Signal Processing Commons^™

Toward A Generalizable Perceptual Hashing Framework For Image Manipulation Detection, Priyanka Samanta

Dissertations, Theses, and Capstone Projects

This thesis contributes to research in adversarial image manipulation detection. The primary motivation is the increasing need to verify digital images, especially for legal evidence, journalistic proof, or social media content—where manipulated or fabricated images can mislead, defame, or distort reality. A key application and contribution of this work is the development of eWitness, a blockchain application that generates and registers image provenance at capture time to enable independent verification of authenticity. The secret sauce behind the system is SmartHash, a novel and efficient perceptual hashing algorithm designed for real-world deployment in systems like eWitness. Unlike existing algorithms, SmartHash targets …

Analog To Digital Converters Topologies For Radar System Application: A Comparison, Kulsoom Mateen, Wafa Alharbi, Aziza I. Hussein

Effat Undergraduate Research Journal

Analog-to-digital converters (ADCs) that convert analog signals into digital ones play a significant role in radar systems. The accuracy and resolution of radar readings are significantly influenced by the quality and performance of ADCs. This paper discusses and compares the application of five different types of ADCs in radar systems. It also elaborates on each ADC's working principle, advantages, and limitations. The parameters compared are resolution and dynamic range, signal-to-noise ratio (SNR), latency and sampling rate, power consumption, size, and cost. After thorough research, we concluded that each ADC differs depending on the designer’s desired application. For example, flash ADCs …

Exploring Longitudinal Stability Of Spatiotemporal Sequential Patterns By Means Of Autoencoder Schemes For Eeg Based Personal Identification, Muhammed E. Oztemel

LSU Doctoral Dissertations

Robust personal identification remains a critical and challenging task in the digital era. Electroencephalography (EEG) offers a unique biometric modality that captures individual brain dynamics through complex neural signals. This dissertation proposes autoencoder (AE) based feature extraction and subject identification through these features. EEG recordings are first transformed into topographic maps to represent spatial brain activity. Consecutive topomaps are then concatenated to capture temporal transitions across frames. Convolutional autoencoders (CAEs) are used to learn spatial and temporal patterns, while domain-adaptive AEs are designed to model evoked potential based responses. Additionally, self-attention mechanism is incorporated to enhance feature representation. To analyze …

Method For Target Detection In A High Noise Environment Through Frequency Analysis Using An Event-Based Vision Sensor, Will Johnston, Shannon Young, David Howe, Rachel Oliver, Zachary Theis, Brian Mcreynolds, Michael L. Dexter

Faculty Publications

Event-based vision sensors (EVSs), often referred to as neuromorphic cameras, operate by responding to changes in brightness on a pixel-by-pixel basis. In contrast, traditional framing cameras employ some fixed sampling interval where integrated intensity is read off the entire focal plane at once. Similar to traditional cameras, EVSs can suffer loss of sensitivity through scenes with high intensity and dynamic clutter, reducing the ability to see points of interest through traditional event processing means. This paper describes a method to reduce the negative impacts of these types of EVS clutter and enable more robust target detection through the use of …

A Deep Learning Approach For Semantic Segmentation And Its Application On Ctc., Samir Farag Harb

Electronic Theses and Dissertations

This dissertation explores the modeling and analysis of medical images, focusing on the intricate task of colon segmentation and subsequent 3D reconstruction, which are critical steps in Computed Tomography Colonography (CTC) systems. The primary objective of this research is to develop precise segmentation approaches to enhance the accuracy of colon identification and reconstruction from abdominal CT scans. Three distinct segmentation approaches are proposed and evaluated: a Markov Random Field (MRF)-based approach, a convolutional neural network (CNN)-based deep learning (DL) approach, and a sequential episodic training with dual contrastive learning Approach (G-SET-DCL) that has a flavor of few-shot learning (FSL). To …

Human Comfort Modeling, Measurement, And Improvement In Human–Robot Collaboration, Yuchen Yan

