Engineering Commons^™

Face Representation Learning And Its Applications: From Image Editing To 3d Avatar Animation, Xudong Liu

Graduate Theses, Dissertations, and Problem Reports

Face representation learning is one of the most popular research topics in the computer vision community, as it is the foundation of face recognition and face image generation. Numerous representation learning frameworks have been integrated into applications in daily life, such as face recognition, image editing, and face tracking. Researchers have developed advanced algorithms for face recognition with successful commercial productions, for example, FaceID on the smartphone. The performance record on face recognition is constantly updated and becoming saturated with the help of large-scale datasets and advanced computational resources. Thanks to the robust representation in face recognition, in this dissertation, …

Incentive Analysis Of Blockchain Technology, Rahul Reddy Annareddy

Graduate Theses, Dissertations, and Problem Reports

Blockchain technology was invented in the Bitcoin whitepaper released in 2008. Since then, several decentralized cryptocurrencies and applications have become mainstream. There has been an immense amount of engineering effort put into developing blockchain networks. Relatively few projects backed by blockchain technology have succeeded and maintained a large community of developers, users, and customers, while many popular projects with billions of dollars in funding and market capitalizations have turned out to be complete scams.

This thesis discusses the technological innovations introduced in the Bitcoin whitepaper and the following work of the last fifteen years that has enabled blockchain technology. A …

Multimodal Adversarial Learning, Uche Osahor

Graduate Theses, Dissertations, and Problem Reports

Deep Convolutional Neural Networks (DCNN) have proven to be an exceptional tool for object recognition, generative modelling, and multi-modal learning in various computer vision applications. However, recent findings have shown that such state-of-the-art models can be easily deceived by inserting slight imperceptible perturbations to key pixels in the input. A good target detection systems can accurately identify targets by localizing their coordinates on the input image of interest. This is ideally achieved by labeling each pixel in an image as a background or a potential target pixel. However, prior research still confirms that such state of the art targets models …

Performance Of Sensor Fusion For Vehicular Applications, Nikola Janevski

Graduate Theses, Dissertations, and Problem Reports

Sensor fusion is a key system in Advanced Driver Assistance Systems, ADAS. The perfor-
mance of the sensor fusion depends on many factors such as the sensors used, the kinematic
model used in the Extended Kalman Filter, EKF, the motion of the vehicles, the type of
road, the density of vehicles, and the gating methods. The interactions between parameters
and the extent to which individual parameters contribute to the overall accuracy of a sensor
fusion system can be difficult to assess.
In this study, a full-factorial experimental evaluation of a sensor fusion system based
on a real vehicle was performed. …

Rania: A Framework For A Modular, Voice Enabled, Gerontechnology-Centric, Smart-Home System, Emily Francis

Graduate Theses, Dissertations, and Problem Reports

In the United States, the proportion of senior citizens is expected to rise significantly over the next few decades. This increasing number of senior citizens combined with the increasing demand for at home healthcare workers is putting a strain on the elderly healthcare system. Smart-home healthcare technology { such as smart medication dispensers, fall detection systems, smart pantry systems, etc. { has the potential to alleviate this strain on the elderly healthcare system. Smart devices can give an individual more autonomized and personalized surveillance of their health and well-being. While these devices are beneficial as standalone devices, they would be …

Development Of Software-Only Simulation Test Beds (Sost) For Spacecraft And Smallsats, Scott Alan Zemerick

Graduate Theses, Dissertations, and Problem Reports

Software-only-Simulation Test Beds (SoST) are beginning to become more popular among aircraft, spacecraft, and smallsat embedded system developers due to the high cost of duplicating hardware test beds.

SoSTs provide a software-only, or virtual test bed, that creates a “digital twin” that contains software models of the ETUs and often includes modeled components such as flight computers, busses (e.g., MIL-STD-1553, SPI, I2C), compact PCI (cPCI) backplane cards, sensors, and actuators. The ultimate goal of a SoST is for it to run the native system software compiled-binary on its native CPU architecture (e.g., PowerPC, LEON3/4, ARM) on a standard X86 personal …

Leveraging Writing And Photography Styles For Drug Trafficker Identification In Darknet Markets, Wei Song

Graduate Theses, Dissertations, and Problem Reports

Due to its anonymity, there has been a dramatic growth of underground drug markets hosted in the darknet (e.g., Dream Market and Valhalla). To combat drug trafficking (a.k.a. illicit drug trading) in the cyberspace, there is an urgent need for automatic analysis of participants in darknet markets. However, one of the key challenges is that drug traffickers (i.e., vendors) may maintain multiple accounts across different markets or within the same market.

To address this issue, in this thesis, we propose and develop an intelligent system named uStyle-uID leveraging both writing and photography styles for drug trafficker identification at the first …