Digital Commons Network^™

Real-Time Prediction Of Dynamical Systems Using A Hybrid Analog Computer: Network Traffic Modeling, Majd Zuhair Tahat

Doctoral Dissertations

As the number of online users grows exponentially, the number and severity of cyber threats escalate, urgently requiring advancements in real-time network modeling and response. Swiftly predicting and analyzing network traffic is crucial for effective network monitoring and control, preventing cyber breaches, and maintaining healthy network functionality. This research presents a novel approach to real-time modeling based on analyzing evolving properties and patterns in a dynamical network system using a hybrid analog-digital computer. An analog computer was utilized as a co-processor to compute differential equations that model the Transmission Control Protocol (TCP) window size. A comparative analysis was conducted between …

Performance Of Neural Networks On Fpga For Embedded Devices Using Hls4ml Framework, Alam N. Romo Lopez

Master's Theses

As machine learning models such as neural networks are investigated for their applications across many fields, the demand for models that can be implemented on an embedded device grows. Field Programmable Gate Arrays (FPGAs) have become an attractive option for implementing these models in hardware. This thesis considers the viability of FPGA implementations for machine learning on low-resourced embedded systems. The hls4ml project is a promising prospect for machine learning on FPGA devices. To test hls4ml, we used a model trained on the MNIST digits dataset, which was then synthesized for the PYNQ-Z2 device. We fine tuned the performance by …

Advances Towards A Robotic Management Vehicle Suited To Nurse Row Crops To More Efficient Outcomes, Adam Mk Gronewold

Dartmouth College Ph.D Dissertations

Enhancing agricultural production while reducing input costs remains a central challenge in modern row-crop management. Recent advances in computation, imagery, and sensors are enabling more efficient practices across various agricultural domains, and automation technologies are increasingly available to manage tasks central to perennial crop development. Automation in row-crop agriculture, by contrast, lags behind. This thesis explores utilizing small, unmanned ground vehicles to transform row cropping through the implementation of unconventional, in-season management strategies. The first focus of this work considers improvements to nitrogen fertilization using small, autonomous vehicles. An agronomy experiment in corn assessed the effects of gradually applying nitrogen …

Applying Image Processing And Computer Vision For Damage Detection In Photovoltaic Panels, Montaser Abdelsattar, Ahmed Abdelmoety, Ahmed Emad-Eldeen

Mansoura Engineering Journal

As the use of Photovoltaic (PV) panels as a sustainable energy source grows, there is a need for effective and precise techniques to monitor and manage these systems. Conventional techniques for identifying faults in PV panels, such as manual inspections, require a significant amount of effort and are susceptible to mistakes made by humans. This study introduces an innovative automated method that utilizes image processing techniques implemented using the OpenCV library to identify panel faults, namely hotspots, which are important indications of possible failures. The study approach combines grayscale conversion, histogram analysis, and adaptive thresholding to accurately detect and evaluate …

Yolot: A Recurrent Yolo Model For Robust Video-Based Automotive Object Detection, Dylan Jay Baxter

Master's Theses

Though incredibly effective at detecting objects in isolated frames, modern object detection models are often not designed to take advantage of information present in previous frames of a video stream, despite that data being readily avail- able. To address this shortcoming, this paper proposes YOLOT, a modification of the widely used YOLOv8 object detection model, which seeks to utilize this temporal information with the addition of recurrent structures. In the design of YOLOT, a series of recurrent convolutional modules were inserted at backbone and neck outputs and the final and most effective design was found to be the insertion of …

Danzens: A Toolkit For Sensing, Labeling And Visualizing Dance Movements, Yanelly Mego, Concepción Valdez, Hector M. Camarillo-Abad, Franceli L. Cibrian

Engineering Faculty Articles and Research

Wearable technology offers new opportunities for analyzing complex movements like dance, where precision, coordination, and feedback are key. In this demo, we present DanZens, a novel toolkit for real-time motion analysis in dance, leveraging wearable sensors to provide accessible and actionable feedback. Combining DanceTag to capture and annotate movements with DanceVis to visualize performance differences, DanZens uses Sony Mocopi sensors to analyze motion and generate intuitive heat maps through Dynamic Time Warping (DTW). This system enables precise, cost-effective comparisons between two people doing dance-related movements, offering personalized feedback and eliminating the need for expensive biomechanical labs. Designed to advance pervasive …

Development And Validation Of An Artificial Intelligence System For Surgical Case Length Prediction, Adhitya Ramamurthi, Bhabishya Neupane, Priya Deshpande, Ryan Hanson, Kellie R. Brown, Kathleen K. Christians, Douglas B. Evans, Anai N. Kothari

Electrical and Computer Engineering Faculty Research and Publications

Background

Accurate case length estimation is a vital part of optimizing operating room use; however, significant inaccuracies exist with current solutions. The purpose of this study was to develop and validate an artificial intelligence system for improved surgical case length prediction by applying natural language processing and machine-learning methods.