All Dissertations

A dissertation is proposed to explore human comfort in human-robot collaboration (HRC) through modeling, prediction, and enhancement methodologies. Human comfort is a crucial yet underexplored factor in HRC, directly influencing task efficiency, trust, and overall collaboration effectiveness. Understanding the influential factors, developing computational models, and refining methods to improve human comfort in HRC are essential steps toward advancing the field of collaborative robotics. To address these challenges, multiple studies have been conducted. A series of experimental studies were performed to investigate how robot motion-based parameters affect human comfort in HRC. These studies examined both analytical comfort modeling approaches and physiological …

Advancing Real-World Implementation Of The Well Optimized Linear Finder (Wolf) High-Speed Atmospheric Turbulence Compensation Method, Timothy Evan Coon

Theses and Dissertations

This dissertation advances the real-world implementation of the Well Optimized Linear Finder (WOLF) method for high-speed Atmospheric Turbulence Compensation (ATC). Atmospheric turbulence introduces phase aberrations into optical wavefronts and degrades image quality in terrestrial imaging systems. Traditional phase diversity methods are computationally intensive and poorly suited to real-time operation. The WOLF method addresses these limitations through a novel, point-wise formulation of the optical transfer function (OTF) as a structured autocorrelation of the generalized pupil function (GPF). This formulation enables the estimation of phase aberrations at individual spatial coordinates with distributed computational complexity.

The research begins by developing a MATLAB-based simulation …

3d Solid Models, Bradley M. Ratliff

Model Desert Terrain Monochromatic DoT Dataset

3D solid models for model vehicles, target panels, objects, and the desert terrain model in STL file format.

Ground Truth Images, Bradley M. Ratliff

Model Desert Terrain Monochromatic DoT Dataset

Laboratory and scenario ground truth images for the Model Desert Terrain Monochromatic DoT dataset.

Asl File Reader (Matlab), Bradley M. Ratliff

Source Code

This zip file contains the necessary files for reading binary ASL data and reading and parsing ASL header file metadata in MATLAB.

Polarimetric Data: Scenario 01, Bradley M. Ratliff

Model Desert Terrain Monochromatic DoT Dataset

Polarimetric data Scenario 01 collected within the Automated Remote Sensing Solar Simulation Lab at the University of Dayton. The data were collected using a visible monochromatic division-of-time imaging polarimeter. The dataset is parameterized across different sensor, scene, and illumination geometries that mimic outdoor solar irradiance conditions.

Dataset Description, Bradley M. Ratliff

Model Desert Terrain Monochromatic DoT Dataset

Polarimetric dataset containing data collected within the Automated Remote Sensing Solar Simulation Lab at the University of Dayton. The data were collected using a visible monochromatic division-of-time imaging polarimeter. A model desert terrain model was constructed and imaged for eight different scenarios consisting of different model panel and vehicle targets. The dataset is parameterized across different sensor, scene, and illumination geometries that mimic outdoor solar irradiance conditions.

Data Annotations, Bradley M. Ratliff

Model Desert Terrain Monochromatic DoT Dataset

Pixel-wise object masks for each polarimetric scene in ASL file format for the Model Desert Terrain Monochromatic DoT data.

A Yolo-Based Deep Learning Approach For Vibration-Based Rotating Shaft Imbalance Detection, Abdelhameed Zayed Dr., Ali Siam Dr.

Journal of Engineering Research

One of the prevailing causes of vibrations in machines is rotor imbalance. Rotor balancing can be used to fix the majority of rotating machinery issues. When it comes to high-speed running equipment, even a slight imbalance can lead to serious issues and decrease the operational efficiency of rotating machinery. This work proposed a deep learning approach for the detection of binary and multiclass imbalance in rotating shafts. A YOLOv11 model-based approach is developed to detect imbalance and identify unbalanced rotor positions. To precisely identify unbalanced positions, this method trains the YOLOv11 model using numerous sets of measured response data and …

Multi-Modal Covid-19 Detection Using Cough Sounds And Medical Information With Attention-Enhanced Deep Learning, Mohamed Talaat Saidahmed, Reda Elbasiony, Marwa Reda Bastwesy, Asmaa Aly Hagar

