Performance Evaluation Of Face Mask Detection For Real-Time Implementation On An Rpi, Ivan George L. Tarun, Vidal Wyatt M. Lopez, Pamela Anne C. Serrano, Patricia Angela R. Abu, Rosula Reyes, Ma. Regina Justina Estuar

Department of Information Systems & Computer Science Faculty Publications

Mask-wearing remains to be one of the primary protective measures against COVID-19. To address the difficulty of manual compliance monitoring, face mask detection models considerate of both frontal and angled faces were developed. This study aimed to test the performance of the said models in classifying multi-face images and upon running on a Raspberry Pi device. The accuracies and inference speeds were measured and compared when inferencing images with one, two, and three faces and on the desktop and the Raspberry Pi. With an increasing number of faces in an image, the models’ accuracies were observed to decline, while their …

Towards The Development Of A Blockchain System For Philippine Government Processes For Enhanced Transparency And Verifiability, Karlo Angelo F. Cabugwang, Raphael Christen K. Enriquez, Bienvenido E. Villabroza, Christian E. Pulmano

Department of Information Systems & Computer Science Faculty Publications

There are cases of corruption and fraud within the Philippine government that have gone under the radar, often due to a lack of transparency and verifiability. The objective of this study is to prototype a blockchain network that can run a government process as a decentralized application such that it can enhance transparency and verifiability in the public sector. This can be accomplished by identifying a government process that would be converted into a decentralized application. One of these processes would be converted into a decentralized application. Afterwards, a blockchain framework should be identified one which can create a public …

Multi-Variable Phase And Gain Calibration For Multi-Channel Transmit Signals, Ryan C. Ball

Browse all Theses and Dissertations

A method for software-defined radio array calibration is presented. The method implements a matched filter approach to calculate the phase shift between channels. The temporal stability of the system and calibration coefficients are shown through the standard deviation over the course of four weeks. The standard deviation of the phase correction was shown to be less than 2 deg. for most channels in the array and within 8 deg. for the most extreme case. The standard deviation in amplitude scaling was calculated to be less than 0.06 for all channels in the array. The performance of the calibration is evaluated …

Digital Beamforming Array Phase Calibration Techniques For Multi-Pass Interferometric Sar, Kelly Cheung

Browse all Theses and Dissertations

Calibration plays a critical role in the optimal performance of algorithms in digital beamforming arrays. Phase incoherency between elements results in poor beamforming with decreased gain and higher sidelobes, leading to a decrease in accuracy and sensitivity of measurements. A similar problem exists in performing multi-pass interferometric SAR (IFSAR) processing of SAR data stacks to generate topological maps of the scene, where phase errors translate to height errors. By treating each SAR image in the data stack like an element of a uniform linear array, this thesis explores several phase calibration techniques that can be used to calibrate digital beamforming …

Computational Mechanisms Of Face Perception, Jinge Wang

Graduate Theses, Dissertations, and Problem Reports (ETD)

The intertwined history of artificial intelligence and neuroscience has significantly impacted their development, with AI arising from and evolving alongside neuroscience. The remarkable performance of deep learning has inspired neuroscientists to investigate and utilize artificial neural networks as computational models to address biological issues. Studying the brain and its operational mechanisms can greatly enhance our understanding of neural networks, which has crucial implications for developing efficient AI algorithms. Many of the advanced perceptual and cognitive skills of biological systems are now possible to achieve through artificial intelligence systems, which is transforming our knowledge of brain function. Thus, the need for …

Investigating The Impact Of Demographic Factors On Contactless Fingerprint Interoperability, Aeddon David Berti

Graduate Theses, Dissertations, and Problem Reports (ETD)

Improvements in contactless fingerprinting have resulted in contactless fingerprints becoming a faster and more convenient alternative to contact fingerprints. The interoperability between contactless fingerprints and contact fingerprints and how demographic factors can change interoperability has been challenging since COVID-19; the need for hygienic alternatives has only grown because of the sudden focus during the pandemic. Past work has shown issues with the interoperability of contactless prints from kiosk devices and phone fingerprint collection apps. Demographic bias in photography for facial recognition could affect photographed fingerprints. The paper focuses on evaluating match performance between contact and contactless fingerprints and evaluating match …

