Theory and Algorithms Commons^™

High Dimensional Outlier Detection, Omid Khormali

Graduate Student Theses, Dissertations, & Professional Papers

In statistics and data science, outliers are data points that differ greatly from other observations in a data set. They are important attributes of the data because they can dramatically influence patterns and relationships manifested by non-outliers. It is therefore very important to detect and adequately deal with outliers. Recently, a novel algorithm, the ROMA algorithm, has been proposed [11]. In this paper, we propose a modification of the ROMA algorithm that reduces its computational complexity from $O(n^2 m)$ to $O((n/(2^m-o(1)))^2 m)$ where $n$ is the number of data points and $m$ is the dimension of the space. And as …

Object-Based Supervised Machine Learning Regional-Scale Land-Cover Classification Using High Resolution Remotely Sensed Data, Christopher A. Ramezan

Graduate Theses, Dissertations, and Problem Reports (ETD)

High spatial resolution (HR) (1m – 5m) remotely sensed data in conjunction with supervised machine learning classification are commonly used to construct land-cover classifications. Despite the increasing availability of HR data, most studies investigating HR remotely sensed data and associated classification methods employ relatively small study areas. This work therefore drew on a 2,609 km2, regional-scale study in northeastern West Virginia, USA, to investigates a number of core aspects of HR land-cover supervised classification using machine learning. Issues explored include training sample selection, cross-validation parameter tuning, the choice of machine learning algorithm, training sample set size, and feature selection. A …

Agent-Based Modeling And Simulation Approaches In Stem Education Research, Shanna R. Simpson-Singleton, Xiangdong Che

Journal of International Technology and Information Management

The development of best practices that deliver quality STEM education to all students, while minimizing achievement gaps, have been solicited by several national agencies. ABMS is a feasible approach to provide insight into global behavior based upon the interactions amongst agents and environments. In this review, we systematically surveyed several modeling and simulation approaches and discussed their applications to the evaluation of relevant theories in STEM education. It was found that ABMS is optimal to simulate STEM education hypotheses, as ABMS will sensibly present emergent theories and causation in STEM education phenomena if the model is properly validated and calibrated.

Randomized Algorithms For Preconditioner Selection With Applications To Kernel Regression, Conner Dipaolo

HMC Senior Theses

The task of choosing a preconditioner M to use when solving a linear system Ax=b with iterative methods is often tedious and most methods remain ad-hoc. This thesis presents a randomized algorithm to make this chore less painful through use of randomized algorithms for estimating traces. In particular, we show that the preconditioner stability || I - M^-1A ||_F, known to forecast preconditioner quality, can be computed in the time it takes to run a constant number of iterations of conjugate gradients through use of sketching methods. This is in spite of folklore which …

Learning To Map The Visual And Auditory World, Tawfiq Salem

Theses and Dissertations--Computer Science

The appearance of the world varies dramatically not only from place to place but also from hour to hour and month to month. Billions of images that capture this complex relationship are uploaded to social-media websites every day and often are associated with precise time and location metadata. This rich source of data can be beneficial to improve our understanding of the globe. In this work, we propose a general framework that uses these publicly available images for constructing dense maps of different ground-level attributes from overhead imagery. In particular, we use well-defined probabilistic models and a weakly-supervised, multi-task training …

Revisiting The Isoperimetric Graph Partitioning Problem, Sravan Danda, Aditya Challa, B. S. Daya Sagar, Laurent Najman

Journal Articles

Isoperimetric graph partitioning, which is also known as the Cheeger cut, is NP-hard in its original form. In the literature, multiple modifications to this problem have been proposed to obtain approximation algorithms for clustering applications. In the context of image segmentation, a heuristic continuous relaxation to this problem introduced by Leo Grady and Eric L. Schwartz has yielded good quality results. This algorithm is based on solving a linear system of equations involving the Laplacian of the image graph. Furthermore, the same algorithm applied to a maximum spanning tree (MST) of the image graph was shown to produce similar results …

Transdimensional Transformation Based Markov Chain Monte Carlo, Moumita Das, Sourabh Bhattacharya

Journal Articles

Variable dimensional problems, where not only the parameters, but also the number of parameters are random variables, pose serious challenge to Bayesians. Although in principle the Reversible Jump Markov Chain Monte Carlo (RJMCMC) methodology is a response to such challenges, the dimension-hopping strategies need not be always convenient for practical implementation, particularly because efficient “move-types” having reasonable acceptance rates are often difficult to devise. In this article, we propose and develop a novel and general dimension-hopping MCMC methodology that can update all the parameters as well as the number of parameters simultaneously using simple deterministic transformations of some low-dimensional (often …

@Yourlocation: A Spatial Analysis Of Geotagged Tweets In The Us, Ocean Mckinney

CMC Senior Theses

This project examines the spatial network properties observable from geo-located tweet data. Conventional exploration examines characteristics of a variety of network attributes, but few employ spatial edge correlations in their analysis. Recent studies have demonstrated the improvements that these correlations contribute to drawing conclusions about network structure. This thesis expands upon social network research utilizing spatial edge correlations and presents processing and formatting techniques for JSON (JavaScript Object Notation) data.

