Digital Commons Network^™

Fairness And Robustness In Decentralized Federated Learning, Kaichuang Zhang

Theses and Dissertations

Federated Learning (FL) has emerged as a privacy-preserving paradigm that allows multiple clients to collaboratively train a machine learning model without sharing raw data. However, traditional FL relies on a central server for model aggregation, which introduces a single point of failure and makes the system vulnerable to server-side attacks or breakdowns. To address these limitations, Decentralized Federated Learning (DFL) has been proposed, eliminating the need for a central server and enhancing system resilience. Despite these advantages, DFL faces critical challenges related to fairness and robustness, especially under non-i.i.d. data distributions and adversarial conditions. In this thesis, we propose a …

Spin Coater Design With Pid Algorithm Using Polynomial Regression Approach And Bias Tuning For Tio2 Deposition Process, Geo Surya Andika, Nofrijon Sofyan, Donanta Dhaneswara, Akhmad Herman Yuwono

Journal of Materials Exploration and Findings

The thin-film deposition technique using spin coating offers a cost-effective alternative to Chemical Vapor Deposition (CVD) and Physical Vapor Deposition (PVD). The spin-coating process requires precise control of the motor drive system to ensure that the rotational speed, measured in rotations per minute (RPM), aligns with the set point and remains stable. This study presents the design and development of a spin coater prototype to achieve uniform thin-film deposition. The control method employed utilizes a Proportional-Integral-Derivative (PID) algorithm, incorporating a polynomial approach with bias tuning. The PID control was chosen to achieve stable operation in a non-linear system. The performance …

Optimizing And Training An Svm-Based Breast Cancer Tumor Classifier, Kevin Lopatka

Master's Theses

With advancements in technology, turning to machine learning has become a popular choice for aiding clinicians in the diagnoses of breast cancer malignancies. While the neural networking approach has been vetted thoroughly, this work aims to take advantage of traditional machine learning techniques; mainly support vector machine learning and the optimizing of feature extraction. The discrete-wavelet transform is used in the feature extraction stage of machine learning. Previous works that use this feature extraction technique are analyzed and expanded upon by utilizing a variety of different wavelets as well as other color-spaces with the goal of achieving higher result metrics …

Enhanced Post-Capture Automatic White Balance For Srgb Images, Eric Huang

Master's Theses

Automatic white balancing (AWB) aims to correct color casts caused by varying illumination conditions, typically assuming access to RAW sensor data. However, many real-world applications involve only sRGB images that have already been processed by in-camera pipelines. In these cases, traditional AWB algorithms often underperform due to the nonlinear transformations done by these pipelines.

This thesis builds upon a data-driven color correction framework introduced by Afifi et al. that relies on RGB-UV histograms and learned color transforms. A revised automatic white balancing (AWB) framework that improves both color accuracy and runtime efficiency is proposed. A fallback routine is implemented to …

Toward The Application Of Natural Language Processing In Electronic Health Record Analysis For Taxonomy Development, Latoya Mcdonald

All Dissertations

Electronic health records (EHRs) are pivotal resources for nurse practice because they increase the timeliness and reliability of patient information at the point of care and support access by multiple healthcare providers and the individual patients themselves. However, it is widely recognized that data extraction from EHRs is challenging due to the variability in the language used in clinical care notes and the lack of standardized terminology across healthcare systems. The broad objective of this dissertation is to develop taxonomy-based classification models for nursing care by applying feature engineering approaches to EHRs that include nursing care of ostomy patients following …

Towards Mitigation Of The Light Network Load Performance Penalty Of The Network Link Outlier Factor (Nlof), Jaime Merin Guzman

Open Access Theses & Dissertations

Detecting and localizing faults in communication networks is critical to maintaining reliable and efficient network operations. The Network Link Outlier Factor with Most Likely Link (NLOF: MLL) algorithm has demonstrated its potential to automate this task but suffers from significant performance degradation under low network load conditions, where limited network flow data reduces its ability to localize faults. This thesis proposes and evaluates the performance of a synthetic traffic generation algorithm to be used with NLOF:MLL. This algorithm strategically injects synthetic flows that supplement the insufficient real network flows, thereby improving NLOF:MLL's performance under low-load conditions. Specifically, we select network …

Blind Construction Of A Party Check Matrix For Arbitrary Linear Block Codes, Aaron J. Womack

