Computer Sciences Commons^™

Synthetic Aperture Radar Image Recognition Of Armored Vehicles, Christopher Szul, Torrey J. Wagner, Brent T. Langhals

Faculty Publications

Synthetic Aperture Radar (SAR) imagery is not affected by weather and allows for day-and-night observations, however it can be difficult to interpret. This work applies classical and neural network machine learning techniques to perform image classification of SAR imagery. The Moving and Stationary Target Acquisition and Recognition dataset from the Air Force Research Laboratory was used, which contained 2,987 total observations of the BMP-2, BTR-70, and T-72 vehicles. Using a 75%/25% train/test split, the classical model achieved an average multi-class image recognition accuracy of 70%, while a convolutional neural network was able to achieve a 97% accuracy with lower model …

Intelligent And Secure Fog-Aided Internet Of Drones, Jingjing Yao

Dissertations

Internet of drones (IoD), which utilize drones as Internet of Things (IoT) devices, deploys several drones in the air to collect ground information and send them to the IoD gateway for further processing. Computing tasks are usually offloaded to the cloud data center for intensive processing. However, many IoD applications require real-time processing and event response (e.g., disaster response and virtual reality applications). Hence, data processing by the remote cloud may not satisfy the strict latency requirement. Fog computing attaches fog nodes, which are equipped with computing, storage and networking resources, to IoD gateways to assume a substantial amount of …

Internet Of Medical Things (Iomt): Overview, Emerging Technologies, And Case Studies, Sahshanu Razdan, Sachin Sharma

Articles

No abstract provided.

Data Forgery Detection In Automatic Generation Control: Exploration Of Automated Parameter Generation And Low-Rate Attacks, Yatish R. Dubasi

Computer Science and Computer Engineering Undergraduate Honors Theses

Automatic Generation Control (AGC) is a key control system utilized in electric power systems. AGC uses frequency and tie-line power flow measurements to determine the Area Control Error (ACE). ACE is then used by the AGC to adjust power generation and maintain an acceptable power system frequency. Attackers might inject false frequency and/or tie-line power flow measurements to mislead AGC into falsely adjusting power generation, which can harm power system operations. Various data forgery detection models are studied in this thesis. First, to make the use of predictive detection models easier for users, we propose a method for automated generation …

A Framework To Detect The Susceptibility Of Employees To Social Engineering Attacks, Hashim H. Alneami

Doctoral Dissertations and Master's Theses

Social engineering attacks (SE-attacks) in enterprises are hastily growing and are becoming increasingly sophisticated. Generally, SE-attacks involve the psychological manipulation of employees into revealing confidential and valuable company data to cybercriminals. The ramifications could bring devastating financial and irreparable reputation loss to the companies. Because SE-attacks involve a human element, preventing these attacks can be tricky and challenging and has become a topic of interest for many researchers and security experts. While methods exist for detecting SE-attacks, our literature review of existing methods identified many crucial factors such as the national cultural, organizational, and personality traits of employees that enable …

Achieving Differential Privacy And Fairness In Machine Learning, Depeng Xu

Graduate Theses and Dissertations

Machine learning algorithms are used to make decisions in various applications, such as recruiting, lending and policing. These algorithms rely on large amounts of sensitive individual information to work properly. Hence, there are sociological concerns about machine learning algorithms on matters like privacy and fairness. Currently, many studies only focus on protecting individual privacy or ensuring fairness of algorithms separately without taking consideration of their connection. However, there are new challenges arising in privacy preserving and fairness-aware machine learning. On one hand, there is fairness within the private model, i.e., how to meet both privacy and fairness requirements simultaneously in …

Analog Spiking Neural Network Implementing Spike Timing-Dependent Plasticity On 65 Nm Cmos, Luke Vincent

Graduate Theses and Dissertations

Machine learning is a rapidly accelerating tool and technology used for countless applications in the modern world. There are many digital algorithms to deploy a machine learning program, but the most advanced and well-known algorithm is the artificial neural network (ANN). While ANNs demonstrate impressive reinforcement learning behaviors, they require large power consumption to operate. Therefore, an analog spiking neural network (SNN) implementing spike timing-dependent plasticity is proposed, developed, and tested to demonstrate equivalent learning abilities with fractional power consumption compared to its digital adversary.