Estimating Waterbird Abundance On Catfish Aquaculture Ponds Using An Unmanned Aerial System, Paul C. Burr, Sathishkumar Samiappan, Lee A. Hathcock, Robert J. Moorhead, Brian S. Dorr

Human–Wildlife Interactions

In this study, we examined the use of an unmanned aerial system (UAS) to monitor fish-eating birds on catfish (Ictalurus spp.) aquaculture facilities in Mississippi, USA. We tested 2 automated computer algorithms to identify bird species using mosaicked imagery taken from a UAS platform. One algorithm identified birds based on color alone (color segmentation), and the other algorithm used shape recognition (template matching), and the results of each algorithm were compared directly to manual counts of the same imagery. We captured digital imagery of great egrets (Ardea alba), great blue herons (A. herodias), …

Optimaztion Of Fantasy Basketball Lineups Via Machine Learning, James Earl

Senior Honors Theses

Machine learning is providing a way to glean never before known insights from the data that gets recorded every day. This paper examines the application of machine learning to the novel field of Daily Fantasy Basketball. The particularities of the fantasy basketball ruleset and playstyle are discussed, and then the results of a data science case study are reviewed. The data set consists of player performance statistics as well as Fantasy Points, implied team total, DvP, and player status. The end goal is to evaluate how accurately the computer can predict a player’s fantasy performance based off a chosen feature …

Marine Quay Crane Scheduling Using A Combined Modified Genetic Algorithm And Priority Rules Approach, V. H. Nguyen, D. T. Nguyen

Civil & Environmental Engineering Faculty Publications

Quay crane scheduling problem (QCSP) is the problem of the allocation of quay cranes to handle the unloading and loading of containers at seaport container terminals and defining the service sequence of vessel bays of each quay crane. The treatment of crane interference constraints and the increased in vessel size make the problem difficult to solve. Due to the growing interest in applied research for this problem, many researchers have used different algorithms and methods to obtain some solutions. This paper will propose a modified genetic algorithm combined with priority rules to deal with it. The advantage of the proposed …

On Hybrid Temporal Basis Functions For Stable Numerical Solution Of Time Domain Boundary Integral Equations, Fang Q. Hu

Mathematics & Statistics Faculty Publications

Problems in unsteady aerodynamics and aeroacoustics can sometimes be formulated as integral equations, such as the boundary integral equations. Numerical discretization of integral equations in the time domain often leads to so-called March-On-in-Time (MOT) schemes. In the literature, the temporal basis functions used in MOT schemes have been largely limited to low-order shifted Lagrange basis functions. In order to evaluate the accuracy and effectiveness of the temporal basis functions, a Fourier analysis of the temporal interpolation schemes is carried out. Based on the Fourier analysis, the spectral resolutions of various temporal basis functions are quantified. It is argued that hybrid …

Building Recommendation Systems, Orion Davis

Williams Honors College, Honors Research Projects

Recommendation systems are pieces of software that suggest new items to a user. There are many moving parts to these systems including data, the actual recommendation model, processing data and finally displaying data. This project explores the role each part plays in the overall system and how to develop a recommendation system for beer from scratch. This project highlights the algorithm behind the recommendations and a user facing Android application.

Absorption Calculator: A Cross-Platform Application For Portable Data Analysis, Annmarie Kolbl

Williams Honors College, Honors Research Projects

Traditional spectrometers are expensive and non-portable, making them inaccessible to the public. This application will be used in conjunction with spectrometer hardware developed by Erie Open Systems. The hardware itself is 3D printed and, in addition to being portable, enables data to be collected easily. The purpose of this project is to create a cross-platform application capable of reading the output from the spectrometer hardware, calculating the absorbance levels of the sample against the control, and recording the data in tables stored on the cloud. The end result will be an application that runs on iOS and Android, and is …

A Hott Approach To Computational Effects, Phillip A. Wells

Senior Independent Study Theses

A computational effect is any mutation of real-world state that occurs as the result of a computation. We develop a model for describing computational effects within homotopy type theory, a branch of mathematics separate from other foundations such as set theory. Such a model allows us to describe programs as total functions over values while preserving information about the effects those programs induce.