Journal of Engineering Research

The COVID-19 pandemic has highlighted the need for fast, non-invasive, and cost-effective diagnostic tools. Cough sounds, as a prominent symptom of respiratory diseases, present a promising modality for automated COVID-19 detection. In this study, we propose a novel multi-modal deep learning framework for COVID-19 detection that leverages cough sounds and patient-specific medical information. Our approach extracts two types of acoustic features—Mel-Frequency Cepstral Coefficients (MFCCs) and Mel spectrograms—and integrates them with clinical metadata to improve diagnostic ac-curacy. The MFCC branch employs 1D convolutional layers followed by Efficient Channel Attention mechanism. The Mel spectrogram branch utilizes ResNet-50 combined with ECA to capture …

Field Deployable Mobile Manipulator For Autonomous Apple Harvesting, Gabriel K. Basus, Antonio Bowen, Andrew Daouda

Electrical Engineering

Increasing labor costs and agricultural demands have created a need for automated apple harvesting. However, automated apple harvesting via robotic manipulation must overcome certain challenges to be an effective and efficient method. First, the system must compete with or perform better than manual human labor. Second, it must safely and accurately navigate an apple orchard autonomously. Third, the robotic manipulator must be able to securely grasp and pick apples without causing damage. To address these challenges, this project utilizes a Husky UGV equipped with a 2D LiDAR sensor, an RGB-D camera, an IMU, an OpenManipulator-X robot arm, and a soft …

Rotating Scatter Mask System Optimization Study For Determining Optimal Image Recreation, Seth L. Grover

Theses and Dissertations

The Rotating Scatter Mask (RSM) system is a radiation imaging technology currently limited by the mask design and governing identification algorithm parameters. To optimize the RSM design, Dakota—an optimization software—was integrated with a ray tracing code that simulates particle interactions with the RSM detector, and with the Locally Competitive Algorithm (LCA), which reconstructs the source image based on the ray tracing code’s Detector Response Matrix (DRM). Since the original ray tracing code was developed in MATLAB, it was translated into Python to improve compatibility with both Dakota and LCA. The Python version of the ray tracing code was then integrated …

Leveraging Machine-Learning Algorithms In Two Car Crash Detection Systems On A Custom Dataset, Addison Jacob Sandvik

Master's Theses

Traffic accidents pose a significant threat to public safety, causing millions of deaths and injuries worldwide each year. While efforts to reduce accidents have seen limited progress in recent years, improving emergency response times through automated detection systems is a promising avenue for saving lives. This thesis describes the development of machine learning-based traffic accident detection systems, exploring both video classification and image detection models. The models are trained on a new dataset deemed the Cal Poly Traffic Accident Dataset, an extension of the existing Car Accident Detection and Prediction (CADP) dataset with a precise collision annotations. Two systems were …

Coherent Synchronization For Distributed Digital Phased Arrays, Zachary C. Numa

Master's Theses

Distributed digital phased arrays are rising technologies that help enable applications such as search and rescue operations, wireless communication, radar navigation, and military operations, among many others. Due to their improved angular resolution, digital phased arrays offer superior direction-finding capabilities compared to traditional analog phased array systems. However, this improvement comes at the cost of increased complexity—specifically, the need for precise synchronization of phase, time, and frequency across physically separated nodes. Without synchronization, the distributed phased array's gain and direction-of-arrival (DoA) estimations deteriorate significantly.

There are multiple aspects to implementing and synchronizing a non-stationary distributed digital phased array. This research …

Single-Sided Hearing Assistance Application, Harryson Nguyen, Jp Haratani

Electrical Engineering

The product is a hearing assistance smartphone application which aims to improve the quality of life of people with single-sided hearing loss/deafness by providing them with a cheaper and more reliable alternative to medically-prescribed hearing aids. Due to development setbacks, the product instead uses open-ear earbuds. Since the earbuds are not directly inserted into the user’s ear canals, they will not obstruct the hearing of the user’s non-deaf ear, and the user will still be able to hear the sounds that come from their non-deaf side. Some users may find that Bluetooth earbuds can be quite expensive, but are ultimately …