Machine Learning For Biosensors, Gayathri Anapanani

Graduate Theses, Dissertations, and Problem Reports (ETD)

Biosensors have become increasingly popular as diagnostic tools due to their ability to detect and quantify biological analytes in a wide range of applications. With the growing demand for faster and more reliable biosensing devices, machine learning has become a valuable tool in enhancing biosensor performance. In this report, we review recent progress in the application of machine learning to biosensors. We discuss the potential benefits of using machine learning in biosensors, including improved sensitivity, selectivity, and accuracy. We also discuss the various machine learning techniques that have been applied to biosensors, including data preprocessing, feature extraction, and classification and …

Object Detection And Classification In The Visible And Infrared Spectrums, Domenick D. Poster

Graduate Theses, Dissertations, and Problem Reports (ETD)

The over-arching theme of this dissertation is the development of automated detection and/or classification systems for challenging infrared scenarios. The six works presented herein can be categorized into four problem scenarios. In the first scenario, long-distance detection and classification of vehicles in thermal imagery, a custom convolutional network architecture is proposed for small thermal target detection. For the second scenario, thermal face landmark detection and thermal cross-spectral face verification, a publicly-available visible and thermal face dataset is introduced, along with benchmark results for several landmark detection and face verification algorithms. Furthermore, a novel visible-to-thermal transfer learning algorithm for face landmark …

Enhancing Vehicular Perception: A Comprehensive Analysis Of Sensor Fusion Performance Through Weighted Averages And Fuzzy C-Means For Optimal Data Association, Zachary Brian Flanigan

Graduate Theses, Dissertations, and Problem Reports (ETD)

This work explores the implementation of sensor fusion and data association for autonomous vehicle design. Advancements in Adaptive Driver Assistance System (ADAS) technology have driven the development of perception algorithms required for higher levels of autonomy in vehicles. Perception algorithms process data collected from radar, camera, and LiDAR sensors to generate a complete model of the ego vehicle’s surrounding environment. Fusion of data from these sensors is important for accurate measurement of longitudinal and lateral distances to surrounding objects. Sensor fusion associates sensor detections to each other through different data association techniques. Data association techniques can consist of independent assignment …

Development Of Automated Egg Incubator With Backup Power Supply, Allen N. Maroma, Dolly P. Maroma, Bernardo A. Pangilinan

ASEAN Journal of Community Engagement

This study addresses the development of an automated egg incubator with backup power supply that could benefit farmer communities through the developmental research approach. A prototype is developed to respond to the needs for uninterrupted incubation which is affected by the frequent power outages that reduce its efficiency in egg handling. In this project, the automated egg incubator with a backup power supply is designed to hatch a capacity of 150 eggs (75 setters and 75 hatchers) every 21 days, ensuring continuous operation even in the absence of a consistent power supply. An inverter, connected to a battery, ensures a …

A Phase Change Memory And Dram Based Framework For Energy-Efficient And High-Speed In-Memory Stochastic Computing, Supreeth Mysore

Theses and Dissertations--Electrical and Computer Engineering

Convolutional Neural Networks (CNNs) have proven to be highly effective in various fields related to Artificial Intelligence (AI) and Machine Learning (ML). However, the significant computational and memory requirements of CNNs make their processing highly compute and memory-intensive. In particular, the multiply-accumulate (MAC) operation, which is a fundamental building block of CNNs, requires enormous arithmetic operations. As the input dataset size increases, the traditional processor-centric von-Neumann computing architecture becomes ill-suited for CNN-based applications. This results in exponentially higher latency and energy costs, making the processing of CNNs highly challenging.

To overcome these challenges, researchers have explored the Processing-In Memory (PIM) …

Application Of Conventional Feedforward And Deep Neural Networks To Power Distribution System State Estimation And State Forecasting, James Paul Carmichael

Theses and Dissertations--Electrical and Computer Engineering

Classical neural networks such as feedforward multilayer perceptron models (MLPs) are well established as universal approximators and as such, show promise in applications such as static state estimation in power transmission systems. This research investigates the application of conventional neural networks (MLPs) and deep learning based models such as convolutional neural networks (CNNs) and long short-term memory networks (LSTMs) to mitigate challenges in power distribution system state estimation and forecasting based upon conventional analytic methods. The ability of MLPs to perform regression to perform power system state estimation will be investigated. MLPs are considered based upon their promise to learn …