App Development For Wearable Sensors, Connor Pittman, Christopher Chappie, Patrick A. Tetreault

Thinking Matters Symposium

The objective of this research project was to create a wearable device that monitors bodily functions for the user to view on their smartphone. Sensor data is processed using the Arduino Nano 33 BLE microcontroller. The sensors used in this project include: proximity, temperature, humidity, heart rate, pressure, and skin impedance. This project takes advantage of the Arduino's Bluetooth low energy (BLE) capabilities so that all the data can be transmitted to a smartphone. This presentation shows the challenges faced during the project and how they were overcome. Some of these challenges include: programming, how heart rate sensors work, and …

Data-Limited Domain Adaptation And Transfer Learning For Learning Latent Expression Labels Of Child Facial Expression Images, Megan Witherow, Winston Shields, Manar Samad, Khan Iftekharuddin

College of Engineering & Technology (Batten) Posters

While state-of-the-art deep learning models have demonstrated success in adult facial expression classification by leveraging large, labeled datasets, labeled data for child facial expression classification is limited. Due to differences in facial morphology and development in child and adult faces, deep learning models trained on adult data do not generalize well to child data. Recent deep domain adaptation approaches have improved the generalizability of models trained on a source domain to a target domain with few labeled samples. We propose that incorporating steps of deep transfer learning, e.g. weights initialization from the pre-trained source model and freezing model layers, may …

Integrated Cyberattack Detection And Handling For Nonlinear Systems With Evolving Process Dynamics Under Lyapunov-Based Economic Model Predictive Control, Keshav Kasturi Rangan, Henrique Oyama, Helen Durand

Chemical Engineering and Materials Science Faculty Research Publications

Safety-critical processes are becoming increasingly automated and connected. While automation can increase effciency, it brings new challenges associated with guaranteeing safety in the presence of uncertainty especially in the presence of control system cyberattacks. One of the challenges for developing control strategies with guaranteed safety and cybersecurity properties under suffcient conditions is the development of appropriate detection strategies that work with control laws to prevent undetected attacks that have immediate closed-loop stability consequences. Achieving this, in the presence of uncertainty brought about by plant/model mismatch and process dynamics that can change with time, requires a fundamental understanding of the characteristics …

Network-Based Analysis Of Early Pandemic Mitigation Strategies: Solutions, And Future Directions, Pegah Hozhabrierdi, Raymond Zhu, Maduakolam Onyewu, Sucheta Soundarajan

Northeast Journal of Complex Systems (NEJCS)

Despite the large amount of literature on mitigation strategies for pandemic spread, in practice, we are still limited by naive strategies, such as lockdowns, that are not effective in controlling the spread of the disease in long term. One major reason behind adopting basic strategies in real-world settings is that, in the early stages of a pandemic, we lack knowledge of the behavior of a disease, and so cannot tailor a more sophisticated response. In this study, we design different mitigation strategies for early stages of a pandemic and perform a comprehensive analysis among them. We then propose a novel …

Strategies In Botnet Detection And Privacy Preserving Machine Learning, Di Zhuang

USF Tampa Graduate Theses and Dissertations

Peer-to-peer (P2P) botnets have become one of the major threats in network security for serving as the infrastructure that responsible for various of cyber-crimes. Though a few existing work claimed to detect traditional botnets effectively, the problem of detecting P2P botnets involves more challenges. In this dissertation, we present two P2P botnet detection systems, PeerHunter and Enhanced PeerHunter. PeerHunter starts from a P2P hosts detection component. Then, it uses mutual contacts as the main feature to cluster bots into communities. Finally, it uses community behavior analysis to detect potential botnet communities and further identify bot candidates. Enhanced PeerHunter is an …

Indoor Navigation Using Convolutional Neural Networks And Floor Plans, Ricky D. Anderson

Theses and Dissertations

The goal of this thesis is to evaluate a new indoor navigation technique by incorporating floor plans along with monocular camera images into a CNN as a potential means for identifying camera position. Building floor plans are widely available and provide potential information for localizing within the building. This work sets out to determine if a CNN can learn the architectural features of a floor plan and use that information to determine a location. In this work, a simulated indoor data set is created and used to train two CNNs. A classification CNN, which breaks up the floor plan into …

