Physical Sciences and Mathematics Commons^™

An Application Of Deep Learning Models To Automate Food Waste Classification, Alejandro Zachary Espinoza

Dissertations and Theses

Food wastage is a problem that affects all demographics and regions of the world. Each year, approximately one-third of food produced for human consumption is thrown away. In an effort to track and reduce food waste in the commercial sector, some companies utilize third party devices which collect data to analyze individual contributions to the global problem. These devices track the type of food wasted (such as vegetables, fruit, boneless chicken, pasta) along with the weight. Some devices also allow the user to leave the food in a kitchen container while it is weighed, so the container weight must also …

Local Radiance, Scott Peter Britell

Dissertations and Theses

Recent years have seen a proliferation of web applications based on content management systems (CMS). Using a CMS, non-technical content authors are able to define custom content types to support their needs. These content type names and the attribute names in each content type are typically domain-specific and meaningful to the content authors. The ability of a CMS to support a multitude of content types allows for endless creation and customization but also leads to a large amount of heterogeneity within a single application. While this meaningful heterogeneity is beneficial, it introduces the problem of how to write reusable functionality …

Fractals As Basis For Design And Critique, John Charles Driscoll

Dissertations and Theses

The design profession is responding to the complex systems represented by architecture and planning by increasingly incorporating the power of computer technology into the design process. This represents a paradigm shift, and requires that designers rise to the challenge of both embracing modern technologies to perform increasingly sophisticated tasks without compromising their objective to create meaningful and environmentally sensitive architecture. This dissertation investigated computer-based fractal tools applied within a traditional architectural charette towards a design process with the potential to address the complex issues architects and planners face today. We developed and presented an algorithm that draws heavily from fractal …

Correct-By-Construction Typechecking With Scope Graphs, Katherine Imhoff Casamento

Dissertations and Theses

Dependently-typed languages are well-known for the ability to enforce program invariants through type signatures, and previous work establishes the effectiveness of this style of program verification in the implementation of type-safe interpreters for a wide class of languages with a variety of interesting scoping semantics, offering an account of dynamic semantics. This thesis covers the complementary topic of static semantics, in the form of a pattern for constructing verified typechecking procedures in a dependently-typed setting. Implementations are given for simply-typed lambda calculus and a small procedural language as well as a module system with unrestricted cyclic module dependency semantics that …

Sensory Relevance Models, Walt Woods

Dissertations and Theses

This dissertation concerns methods for improving the reliability and quality of explanations for decisions based on Neural Networks (NNs). NNs are increasingly part of state-of-the-art solutions for a broad range of fields, including biomedical, logistics, user-recommendation engines, defense, and self-driving vehicles. While NNs form the backbone of these solutions, they are often viewed as "black box" solutions, meaning the only output offered is a final decision, with no insight into how or why that particular decision was made. For high-stakes fields, such as biomedical, where lives are at risk, it is often more important to be able to explain a …

Versatile Binary-Level Concolic Testing, Bo Chen

Dissertations and Theses

Computing systems are experiencing an explosive growth, both in complexities and diversities, ushered in by the proliferation of cloud computing, mobile computing, and Internet of Things. This growth has also exposed the consequences of unsafe, insecure, and unreliable computing systems. These all point to the great needs of sophisticated system validation techniques. Recent advances in research on symbolic execution has shown great promises for automated software analysis, e.g., generating test cases, finding bugs, and detecting security vulnerabilities. However, symbolic execution is mostly adopted to analyze user applications, while modern computing systems in practice consist of many components shipped by various …

A Secure Anti-Counterfeiting System Using Near Field Communication, Public Key Cryptography, Blockchain, And Bayesian Games, Naif Saeed Alzahrani

Dissertations and Theses

Counterfeit products, especially in the pharmaceutical sector, have plagued the international community for decades. To combat this problem, many anti-counterfeiting approaches have been proposed. They use either Radio Frequency Identification (RFID) or Near Field Communication (NFC) physical tags affixed to the products. Current anti-counterfeiting approaches detect two counterfeiting attacks: (1) modifications to a product's tag details, such as changing the expiration date; and (2) cloning of a genuine product's details to reuse on counterfeit products. In addition, these anti-counterfeiting approaches track-and-trace the physical locations of products as the products flow through supply chains.