Pharmaceutical Scheduling Using Simulated Annealing And Steepest Descent Method, Bryant Jamison Spencer

Graduate Theses, Dissertations, and Problem Reports (ETD)

In the pharmaceutical manufacturing world, a deadline could be the difference between losing a multimillion-dollar contract or extending it. This, among many other reasons, is why good scheduling methods are vital. This problem report addresses Flexible Flowshop (FF) scheduling using Simulated Annealing (SA) in conjunction with the Steepest Descent heuristic (SD).

FF is a generalized version of the flowshop problem, where each product goes through S number of stages, where each stage has M number of machines. As opposed to a normal flowshop problem, all ‘jobs’ do not have to flow in the same sequence from stage to stage. The …

Analyzing Satisfiability And Refutability In Selected Constraint Systems, Piotr Jerzy Wojciechowski

Graduate Theses, Dissertations, and Problem Reports (ETD)

This dissertation is concerned with the satisfiability and refutability problems for several constraint systems. We examine both Boolean constraint systems, in which each variable is limited to the values true and false, and polyhedral constraint systems, in which each variable is limited to the set of real numbers R in the case of linear polyhedral systems or the set of integers Z in the case of integer polyhedral systems. An important aspect of our research is that we focus on providing certificates. That is, we provide satisfying assignments or easily checkable proofs of infeasibility depending on whether the instance …

Quantifying Human Biological Age: A Machine Learning Approach, Syed Ashiqur Rahman

Graduate Theses, Dissertations, and Problem Reports (ETD)

Quantifying human biological age is an important and difficult challenge. Different biomarkers and numerous approaches have been studied for biological age prediction, each with its advantages and limitations. In this work, we first introduce a new anthropometric measure (called Surface-based Body Shape Index, SBSI) that accounts for both body shape and body size, and evaluate its performance as a predictor of all-cause mortality. We analyzed data from the National Health and Human Nutrition Examination Survey (NHANES). Based on the analysis, we introduce a new body shape index constructed from four important anthropometric determinants of body shape and body size: body …

Separability And Vertex Ordering Of Graphs, Elizabeth Gorbonos

Theses and Dissertations (Comprehensive)

Many graph optimization problems, such as finding an optimal coloring, or a largest clique, can be solved by a divide-and-conquer approach. One such well-known technique is decomposition by clique separators where a graph is decomposed into special induced subgraphs along their clique separators. While the most common practice of this method employs minimal clique separators, in this work we study other variations as well. We strive to characterize their structure and in particular the bound on the number of atoms. In fact, we strengthen the known bounds for the general clique cutset decomposition and the minimal clique separator decomposition. Graph …

Hedonic Coalition Formation For Task Allocation With Heterogeneous Robots, Emily Czarnecki

UNF Graduate Theses and Dissertations

Tasks in the real world are complex in nature and often require multiple robots to collaborate in order to be accomplished. However, multiple robots with the same set of sensors working together might not be the optimal solution. In many cases a task might require different sensory inputs and outputs. However, allocating a large variety of sensors on each robot is not a cost-effective solution. As such, robots with different attributes must be considered. In this thesis we study the coalition formation problem for task allocation with multiple heterogeneous (equipped with a different set of sensors) robots. The proposed solution …

Vertex Coloring With Forbidden Subgraphs, Yingjun Dai

Theses and Dissertations (Comprehensive)

Given a set $L$ of graphs, a graph $G$ is $L$-free if $G$ does not contain any graph in $L$ as induced subgraph. A $hole$ is an induced cycle of length at least $4$. A $hole$-$twin$ is a graph obtained by adding a vertex adjacent to three consecutive vertices in a $hole$. Hole-twins are closely related to the characterization of the line graphs in terms of forbidden subgraphs.

By using {\it clique-width} and {\it perfect graphs} theory, we show that ($claw$,$4K_1$,$hole$-$twin$)-free graphs and ($4K_1$,$hole$-$twin$,$5$-$wheel$)-free graphs are either perfect or have bounded clique-width. And thus the coloring of them can be …

Large Scale Online Multiple Kernel Regression With Application To Time-Series Prediction, Doyen Sahoo, Steven C. H. Hoi, Bin Lin

Research Collection School Of Computing and Information Systems

Kernel-based regression represents an important family of learning techniques for solving challenging regression tasks with non-linear patterns. Despite being studied extensively, most of the existing work suffers from two major drawbacks as follows: (i) they are often designed for solving regression tasks in a batch learning setting, making them not only computationally inefficient and but also poorly scalable in real-world applications where data arrives sequentially; and (ii) they usually assume that a fixed kernel function is given prior to the learning task, which could result in poor performance if the chosen kernel is inappropriate. To overcome these drawbacks, this work …