Laser Illuminated Imaging: Beam And Scene Deconvolution Algorithm, Benjamin W. Davis

Theses and Dissertations

Laser illuminated imaging systems deal with several physical challenges that must be overcome to achieve high-resolution images of the target. Noise sources like background noise, photon counting noise, and laser speckle noise will all greatly affect the imaging systems ability to produce a high-resolution image. An even bigger challenge to laser illuminated imaging systems is atmospheric turbulence and the effect that it will have on the imaging system. The illuminating beam will experience tilt, causing the beam to wander off the center of the target during propagation. The light returning to the detector will similarly be affected by turbulence, and …

Comparison Of Conic Ray Tracing For Occlusion Determination On 3d Point Cloud Data, Henry Cho

Theses and Dissertations

The US Air Force has been increasing the use of automation in its weapon systems to include the remotely piloted aircraft (RPA) platforms. The RPA career field has had issues with poor pilot retention due to job stressors. For example, RPA operators spend a lot of time and attention surveilling a suspect on the ground for many hours, so adding automation to this activity could help improve pilot retention. The research problem in this thesis attempted to automate the process of observing a ground target. This thesis presents a method termed conic ray tracing for determining visibility and occlusion of …

Exploring The Efficiency Of Self-Organizing Software Teams With Game Theory, Clay Stevens, Jared Soundy, Hau Chan

School of Computing: Conference and Workshop Papers

Over the last two decades, software development has moved away from centralized, plan-based management toward agile methodologies such as Scrum. Agile methodologies are founded on a shared set of core principles, including self-organizing software development teams. Such teams are promoted as a way to increase both developer productivity and team morale, which is echoed by academic research. However, recent works on agile neglect to consider strategic behavior among developers, particularly during task assignment–one of the primary functions of a self-organizing team. This paper argues that self-organizing software teams could be readily modeled using game theory, providing insight into how agile …

Parking Recommender System Privacy Preservation Through Anonymization And Differential Privacy, Yasir Saleem Shaikh, Mubashir Husain Rehmani, Noel Crespi, Roberto Minerva

Publications

Recent advancements in the Internet of Things (IoT) have enabled the development of smart parking systems that use services of third-party parking recommender system to provide recommendations of personalized parking spot to users based on their past experience. However, the indiscriminate sharing of users’ data with an untrusted (or semitrusted) parking recommender system may breach the privacy because users’ behavior and mobility patterns could be inferred by analyzing their past history. Therefore, in this article, we present two solutions that preserve privacy of users in parking recommender systems while analyzing the past parking history using k-anonymity (anonymization) and differential privacy …

Statistical Analysis And Comparison Of Optical Classification Of Atmospheric Aerosol Lidar Data, Mohammed Alqawba, Norou Diawara, Kwasi G. Afrifa, Mohamed I. Elbakary, Mecit Cetin, Khan Iftekharuddin

Mathematics & Statistics Faculty Publications

In this article, we present a new study for the analysis and classification of atmospheric aerosols in remote sensing LIDAR data. Information on particle size and associated properties are extracted from these remote sensing atmospheric data which are collected by a ground-based LIDAR system. This study first considers optical LIDAR parameter-based classification methods for clustering and classification of different types of harmful aerosol particles in the atmosphere. Since accurate methods for aerosol prediction behaviors are based upon observed data, computational approaches must overcome design limitations, and consider appropriate calibration and estimation accuracy. Consequently, two statistical methods based on generalized linear …

Zooming Into The Pandemic! A Forensic Analysis Of The Zoom Application, Andrew Mahr, Meghan Cichon, Sophia Mateo, Cinthya Grajeda, Ibrahim Baggili

Electrical & Computer Engineering and Computer Science Faculty Publications

The global pandemic of COVID-19 has turned the spotlight on video conferencing applications like never before. In this critical time, applications such as Zoom have experienced a surge in its user base jump over the 300 million daily mark (ZoomBlog, 2020). The increase in use has led malicious actors to exploit the application, and in many cases perform Zoom Bombings. Therefore forensically examining Zoom is inevitable. Our work details the primary disk, network, and memory forensic analysis of the Zoom video conferencing application. Results demonstrate it is possible to find users' critical information in plain text and/or encrypted/encoded, such …