All Graduate Theses and Dissertations, Fall 2023 to Present

Communication systems are systems in which a transmitter sends data across a channel to a receiver. In any modern communication system, Forward Error Correction (FEC) is used to detect and correct errors that occur during transmission. As communication systems have developed over the years, many FEC algorithms have been proposed. Each FEC algorithm has parameters that can be selected based on the needs of the communication system. Typically, the transmitter and receiver are both aware of the FEC parameters, but in some cases the receiver may not know how the transmitter encoded its message. In this case, the receiver must …

Generative Ai For 3d Printed Antenna Design, Jennifer Ann Chavez

Open Access Theses & Dissertations

This research explores the integration of generative artificial intelligence (AI) with a physics-informed particle swarm optimizer (PSO) to develop 3D printable microstrip patch antennas. A neural network was trained on a dataset of microstrip patch antenna geometries and their corresponding performance metrics: return loss and gain. The PSO used a fitness function prioritizing low return loss in potential antennas, eventually yielding novel antenna geometries with parasitic components. 3D printing constraints were also hard coded into the framework, thus preventing any geometries being generated that cannot be fabricated. When simulated using Ansys HFSS, the AI generated microstrip patch antennas exceeded the …

Real Time Adaptive Control Of A Pid Via Genetic Algorithm Machine Learning Systems, Cemre Tas

Graduate Theses and Dissertations

The most common control method that is utilized by all industries across the world is the proportional-integrative-derivative controller (PID) due the relatively low cost and complexity of the system. However, there are draw-backs with PIDs, it is not adaptative to a changing system, so it works on nominal systems, and it starts breaking down when a system begins to have a non-linear response. The method chosen to overcome both is the utilization of machine learning with the use of genetic algorithms.

This method allows any PID system to be capable of adapting in real-time, while not adding significant additional cost …

Real-Time Active Thermal Management And Degradation Forecasting Of Power Electronics Building Blocks In All-Electric Ships, Ali Moghassemi

All Dissertations

With advancements in semiconductor technology, power electronic devices play a critical role in modern power systems, enabling efficient energy conversion in applications such as renewable energy integration, electric vehicle drives, industrial automation, and Navy ship power systems. However, the increasing use of power converters presents challenges such as harmonic reduction, cost optimization, reliability improvement, and thermal management, especially in weight- and space-constrained environments like wind turbines and shipboard systems. High-frequency switching, while reducing passive filter size, increases thermal stress on semiconductor devices, impacting efficiency and longevity. Active thermal control, which regulates junction temperature through power loss management, and degradation forecasting, …

Advanced Day-Ahead Scheduling Of Hvac Demand Response Control Using Novel Strategy Of Q-Learning, Model Predictive Control, And Input Convex Neural Networks, Rahman Heidarykiany, Cristinel Ababei

Electrical and Computer Engineering Faculty Research and Publications

In this paper, we present a Q-Learning optimization algorithm for smart home HVAC systems. The proposed algorithm combines new convex deep neural network models with model predictive control (MPC) techniques. More specifically, new input convex long short-term memory (ICLSTM) models are employed to predict dynamic states in an MPC optimal control technique integrated within a Q-Learning reinforcement learning (RL) algorithm to further improve the learned temporal behaviors of nonlinear HVAC systems. As a novel RL approach, the proposed algorithm generates day-ahead HVAC demand response (DR) signals in smart homes that optimally reduce and/or shift peak energy usage, reduce electricity costs, …

Empowering Optimal Operations With Renewable Energy Solutions For Grid Connected Merredin Wa Mining Sector, Md Ohirul Qays, Ravi Kumar, Minhaz Ahmed, Stefan Lachowicz, Uzma Amin

Research outputs 2022 to 2026

Mining sectors require a continuous and reliable power supply; however, reliance on traditional grid utilities results in high costs and disruptions and increases extreme carbon emission. The Merredin WA sector seeks to resolve critical energy challenges affecting mining operations in Western Australia. Thus, this research proposes an optimal solar PV system with battery storage and backup generation for the mining sector to ensure a stable and cost-effective power supply that reduces harmful environmental effect. A hybrid data-driven long short-term memory (LSTM)-classical optimization framework is designed here, thereby optimizing PV-battery storage operational cost savings and energy usage. The optimization results indicate …