Modeling The Early Visual System, Nicholas Lanning

Theses and Dissertations--Electrical and Computer Engineering

There are two encoding schema present in simple cells in the early visual system of vertebrates: the retinal simple cells activate highly when the receptive field contains a center surround stimulus, while the primary visual cortex’s (V1) simple cells activate highly when the receptive field contains visual edges. Work has been done in the past to enforce constraints on visual machine learning such that the retinal or V1 encoding is learned, but this work is often done to emulate retinal and V1 encoding in a vacuum. Recent work using convolutional neural networks focuses on anatomical constraints along with a supervised …

Improving The Flexibility And Robustness Of Machine Tending Mobile Robots, Richard Ethan Hollingsworth

Theses and Dissertations

While traditional manufacturing production cells consist of a fixed base robot repetitively performing tasks, the Industry 5.0 flexible manufacturing cell (FMC) aims to bring Autonomous Industrial Mobile Manipulators (AIMMs) to the factory floor. Composed of a wheeled base and a robot arm, these collaborative robots (cobots) operate alongside people while autonomously performing tasks at different workstations. AIMMs have been tested in real production systems, but the development of the control algorithms necessary for automating a robot that is a combination of two cobots remains an open challenge before the large scale adoption of this technology occurs in industry. Currently popular …

Wifi Sensing At The Edge Towards Scalable On-Device Wireless Sensing Systems, Steven M. Hernandez

Theses and Dissertations

WiFi sensing offers a powerful method for tracking physical activities using the radio-frequency signals already found throughout our homes and offices. This novel sensing modality offers continuous and non-intrusive activity tracking since sensing can be performed (i) without requiring wearable sensors, (ii) outside the line-of-sight, and even (iii) through the wall. Furthermore, WiFi has become a ubiquitous technology in our computers, our smartphones, and even in low-cost Internet of Things devices. In this work, we consider how the ubiquity of these low-cost WiFi devices offer an unparalleled opportunity for improving the scalability of wireless sensing systems. Thus far, WiFi sensing …

Teaching Data Acquisition Through The Arduino-Driven Home Weather Station Project, Sheryl Dutton, Kurt Galderisi, Murat Kuzlu, Otilia Popescu, Vukica Jovanovic

Engineering Technology Faculty Publications

The main objective of this paper is to present one possible way to engage undergraduate students in designing a system that uses the Internet of Things (IoT) strategy for data acquisition and management. The MATLAB home weather station project presented here was developed by a team of students for the senior design course in the Electrical Engineering Technology undergraduate program at Old Dominion University (ODU). The main purpose of this project was for undergraduate students to learn how to create a localized, compact, and precise weather station. Utilizing various sensors, both homemade and sourced online, this weather station is capable …

Topological Photonic Metasurfaces For Light Manipulation And Strong Light-Matter Interaction, Svetlana Kiriushechkina

Dissertations and Theses

High-resolution nanopatterning techniques, such as electron beam lithography, extended opportunities for implementation of the various designs of photonic structures which exhibit exciting physical phenomena in the optical domain. A straightforward fabrication of on-slab nanostructures is advantageous for integration with various photonic on-chip devices. Last decade all-dielectric periodic nanostructures (photonic metasurfaces) boost a growth of novel optical technologies, from ultra-sensitive detectors to compact beam structured lasers. Moreover, they represent one of the most promising platforms in which topological phases can be explored and exploited.

Topological photonic structures attract a significant interest owing to their outstanding properties such as a resilience to …

Blockchain Framework For Secured On-Demand Patient Health Records Sharing, Meryem Abouali

Dissertations and Theses

As the healthcare industry continues to digitize and share patient data for a better understanding of patient health history, cybersecurity must remain a top priority. However, patient health record (PHR) data is extremely sensitive and faces significant challenges due to its distributed nature across various healthcare facilities and providers, which creates a lack of interoperability among healthcare systems. Most patient health record systems adopt a centralized management structure and deploy PHRs to the cloud, which raises privacy concerns when sharing patient information over a network. Thus, there is a need for a framework that considers patient privacy and data security …

Design And Experimental Observation Of Topological States In Photonic Metasurfaces, Anton Vakulenko

Dissertations and Theses

Topological phases in photonics attract a lot of attention due to their unique properties which allow controlling optical coupling and electromagnetic field distributions in nanostructures. Diverse phenomena supported by photonic topological structures include robust scatter-free waveguiding, an extreme confinement of light, lasing and strong coupling with novel low- dimensional materials. A very convenient integration with on-chip optical devices and also with quantum dots or monolayers of van der Waals materials promise even brighter future for photonic topological insulators as a useful platform for innovative photonic and compact quantum devices.

