Physical Sciences and Mathematics Commons^™

A Survey On Few-Shot Class-Incremental Learning, Songsong Tian, Lusi Li, Weijun Li, Hang Ran, Xin Ning, Prayag Tiwari

Computer Science Faculty Publications

Large deep learning models are impressive, but they struggle when real-time data is not available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for deep neural networks to learn new tasks from just a few labeled samples without forgetting the previously learned ones. This setup can easily leads to catastrophic forgetting and overfitting problems, severely affecting model performance. Studying FSCIL helps overcome deep learning model limitations on data volume and acquisition time, while improving practicality and adaptability of machine learning models. This paper provides a comprehensive survey on FSCIL. Unlike previous surveys, we aim to synthesize few-shot learning and incremental …

Learning Mortality Risk For Covid-19 Using Machine Learning And Statistical Methods, Shaoshi Zhang

Electronic Thesis and Dissertation Repository

This research investigates the mortality risk of COVID-19 patients across different variant waves, using the data from Centers for Disease Control and Prevention (CDC) websites. By analyzing the available data, including patient medical records, vaccination rates, and hospital capacities, we aim to discern patterns and factors associated with COVID-19-related deaths.

To explore features linked to COVID-19 mortality, we employ different techniques such as Filter, Wrapper, and Embedded methods for feature selection. Furthermore, we apply various machine learning methods, including support vector machines, decision trees, random forests, logistic regression, K-nearest neighbours, na¨ıve Bayes methods, and artificial neural networks, to uncover underlying …

Robust Test Selection For Deep Neural Networks, Weifeng Sun, Meng Yan, Zhongxin Liu, David Lo

Research Collection School Of Computing and Information Systems

Deep Neural Networks (DNNs) have been widely used in various domains, such as computer vision and software engineering. Although many DNNs have been deployed to assist various tasks in the real world, similar to traditional software, they also suffer from defects that may lead to severe outcomes. DNN testing is one of the most widely used methods to ensure the quality of DNNs. Such method needs rich test inputs with oracle information (expected output) to reveal the incorrect behaviors of a DNN model. However, manually labeling all the collected test inputs is a labor-intensive task, which delays the quality assurance …

On The Computability Of Primitive Recursive Functions By Feedforward Artificial Neural Networks, Vladimir A. Kulyukin

Computer Science Faculty and Staff Publications

We show that, for a primitive recursive function h(x, t), where x is a n-tuple of natural numbers and t is a natural number, there exists a feedforward artificial neural network 𝔑(x, t), such that for any n-tuple of natural numbers z and a positive natural number m, the first m + 1 terms of the sequence {h(z, t)} are the same as the terms of the tuple (𝔑(z, 0), ... ,𝔑(z, m)).

Explainable Machine Learning Reveals The Relationship Between Hearing Thresholds And Speech-In-Noise Recognition In Listeners With Normal Audiograms, Jithin Raj Balan, Hansapani Rodrigo, Udit Saxena, Srikanta K. Mishra

School of Mathematical and Statistical Sciences Faculty Publications and Presentations

Some individuals complain of listening-in-noise difficulty despite having a normal audiogram. In this study, machine learning is applied to examine the extent to which hearing thresholds can predict speech-in-noise recognition among normal-hearing individuals. The specific goals were to (1) compare the performance of one standard (GAM, generalized additive model) and four machine learning models (ANN, artificial neural network; DNN, deep neural network; RF, random forest; XGBoost; eXtreme gradient boosting), and (2) examine the relative contribution of individual audiometric frequencies and demographic variables in predicting speech-in-noise recognition. Archival data included thresholds (0.25–16 kHz) and speech recognition thresholds (SRTs) from listeners with …

Multiclass Confidence And Localization Calibration For Object Detection, Bimsara Pathiraja, Malitha Gunawardhana, Muhammad Haris Khan

Computer Vision Faculty Publications

Albeit achieving high predictive accuracy across many challenging computer vision problems, recent studies suggest that deep neural networks (DNNs) tend to make over-confident predictions, rendering them poorly calibrated. Most of the existing attempts for improving DNN calibration are limited to classification tasks and restricted to calibrating in-domain predictions. Surprisingly, very little to no attempts have been made in studying the calibration of object detection methods, which occupy a pivotal space in vision-based security-sensitive, and safety-critical applications. In this paper, we propose a new train-time technique for calibrating modern object detection methods. It is capable of jointly calibrating multiclass confidence and …

On Correspondences Between Feedforward Artificial Neural Networks On Finite Memory Automata And Classes Of Primitive Recursive Functions, Vladimir A. Kulyukin

Computer Science Faculty and Staff Publications

When realized on computational devices with finite quantities of memory, feedforward artificial neural networks and the functions they compute cease being abstract mathematical objects and turn into executable programs generating concrete computations. To differentiate between feedforward artificial neural networks and their functions as abstract mathematical objects and the realizations of these networks and functions on finite memory devices, we introduce the categories of general and actual computabilities and show that there exist correspondences, i.e., bijections, between functions computable by trained feedforward artificial neural networks on finite memory automata and classes of primitive recursive functions.