C-Band Air To Ground Communication System For Uav, Mubark Alghamdi

Theses and Dissertations

C band spectrum 5030-5091 MHz is allocated for command-and-control communication services with unmanned aircraft systems. This document evaluates the possibility of using 3GPP 5G standards for provisioning of such services. Channelization of the spectrum and major system parameters are proposed. The performance of the proposed system in channel fading environment is evaluated using MATLAB based simulations. The evaluations examine SINR, and average throughput of the proposed system at different altitudes of the unmanned aircraft system. MATLAB simulations are used to evaluate system performance in free-space environments. Signal-to-Interference-plus-Noise Ratio (SINR) and Reference Signal Received Power (RSRP) are predicted at different UAS …

Improving Image Quality In Electrical Capacitance Tomography Using Otsu Thresholding, Josiah Nombo

Tanzania Journal of Engineering and Technology (TJET)

Electrical Capacitance Tomography (ECT) is an imaging technique used in industrial process monitoring, particularly for monitoring and measuring the composition of multiphase flows. Despite its widespread application, the commonly used Linear Back Projection (LBP) algorithm often produces low-quality images due to its limited ability to handle high permittivity contrasts and nonlinearities. This study investigates the use of Otsu thresholding as a post-processing technique to enhance ECT image quality. By maximizing inter-class variance in the image histogram, Otsu thresholding improves contrast, clarity, and structural definition, enabling more effective segmentation of oil and gas components in multiphase flows. The proposed Otsu-based reconstruction …

Development Of A Microcontroller-Based Intelligent Traffic Light Control System For Vehicular Movement In T-Junctions, Frederick O. Ehiagwina

Tanzania Journal of Engineering and Technology (TJET)

This research is devoted to the issue of regulating traffic congestion in major cities using light-dependent resistors coupled with the PIC16F877A microcontroller. This study proposes an intelligent traffic control system for T-Junctions, utilizing sensing and control to optimize traffic flow through dynamic phase adjustments and congestion reduction, enabled by a microcontroller-based decision-making system. The proposed system reduces traffic congestion, automates control, and enhances safety, minimizing accidents and lowering infrastructure costs. Under simulated environment, it demonstrates an average response time of 50 ms and achieves 99% accuracy in displaying the correct countdown. Finally, the number of state transitions handled per minute …

Investigation Of The Electrical Capacitance Tomography System For Determining The Spatial Distribution Of Moisture In Grain Storage, Shamte J. Kawambwa

Tanzania Journal of Engineering and Technology (TJET)

Excessive moisture content (MC) in stored grains promotes the growth of fungi and molds, which affects the quality of the grains. Effective grain monitoring methods are essential for detecting and managing grain spoilage. Electromagnetic imaging (EMI) techniques provide a promising alternative to traditional techniques by visualizing the spatial distribution of moisture within grains rather than merely average MC values offered by traditional techniques. However, existing EMI approaches often use hard-field waves, which are expensive and fragile. This study introduces an Electrical Capacitance Tomography (ECT) system that employs soft-field waves to monitor the moisture content of the grains. The system was …

Design And Performance Analysis Of Fiber Bragg Grating Temperature Sensor For Industrial Processes Sensing Applications, Paul Stone Stone Brown Macheso S.B.

Tanzania Journal of Engineering and Technology (TJET)

The Fiber Bragg Grating (FBG) sensor has become a widespread sensing device because of its small size, passive design, immunity to electromagnetic interference, and direct ability to measure physical properties like temperature and strain. Recently, femtosecond infrared laser processing and regeneration techniques have resulted in the development of stable high-temperature gratings, which are a powerful tool in smart factories, an aspect of the fourth Industrial Revolution (4IR), and show promise for application in harsh environments like high pressure, high temperature, or ionizing radiation. The development of stable high-temperature gratings that can withstand harsh environmental factors like high temperatures, pressures, and …

Clustering Mini-Grids To Enhance Power Systems Reliability In Distributed Generation, Santos Kihwele

Tanzania Journal of Engineering and Technology (TJET)

This study investigates the effectiveness of clustering mini-grids as a method to improve the reliability and operational stability of distributed generation systems in remote areas, particularly where renewable energy sources are predominant. As renewable resources like solar and wind are increasingly integrated into mini-grids, these systems face various challenges, particularly in maintaining stable voltage and frequency across interconnected networks. Such issues are compounded by the intermittent nature of renewable energy sources and the lack of extensive communication infrastructure in rural or resource-constrained settings. To address these control challenges, this study applies droop control techniques to two mini-grids in Uganda, utilizing …

