Digital Commons Network^™

Systematic Comparison Of Reservoir Computing Frameworks, Nihar S. Koppolu, Christof Teuscher

Student Research Symposium

In this poster, we present a systematic evaluation and comparison of five Reservoir computing (RC) software simulation frameworks, namely reservoirpy, RcTorch, pyRCN, pytorch-esn, and ReservoirComputing.jl. RC is a specific machine learning approach that leverages fixed, nonlinear systems to map signals into higher dimensions. Its unique strength lies in training only the readout layer, which reduces the training complexity. RC excels in temporal signal processing and is also well suited for various physical implementations. The increasing interest in RC has led to the proliferation of various RC simulation frameworks. Our RC simulation framework evaluation focuses on a feature comparison, documentation quality, …

Energy-Efficient Neuromorphic Architectures For Nuclear Radiation Detection Applications, Jorge I. Canales-Verdial, Jamison R. Wagner, Landon A. Schmucker, Mark Wetzel, Nathan J. Withers, Philippe Erol Proctor, Christof Teuscher, Multiple Additional Authors

Electrical and Computer Engineering Faculty Publications and Presentations

A comprehensive analysis and simulation of two memristor-based neuromorphic architectures for nuclear radiation detection is presented. Both scalable architectures retrofit a locally competitive algorithm to solve overcomplete sparse approximation problems by harnessing memristor crossbar execution of vector–matrix multiplications. The proposed systems demonstrate excellent accuracy and throughput while consuming minimal energy for radionuclide detection. To ensure that the simulation results of our proposed hardware are realistic, the memristor parameters are chosen from our own fabricated memristor devices. Based on these results, we conclude that memristor-based computing is the preeminent technology for a radiation detection platform.

Interlacing Unstructured Data With Deep Neural Nets For Predicting Pervious And Impervious Land Cover Types, Srivani Athmakur

Theses

This research delves into the intricate task of delineating land cover types in Tallahassee-Leon County and emphasizes the need for detailed granularity beyond existing classification systems. Utilizing cutting-edge GIS data, the study harnesses the power of deep learning algorithms, including U-net, UNetPlusPlus, FPNnet, and DeepLabV3Plus. A unique approach, ”Interlacing Unstructured Data with Deep Neural Nets,” integrates shapefiles and Tiff images to enhance classification metrics such as mean intersection over union, pixel accuracy, and loss functions. The research aspires to significantly improve the precision of land cover classification, holding implications for urban planning and environmental management. By innovatively integrating unstructured data, …

Synthetic Image Generation And The Use Of Virtual Environments For Image Enhancement Tasks, Neil Patrick Del Gallego

Software Technology Dissertations

Deep learning networks are often difficult to train if there are insufficient image samples. Gathering real-world images tailored for a specific job takes a lot of work to perform. This dissertation explores techniques for synthetic image generation and virtual environments for various image enhancement/ correction/restoration tasks, specifically distortion correction, dehazing, shadow removal, and intrinsic image decomposition. First, given various image formation equations, such as those used in distortion correction and dehazing, synthetic image samples can be produced, provided that the equation is well-posed. Second, using virtual environments to train various image models is applicable for simulating real-world effects that are …

An Evaluation Of The Robustness Of The Natural-Adversarial Mutual Information-Based Defense And Malware Classification Against Adversarial Attacks For Deep Learning, David Schwab

Masters Theses and Doctoral Dissertations

In today’s technology driven world, the use of Machine Learning (ML) systems is becoming ubiquitous, albeit often in the background, in many areas of daily life. ML systems are being used to detect malware, control autonomous vehicles, classify images, assist with medical diagnosis, and block internet ads with high precision. Although the use of these ML systems has become widespread in our society, there is the potential for systems used in high-stakes situations to make faulty predictions that can have serious consequences. Recently researchers have shown that even deep neural networks (DNNs) can be “fooled” into misclassifying an input sample …

Toward Efficient Rendering: A Neural Network Approach, Qiqi Hou

Dissertations and Theses

Physically-based image synthesis has attracted considerable attention due to its wide applications in visual effects, video games, design visualization, and simulation. However, obtaining visually satisfactory renderings with ray tracing algorithms often requires casting a large number of rays and thus takes a vast amount of computation. The extensive computational and memory requirements of ray tracing methods pose a challenge, especially when running these rendering algorithms on resource-constrained platforms, and impede their applications that require high resolutions and refresh rates. This thesis presents three methods to address the challenge of efficient rendering.