Toward Real-Time, Robust Wearable Sensor Fall Detection Using Deep Learning Methods: A Feasibility Study, Haben Yhdego, Christopher Paolini, Michel Audette

Electrical & Computer Engineering Faculty Publications

Real-time fall detection using a wearable sensor remains a challenging problem due to high gait variability. Furthermore, finding the type of sensor to use and the optimal location of the sensors are also essential factors for real-time fall-detection systems. This work presents real-time fall-detection methods using deep learning models. Early detection of falls, followed by pneumatic protection, is one of the most effective means of ensuring the safety of the elderly. First, we developed and compared different data-segmentation techniques for sliding windows. Next, we implemented various techniques to balance the datasets because collecting fall datasets in the real-time setting has …

Deep-Learning-Based Classification Of Digitally Modulated Signals Using Capsule Networks And Cyclic Cumulants, John A. Snoap, Dimitrie C. Popescu, James A. Latshaw, Chad M. Spooner

Electrical & Computer Engineering Faculty Publications

This paper presents a novel deep-learning (DL)-based approach for classifying digitally modulated signals, which involves the use of capsule networks (CAPs) together with the cyclic cumulant (CC) features of the signals. These were blindly estimated using cyclostationary signal processing (CSP) and were then input into the CAP for training and classification. The classification performance and the generalization abilities of the proposed approach were tested using two distinct datasets that contained the same types of digitally modulated signals, but had distinct generation parameters. The results showed that the classification of digitally modulated signals using CAPs and CCs proposed in the paper …

Cooperative Deep Q -Learning Framework For Environments Providing Image Feedback, Krishnan Raghavan, Vignesh Narayanan, Sarangapani Jagannathan

Publications

In this article, we address two key challenges in deep reinforcement learning (DRL) setting, sample inefficiency, and slow learning, with a dual-neural network (NN)-driven learning approach. In the proposed approach, we use two deep NNs with independent initialization to robustly approximate the action-value function in the presence of image inputs. In particular, we develop a temporal difference (TD) error-driven learning (EDL) approach, where we introduce a set of linear transformations of the TD error to directly update the parameters of each layer in the deep NN. We demonstrate theoretically that the cost minimized by the EDL regime is an approximation …

Toward A Generative Modeling Analysis Of Clas Exclusive 2𝜋 Photoproduction, T. Alghamdi, Y. Alanazi, M. Battaglieri, Ł. Bibrzycki, A. V. Golda, A. N. Hiller Blin, E. L. Isupov, Y. Li, L. Marsicano, W. Melnitchouk, V. I. Mokeev, G. Montaña, A. Pilloni, N. Sato, A. P. Szczepaniak, T. Vittorini

Computer Science Faculty Publications

AI-supported algorithms, particularly generative models, have been successfully used in a variety of different contexts. This work employs a generative modeling approach to unfold detector effects specifically tailored for exclusive reactions that involve multiparticle final states. Our study demonstrates the preservation of correlations between kinematic variables in a multidimensional phase space. We perform a full closure test on two-pion photoproduction pseudodata generated with a realistic model in the kinematics of the Jefferson Lab CLAS g11 experiment. The overlap of different reaction mechanisms leading to the same final state associated with the CLAS detector’s nontrivial effects represents an ideal test case …

Continual Reinforcement Learning Formulation For Zero-Sum Game-Based Constrained Optimal Tracking, Behzad Farzanegan, Sarangapani Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

This study provides a novel reinforcement learning-based optimal tracking control of partially uncertain nonlinear discrete-time (DT) systems with state constraints using zero-sum game (ZSG) formulation. To address optimal tracking, a novel augmented system consisting of tracking error and its integral value, along with an uncertain desired trajectory, is constructed. A barrier function (BF) with a tradeoff factor is incorporated into the cost function to keep the state trajectories to remain within a compact set and to balance safety with optimality. Next, by using the modified value functional, the ZSG formulation is introduced wherein an actor–critic neural network (NN) framework is …