Synthetic Inertia Provision For Load Frequency Control In Networks With High Penetration Of Renewable Energy Sources, Paulina Mkoi

Tanzania Journal of Engineering and Technology (TJET)

The integration of renewable energy sources (RESs) such as solar photovoltaic (PV) and wind energy has become a promising solution as the world shifts toward clean energy. Solar PV and wind resources are increasingly replacing conventional synchronous generators, leading to reduced system inertia and increased vulnerability to frequency instability during disturbances. To address this challenge, this study proposes a novel synthetic inertia provision strategy using a battery energy storage system (BESS) integrated alongside solar PV. The proposed method dynamically compensates for the loss of inertia by considering the variability of solar PV output due to changes in irradiance and temperature. …

Artificial Intelligence Applications For Grid-Connected Solar Inverters, Utkirjon Ubaydullaev, Sarvinoz Mirzaeva, Hasan Mustafoev

Chemical Technology, Control and Management

The increasing global demand for renewable energy has highlighted the importance of grid-connected solar inverters in ensuring efficient and stable power conversion. However, challenges such as fluctuations in solar energy generation, grid disturbances, and power quality issues necessitate advanced control strategies. The integration of artificial intelligence (AI) into solar inverters presents a transformative solution, enhancing performance, adaptability, and reliability in real-world applications.

This review explores the role of AI techniques, including machine learning (ML), deep learning (DL), fuzzy logic, and reinforcement learning (RL), in optimizing key inverter functionalities such as maximum power point tracking (MPPT), fault detection, power quality enhancement, …

Static Characteristics Of An Electromagnetic Three-Phase Reactive Power Sensor For Converting Asymmetric Currents, Timur Urunbayevich Kurbaniyazov

Chemical Technology, Control and Management

This article discusses the processes in the elements and structures of three-phase electromagnetic current sensors used in measuring and controlling three-phase asymmetric reactive power in power supply systems, research models of quantities and parameters, physical mechanisms, and mathematical formulas based on graphical models.

Algorithms For Feature Extraction And Optimisation Of Object Recognition Operator, Hudayberdiev Xakkulmirzayevich Mirzaakbar, Bobomurod Mamitjonovich Tojiboev, Feruza Komiljonovna Samadova

Chemical Technology, Control and Management

This paper deals with the development and analysis of feature extraction and optimisation algorithms for object recognition operators. Different algorithms are used to improve the efficiency of recognition operators in the automatic analysis of remote sensing images. The information model of objects and methods for selecting, extracting and optimising their features have been studied. The issue of extracting important features of objects using spectral, textural and statistical features and constructing optimal operators based on them has also been studied. Effective approaches based on the theory of convex hulls and multidimensional analysis methods have been proposed, taking into account the mutual …

Application Of Quantum Algorithms In Optimization Of Cognitive Decision-Making Systems, Noilakhon Yakubova

Chemical Technology, Control and Management

The article analyzes the potential of quantum algorithms for optimizing cognitive decision-making systems in production processes in the energy sector. Compared with traditional algorithms, quantum algorithms allow high-speed processing of large amounts of variable data in real time and solving multiparameter problems based on an integrated approach. The study considers uncertainties and issues of increasing efficiency in the processes of production and distribution of electricity using a cognitive model. The integration of quantum algorithms into this model allows developing optimal strategies for using resources in production. A heating boiler was taken as a control object, and taking into account its …

Algorithms For Fast Fire Risk Prediction And Real-Time Data Processing, Mirzoyan Mirzaaxmedovich Kamilov, Tolaniddin Ramziddinovich Nurmukhamedov, Oybek Zokirovich Koraboshev, Bakhodir Saydullayevich Achilov

Chemical Technology, Control and Management

Ensuring fire safety in facilities with high fire risk is one of the pressing problems of modern society. Nowadays, there is a great need for accurate and effective prediction systems for fire prevention and rapid response. Since traditional methods do not provide the ability to quickly analyze and predict in real time, the development of algorithms and modern approaches using modern technologies is of great importance. This article analyzes fire risk prediction algorithms, their principles of operation and effectiveness, and considers methods for assessing and predicting fire risk using Artificial Intelligence (AI), Machine Learning (ML), and Big Data technologies. The …

Detection Of Http Flood Attacks Based On Machine Learning Algorithms, Norbek Karimov, Furkat Rakhmatov, Oybek Xolmuminov

Chemical Technology, Control and Management

This paper analyzes the effectiveness of Random Forest and SVM models for detecting HTTP Flood attacks. Experimental results demonstrate that both models achieve high accuracy. Evaluation was conducted using Precision, Recall, and F1 Score metrics. Additionally, key features of network traffic were extracted through correlation analysis to enable real-time application of the models in attack detection. The findings provide important insights into detecting DDoS attacks using machine learning and improving model performance.

