Artificial Intelligence and Robotics Commons^™

Predicting Post-Procedural Complications Using Neural Networks On Mimic-Iii Data, Namratha Mohan

LSU Master's Theses

The primary focus of this paper is the creation of a Machine Learning based algorithm for the analysis of large health based data sets. Our input was extracted from MIMIC-III, a large Health Record database of more than 40,000 patients. The main question was to predict if a patient will have complications during certain specified procedures performed in the hospital. These events are denoted by the icd9 code 996 in the individuals' health record. The output of our predictive model is a binary variable which outputs the value 1 if the patient is diagnosed with the specific complication or 0 …

Learning-Based Analysis On The Exploitability Of Security Vulnerabilities, Adam Bliss

Computer Science and Computer Engineering Undergraduate Honors Theses

The purpose of this thesis is to develop a tool that uses machine learning techniques to make predictions about whether or not a given vulnerability will be exploited. Such a tool could help organizations such as electric utilities to prioritize their security patching operations. Three different models, based on a deep neural network, a random forest, and a support vector machine respectively, are designed and implemented. Training data for these models is compiled from a variety of sources, including the National Vulnerability Database published by NIST and the Exploit Database published by Offensive Security. Extensive experiments are conducted, including testing …

Improving Ultra-Wideband Localization By Detecting Radio Misclassification, Cory A. Mayer

Master's Theses

The Global Positioning System (GPS) and other satellite-based positioning systems are often a key component in applications requiring localization. However, accurate positioning in areas with poor GPS coverage, such as inside buildings and in dense cities, is in increasing demand for many modern applications. Fortunately, recent developments in ultra-wideband (UWB) radio technology have enabled precise positioning in places where it was not previously possible by utilizing multipath-resistant wide band pulses.

Although ultra-wideband signals are less prone to multipath interference, it is still a bottleneck as increasingly ambitious projects continue to demand higher precision. Some UWB radios include on-board detection of …

A Model-Based Ai-Driven Test Generation System, Dionny Santiago

FIU Electronic Theses and Dissertations

Achieving high software quality today involves manual analysis, test planning, documentation of testing strategy and test cases, and development of automated test scripts to support regression testing. This thesis is motivated by the opportunity to bridge the gap between current test automation and true test automation by investigating learning-based solutions to software testing. We present an approach that combines a trainable web component classifier, a test case description language, and a trainable test generation and execution system that can learn to generate new test cases. Training data was collected and hand-labeled across 7 systems, 95 web pages, and 17,360 elements. …

Machine Learning Methods For Activity Detection In Wearable Sensor Data Streams, Roy Adams

Doctoral Dissertations

Wearable wireless sensors have the potential for transformative impact on the fields of health and behavioral science. Recent advances in wearable sensor technology have made it possible to simultaneously collect multiple streams of physiological and context data from individuals in natural environments; however, extracting reliable high-level inferences from these raw data streams remains a key data analysis challenge. In this dissertation, we address three challenges that arise when trying to perform activity detection from wearable sensor streams. First, we address the challenge of learning from small amounts of noisy data by proposing a class of conditional random field models for …

Cryptovisor: A Cryptocurrency Advisor Tool, Matthew Baldree, Paul Widhalm, Brandon Hill, Matteo Ortisi

SMU Data Science Review

In this paper, we present a tool that provides trading recommendations for cryptocurrency using a stochastic gradient boost classifier trained from a model labeled by technical indicators. The cryptocurrency market is volatile due to its infancy and limited size making it difficult for investors to know when to enter, exit, or stay in the market. Therefore, a tool is needed to provide investment recommendations for investors. We developed such a tool to support one cryptocurrency, Bitcoin, based on its historical price and volume data to recommend a trading decision for today or past days. This tool is 95.50% accurate with …