Methods

All inpatient elective surgical cases longer than 30 minutes completed between 2017 and 2023 at a single, quaternary care hospital were considered. Data were split into training, test, and hold-out validation for model training and testing. Linear regression, CategoricalBoost, and feed-forward neural network each were trained and used embeddings created …

Island Nation Duress: Simulating Passive Peer-To-Peer Bluetooth Communication During Disaster Relief, Jason K. Medeiros

Theses and Dissertations

Pacific Islands under U.S. jurisdiction are highly vulnerable to natural disasters, yet many lack the infrastructure to effectively respond and recover. Clear communication during and after such events is critical for evacuation, hazard awareness, and first responders’ coordination. This research explores a simulation-based approach using Bluetooth communication to relay messages across Guam, assessing its efficiency through statistical analysis. By examining regional differences and geographic impacts on Bluetooth messaging, the study aims to identify key factors that enhance peer-to-peer communication for timely and effective disaster response.

Statistical Analysis Of Spreading Code Authentication (Sca) Performance Under Varying Signal Conditions And Marker Quantization Schemes, Joseph Quinones-Ocasio

Theses and Dissertations

This thesis analyzes Spreading Code Authentication (SCA) in the GPS L1C signal using the PyChips software-defined receiver (SDR)framework. Monte Carlo simulations evaluate authentication performance under varying signal conditions, assessing the impact of double-precision and quantized data on signal integrity. Results demonstrate that authentication remains achievable at low signal-to-noise ratio(SNR) conditions but introduces trade-offs in memory usage and authentication time. These findings provide insights into optimizing SCAfor resource-constrained environments, contributing to secure GPS operations in critical applications such as aviation, autonomous systems,and national defense.

Development Of An Advanced 16-Channel High-Fidelity Multi-Frequency Software-Defined Rf Front-End For Advanced Satnav Signal Monitoring Applications, Melbourne T. Ketteridge

Theses and Dissertations

Multi-element antenna array technology provides significant performance advantages in satellite timing and navigation (satnav) receiver applications. It is the most effective anti-jamming method with the ability to place steep nulls in the direction of jammers. Until recently, satnav systems with 4 or more antenna elements were designated as weapons technology and restricted under ITAR regulations. This opens the door to commercial multi-element satnav receivers. Due to advancements in wireless broadband technology a receiver built entirely using commercial off-the-shelf (COTS) components is possible. This thesis presents an architecture for a high fidelity 16-channel RF front-end (RFFE) for research and development of …

Quantum Ghost Imaging Through An Atmospheric Turbulence Simulator, Mikaela R. Morris

Theses and Dissertations

The use of single photons and photon pairs has become a cornerstone for new developments in the sensing and imaging community for their ability to improve image resolution and signal to noise readings in low light environments and large standoff distances. Quantum imaging techniques have an ability to overcome the fundamental limits of classical imaging, like diffraction. Quantum ghost imaging, a specific type of quantum imaging, uses a bi-photon pair produced during the process of spontaneous parametric down conversion to produce an image. The pair is split using a beam splitter, the signal photon is transmitted through an aperture and …

Misalignment Uncertainty In Near-Field Thz Scattering Experiments, Philip Patterson

Theses and Dissertations

This research investigates the effect of misalignment on the near-field scattering of cylinders in the 550-700 GHz frequency band. A Type-1 calibration is performed on previously collected data, using a near-field physical optics solution to simulate scattering at various positions and orientations. The alignment of the cylinders at the time of measurement is predicted by comparing the range profiles of the theoretical and calibrated responses. The data with the most similar range profiles had a mean calibration difference metric of -2.78 dB and a standard deviation of -0.57 dB, demonstrating the presence of sources of error that are dominant over …

Enhancing Cycle Life Of Graphite ‖ Lifepo4 Batteries Via Copper Substituted Li2Ni1-XCuXO2 Cathode Prelithiation Additive, Jian-Ming Zheng, Jing-Wen Zhang, Tian-Peng Jiao

