Physical Sciences and Mathematics Commons^™

A Deep Machine Learning Approach For Predicting Freeway Work Zone Delay Using Big Data, Abdullah Shabarek

Dissertations

The introduction of deep learning and big data analytics may significantly elevate the performance of traffic speed prediction. Work zones become one of the most critical factors causing congestion impact, which reduces the mobility as well as traffic safety. A comprehensive literature review on existing work zone delay prediction models (i.e., parametric, simulation and non-parametric models) is conducted in this research. The research shows the limitations of each model. Moreover, most previous modeling approaches did not consider user delay for connected freeways when predicting traffic speed under work zone conditions. This research proposes Deep Artificial Neural Network (Deep ANN) and …

Distributed Load Testing By Modeling And Simulating User Behavior, Chester Ira Parrott

LSU Doctoral Dissertations

Modern human-machine systems such as microservices rely upon agile engineering practices which require changes to be tested and released more frequently than classically engineered systems. A critical step in the testing of such systems is the generation of realistic workloads or load testing. Generated workload emulates the expected behaviors of users and machines within a system under test in order to find potentially unknown failure states. Typical testing tools rely on static testing artifacts to generate realistic workload conditions. Such artifacts can be cumbersome and costly to maintain; however, even model-based alternatives can prevent adaptation to changes in a system …

A Neat Approach To Malware Classification, Jason Do

Master's Projects

Current malware detection software often relies on machine learning, which is seen as an improvement over signature-based techniques. Problems with a machine learning based approach can arise when malware writers modify their code with the intent to evade detection. This leads to a cat and mouse situation where new models must constantly be trained to detect new malware variants. In this research, we experiment with genetic algorithms as a means of evolving machine learning models to detect malware. Genetic algorithms, which simulate natural selection, provide a way for models to adapt to continuous changes in a malware families, and thereby …

Multi-Agent Deep Reinforcement Learning For Walkers, Inhee Park

Master's Projects

This project was motivated by seeking an AI method towards Artificial General Intelligence (AGI), that is, more similar to learning behavior of human-beings. As of today, Deep Reinforcement Learning (DRL) is the most closer to the AGI compared to other machine learning methods. To better understand the DRL, we compares and contrasts to other related methods: Deep Learning, Dynamic Programming and Game Theory.

We apply one of state-of-art DRL algorithms, called Proximal Policy Op- timization (PPO) to the robot walkers locomotion, as a simple yet challenging environment, inherently continuous and high-dimensional state/action space.

The end goal of this project is …

Lidar Object Detection Utilizing Existing Cnns For Smart Cities, Vinay Ponnaganti

Master's Projects

As governments and private companies alike race to achieve the vision of a smart city — where artificial intelligence (AI) technology is used to enable self-driving cars, cashier-less shopping experiences and connected home devices from thermostats to robot vacuum cleaners — advancements are being made in both software and hardware to enable increasingly real-time, accurate inference at the edge. One hardware solution adopted for this purpose is the LiDAR sensor, which utilizes infrared lasers to accurately detect and map its surroundings in 3D. On the software side, developers have turned to artificial neural networks to make predictions and recommendations with …

End-To-End Learning Utilizing Temporal Information For Vision- Based Autonomous Driving, Dapeng Guo

Master's Projects

End-to-End learning models trained with conditional imitation learning (CIL) have demonstrated their capabilities in driving autonomously in dynamic environments. The performance of such models however is limited as most of them fail to utilize the temporal information, which resides in a sequence of observations. In this work, we explore the use of temporal information with a recurrent network to improve driving performance. We propose a model that combines a pre-trained, deeper convolutional neural network to better capture image features with a long short-term memory network to better explore temporal information. Experimental results indicate that the proposed model achieves performance gain …

Detecting Deepfakes With Deep Learning, Eric C. Tjon

Master's Projects

Advances in generative models and manipulation techniques have given rise to digitally altered videos known as deepfakes. These videos are difficult to identify for both humans and machines. Typical detection methods exploit various imperfections in deepfake videos, such as inconsistent posing and visual artifacts. In this paper, we propose a pipeline with two distinct pathways for examining individual frames and video clips. The image pathway contains a novel architecture called Eff-YNet capable of both segmenting and detecting frames from deepfake videos. It consists of a U-Net with a classification branch and an EfficientNet B4 encoder. The video pathway implements a …

Malware Classification With Gaussian Mixture Model-Hidden Markov Models, Jing Zhao