Transfer Learning With Mixtures Of Manifolds, Thomas Boucher

Doctoral Dissertations

Advances in scientific instrumentation technology have increased the speed of data acquisition and the precision of sampling, creating an abundance of high-dimensional data sets. The ability to combine these disparate data sets and to transfer information between them is critical to accurate scientific analysis. Many modern-day instruments can record data at many thousands of channels, far greater than the actual degrees of freedom in the sample data. This makes manifold learning, a class of methods that exploit the observation that high-dimensional data tend to lie on lower-dimensional manifolds, especially well-suited to this transfer learning task. Existing manifold-based transfer learning methods …

Non-Destructive Evaluation For Composite Material, Desalegn Temesgen Delelegn

Electrical & Computer Engineering Theses & Dissertations

The Nondestructive Evaluation Sciences Branch (NESB) at the National Aeronautics and Space Administration (NASA) Langley Research Center (LaRC) has conducted impact damage experiments over the past few years with the goal of understanding structural defects in composite materials. The Data Science Team within the NASA LaRC Office of the Chief Information Officer (OCIO) has been working with the Non-Destructive Evaluation (NDE) subject matter experts (SMEs), Dr. Cheryl Rose, from the Structural Mechanics & Concepts Branch and Dr. William Winfree, from the Research Directorate, to develop computer vision solutions using digital image processing and machine learning techniques that can help identify …

Baseline Assisted Classification Of Heart Rate Variability, Elham Harirpoush

Electronic Thesis and Dissertation Repository

Recently, among various analysis methods of physiological signals, automatic analysis of Electrocardiogram (ECG) signals, especially heart rate variability (HRV) has received significant attention in the field of machine learning. Heart rate variability is an important indicator of health prediction and it is applicable to various fields of scientific research. Heart rate variability is based on measuring the differences in time between consecutive heartbeats (also known as RR interval), and the most common measuring techniques are divided into the time domain and frequency domain. In this research study, a classifier based on analysis of HRV signal is developed to classify different …

2018 Ieee Signal Processing Cup: Forensic Camera Model Identification Challenge, Michael Geiger

Honors Theses

The goal of this Senior Capstone Project was to lead Union College’s first ever Signal Processing Cup Team to compete in IEEE’s 2018 Signal Processing Cup Competition. This year’s competition was a forensic camera model identification challenge and was divided into two separate stages of competition: Open Competition and Final Competition. Participation in the Open Competition was open to any teams of undergraduate students, but the Final Competition was only open to the three finalists from Open Competition and is scheduled to be held at ICASSP 2018 in Calgary, Alberta, Canada. Teams that make it to the Final Competition will …

Ai-Human Collaboration Via Eeg, Adam Noack

All College Thesis Program, 2016-2019

As AI becomes ever more competent and integrated into our lives, the issue of AI-human goal misalignment looms larger. This is partially because there is often a rift between what humans explicitly command and what they actually mean. Most contemporary AI systems cannot bridge this gap. In this study we attempted to reconcile the goals of human and machine by using EEG signals from a human to help a simulated agent complete a task.

Evaluating Sequence Discovery Systems In An Abstraction-Aware Manner, Eoin Rogers, Robert J. Ross, John D. Kelleher

Conference papers

Activity discovery is a challenging machine learning problem where we seek to uncover new or altered behavioural patterns in sensor data. In this paper we motivate and introduce a novel approach to evaluating activity discovery systems. Pre-annotated ground truths, often used to evaluate the performance of such systems on existing datasets, may exist at different levels of abstraction to the output of the output produced by the system. We propose a method for detecting and dealing with this situation, allowing for useful ground truth comparisons. This work has applications for activity discovery, and also for related fields. For example, it …

Parameterizing And Aggregating Activation Functions In Deep Neural Networks, Luke Benjamin Godfrey

Graduate Theses and Dissertations

The nonlinear activation functions applied by each neuron in a neural network are essential for making neural networks powerful representational models. If these are omitted, even deep neural networks reduce to simple linear regression due to the fact that a linear combination of linear combinations is still a linear combination. In much of the existing literature on neural networks, just one or two activation functions are selected for the entire network, even though the use of heterogenous activation functions has been shown to produce superior results in some cases. Even less often employed are activation functions that can adapt their …