First, we present a hybrid rendering method to speed …

Application Of Machine Learning Techniques For Traffic State Estimation, Pattern Recognition, And Crash Detection, Muhammad Usama

Dissertations

In the quest to optimize traffic management through machine learning (ML), this dissertation delves into three foundational areas: Traffic state estimation (TSE), traffic pattern classification, and traffic crash detection. The first facet of this dissertation focuses on TSE. Traditionally, TSE methods are categorized into two approaches: model and data-driven methodologies, each with its limitations. Data-driven ML models can falter with limited training data or misleading samples. Moreover, their “black-box” nature makes them hard to interpret. This research introduces a physics-based neural network (PINN) framework that combines the strengths of both TSE methods. The presented approach uses limited observational speed data …

Sequential Frame-Interpolation And Dct-Based Video Compression Framework, Yeganeh Jalalpour, Wu-Chi Feng, Feng Liu

Computer Science Faculty Publications and Presentations

Video data is ubiquitous; capturing, transferring, and storing even compressed video data is challenging because it requires substantial resources. With the large amount of video traffic being transmitted on the internet, any improvement in compressing such data, even small, can drastically impact resource consumption. In this paper, we present a hybrid video compression framework that unites the advantages of both DCT-based and interpolation-based video compression methods in a single framework. We show that our work can deliver the same visual quality or, in some cases, improve visual quality while reducing the bandwidth by 10--20%.

Unpaired Style Transfer Conditional Generative Adversarial Network For Scanned Document Generation, David Jonathan Hawbaker

Dissertations and Theses

Neural networks are a powerful machine learning tool, especially when trained on a large dataset of relevant high-quality data. Generative adversarial networks, image super resolution and most other image manipulation neural networks require a dataset of images and matching target images for training. Collecting and compiling that data can be time consuming and expensive. This work explores an approach for building a dataset of paired document images with a matching scanned version of each document without physical printers or scanners. A dataset of these document image pairs could be used to train a generative adversarial network or image super resolution …

Deep Learning-Based Anomaly Detection For Edge-Layer Devices, Jonathan Hunter

Masters Theses and Doctoral Dissertations

This thesis work proposes a novel DL-based anomaly detection framework for IoT environments, employing higher-capacity embedded devices as a first line of defense for the IoT edge layer. In the proposed framework, embedded devices implement the DL anomaly detection engine at the network gateway and adapt to potential attacks by retraining on incoming network traffic. In order to test the feasibility of this framework, two neural network models, trained on variations of the CICIDS 2018 Intrusion Detection Data Set, are deployed and tested on the Raspberry Pi 4. Model performance metrics, including fit and evaluation time across various batch and …

Knowledge-Based Artificial Neural Network Modeling Assessment: Integrating Heterogeneous Genomics Data To Uncover Lifespan Regulation, Taylor Day

Masters Theses and Doctoral Dissertations

Biological analytics and more advanced data analysis techniques have made remarkable advancements as the area of machine learning continues to grow. More specifically, genetic modeling and neural network building are gaining interest as it becomes a fundamental piece of most model building we see today. We propose a Knowledge-Based Artificial Neural Network (KBANN) to predict phenotype while providing insight to effected subsystems. Within KBANN, the input layers are a single or group of Gene Ontology (GO) terms while each layer’s input is a single number between 0 and 1, explaining how expressed the given term is. The expression number provides …

Exposing Gan-Generated Faces Using Deep Neural Network, Hui Guo

Legacy Theses & Dissertations (2009 - 2024)

Generative adversarial network (GAN) generated high-realistic human faces are visually challenging to discern from real ones. They have been used as profile images for fake social media accounts, which leads to high negative social impacts.In this work, we explore a universal physiological cue of the eye, namely the pupil shape consistency, to identify GAN-generated faces reliably. We show that GAN-generated faces can be exposed via irregular pupil shapes. This phenomenon is caused by the lack of physiological constraints in the GAN models. We demonstrate that such artifacts exist widely in high-quality GAN-generated faces. We design an automatic method to segment …

Efficient Neuromorphic Algorithms For Gamma-Ray Spectrum Denoising And Radionuclide Identification, Merlin Phillip Carson

Dissertations and Theses

Radionuclide detection and identification are important tasks for deterring a potentially catastrophic nuclear event. Due to high levels of background radiation from both terrestrial and extraterrestrial sources, some form of noise reduction pre-processing is required for a gamma-ray spectrum prior to being analyzed by an identification algorithm so as to determine the identity of anomalous sources. This research focuses on the use of neuromorphic algorithms for the purpose of developing low power, accurate radionuclide identification devices that can filter out non-anomalous background radiation and other artifacts created by gamma-ray detector measurement equipment, along with identifying clandestine, radioactive material.