Master's Projects

Discrete hidden Markov models (HMM) are often applied to the malware detection and classification problems. However, the continuous analog of discrete HMMs, that is, Gaussian mixture model-HMMs (GMM-HMM), are rarely considered in the field of cybersecurity. In this study, we apply GMM-HMMs to the malware classification problem and we compare our results to those obtained using discrete HMMs. As features, we consider opcode sequences and entropy-based sequences. For our opcode features, GMM-HMMs produce results that are comparable to those obtained using discrete HMMs, whereas for our entropy-based features, GMM-HMMs generally improve on the classification results that we can attain with …

The Use Of Evidential Reasoning Model With Biomarkers In Pancreatic Cancer Prediction, Qianhui Fan

Master's Projects

In this project, an evidential reasoning model is built to amalgamate factors that could be used in early detection of pancreatic cancer. Our machine learning model outputs a probability of a given patient having prostate cancer based on various input variables. These variables include health history factors, such as smoking and medical history, technical artifacts, such as biopsy sequencing technology, and genomic biomarkers such as mutational, transcriptional and methylomic profiles, cfDNA, and copy number variation. The dataset used in this project is a part of The Cancer Genome Atlas (TCGA) project and was collected from the National Cancer Institute (NIH) …

Reasoning About User Feedback Under Identity Uncertainty In Knowledge Base Construction, Ariel Kobren

Doctoral Dissertations

Intelligent, automated systems that are intertwined with everyday life---such as Google Search and virtual assistants like Amazon’s Alexa or Apple’s Siri---are often powered in part by knowledge bases (KBs), i.e., structured data repositories of entities, their attributes, and the relationships among them. Despite a wealth of research focused on automated KB construction methods, KBs are inevitably imperfect, with errors stemming from various points in the construction pipeline. Making matters more challenging, new data is created daily and must be integrated with existing KBs so that they remain up-to-date. As the primary consumers of KBs, human users have tremendous potential to …

Understanding The Dynamic Visual World: From Motion To Semantics, Huaizu Jiang

Doctoral Dissertations

We live in a dynamic world, which is continuously in motion. Perceiving and interpreting the dynamic surroundings is an essential capability for an intelligent agent. Human beings have the remarkable capability to learn from limited data, with partial or little annotation, in sharp contrast to computational perception models that rely on large-scale, manually labeled data. Reliance on strongly supervised models with manually labeled data inherently prohibits us from modeling the dynamic visual world, as manual annotations are tedious, expensive, and not scalable, especially if we would like to solve multiple scene understanding tasks at the same time. Even worse, in …

Machine Learning Model Selection For Predicting Global Bathymetry, Nicholas P. Moran

University of New Orleans Theses and Dissertations

This work is concerned with the viability of Machine Learning (ML) in training models for predicting global bathymetry, and whether there is a best fit model for predicting that bathymetry. The desired result is an investigation of the ability for ML to be used in future prediction models and to experiment with multiple trained models to determine an optimum selection. Ocean features were aggregated from a set of external studies and placed into two minute spatial grids representing the earth's oceans. A set of regression models, classification models, and a novel classification model were then fit to this data and …

Bioinformatics Metadata Extraction For Machine Learning Analysis, Zachary Tom

Master's Projects

Next generation sequencing (NGS) has revolutionized the biological sciences. Today, entire genomes can be rapidly sequenced, enabling advancements in personalized medicine, genetic diseases, and more. The National Center for Biotechnology Information (NCBI) hosts the Sequence Read Archive (SRA) containing vast amounts of valuable NGS data. Recently, research has shown that sequencing errors in conventional NGS workflows are key confounding factors for detecting mutations. Various steps such as sample handling and library preparation can introduce artifacts that affect the accuracy of calling rare mutations. Thus, there is a need for more insight into the exact relationship between various steps of the …

Malware Classification Using Lstms, Dennis Dang

Master's Projects

Signature and anomaly based detection have long been quintessential techniques used in malware detection. However, these techniques have become increasingly ineffective as malware becomes more complex. Researchers have therefore turned to deep learning to construct better performing models. In this project, we create four different long-short term memory (LSTM) models and train each model to classify malware by family type. Our data consists of opcodes extracted from malware executables. We employ techniques used in natural language processing (NLP) such as word embedding and bidirection LSTMs (biLSTM). We also use convolutional neural networks (CNN). We found that our model consisting of …

Quantifying Deepfake Detection Accuracy For A Variety Of Natural Settings, Pratikkumar Prajapati

Master's Projects

Deep fakes are videos generated from a starting video of a person where that person's face has been swapped for someone else's. In this report, we describe our work to develop general, deep learning-based models to classify Deep Fake content. Our first experiments involved simple Convolution Neural Network (CNN)-based models where we varied how individual frames from the source video were passed to the CNN. These simple models tended to give low accuracy scores for discriminating fake versus non-fake videos of less than 60%. We then developed three more sophisticated models: one based on choosing test frames, one based on …

Research On Improving Maritime Emergency Management Based On Ai And Vr In Tianjin Port, Shuli Sun

Maritime Safety & Environment Management Dissertations (Dalian)

No abstract provided.