Journal of Electrochemistry

Lithium nickel oxide (Li₂NiO₂), as a sacrificial cathode prelithiation additive, has been used to compensate for the lithium loss for improving the lifespan of lithium-ion batteries (LIBs). However, high-cost Li₂NiO₂ suffers from inferior delithiation kinetics during the first cycle. Herein, we investigate the effects of the cost-effective Cu substitution of Li₂Ni_1-xCu_xO₂ (x = 0, 0.2, 0.3, 0.5, 0.7) synthesized by high-temperature solid-phase method on the structure, morphology, electrochemical performance of graphite‖LiFePO₄ battery. The X-ray Diffraction (XRD) refinement result demonstrates that Cu substitution strategy is favorable …

Modeling Of Analog-To-Digital Converter In Signal Processing, Ravshan Aliev, A.U. Djalilov

Chemical Technology, Control and Management

This article is devoted to the study of the modeling process of analog-to-digital converters (ADCs) that process signals, one of the main parts of control system elements and devices. As we know, ADCs are an important part of modern control systems. During the research, the main stages of analog signal conversion were analyzed, i.e. discretization, quantization, coding. A classification of analog-to-digital conversion methods was made and the advantages and disadvantages of each were identified. Also, the characteristics and parameters of ADC were studied, their impact on ADCs performance was evaluated, and it was determined that certain characteristics should be taken …

Methodology Of Automated Control Of Situations In Structurally Complex Systems With Recycled Flows, Khusan Zokirovich Igamberdiev Academician, Madina Mirxalilovma Fozilova

Chemical Technology, Control and Management

This article discusses the methodology of automated management of situations in structurally complex systems with recycled flows. The need to develop a correct model for effectively controlling such systems based on scientific principles of analysis and decision-making is substantiated. Particular attention is paid to modeling, optimizing, and using digital technologies, including artificial intelligence, to improve the accuracy and efficiency of management decisions. The principles of decomposition, multi-criteria optimization, and linguistic models of fuzzy correspondence are described, which can be used in conditions of uncertainty and complexity of industrial facilities.

Application Of An Adaptive Neuro-Fuzzy Inference System To Control The Wastewater Treatment Process, Jaloliddin Abdurazzakovich Eshbobaev, Bakhodir Tajiddinovich Khamidov, Marcos Torices Fallanza

Chemical Technology, Control and Management

This study explores the application of an Adaptive Neuro-Fuzzy Inference System (ANFIS) for controlling wastewater treatment processes using ion-exchange resins. It addresses the critical challenges of water scarcity and pollution by enhancing the regulation of water hardness (H) and Total Dissolved Solids (TDS). Using a pilot laboratory device and experimental data from the mixed wastewater of the Kungrad Soda Plant in Uzbekistan, an ANFIS model was developed in MATLAB to automate process control. The model leverages water hardness and TDS as input parameters to regulate the water flow rate by servo valve opening degree, ensuring precise and efficient treatment. Compared …

Power System Operations Modeling And Optimization Using Pyomo, Ahmad Heidari, Rui Bo

Graduate Student Research & Creative Works

"The energy sector has witnessed transformative advancements over the past few decades. Power systems, which form the backbone of modern society, have grown increasingly complex with the integration of renewable energy sources, energy storage, and emerging technologies. As these systems evolve, so does the need for efficient operation and optimization strategies to ensure reliability, sustainability, and economic performance.

Optimization plays a central role in solving real-world challenges such as balancing power generation and demand, minimizing operational costs, and managing grid constraints. However, many existing resources tend to focus either on theoretical aspects of optimization or rely on expensive, proprietary software …

A Novel Preprocessing Model For Multi Modal Brain Mri Image Classification For Stroke Prognosis, Alwin Joseph, Chandra J

Northeast Journal of Complex Systems (NEJCS)

Magnetic Resonance Imaging (MRI) is an imaging technique used for the diagnosis and observing the progression in various neurological disorders. Stroke is one of the prominent neurological disorders that creates significant impacts in the patients. It occurs when the blood supply to part of the brain is interrupted or reduced, preventing brain tissues from getting oxygen and nutrients. Multimodal data from various modalities help clinicians in proper prognosis of stroke. Ischemic Stroke Lesion Segmentation Challenge (ISLES22) provides data of stroke data for various stroke patients, the dataset consists of three modalities of data – Fluid Attenuated Inversion Recovery (FLAIR), Apparent …

Classification Of Microcontroller Integrated Circuit On The Pocket Of Jedec Tray Using Convolutional Neural Network In Embedded Machine Learning System, Mark Pallones, King Harold A. Recto