A sparse …

Proximal Policy Optimization For Radiation Source Search, Philippe Erol Proctor

Dissertations and Theses

Rapid localization and search for lost nuclear sources in a given area of interest is an important task for the safety of society and the reduction of human harm. Detection, localization and identification are based upon the measured gamma radiation spectrum from a radiation detector. The nonlinear relationship of electromagnetic wave propagation paired with the probabilistic nature of gamma ray emission and background radiation from the environment leads to ambiguity in the estimation of a source's location. In the case of a single mobile detector, there are numerous challenges to overcome such as weak source activity, multiple sources, or the …

Understanding Complex Human Activities In Videos : The Study Of Concurrent Activity Detection And Group Activity Recognition, Yi Wei

Legacy Theses & Dissertations (2009 - 2024)

Human activity understanding, as one of the most important task in video analysis, has been studied for decades. Great efforts have been made to push the activity recognition models towards effective and efficient representation learning. However, it is difficult to define an explicit semantic organization of activities, even for human. Current activity recognition benchmarks only organize the activity labels with shallow hierarchies, which hinders the development of activity recognition system.

Extensive Huffman-Tree-Based Neural Network For The Imbalanced Dataset And Its Application In Accent Recognition, Jeremy Merrill

Masters Theses and Doctoral Dissertations

To classify the data-set featured with a large number of heavily imbalanced classes, this thesis proposed an Extensive Huffman-Tree Neural Network (EHTNN), which fabricates multiple component neural network-enabled classifiers (e.g., CNN or SVM) using an extensive Huffman tree. Any given node in EHTNN can have arbitrary number of children. Compared with the Binary Huffman-Tree Neural Network (BHTNN), EHTNN may have smaller tree height, involve fewer component neural networks, and demonstrate more flexibility on handling data imbalance. Using a 16-class exponentially imbalanced audio data-set as the benchmark, the proposed EHTNN was strictly assessed based on the comparisons with alternative methods such …

Learning Graphs For Object Tracking And Counting, Shengkun Li

Legacy Theses & Dissertations (2009 - 2024)

As important problems in computer vision, object tracking and counting attract increasing amounts of attention in recent years due to its wide range of applications, such as video surveillance, human- computer interaction, smart city. Despite much progress has been made in object tracking and counting with the arriving of deep neural networks (DNN), there still remains much room for improvement to satisfy the real-world applications.

On The (Im)Practicality Of Adversarial Perturbation For Image Privacy, Arezoo Rajabi, Rakesh B. Bobba, Mike Rosulek, Charles Wright, Wu-Chi Feng

Computer Science Faculty Publications and Presentations

Image hosting platforms are a popular way to store and share images with family members and friends. However, such platforms typically have full access to images raising privacy concerns. These concerns are further exacerbated with the advent of Convolutional Neural Networks (CNNs) that can be trained on available images to automatically detect and recognize faces with high accuracy.

Recently, adversarial perturbations have been proposed as a potential defense against automated recognition and classification of images by CNNs. In this paper, we explore the practicality of adversarial perturbation based approaches as a privacy defense against automated face recognition. Specifically, we first …

View Synthesis Of Dynamic Scenes Based On Deep 3d Mask Volume, Kai-En Lin, Guowei Yang, Lei Xiao, Feng Liu, Ravi Ramamoorthi

Computer Science Faculty Publications and Presentations

Image view synthesis has seen great success in reconstructing photorealistic visuals, thanks to deep learning and various novel representations. The next key step in immersive virtual experiences is view synthesis of dynamic scenes. However, several challenges exist due to the lack of high-quality training datasets, and the additional time dimension for videos of dynamic scenes. To address this issue, we introduce a multi-view video dataset, captured with a custom 10-camera rig in 120FPS. The dataset contains 96 high-quality scenes showing various visual effects and human interactions in outdoor scenes. We develop a new algorithm, Deep 3D Mask Volume, which enables …

Vessel Trajectory Prediction Using Historical Ais Data, Jagir Laxmichand Charla

Dissertations and Theses

Maritime vessel position coordinates are important information for maritime situational planning and organization. A better estimate of future locations of the maritime vessels, from their current locations, can help maritime authorities to make planned decisions, which can be helpful to avoid traffic congestion and longer waiting times. This thesis develops a method for estimating future locations of the vessels using their current and previous locations and other data.

The motivating scenario for this work is that of determining the future locations of the vessels based on their current location and previous locations for accurate modelling of underwater acoustic noise. As …

Extending The Functional Subnetwork Approach To A Generalized Linear Integrate-And-Fire Neuron Model, Nicholas Szczecinski, Roger Quinn, Alexander J. Hunt

Mechanical and Materials Engineering Faculty Publications and Presentations

Engineering neural networks to perform specific tasks often represents a monumental challenge in determining network architecture and parameter values. In this work, we extend our previously-developed method for tuning networks of non-spiking neurons, the “Functional subnetwork approach” (FSA), to the tuning of networks composed of spiking neurons. This extension enables the direct assembly and tuning of networks of spiking neurons and synapses based on the network’s intended function, without the use of global optimization ormachine learning. To extend the FSA, we show that the dynamics of a generalized linear integrate and fire (GLIF) neuronmodel have fundamental similarities to those of …