Existing approaches suffer from two main drawbacks. …

Design And Experimental Evaluation Of Deepmarket: An Edge Computing Marketplace With Distributed Tensorflow Execution Capability, Soyoung Kim

Dissertations and Theses

There is a rise in demand among machine learning researchers for powerful computational resources to train complex machine learning models, e.g., deep learning models. In order to train these models in a reasonable amount of time, the training is often distributed among multiple machines; yet paying for such machines (either through renting them on cloud data centers or building a local infrastructure) is costly. DeepMarket attempts to reduce these costs by creating a marketplace that integrates multiple computational resources over a distributed TensorFlow framework. Instead of requiring users to rent expensive GPU/CPUs from a third-party cloud provider, DeepMarket allows users …

Context-Aware Wi-Fi Infrastructure-Based Indoor Positioning Systems, Huy Phuong Tran

Dissertations and Theses

Large enterprises are often interested in tracking objects and people within buildings to improve resource allocation and occupant experience. Infrastructure-based indoor positioning systems (IIPS) can provide this service at low-cost by leveraging already deployed Wi-Fi infrastructure. Typically, IIPS perform localization and tracking of devices by measuring only Wi-Fi signals at wireless access points and do not rely on inertial sensor data at mobile devices (e.g., smartphones), which would require explicit user consent and sensing capabilities of the devices.

Despite these advantages, building an economically viable cost-effective IIPS that can accurately and simultaneously track many devices over very large buildings is …

Crumpled And Abraded Encryption: Implementation And Provably Secure Construction, Scott Sherlock Griffy

Dissertations and Theses

Abraded and crumpled encryption allows communication software such as messaging platforms to ensure privacy for their users while still allowing for some investigation by law enforcement. Crumpled encryption ensures that each decryption is costly and prevents law enforcement from performing mass decryption of messages. Abrasion ensures that only large organizations like law enforcement are able to access any messages. The current abrasion construction uses public key parameters such as prime numbers which makes the abrasion scheme difficult to analyze and allows possible backdoors. In this thesis, we introduce a new abrasion construction which uses hash functions to avoid the problems …

Localizing Little Landmarks With Transfer Learning, Sharad Kumar

Dissertations and Theses

Locating a small object in an image -- like a mouse on a computer desk or the door handle of a car -- is an important computer vision problem to solve because in many real life situations a small object may be the first thing that gets operated upon in the image scene. While a significant amount of artificial intelligence and machine learning research has focused on localizing prominent objects in an image, the area of small object detection has remained less explored. In my research I explore the possibility of using context information to localize small objects in an …

Spectral Clustering For Electrical Phase Identification Using Advanced Metering Infrastructure Voltage Time Series, Logan Blakely

Dissertations and Theses

The increasing demand for and prevalence of distributed energy resources (DER) such as solar power, electric vehicles, and energy storage, present a unique set of challenges for integration into a legacy power grid, and accurate models of the low-voltage distribution systems are critical for accurate simulations of DER. Accurate labeling of the phase connections for each customer in a utility model is one area of grid topology that is known to have errors and has implications for the safety, efficiency, and hosting capacity of a distribution system. This research presents a methodology for the phase identification of customers solely using …

Knowing Without Knowing: Real-Time Usage Identification Of Computer Systems, Leila Mohammed Hawana

Dissertations and Theses

Contemporary computers attempt to understand a user's actions and preferences in order to make decisions that better serve the user. In pursuit of this goal, computers can make observations that range from simple pattern recognition to listening in on conversations without the device being intentionally active. While these developments are incredibly useful for customization, the inherent security risks involving personal data are not always worth it. This thesis attempts to tackle one issue in this domain, computer usage identification, and presents a solution that identifies high-level usage of a system at any given moment without looking into any personal data. …

Towards Improving Accuracy And Interpretability Of Deep Learning Based On Satellite Image Classification, Yamile Patino Vargas

Dissertations and Theses

ABSTRACT

The study of satellite images provides a way to monitor changes in the surface of the Earth and the atmosphere. Convolutional Neural Networks (CNN) have shown accurate results in solving practical problems in multiple fields. Some of the more recognized fields using CNNs are satellite imagery processing, medicine, communication, transportation, and computer vision. Despite the success of CNNs, there remains a need to explain the network predictions further and understand what the network is determining as valuable information.

There are several frameworks and methodologies developed to explain how CNNs predict outputs and what their internal representations are [1, 4, …