Electronics, Computer, and Communications Engineering Faculty Publications

One serious issue in the microcontroller manufacturing environment is the mixing of microcontroller unit (MCU) parts, leading to the wastage of materials, dissatisfied customers, and the implementation of non-value-adding activities to address it. More adverse effects include negative feedback from customers, loss of confidence, and impact on business growth. One root cause traces back to the final testing of the manufacturing back-end process when reusing unemptied standard JEDEC matrix trays for good and bad units in the test handler. Currently, emptying the JEDEC matrix tray and inspecting it is a manual process prone to human error due to high-volume test …

Zno Nanowires For Biosensing Applications, G.M. Mehedi Hossain, Daniel Garza, Emilio Chavez, Ahmed Hasnain Jalal, Fahmida Alam

Electrical and Computer Engineering Faculty Publications

Zinc oxide Nanowires (ZnO-NWs) are promising biosensor materials and hold the key to overcoming challenges in the field. This chapter provides an introductory overview of biosensing technology, focusing on the fundamental principles and comparing ZnO-NWs with other nanostructures regarding the surface area, reactivity, electrical properties, charge transport behavior, optical, magnetic, and piezoelectric properties, and mechanical flexibility. Providing the synthesis and characterization methods, ZnO-NWs’ biosensing processes are also elaborated on surface modification for selectivity, integration with microfluidic systems, enhancing signal transduction, and connecting with biological elements like enzymes, antibodies, and DNA. The chapter also discusses the applications of ZnO-NWs-based biosensors in …

Multimodal Search On A Line, Jared Coleman, Dmitry Ivanov, Evangelos Kranakis, Danny Krizanc, Oscar Morales Ponce

Computer Science Faculty Works

Inspired by the diverse set of technologies used in underground object detection and imaging, we introduce a novel multimodal linear search problem whereby a single searcher starts at the origin and must find a target that can only be detected when the searcher moves through its location using the correct of p possible search modes. The target’s location, its distance d from the origin, and the correct search mode are all initially unknown to the searcher. We prove tight upper and lower bounds on the competitive ratio for this problem. Specifically, we show that when p is odd, the optimal …

Integration Of Artificial Intelligence With A Customized Four-Probe Station For I-V Characteristic Classification And Prediction, Sameh O. Abdellatif, Ahmed Ghanem, Ahmmat Abdel Whahid, Amr Hatem, Belal Ahmed

Electrical Engineering

The incorporation of Artificial Intelligence (AI) is pivotal in automating intricate technical tasks, significantly enhancing accuracy and efficiency while alleviating the burdens of repetitive monitoring traditionally borne by technicians. This study focuses on developing a customized four-probe station integrated with sophisticated AI models aimed at classifying current–voltage () characteristics and extracting essential parameters. Our methodology encompasses the fabrication of precision-engineered gold-plated probes, meticulously assembled with a three-dimensional (3D) moving head to ensure optimal contact and measurement fidelity across a variety of electronic and optoelectronic devices. Data acquisition is executed via a source meter unit, followed by rigorous post-processing utilizing advanced …

Phase Of The Seabed Frequency-Domain Reflection Coefficient: Measurements And Modeling, Charles W. Holland

Electrical and Computer Engineering Faculty Publications and Presentations

The phase of the seabed frequency-domain reflection coefficient potentially contains valuable information on the geoacoustic properties in a layered/refracting seabed. However, heretofore, the phase has not been exploited. Measurements of phase are presented in an area of thick mud at the New England Mud Patch. In addition, a model is presented along with the modeling results. While this is only a first step towards understanding the potential value of exploiting the phase, it seems clear that in some instances, the phase not only contains valuable geoacoustic information, but carries a higher information content than the magnitude.

Design And Implementation Of Uvm-Based Verification Framework For Deep Learning Accelerators, Randa Ahmed Hussein Aboudeif

Theses and Dissertations

Recent advancements in deep learning (DL) have made hardware accelerators, known as deep learning accelerators (DLAs), a preferred solution for numerous high-performance computing (HPC) applications, including speech recognition, computer vision, and image classification. DLAs are composed of hundreds of parallel processing engines to speed up computations and can gain access to pre-trained networks from the cloud or through on-chip memory to implement the DNN inference process. DLA verification is becoming an important and challenging phase. The verification process is required to handle the complex DLA design. Moreover, the reliability of DLAs is critical for assessment as they are involved in …

A Precoding, Companding, And Nonlinearity Reduction Approach To Optimize High-Speed Ado-Ofdm For Visible Light Communication, Swaminathan S