Exploring The Potential Of Sparse Coding For Machine Learning, Sheng Yang Lundquist

Dissertations and Theses

While deep learning has proven to be successful for various tasks in the field of computer vision, there are several limitations of deep-learning models when compared to human performance. Specifically, human vision is largely robust to noise and distortions, whereas deep learning performance tends to be brittle to modifications of test images, including being susceptible to adversarial examples. Additionally, deep-learning methods typically require very large collections of training examples for good performance on a task, whereas humans can learn to perform the same task with a much smaller number of training examples.

In this dissertation, I investigate whether the use …

Flight Simulator Modeling Using Recurrent Neural Networks, Nickolas Sabatini, Andreas Natsis

Undergraduate Research & Mentoring Program

Recurrent neural networks (RNNs) are a form of machine learning used to predict future values. This project uses RNNs tor predict future values for a flight simulator. Coded in Python using the Keras library, the model demonstrates training loss and validation loss, referring to the error when training the model.

Fallen Objects: Collaborating With Artificial Intelligence In The Field Of Graphic Design, Harrison S. Gerard

University Honors Theses

In this paper, I discuss the creation, execution and reception of my digital art series Fallen Objects, in which I collaborate with a neural net to create pseudo-found objects. I explore how artists might collaborate with Artificial Intelligence obliquely, not by having the AI generate the images themselves, but instead generate input for the artists to make the images. While many artists are focused on training neural nets to replicate their own art inputs, I instead focus on working with an AI trained on external, easily-accessible data and creating images from the prompts it delivers. In this way, the AI …

Minimum Complexity Echo State Networks For Genome And Sequence Analysis, Christopher John Neighbor

Dissertations and Theses

Increasing viral illnesses threatens global human health and welfare. Due to the distribution of disease and the expense of diagnosis, it is of value to develop portable assays that can detect viral infections early. DNA molecular logic technology offers a portable detection method due to the versatility and stability of DNA and the potential of in situ computation.

Top-down engineering of these chemical logic networks can be difficult due to the difficulties of their implementation using DNA as a substrate. In this work echo state networks, a form of recurrent neural networks, were explored with the motivation that their implementation …

Information Discovery In Coronagraph Images, Jeren Suzuki

Theses

Three areas of research for information discovery in solar coronal mass ejections (CMEs) are presented. These include CME leading front detection, clustering approaches on CME catalog data, and neural network-based classication of CMEs into speed categories. In addition to describing explored methodologies, the experimental results and analyses are presented.

Uncertainty Learning In Subjective Logic And Pattern Discovery In Network Data, Adilijiang Alimu

Legacy Theses & Dissertations (2009 - 2024)

Uncertainty caused by unreliable or insufficient data and vulnerable machine learning models

Feature Extraction For Classification Of Auroral Images, Shwetha Herga

Theses

Auroras are a dynamically evolving phenomenon. Different auroral forms are correlated with various physical processes in the magnetosphere and ionosphere system. Millions of auroral images are captured every year by the modern ground-based All-Sky Imager(ASI). In dealing with data from ASI, machine learning techniques play a critical scientific role, facilitating both efficient searches and statistical studies. In this work, we manually label night-side auroral images from various Time History of Events and Macroscale Interactions during Substorms (THEMIS) all-sky imager based on the sky conditions; the labels are clear sky with auroras, cloudy with the moon, cloudy, clear-sky with the moon, …

Experimenting With A Biologically Plausible Neural Network, Dmitri Murphy

University Honors Theses

We present research on an implementation of a biologically inspired Bayesian Confidence Propagation Neural Network (BCPNN). Based on previous work by Christopher Johansson and Anders Lansner, our implementation seeks to test and understand the various properties of this model. The floating-point implementation we built uses discrete time and bit-vectors as input/output. We found that the column based BCPNN model is able to memorize a decent number of input vectors and is able to restore noisy versions of these vectors with relatively high accuracy. We examine the model’s capacity, noise recovery ability and cross-column connection influence, among other attributes. The clearest …

An Application Of Deep Learning Models To Automate Food Waste Classification, Alejandro Zachary Espinoza

Dissertations and Theses

Food wastage is a problem that affects all demographics and regions of the world. Each year, approximately one-third of food produced for human consumption is thrown away. In an effort to track and reduce food waste in the commercial sector, some companies utilize third party devices which collect data to analyze individual contributions to the global problem. These devices track the type of food wasted (such as vegetables, fruit, boneless chicken, pasta) along with the weight. Some devices also allow the user to leave the food in a kitchen container while it is weighed, so the container weight must also …