Deep Learning For Task-Based Image Quality Assessment In Medical Imaging, Weimin Zhou

McKelvey School of Engineering Graduate Student Theses & Dissertations

It has been advocated to use objective measures of image quality (IQ) for assessing and optimizing medical imaging systems. Objective measures of IQ quantify the performance of an observer at a specific diagnostic task. Binary signal detection tasks and joint signal detection and localization (detection-localization) tasks are commonly considered in medical imaging. When optimizing imaging systems for binary signal detection tasks, the performance of the Bayesian Ideal Observer (IO) has been advocated for use as a figure-of-merit (FOM). The IO maximizes the observer performance that is summarized by the receiver operating characteristic (ROC) curve. When signal detection-localization tasks are considered, …

Machine Learning Morphisms: A Framework For Designing And Analyzing Machine Learning Work Ows, Applied To Separability, Error Bounds, And 30-Day Hospital Readmissions, Eric Zenon Cawi

McKelvey School of Engineering Graduate Student Theses & Dissertations

A machine learning workflow is the sequence of tasks necessary to implement a machine learning application, including data collection, preprocessing, feature engineering, exploratory analysis, and model training/selection. In this dissertation we propose the Machine Learning Morphism (MLM) as a mathematical framework to describe the tasks in a workflow. The MLM is a tuple consisting of: Input Space, Output Space, Learning Morphism, Parameter Prior, Empirical Risk Function. This contains the information necessary to learn the parameters of the learning morphism, which represents a workflow task. In chapter 1, we give a short review of typical tasks present in a workflow, as …

Holistic Control For Cyber-Physical Systems, Yehan Ma

McKelvey School of Engineering Graduate Student Theses & Dissertations

The Industrial Internet of Things (IIoT) are transforming industries through emerging technologies such as wireless networks, edge computing, and machine learning. However, IIoT technologies are not ready for control systems for industrial automation that demands control performance of physical processes, resiliency to both cyber and physical disturbances, and energy efficiency. To meet the challenges of IIoT-driven control, we propose holistic control as a cyber-physical system (CPS) approach to next-generation industrial automation systems. In contrast to traditional industrial automation systems where computing, communication, and control are managed in isolation, holistic control orchestrates the management of cyber platforms (networks and computing platforms) …

Deep Learning Methods For Fingerprint-Based Indoor And Outdoor Positioning, Fahad Alhomayani

Electronic Theses and Dissertations

Outdoor positioning systems based on the Global Navigation Satellite System have several shortcomings that have deemed their use for indoor positioning impractical. Location fingerprinting, which utilizes machine learning, has emerged as a viable method and solution for indoor positioning due to its simple concept and accurate performance. In the past, shallow learning algorithms were traditionally used in location fingerprinting. Recently, the research community started utilizing deep learning methods for fingerprinting after witnessing the great success and superiority these methods have over traditional/shallow machine learning algorithms. The contribution of this dissertation is fourfold:

First, a Convolutional Neural Network (CNN)-based method for …

Wind Turbine Parameter Calibration Using Deep Learning Approaches, Rebecca Mccubbin

Electronic Theses and Dissertations

The inertia and damping coefficients are critical to understanding the workings of a wind turbine, especially when it is in a transient state. However, many manufacturers do not provide this information about their turbines, requiring people to estimate these values themselves. This research seeks to design a multilayer perceptron (MLP) that can accurately predict the inertia and damping coefficients using the power data from a turbine during a transient state. To do this, a model of a wind turbine was built in Matlab, and a simulation of a three-phase fault was used to collect realistic fault data to input into …

Deep Learning For High-Impedance Fault Detection: Convolutional Autoencoders, Khushwant Rai, Firouz Badrkhani Ajaei, Farnam Hojatpanah, Katarina Grolinger

Electrical and Computer Engineering Publications

High-impedance faults (HIF) are difficult to detect because of their low current amplitude and highly diverse characteristics. In recent years, machine learning (ML) has been gaining popularity in HIF detection because ML techniques learn patterns from data and successfully detect HIFs. However, as these methods are based on supervised learning, they fail to reliably detect any scenario, fault or non-fault, not present in the training data. Consequently, this paper takes advantage of unsupervised learning and proposes a convolutional autoencoder framework for HIF detection (CAE-HIFD). Contrary to the conventional autoencoders that learn from normal behavior, the convolutional autoencoder (CAE) in CAE-HIFD …