In the course of my dissertation work, I investigated topological structures …

Lidar Remote Sensing Of Aerosol And Ozone Profiles And Application To Air Quality Studies In New York City Area, Dingdong Li

Dissertations and Theses

Ozone (O₃) and PM2.5 (Particulate Matter with a diameter less than 2.5 μm) are the main pollutants in New York City (NYC) due to high levels of anthropogenic emissions, complex urban meteorology, and regional transport. However, vertical distribution observations are still lacking. This thesis utilizes lidar remote sensing techniques to retrieve the vertical distribution of O₃ and aerosols and study air pollution episodes in the NYC metropolitan area.

The thesis includes three parts. The first part analyzes continuous ceilometer observations of aerosols and atmospheric mixed-layer height (ML). We investigate the vertical, diurnal, and seasonal characteristics of the …

Comprehensive Fault Diagnostics And Performance Forecasting Of Wind Turbines Through Condition Monitoring Solutions, Shuo Zhang

Doctoral

The operation and maintenance (O&M) issues of wind turbines (WTs) are challenging because unplanned maintenance, caused by sudden component failures, can bring about durable downtimes and significant revenue losses. It is important to carry out effective fault diagnostics and prognostics schemes under the rapid development of wind power generation. Hence, Condition Monitoring (CM) solutions focus on measurements and detections of high-risk WT components, which could result in high failure rates and long downtimes. Machine Learning (ML) models have been commonly applied in CM to allocate imminent indications of failure or degradation for curtailing the O&M costs of WTs. By way …

Prediction And Root-Cause Analysis For Smart Speaker Intentional Electromagnetic Interference Attacks, Tanner Fokkens

Masters Theses

"Smart home and Internet of Things (IoT) devices have become ubiquitous in homes over the past decade. The smart speaker itself is often the device that interfaces all these devices together. Because of this, the smart speaker can become a point of attack for someone trying to exploit or hack into the smart home devices. In the past few years, it was discovered that smart speakers with microwave electromechanical system (MEMS) microphones are susceptible to intentional electromagnetic interference (I-EMI) attacks by modulating an audio command to a high-frequency carrier signal. This attack allows for command recognition for long-distances and smart …

Improved Decap Model And Placement Optimization Algorithm For Power Distribution Network Design, Jack Juang

Masters Theses

"Decoupling capacitors (decaps) are used in power distribution network (PDN) design to act as a low impedance return path for noise and act as a local source of charge when required by integrated circuits (IC). For placement of decaps, which can number even to the hundreds, many algorithms have been proposed including genetic algorithms (GA), iterative algorithm, and machine learning methods.

One limitation of iterative decap placement algorithms (adding one decap at a time) is how the construction of the algorithm affects the form of the final solution. For example, if the reward function (used in GA and machine learning …

Experimental Evaluation Of Micro-Epidermal Actuators On Flexible Substrates, Courtney D. Bradley

Graduate Research Theses & Dissertations

Does embedding actuators in a flexible substrate increase their performance in hearing aids? What are the differences in damping experienced by actuators of different diameters and at different locations? At what frequency is peak acceleration achieved and what role does the size of the actuator and embedding it in a flexible substrate play? These questions will form the basis of this thesis. This work was done to develop a small non-invasive Band-Aid-©-like hearing aid. The novelty of this device requires a detailed analysis of piezoelectric actuators. This is a continuation of past students’ work on the topic. The main parameters …

Prioritized Object Detection Integrating Fuzzy Logic Risk Assessment And Planned Path., Khatereh Mohammadi

