Physical Sciences and Mathematics Commons^™

Color Separation For Background Subtraction, Jiaqi Zhou

Electronic Thesis and Dissertation Repository

Background subtraction is a vital step in many computer vision systems. In background subtraction, one is given two (or more) frames of a video sequence taken with a still camera. Due to the stationarity of the camera, any color change in the scene is mainly due to the presence of moving objects. The goal of background subtraction is to separate the moving objects (also called the foreground) from the stationary background. Many background subtraction approaches have been proposed over the years. They are usually composed of two distinct stages, background modeling and foreground detection.

Most of the standard background subtraction …

Cultural Diversity In Artificial Societies: Case Studies Of The Maya Peoples, Roberto Ulloa

Electronic Thesis and Dissertation Repository

The existence of cultural diversity in a connected world is paradoxical given that all individuals constantly interact and share information, and that individuals are all part of one giant network of connections. In the long term, it seems logical to assume that everybody should hold the same cultural information and, therefore, the same culture. Yet cultural diversity is still manifest around the globe. Cultural diversity as a phenomenon becomes even more puzzling when we take into account how it survives catastrophic events which regularly befall societies, such as invasions, natural disasters, and civil wars. In this thesis, agent-based computer simulations …

Molecular Distance Maps: An Alignment-Free Computational Tool For Analyzing And Visualizing Dna Sequences' Interrelationships, Rallis Karamichalis

Electronic Thesis and Dissertation Repository

In an attempt to identify and classify species based on genetic evidence, we propose a novel combination of methods to quantify and visualize the interrelationships between thousand of species. This is possible by using Chaos Game Representation (CGR) of DNA sequences to compute genomic signatures which we then compare by computing pairwise distances. In the last step, the original DNA sequences are embedded in a high dimensional space using Multi-Dimensional Scaling (MDS) before everything is projected on a Euclidean 3D space.

To start with, we apply this method to a mitochondrial DNA dataset from NCBI containing over 3,000 species. The …

A Data Fusion Approach To Automated Decision Making In Intelligent Vehicles, Besat Zardosht

Electronic Thesis and Dissertation Repository

The goal of an intelligent transportation system is to increase safety, convenience and efficiency in driving. Besides these obvious advantages, the integration of intelligent features and autonomous functionalities on vehicles will lead to major economic benefits from reduced fuel consumption to efficient exploitation of the road network.

While giving this information to the driver can be useful, there is also the possibility of overloading the driver with too much information. Existing vehicles already have some mechanisms to take certain actions if the driver fails to act. Future vehicles will need more complex decision making modules which receive the raw data …

Agora: A Knowledge Marketplace For Machine Learning, Mauro Ribeiro

Electronic Thesis and Dissertation Repository

More and more data are becoming part of people's lives. With the popularization of technologies like sensors, and the Internet of Things, data gathering is becoming possible and accessible for users. With these data in hand, users should be able to extract insights from them, and they want results as soon as possible. Average users have little or no experience in data analytics and machine learning and are not great observers who can collect enough data to build their own machine learning models. With large quantities of similar data being generated around the world and many machine learning models being …

Using Physical And Social Sensors In Real-Time Data Streaming For Natural Hazard Monitoring And Response, Yelena Kropivnitskaya

Electronic Thesis and Dissertation Repository

Technological breakthroughs in computing over the last few decades have resulted in important advances in natural hazards analysis. In particular, integration of a wide variety of information sources, including observations from spatially-referenced physical sensors and new social media sources, enables better estimates of real-time hazard. The main goal of this work is to utilize innovative streaming algorithms for improved real-time seismic hazard analysis by integrating different data sources and processing tools into cloud applications. In streaming algorithms, a sequence of items from physical and social sensors can be processed in as little as one pass with no need to store …

Advanced Driving Assistance Prediction Systems, Maedeh Hesabgar

Electronic Thesis and Dissertation Repository

Future automobiles are going to experience a fundamental evolution by installing semiotic predictor driver assistance equipment. To meet these equipment, Continuous driving-behavioral data have to be observed and processed to construct powerful predictive driving assistants. In this thesis, we focus on raw driving-behavioral data and present a prediction method which is able to prognosticate the next driving-behavioral state. This method has been constructed based on the unsupervised double articulation analyzer method (DAA) which is able to segment meaningless continuous driving-behavioral data into a meaningful sequence of driving situations. Thereafter, our novel model by mining the sequences of driving situations can …