Utilizing Resonant Scattering Signal Characteristics Via Deep Learning For Improvedclassification Of Complex Targets, Tuğçe Toprak, Mustafa Alper Selver, Mustafa Seçmen, Emi̇ne Yeşi̇m Zoral

Turkish Journal of Electrical Engineering and Computer Sciences

Object classification using late-time resonant scattering electromagnetic signals is a significant problem found in different areas of application. Due to their unique properties, spherical objects play an essential role in this field both as a challenging target and a resource of analytical late-time resonant scattering electromagnetic signals. Although many studies focus on their detailed analysis, the challenges associated with target classification by resonant late-time resonant scattering electromagnetic signals from multilayer spheres have not been investigated in detail. Moreover, existing studies made the simplifying assumption that the objects having (one or more) layers constitute equal permeability values at the core and …

The Effect Of Demand Response Control On Stability Delay Margins Of Loadfrequency Control Systems With Communication Time-Delays, Deni̇z Kati̇poğlu, Şahi̇n Sönmez, Saffet Ayasun, Ausnain Naveed

Turkish Journal of Electrical Engineering and Computer Sciences

This paper studies the effect of dynamic demand response (DR) control on stability delay margins of load frequency control (LFC) systems including communication time-delays. A DR control loop is included in each control area, called as LFC-DR system and Rekasius substitution is utilized to identify stability margins for various proportionalintegral (PI) gains and participation ratios of the secondary and DR control loops. The purpose of Rekasius substitution technique is to obtain purely complex roots on the imaginary axis of the time-delayed LFC-DR system. This substitution first converts the characteristic equation of the LFC-DR system including delay-dependent exponential terms into an …

An Improved Version Of Multi-View K-Nearest Neighbors (Mvknn) For Multipleview Learning, Eli̇fe Öztürk Kiyak, Derya Bi̇rant, Kökten Ulaş Bi̇rant

Turkish Journal of Electrical Engineering and Computer Sciences

Multi-view learning (MVL) is a special type of machine learning that utilizes more than one views, where views include various descriptions of a given sample. Traditionally, classification algorithms such as k-nearest neighbors (KNN) are designed for learning from single-view data. However, many real-world applications involve datasets with multiple views and each view may contain different and partly independent information, which makes the traditional single-view classification approaches ineffective. Therefore, this article proposes an improved MVL algorithm, called multi-view k-nearest neighbors (MVKNN), based on the existing KNN algorithm. The experimental results conducted in this research show that a significant improvement is achieved …

Classification Of Neonatal Jaundice In Mobile Application With Noninvasive Imageprocessing Methods, Firat Hardalaç, Mustafa Aydin, Uğurhan Kutbay, Kubi̇lay Ayturan, Anil Akyel, Ati̇ka Çağlar, Bo Hai̇, Fati̇h Mert

Turkish Journal of Electrical Engineering and Computer Sciences

This study aims a mobile support system to aid health care professionals in hospitals or in regions far away from hospitals to utilize noninvasive image processing methods for classification of neonatal jaundice. A considerably low processing cost is aimed to be attained by developing an algorithm that could work on a mobile device with low-end camera and processor capabilities within this study. In this context, an algorithm with low cost is developed performing detection of most meaningful parameters by a multiple input single output regression model and correlation.The advantage of the proposed method is that it can estimate bilirubin with …

Semantics Of The Black-Box: Can Knowledge Graphs Help Make Deep Learning Systems More Interpretable And Explainable?, Manas Gaur, Keyur Faldu, Amit Sheth

Publications

The recent series of innovations in deep learning (DL) have shown enormous potential to impact individuals and society, both positively and negatively. The DL models utilizing massive computing power and enormous datasets have significantly outperformed prior historical benchmarks on increasingly difficult, well-defined research tasks across technology domains such as computer vision, natural language processing, signal processing, and human-computer interactions. However, the Black-Box nature of DL models and their over-reliance on massive amounts of data condensed into labels and dense representations poses challenges for interpretability and explainability of the system. Furthermore, DLs have not yet been proven in their ability to …