Comparative Study Of Deep Learning Models For Network Intrusion Detection, Brian Lee, Sandhya Amaresh, Clifford Green, Daniel Engels

SMU Data Science Review

In this paper, we present a comparative evaluation of deep learning approaches to network intrusion detection. A Network Intrusion Detection System (NIDS) is a critical component of every Internet connected system due to likely attacks from both external and internal sources. A NIDS is used to detect network born attacks such as Denial of Service (DoS) attacks, malware replication, and intruders that are operating within the system. Multiple deep learning approaches have been proposed for intrusion detection systems. We evaluate three models, a vanilla deep neural net (DNN), self-taught learning (STL) approach, and Recurrent Neural Network (RNN) based Long Short …

Cognitive Virtual Admissions Counselor, Kumar Raja Guvindan Raju, Cory Adams, Raghuram Srinivas

SMU Data Science Review

Abstract. In this paper, we present a cognitive virtual admissions counselor for the Master of Science in Data Science program at Southern Methodist University. The virtual admissions counselor is a system capable of providing potential students accurate information at the time that they want to know it. After the evaluation of multiple technologies, Amazon’s LEX was selected to serve as the core technology for the virtual counselor chatbot. Student surveys were leveraged to collect and generate training data to deploy the natural language capability. The cognitive virtual admissions counselor platform is currently capable of providing an end-to-end conversational dialog to …

Using Latent Variable Models To Improve Causal Estimation, Huseyin Oktay

Doctoral Dissertations

Estimating the causal effect of a treatment from data has been a key goal for a large number of studies in many domains. Traditionally, researchers use carefully designed randomized experiments for causal inference. However, such experiments can not only be costly in terms of time and money but also infeasible for some causal questions. To overcome these challenges, causal estimation methods from observational data have been developed by researchers from diverse disciplines and increasingly studies using such methods account for a large share in empirical work. Such growing interest has also brought together two arguably separate fields: machine learning and …

Gradient Estimation For Attractor Networks, Thomas Flynn

Dissertations, Theses, and Capstone Projects

It has been hypothesized that neural network models with cyclic connectivity may be more powerful than their feed-forward counterparts. This thesis investigates this hypothesis in several ways. We study the gradient estimation and optimization procedures for several variants of these networks. We show how the convergence of the gradient estimation procedures are related to the properties of the networks. Then we consider how to tune the relative rates of gradient estimation and parameter adaptation to ensure successful optimization in these models. We also derive new gradient estimators for stochastic models. First, we port the forward sensitivity analysis method to the …

Object Localization, Segmentation, And Classification In 3d Images, Allan Zelener

Dissertations, Theses, and Capstone Projects

We address the problem of identifying objects of interest in 3D images as a set of related tasks involving localization of objects within a scene, segmentation of observed object instances from other scene elements, classifying detected objects into semantic categories, and estimating the 3D pose of detected objects within the scene. The increasing availability of 3D sensors motivates us to leverage large amounts of 3D data to train machine learning models to address these tasks in 3D images. Leveraging recent advances in deep learning has allowed us to develop models capable of addressing these tasks and optimizing these tasks jointly …

Deep Learning Of 2-D Images Representing N-D Data In General Line Coordinates, Dmytro Dovhalets, Boris Kovalerchuk, Szilárd Vajda, Răzvan Andonie

Computer Science Faculty Scholarship

While knowledge discovery and n-D data visualization procedures are often efficient, the loss of information, occlusion, and clutter continue to be a challenge. General Line Coordinates (GLC) is a rather new technique to deal with such artifacts. GLC-Linear, which is one of the methods in GLC, allows transforming n-D numerical data to their visual representation as polylines losslessly. The method proposed in this paper uses these 2-D visual representations as input to Convolutional Neural Network (CNN) classifiers. The obtained classification accuracies are close to the ones obtained by other machine learning algorithms. The main benefit of the method is the …

Rnn-Based Generation Of Polyphonic Music And Jazz Improvisation, Andrew Hannum

Electronic Theses and Dissertations

This paper presents techniques developed for algorithmic composition of both polyphonic music, and of simulated jazz improvisation, using multiple novel data sources and the character-based recurrent neural network architecture char-rnn. In addition, techniques and tooling are presented aimed at using the results of the algorithmic composition to create exercises for musical pedagogy.