Graduate Research Theses & Dissertations

Nowadays, Autonomous Vehicles are in the spotlight as a response to the challenges stemming from population growth, worsening traffic congestion, and rising road accidents. Researchers and companies are concentrating on developing Automated Driving Systems (ADS) to tackle these issues.Of the various components that constitute an autonomous vehicle, perception plays a pivotal role, akin to the function of human eyes and the human brain. Therefore, ensuring precise and reliable perception within Autonomous Vehicles is paramount. This thesis is inspired by the principles of human perception, particularly on the road, and endeavors to replicate this process. Just as a human driver does …

A High-Precision Electron Emission Model: Computational Methods For Nanoscale Structures, Alister J. Tencate

Graduate Research Theses & Dissertations

The high-intensity, high-brightness and precision frontiers for charged particle beams are an increasingly important focus for study. Electron microscopy has demonstrated high quality beams from a single nanotip emitter, and cathodes of structured nanoscale arrays show promise as ultracold electron sources. Optimization of the cathode design for precision applications necessitates a detailed treatment of the interplay between the structure geometry, quantum mechanical emission mechanism, and electromagnetic interactions between the emitted electrons and the boundary interface. This dissertation details the numerical tools developed to simulate these processes efficiently with enough fidelity to be accurate even in the ultracold regime.

Conventional simulation …

Analysis Of Localization Algorithms For Wireless Sensor Networks Using Binary Data, Alexander Joseph Hart

Graduate Research Theses & Dissertations

The detection, localization, and tracking of environmental and physical conditions can be accomplished using wireless sensor networks (WSNs). Recent advancements in sensors, processors, and wireless communications have improved the quality and acquisition speed of data in WSNs. However, the data gathered by a WSN is inherently random due to component and environmental variations. Thus, statistical signal processing algorithms are needed to analyze the random data in a robust way. Though many algorithms for the analysis of random data are established and available, they are problem-specific and must be adapted to the application. This thesis provides an analysis of established localization …

Spherical Modes Driven Directional Modulation With A Compact Mimo Antenna, Abel Zamdemala, Nicola Marchetti, Max Ammann, Adam Narbudowicz

Articles

In this letter, a compact beamsteering MIMO antenna is proposed for Directional Modulation (DM) applications. A generalization of the beamsteering principle is presented and by exploiting the antenna’s unidirectional beamsteering capability within the entire azimuth plane, the system realizes secure steerable transmissions in the direction of the legitimate receiver, with a low Bit Error Rate (BER) of 10^(-5), while a high error rate of 10^(-1) is seen outside the desired regions. Numerical and experimental verifications are carried out to validate the proposed concept and comparisons with circular arrays are conducted, revealing that the system achieves comparable performance but with up …

Technical And Economic Feasibility Of A Microgrid For A Fire Station In Humboldt County, California., Nishaant Kumar Sinha

Cal Poly Humboldt theses and projects

Microgrids are emerging as a promising solution to unreliable grid energy. Today, California is not only witnessing grid resiliency challenges from natural disasters such as wildfires, earthquakes, floods and heatwaves, but it is also seeking to green the grid and bring more renewables online. For example, Humboldt County, where this project is focused, has recently experienced an earthquake of 6.4M (on December 22nd, 2022), which shut down the regional grid for ~20 hours.

Microgrid adoption enables critical facilities to operate seamlessly. The Humboldt Bay Fire Station (HBFS) No.1 is one such example, where first responders work to protect citizens against …

The Troubling Emergence Of Hallucination In Large Language Models--An Extensive Definition, Quantification, And Prescriptive Remediations, Vipula Rawte, Swagata Chakraborty, Agnibh Pathak, Anubhav Sarkar, S.M Towhidul Islam Tonmoy, Aman Chadha, Amit Sheth, Amitava Das

Publications

The recent advancements in Large Language Models (LLMs) have garnered widespread acclaim for their remarkable emerging capabilities. However, the issue of hallucination has parallelly emerged as a by-product, posing significant concerns. While some recent endeavors have been made to identify and mitigate different types of hallucination, there has been a limited emphasis on the nuanced categorization of hallucination and associated mitigation methods. To address this gap, we offer a finegrained discourse on profiling hallucination based on its degree, orientation, and category, along with offering strategies for alleviation. As such, we define two overarching orientations of hallucination: (i) factual mirage (FM) …