Optimal Adaptive Tracking Control Of Partially Uncertain Nonlinear Discrete-Time Systems Using Lifelong Hybrid Learning, Behzad Farzanegan, Rohollah Moghadam, Sarangapani Jagannathan, Pappa Natarajan

Electrical and Computer Engineering Faculty Research & Creative Works

This article addresses a multilayer neural network (MNN)-based optimal adaptive tracking of partially uncertain nonlinear discrete-time (DT) systems in affine form. By employing an actor–critic neural network (NN) to approximate the value function and optimal control policy, the critic NN is updated via a novel hybrid learning scheme, where its weights are adjusted once at a sampling instant and also in a finite iterative manner within the instants to enhance the convergence rate. Moreover, to deal with the persistency of excitation (PE) condition, a replay buffer is incorporated into the critic update law through concurrent learning. To address the vanishing …

Detection And Diagnosis Of Bacterial Pathogens In Blood And Urine Using Laser-Induced Breakdown Spectroscopy, Emma J.M. Blanchette

Electronic Theses and Dissertations

The aim of this thesis is to expand on and improve the existing techniques used for detecting and identifying bacterial pathogens in clinical specimens with laser-induced breakdown spectroscopy (LIBS). Specifically, the existing experimental procedures, including bacterial sample preparation and data acquisition, as well as the data analysis with chemometric algorithms were investigated. Substantial reductions in LIBS background signal were achieved by implementing rigorous cleaning steps and the introduction of the use of ultrapure water. Following this, a database of LIBS spectra was acquired from specimens of E. coli, S. aureus, E. cloacae, M. smegmatis, and P. …

Evaluation Of Artificial Neural Network Methods To Forecast Short-Term Solar Power Generation: A Case Study In Eastern Mediterranean Region, Heli̇n Bozkurt, Ramazan Maci̇t, Özgür Çeli̇k, Ahmet Teke

Turkish Journal of Electrical Engineering and Computer Sciences

Solar power forecasting is substantial for the utilization, planning, and designing of solar power plants. Global solar irradiation (GSI) and meteorological variables have a crucial role in solar power generation. The ever-changing meteorological variables and imprecise measurement of GSI raise difficulties for forecasting photovoltaic (PV) output power. In this context, a major motivation appears for the accurate forecast of GSI to perform effective forecasting of the short-term output power of a PV plant. The presented study comprises of four artificial neural network (ANN) methods; recurrent neural network (RNN) method, feedforward backpropagation neural network (FFBPNN) method, support vector regression (SVR) method, …

Artificial Neural Networks And Gradient Boosted Machines Used For Regression To Evaluate Gasification Processes: A Review, Owen Sedej, Eric Mbonimpa, Trevor Sleight, Jeremy M. Slagley

Faculty Publications

Waste-to-Energy technologies have the potential to dramatically improve both the natural and human environment. One type of waste-to-energy technology that has been successful is gasification. There are numerous types of gasification processes and in order to drive understanding and the optimization of these systems, traditional approaches like computational fluid dynamics software have been utilized to model these systems. The modern advent of machine learning models has allowed for accurate and computationally efficient predictions for gasification systems that are informed by numerous experimental and numerical solutions. Two types of machine learning models that have been widely used to solve for quantitative …

Pervasive Machine Learning For Smart Radio Environments Enabled By Reconfigurable Intelligent Surfaces, George C. Alexandropoulos, Kyriakos Stylianopoulos, Chongwen Huang, Chau Yuen, Mehdi Bennis, Mérouane Debbah

Machine Learning Faculty Publications

The emerging technology of Reconfigurable Intelligent Surfaces (RISs) is provisioned as an enabler of smart wireless environments, offering a highly scalable, low-cost, hardware-efficient, and almost energy-neutral solution for dynamic control of the propagation of electromagnetic signals over the wireless medium, ultimately providing increased environmental intelligence for diverse operation objectives. One of the major challenges with the envisioned dense deployment of RISs in such reconfigurable radio environments is the efficient configuration of multiple metasurfaces with limited, or even the absence of, computing hardware. In this paper, we consider multi-user and multi-RIS-empowered wireless systems, and present a thorough survey of the online …

Application Of Machine Learning To Predict The Performance Of An Emipg Reactor Using Data From Numerical Simulations, Owen Sedej, Eric G. Mbonimpa, Trevor Sleight, Jeremy Slagley