Leveraging Overhead Imagery For Localization, Mapping, And Understanding, Scott Workman

Theses and Dissertations--Computer Science

Ground-level and overhead images provide complementary viewpoints of the world. This thesis proposes methods which leverage dense overhead imagery, in addition to sparsely distributed ground-level imagery, to advance traditional computer vision problems, such as ground-level image localization and fine-grained urban mapping. Our work focuses on three primary research areas: learning a joint feature representation between ground-level and overhead imagery to enable direct comparison for the task of image geolocalization, incorporating unlabeled overhead images by inferring labels from nearby ground-level images to improve image-driven mapping, and fusing ground-level imagery with overhead imagery to enhance understanding. The ultimate contribution of this thesis …

Quantitative Forecasting Of Risk For Ptsd Using Ecological Factors: A Deep Learning Application, Nuriel S. Mor, Kathryn L. Dardeck

Journal of Social, Behavioral, and Health Sciences

Forecasting the risk for mental disorders from early ecological information holds benefits for the individual and society. Computational models used in psychological research, however, are barriers to making such predictions at the individual level. Preexposure identification of future soldiers at risk for posttraumatic stress disorder (PTSD) and other individuals, such as humanitarian aid workers and journalists intending to be potentially exposed to traumatic events, is important for guiding decisions about exposure. The purpose of the present study was to evaluate a machine learning approach to identify individuals at risk for PTSD using readily collected ecological risk factors, which makes scanning …

Expanding The Artificial Intelligence-Data Protection Debate, Fred H. Cate, Christopher Kuner, Orla Lynskey, Christopher Millard, Nora Ni Loideain, Dan Jerker B. Svantesson

Articles by Maurer Faculty

No abstract provided.

Data Visualization And Classification Of Artificially Created Images, Dmytro Dovhalets

All Master's Theses

Visualization of multidimensional data is a long-standing challenge in machine learning and knowledge discovery. A problem arises as soon as 4-dimensions are introduced since we live in a 3-dimensional world. There are methods out there which can visualize multidimensional data, but loss of information and clutter are still a problem. General Line Coordinates (GLC) can losslessly project n-dimensional data in 2- dimensions. A new method is introduced based on GLC called GLC-L. This new method can do interactive visualization, dimension reduction, and supervised learning. One of the applications of GLC-L is transformation of vector data into image data. This novel …

Recurrent Neural Networks And Their Applications To Rna Secondary Structure Inference, Devin Willmott

Theses and Dissertations--Mathematics

Recurrent neural networks (RNNs) are state of the art sequential machine learning tools, but have difficulty learning sequences with long-range dependencies due to the exponential growth or decay of gradients backpropagated through the RNN. Some methods overcome this problem by modifying the standard RNN architecure to force the recurrent weight matrix W to remain orthogonal throughout training. The first half of this thesis presents a novel orthogonal RNN architecture that enforces orthogonality of W by parametrizing with a skew-symmetric matrix via the Cayley transform. We present rules for backpropagation through the Cayley transform, show how to deal with the Cayley …

Old English Character Recognition Using Neural Networks, Sattajit Sutradhar

Electronic Theses and Dissertations

Character recognition has been capturing the interest of researchers since the beginning of the twentieth century. While the Optical Character Recognition for printed material is very robust and widespread nowadays, the recognition of handwritten materials lags behind. In our digital era more and more historical, handwritten documents are digitized and made available to the general public. However, these digital copies of handwritten materials lack the automatic content recognition feature of their printed materials counterparts. We are proposing a practical, accurate, and computationally efficient method for Old English character recognition from manuscript images. Our method relies on a modern machine learning …