Nonparametric Bayesian Deep Learning For Scientific Data Analysis, Devanshu Agrawal

Doctoral Dissertations

Deep learning (DL) has emerged as the leading paradigm for predictive modeling in a variety of domains, especially those involving large volumes of high-dimensional spatio-temporal data such as images and text. With the rise of big data in scientific and engineering problems, there is now considerable interest in the research and development of DL for scientific applications. The scientific domain, however, poses unique challenges for DL, including special emphasis on interpretability and robustness. In particular, a priority of the Department of Energy (DOE) is the research and development of probabilistic ML methods that are robust to overfitting and offer reliable …

Development Of Computational Tools To Target Microrna, Luo Song

Dissertations & Theses (Open Access)

MicroRNAs (a.k.a, miRNAs) play an important role in disease development. However, few of their structures have been determined and structure-based computational methods remain challenging in accurately predicting their interactions with small molecules. To address this issue, my thesis is to develop integrated approaches to screening for novel inhibitors by targeting specific structure motifs in miRNAs. The project starts with implementing a tool to find potential miRNA targets with desired motifs. I combined both sequence information of miRNAs and known RNA structure data from Protein Data Bank (PDB) to predict the miRNA structure and identify the motif to target, then I …

Random Search Plus: A More Effective Random Search For Machine Learning Hyperparameters Optimization, Bohan Li

Masters Theses

Machine learning hyperparameter optimization has always been the key to improve model performance. There are many methods of hyperparameter optimization. The popular methods include grid search, random search, manual search, Bayesian optimization, population-based optimization, etc. Random search occupies less computations than the grid search, but at the same time there is a penalty for accuracy. However, this paper proposes a more effective random search method based on the traditional random search and hyperparameter space separation. This method is named random search plus. This thesis empirically proves that random search plus is more effective than random search. There are some case …

Vision-Based Analytics For Improved Ai-Driven Iot Applications, Amit Sharma

Dissertations and Theses Collection (Open Access)

Proliferation of Internet of Things (IoT) sensor systems, primarily driven by cheaper embedded hardware platforms and wide availability of light-weight software platforms, has opened up doors for large-scale data collection opportunities. The availability of massive amount of data has in-turn given way to rapidly growing machine learning models e.g. You Only Look Once (YOLO), Single-Shot-Detectors (SSD) and so on. There has been a growing trend of applying machine learning techniques, e.g., object detection, image classification, face detection etc., on data collected from camera sensors and therefore enabling plethora of vision-sensing applications namely self-driving cars, automatic crowd monitoring, traffic-flow analysis, occupancy …

Intelligent Therapeutic Robot: Design, Development, And Control, Asif Al Zubayer Swapnil

Theses and Dissertations

This research contributes to developing an Intelligent Therapeutic Robot (iTbot) designed to provide therapy to patients with upper limb impairment due to stroke, injury, and other trauma. This robot aims to implement robotic rehabilitation based on principles of motor rehabilitation and Neuroplasticity. The iTbot, as developed in this research, can provide end-effector type rehabilitation exercises in various configurations, including motion in the vertical and horizontal plane. It can provide passive, active, and active-assisted rehabilitation therapies to patients with limited upper limb mobility.

The iTbot has been designed with simplicity in mind with a minimum viability approach. With a minimum amount …

Enhanced Traffic Incident Analysis With Advanced Machine Learning Algorithms, Zhenyu Wang

Computational Modeling & Simulation Engineering Theses & Dissertations

Traffic incident analysis is a crucial task in traffic management centers (TMCs) that typically manage many highways with limited staff and resources. An effective automatic incident analysis approach that can report abnormal events timely and accurately will benefit TMCs in optimizing the use of limited incident response and management resources. During the past decades, significant efforts have been made by researchers towards the development of data-driven approaches for incident analysis. Nevertheless, many developed approaches have shown limited success in the field. This is largely attributed to the long detection time (i.e., waiting for overwhelmed upstream detection stations; meanwhile, downstream stations …

Lightweight Deep Learning For Botnet Ddos Detection On Iot Access Networks, Eric A. Mccullough

MSU Graduate Theses

With the proliferation of the Internet of Things (IoT), computer networks have rapidly expanded in size. While Internet of Things Devices (IoTDs) benefit many aspects of life, these devices also introduce security risks in the form of vulnerabilities which give hackers billions of promising new targets. For example, botnets have exploited the security flaws common with IoTDs to gain unauthorized control of hundreds of thousands of hosts, which they then utilize to carry out massively disruptive distributed denial of service (DDoS) attacks. Traditional DDoS defense mechanisms rely on detecting attacks at their target and deploying mitigation strategies toward the attacker …