Faculty Publications

Microwave-driven plasma gasification technology has the potential to produce clean energy from municipal and industrial solid wastes. It can generate temperatures above 2000 K (as high as 30,000 K) in a reactor, leading to complete combustion and reduction of toxic byproducts. Characterizing complex processes inside such a system is however challenging. In previous studies, simulations using computational fluid dynamics (CFD) produced reproducible results, but the simulations are tedious and involve assumptions. In this study, we propose machine-learning models that can be used in tandem with CFD, to accelerate high-fidelity fluid simulation, improve turbulence modeling, and enhance reduced-order models. A two-dimensional …

Thermo-Fluidic Transport Process In A Novel M-Shaped Cavity Packed With Non-Darcian Porous Medium And Hybrid Nanofluid: Application Of Artificial Neural Network (Ann), Dipak Kumar Mandal, Nirmalendu Biswas, Nirmal K. Manna, Dilip Kumar Gayen, Rama S. R. Gorla, Ali J. Chamkha

Faculty Publications

In this work, an attempt has been made to explore numerically the thermo-fluidic transport process in a novel M-shaped enclosure filled with permeable material along with Al₂O₃-Cu hybrid nanoparticles suspended in water under the influence of a horizontal magnetizing field. To exercise the influence of geometric parameters, a classical trapezoidal cavity is modified with an inverted triangle at the top to construct an M-shaped cavity. The cavity is heated isothermally from the bottom and cooled from the top, whereas the inclined sidewalls are insulated. The role of geometric parameters on the thermal performance is scrutinized thoroughly …

Analysis Of Generalized Artificial Intelligence Potential Through Reinforcement And Deep Reinforcement Learning Approaches, Jonathan Turner

Theses and Dissertations

Artificial Intelligence is the next competitive domain; the first nation to develop human level artificial intelligence will have an impact similar to the development of the atomic bomb. To maintain the security of the United States and her people, the Department of Defense has funded research into the development of artificial intelligence and its applications. This research uses reinforcement learning and deep reinforcement learning methods as proxies for current and future artificial intelligence agents and to assess potential issues in development. Agent performance were compared across two games and one excursion: Cargo Loading, Tower of Hanoi, and Knapsack Problem, respectively. …

Using Generative Adversarial Networks To Augment Unmanned Aerial Vehicle Image Classification Training Sets, Benjamin J. Mccloskey

Theses and Dissertations

A challenging task in computer vision is finding techniques to improve the object detection and classification capabilities of ML models used for processing images acquired by moving aerial platforms. This research explores if GAN augmented UAV training sets can increase the generalizability of a detection model trained on said data. To answer this question, the YOLOv4-Tiny Object Detection Model was trained with aerial image training sets depicting rural environments. The salient objects within the frames were recreated using various GAN architectures, placed back into the original frames, and the augmented frames appended to the original training sets. GAN augmentation on …

Application Of Machine Learning Models With Numerical Simulations Of An Experimental Microwave Induced Plasma Gasification Reactor, Owen D. Sedej

Theses and Dissertations

This thesis aims to contribute to the future development of this technology by providing an in-depth literature review of how this technology physically operates and can be numerically modeled. Additionally, this thesis reviews literature of machine learning models that have been applied to gasification to make accurate predictions regarding the system. Finally, this thesis provides a framework of how to numerically model an experimental plasma gasification reactor in order to inform a variety of machine learning models.

Machine Learning-Based Event Generator For Electron-Proton Scattering, Y. Alanazi, P. Ambrozewicz, M. Battaglieri, A.N. Hiller Blin, M. P. Kuchera, Y. Li, T. Liu, R. E. Mcclellan, W. Melnitchouk, E. Pritchard, M. Robertson, N. Sato, R. Strauss, L. Velasco

Computer Science Faculty Publications

We present a new machine learning-based Monte Carlo event generator using generative adversarial networks (GANs) that can be trained with calibrated detector simulations to construct a vertex-level event generator free of theoretical assumptions about femtometer scale physics. Our framework includes a GAN-based detector folding as a fast-surrogate model that mimics detector simulators. The framework is tested and validated on simulated inclusive deep-inelastic scattering data along with existing parametrizations for detector simulation, with uncertainty quantification based on a statistical bootstrapping technique. Our results provide for the first time a realistic proof of concept to mitigate theory bias in inferring vertex-level event …

Deeply Learning Deep Inelastic Scattering Kinematics, Markus Diefenthaler, Abdullah Farhat, Andrii Verbytskyi, Yuesheng Xu

