in various applications, such as health and wellness promotion, smart homes, and intelligent surveillance. In general, stacking more layers or increasing the number of trainable parameters causes deep networks to exhibit improved performance. However, this causes the model to become large, resulting in an additional need for computing and power resources for training, storage, and deployment. These are the core challenges in incorporating such models into small devices with limited power and computational resources. In this thesis, robust solutions aimed at addressing the aforementioned challenges are presented. These proposed methodologies and algorithmic contributions enhance the performance and efficiency of deep learning models. The thesis encompasses a comprehensive exploration of knowledge distillation, an approach that holds promise for creating compact models from high-capacity ones, while preserving their performance. This exploration covers diverse datasets, including both time series and image data, shedding light on the pivotal role of augmentation methods in knowledge distillation. The effects of these methods are rigorously examined through empirical experiments. Furthermore, the study within this thesis delves into the efficient utilization of features derived from two different teacher models, each trained on dissimilar data representations, including time-series and image data. Through these investigations, I present novel approaches to knowledge distillation, leveraging geometric techniques for the analysis of multimodal data. These solutions not only address real-world challenges but also offer valuable insights and recommendations for modeling in new applications.
ContributorsJeon, Eunsom (Author) / Turaga, Pavan (Thesis advisor) / Li, Baoxin (Committee member) / Lee, Hyunglae (Committee member) / Jayasuriya, Suren (Committee member) / Arizona State University (Publisher)
Created2023

Design, Fabrication, and Characterization of a Sand Burrowing Robot

Description
Unmanned subsurface investigation technologies for the Moon are of special significance for future exploration when considering the renewed interest of the international community for this interplanetary destination. In precision agriculture, farmers demand quasi-real-time sensors and instruments with remote crop and soil detection properties to meet sustainability goals and achieve healthier…

Unmanned subsurface investigation technologies for the Moon are of special significance for future exploration when considering the renewed interest of the international community for this interplanetary destination. In precision agriculture, farmers demand quasi-real-time sensors and instruments with remote crop and soil detection properties to meet sustainability goals and achieve healthier and higher crop yields. Hence, there is the need for a robot that will be able to travel through the soil and conduct sampling or in-situ analysis of the subsurface materials on earth and in space. This thesis presents the design, fabrication, and characterization of a robot that can travel through the soil. The robot consists of a helical screw design coupled with a fin that acts as an anchor. The fin design is an integral part of the robot, allowing it to travel up and down the medium unaided. Experiments were performed to characterize different designs. It was concluded that the most energy-efficient speed from traveling down the medium is 20 rpm, while 60 rpm was the efficient speed for traveling up the medium. This research provides vital insight into developing subsurface robots enabling us to unearth the valuable knowledge that subsurface environment holds to help the agricultural, construction, and exploration communities.
ContributorsOkwae, Nana Kwame Kwame (Author) / Marvi, Hamidreza (Thesis advisor) / Tao, Jungliang (Committee member) / Lee, Hyunglae (Committee member) / Arizona State University (Publisher)
Created2020