Dataset And Evaluation Of Self-Supervised Learning For Panoramic Depth Estimation, Ryan Nett

Master's Theses

Depth detection is a very common computer vision problem. It shows up primarily in robotics, automation, or 3D visualization domains, as it is essential for converting images to point clouds. One of the poster child applications is self driving cars. Currently, the best methods for depth detection are either very expensive, like LIDAR, or require precise calibration, like stereo cameras. These costs have given rise to attempts to detect depth from a monocular camera (a single camera). While this is possible, it is harder than LIDAR or stereo methods since depth can't be measured from monocular images, it has to …

Attentional Parsing Networks, Marcus Karr

Master's Theses

Convolutional neural networks (CNNs) have dominated the computer vision field since the early 2010s, when deep learning largely replaced previous approaches like hand-crafted feature engineering and hierarchical image parsing. Meanwhile transformer architectures have attained preeminence in natural language processing, and have even begun to supplant CNNs as the state of the art for some computer vision tasks.

This study proposes a novel transformer-based architecture, the attentional parsing network, that reconciles the deep learning and hierarchical image parsing approaches to computer vision. We recast unsupervised image representation as a sequence-to-sequence translation problem where image patches are mapped to successive layers …

New Methods For Deep Learning Based Real-Valued Inter-Residue Distance Prediction, Jacob Barger

Theses

Background: Much of the recent success in protein structure prediction has been a result of accurate protein contact prediction--a binary classification problem. Dozens of methods, built from various types of machine learning and deep learning algorithms, have been published over the last two decades for predicting contacts. Recently, many groups, including Google DeepMind, have demonstrated that reformulating the problem as a multi-class classification problem is a more promising direction to pursue. As an alternative approach, we recently proposed real-valued distance predictions, formulating the problem as a regression problem. The nuances of protein 3D structures make this formulation appropriate, allowing predictions …

Bert Efficacy On Scientific And Medical Datasets: A Systematic Literature Review, Clayton Cohn

College of Computing and Digital Media Dissertations

Bidirectional Encoder Representations from Transformers (BERT) [Devlin et al., 2018] has been shown to be effective at modeling a multitude of datasets across a wide variety of Natural Language Processing (NLP) tasks; however, little research has been done regarding BERT’s effectiveness at modeling domain-specific datasets. Specifically, scientific and medical datasets present a particularly difficult challenge in NLP, as these types of corpora are often rife with technical jargon that is largely absent from the canonical corpora that BERT and other transfer learning models were originally trained on. This thesis is a Systematic Literature Review (SLR) of twenty-seven studies that were …

Integrating Deep Learning And Augmented Reality To Enhance Situational Awareness In Firefighting Environments, Manish Bhattarai

Electrical and Computer Engineering ETDs

We present a new four-pronged approach to build firefighter's situational awareness for the first time in the literature. We construct a series of deep learning frameworks built on top of one another to enhance the safety, efficiency, and successful completion of rescue missions conducted by firefighters in emergency first response settings. First, we used a deep Convolutional Neural Network (CNN) system to classify and identify objects of interest from thermal imagery in real-time. Next, we extended this CNN framework for object detection, tracking, segmentation with a Mask RCNN framework, and scene description with a multimodal natural language processing(NLP) framework. Third, …

Multimodal Data Fusion And Attack Detection In Recommender Systems, Mehmet Aktukmak

USF Tampa Graduate Theses and Dissertations

The commercial platforms that use recommender systems can collect relevant information to produce useful recommendations to the platform users. However, these sources usually contain missing values, imbalanced and heterogeneous data, and noisy observations. Such characteristics render the process of exploiting the information nontrivial, as one should carefully address them during the data fusion process. In addition to the degenerative characteristics, some entries can be fake, i.e., they can be the outcomes of malicious intents to manipulate the system. These entries should be eliminated before incorporation to any recommendation task. Detecting such malicious attacks quickly and accurately and then mitigating them …

Exploring Explicit And Implicit Feature Spaces In Natural Language Processing Using Self-Enrichment And Vector Space Analysis, Vincent Sippola

Electronic Thesis and Dissertation Repository

Machine Learning in Natural Language Processing (NLP) deals directly with distributed representations of words and sentences. Words are transformed into vectors of real values, called embeddings, and used as the inputs to machine learning models. These architectures are then used to solve NLP tasks such as Sentiment Analysis and Natural Language Inference. While solving these tasks many models will create word embeddings and sentence embeddings as outputs. We are interested in how we can transform and analyze these output embeddings and modify our models, to both improve the task result and give us an understanding of the spaces. To this …