Mathematics & Statistics Faculty Publications

We study the use of deep learning techniques to reconstruct the kinematics of the neutral current deep inelastic scattering (DIS) process in electron–proton collisions. In particular, we use simulated data from the ZEUS experiment at the HERA accelerator facility, and train deep neural networks to reconstruct the kinematic variables Q² and x. Our approach is based on the information used in the classical construction methods, the measurements of the scattered lepton, and the hadronic final state in the detector, but is enhanced through correlations and patterns revealed with the simulated data sets. We show that, with the appropriate selection …

Eeg Signals Classification Using Lstm-Based Models And Majority Logic, James A. Orgeron

Electronic Theses and Dissertations

The study of elecroencephalograms (EEGs) has gained enormous interest in the last decade with the increase of computational power and availability of EEG signals collected from various human activities or produced during medical tests. The applicability of analyzing EEG signals ranges from helping impaired people communicate or move (using appropriate medical equipment) to understanding people's feelings and detecting diseases.

We proposed new methodology and models for analyzing and classifying EEG signals collected from individuals observing visual stimuli. Our models rely on powerful Long-Short Term Memory (LSTM) Neural Network models, which are currently the state of the art models for performing …

Forecasting Locational Marginal Prices In Electricity Markets By Using Artificial Neural Networks, Kim Jay R. Rosano, Allan C. Nerves

Journal of Economics, Management and Agricultural Development

Electricity price forecasting is an important tool used by market players in decision-making and strategizing their participation in the electricity market. In most studies, market-clearing price is forecasted as it gives an aggregated overview of system price. However, locational marginal price (LMP) gives better outlook of the price particular to the customer location in the electrical power grid. This study utilizes Artificial Neural Networks to forecast weekday LMP of generator and load nodes. Various inputs such as historical prices and demand, and temporal indices were used. Using data for selected nodes of the Philippine Wholesale Electricity Spot Market, forecast Mean …

(R1494) Approximate Solutions Of The Telegraph Equation, Ilija Jegdić

Applications and Applied Mathematics: An International Journal (AAM)

In this paper the initial boundary value problems for the linear telegraph equation in one and two space dimensions are considered. To find approximate solutions, a recently proposed optimization-free approach that utilizes artificial neural networks with one hidden layer is used, in which the connecting weights from the input layer to the hidden layer are chosen randomly and the weights from the hidden layer to the output layer are found by solving a system of linear equations. One of the advantages of this method, in comparison to the usual discretization methods for the two-dimensional linear telegraph equation, is that this …

Factors Influencing Intent To Take A Covid-19 Test In The United States, Sheila Rutto

Theses and Dissertations

In 2020, COVID-19 became the first pandemic in the world’s history that brought the entire world to an abrupt and unexpected halt. Since the first reported case of the disease to date, the novel coronavirus has been able to wreak havoc in literary every corner of the globe and left an ever-growing number of unprecedented fatalities. The normal way of life has been disrupted, and the level of uncertainty about the end of this pandemic continues to manifest to many. Due to the urgency to bring this pandemic under control, medical officers have been able to recommend actions that people …

Jmasm 55: Matlab Algorithms And Source Codes Of 'Cbnet' Function For Univariate Time Series Modeling With Neural Networks (Matlab), Cagatay Bal, Serdar Demir

Journal of Modern Applied Statistical Methods

Artificial Neural Networks (ANN) can be designed as a nonparametric tool for time series modeling. MATLAB serves as a powerful environment for ANN modeling. Although Neural Network Time Series Tool (ntstool) is useful for modeling time series, more detailed functions could be more useful in order to get more detailed and comprehensive analysis results. For these purposes, cbnet function with properties such as input lag generator, step-ahead forecaster, trial-error based network selection strategy, alternative network selection with various performance measure and global repetition feature to obtain more alternative network has been developed, and MATLAB algorithms and source codes has been …

Flying Free: A Research Overview Of Deep Learning In Drone Navigation Autonomy, Thomas Lee, Susan Mckeever, Jane Courtney

Articles

With the rise of Deep Learning approaches in computer vision applications, significant strides have been made towards vehicular autonomy. Research activity in autonomous drone navigation has increased rapidly in the past five years, and drones are moving fast towards the ultimate goal of near-complete autonomy. However, while much work in the area focuses on specific tasks in drone navigation, the contribution to the overall goal of autonomy is often not assessed, and a comprehensive overview is needed. In this work, a taxonomy of drone navigation autonomy is established by mapping the definitions of vehicular autonomy levels, as defined by the …