Theses and Dissertations

Using light-emitting diodes (LEDs) for data transfer, visible light communication (VLC) presents a strong substitute for radio frequency communication. Yet, because of the non-linearity of LEDs, conventional Orthogonal Frequency-Division Multiplexing (OFDM) approaches in VLC are limited regarding spectrum efficiency, peak-to-average power ratio (PAPR), and system linearity. Multi-carrier asymmetrically Clipped Optical OFDM (MADO-OFDM) is introduced in this study. For VLC operations based on Optical Orthogonal Frequency Division Multiplexing (O-OFDM), a model-driven Deep Learning (DL) approach has been presented. Utilizing an Auto Encoder (AE) network technology reduced the non-linearity of the LEDs. A proposed improved ADO-OFDM protocol, called MADO-OFDM, adaptively modifies the …

A Cnt Intercalated Co Porphyrin-Based Metal Organic Framework Catalyst For Oxygen Reduction Reaction, Pei-Pei He, Jin-Hua Shi, Xiao-Yu Li, Ming-Jie Liu, Zhou Fang, Jing He, Zhong-Jian Li, Xin-Sheng Peng, Qing-Gang He

Journal of Electrochemistry

The poor electronic conductivity of metal-organic framework (MOF) materials hinders their direct application in the field of electrocatalysis in fuel cells. Herein, we proposed a strategy of embedding carbon nanotubes (CNTs) during the growth process of MOF crystals, synthesizing a metalloporphyrin-based MOF catalyst TCPPCo-MOF-CNT with a unique CNT-intercalated MOF structure. Physical characterization revealed that the CNTs enhance the overall conductivity while retaining the original characteristics of the MOF and metalloporphyrin. Simultaneously, the insertion of CNTs generated adequate mesopores and created a hierarchical porous structure that enhances mass transfer efficiency. X-ray photoelectron spectroscopic analysis confirmed that the C atom in CNT …

Feasibility And Acceptability Of The Mazi Umntanakho Digital Tool In South African Settings: A Qualitative Evaluation, Catherine E. Draper, Caylee J. Cook, Elizabeth A. Ankrah, Jesus A. Beltran, Franceli L. Cibrian, Kimberley D. Lakes, Hanna Mofid, Lucretia Williams, Gillian R. Hayes

Engineering Faculty Articles and Research

To address the need for interventions targeting social emotional development and mental health of young children in South Africa, the Mazi Umntanakho (‘know your child’) digital tool was co-designed, and piloted with caregivers and 3–5-year-old children involved in home visiting programmes promoting early childhood development. The aim of this study was to qualitatively evaluate the feasibility and acceptability of this tool in four urban and four rural low-income communities, from the perspective of home visitors and caregivers. Focus groups were conducted with home visitors (n = 117) and caregivers (n = 72). Issues relating to the feasibility of …

Novel Approach For The Micro Cracks Detection Of Solar Wafers And Cells, Mohd Israil, Arvind Kumar Sharma, Ekta Gupta

Al-Bahir

This paper deals with the review of various existing technique for the microcracks detection in silicon solar cell and wafer. In addition to this, we proposed a novel approach for the machine learning technique for the inspection of the cracks those are existed in the solar cell and wafer and not able to detect by the naked eyes. There are many techniques have been developed by the various researchers around the world to inspect solar cells for defect. All the techniques discussed in this article having some features and some weakness too. This paper present here gives the two-fold solution …

Advanced Prediction Of Events And Temporal Expressions In Medical Text Using The Jena Api: Integrating Ontologies And Deep Learning, Hafida Tiaiba, Lyazid Sabri, Okba Kazar

Turkish Journal of Electrical Engineering and Computer Sciences

The automatic recognition of medical concepts and temporal expressions in narrative clinical text enhances the utility of electronic health records (EHRs) and supports clinical decision-making and research. However, challenges arise due to the complexity of medical language, ambiguity of terms, and variability in expression. To address these issues, the use of medical ontologies significantly improves data management in healthcare. A novel approach integrates various medical ontologies covering drugs, symptoms, diseases, anatomy, disease drivers, and food, and with convolutional neural networks (CNNs) -including Standard, Transposed, and Separable convolution models (CONSEPTR)- to extract both medical events (e.g., clinical departments, treatments, problems) and …

Long-Range Inertia Prediction Considering Contemporary Evolution Of Power Grid Networks, Peter M. Makolo

Tanzania Journal of Engineering and Technology (TJET)

Reduced network inertia due to high penetration levels of non-synchronous generators in modern power systems is becoming a pressing issue. As a result, very quick inertial responses are observed after contingency events in networks. Due to quick inertial responses, there is a practically very limited time interval for control actions in real-time. Thus, system operators need to understand the prior inertia values to plan, control, and operate the network securely. Long-range forecasting of the network's inertia values, in contrast to short-range forecasting techniques, can pinpoint when the network is most likely to be vulnerable in a reasonable time ahead. Thus, …