Power-Beaming: Wireless Energy Transfer Using Lasers, Spencer L. Barnett

ATU Scholars Symposium

The objective of the project is to implement a wireless energy transfer system utilizing laser technology. This system involves modulating the laser’s beam profile and spatial distribution through precise optical manipulation. The energy transmitted by the laser is captured by a photovoltaic array, commonly referred to as a solar panel, which is engineered to convert incident photons into direct current (DC) electrical power. The current challenge is to develop a reliable wireless energy transfer mechanism capable of operating over extended distances, thereby overcoming the constraints imposed by wired connections, particularly in environments where wiring is impractical, such as in space. …

Variation Of Membrane Electrode Assembly Catalyst Layer In Unitized Regenerative Fuel Cell, Yollanda Nurcholifah, Dedi Rohendi, Edy Herianto Majlan, Nirwan Syarif, Addy Rachmat, Dwi Hawa Yulianti, Nyimas Febrika S

Journal of Electrochemistry

A unitized regenerative fuel cell (URFC) is a device that may function reversibly as either a fuel cell (FC) or water electrolysis (WE). An important component of this device is the Membrane electrode assembly (MEA). Therefore, this study aimed to compare the performance outcomes of MEA using electrodes with single and three catalyst layers. This study measured Electrochemical Surface Area (ECSA), Electrochemical Impedance Spectroscopy (EIS), X-ray Diffraction analysis (XRD), and X-ray Fluorescence (XRF). Furthermore, the round-trip efficiency (RTE) of the MEA, as well as the performance in FC and WE mode, was measured. In comparison, The ECSA values of Pt-Ru/C …

Performance Of Co2/H2O Co-Electrolysis In A Flat-Tube Solid Oxide Electrolysis Cell Stack Under Air-Free Environment, Xiao-Hui Zhong, Fei Wang, An-Qi Wu, Bei-Bei Han, Jian-Xin Wang, Wan-Bing Guan

Journal of Electrochemistry

This work investigates the transient performance and stability of CO₂/H₂O co-electrolysis in an air-free environment using a flat-tube solid oxide electrolysis cell (SOEC) stack. The results show that the transient behavior of the stack with and without blowing gas in the air electrode is almost the same. With a current density of 0.67 A·cm⁻²@750 °C, the stack operated for over 200 h under co-electrolysis conditions with no air blowing, and the voltage drop rate of the stack was approximately 0.203%/100 hours. Microstructure analysis reveals significant loss of Ni particles and formation of an insulating …

Electrocatalytic Nitric Oxide Reduction To Yield Ammonia Over Fe3C Nanocrystals, Sen Lin, Lang Zhang, Tong Hou, Jun-Yang Ding, Zi-Mo Peng, Yi-Fan Liu, Xi-Jun Liu

Journal of Electrochemistry

Nitric oxide (NO), which generally originates from vehicle exhaust and industrial flue gases, is one of the most serious air pollutants. In this case, the electrochemical NO reduction reaction (NORR) not only removes the atmospheric pollutant NO but also produces valuable NH₃. Hence, through the synthesis and modification of Fe₃C nanocrystal catalysts, the as-obtained optimal sample of Fe₃C/C-900 was adopted as NORR catalyst at ambient conditions. As a result, the Fe₃C/C-900 catalyst showed an NH₃ Faraday efficiency of 76.5% and an NH₃ yield rate of 177.5 μmol·h^–1·cm^{–2 …}

Ordering Degree Regulation Of Pt2Nico Intermetallics For Efficient Oxygen Reduction Reaction, Chen-Hao Zhang, Han-Yu Hua, Jun-Hao Yang, Qian Zhang, Chang Yang, De-Li Wang

Journal of Electrochemistry

Alloying transition metals with Pt is an effective strategy for optimizing Pt-based catalysts toward the oxygen reduction reaction (ORR). Atomic ordered intermetallic compounds (IMC) provide unique electronic and geometrical effects as well as stronger intermetallic interactions due to the ordered arrangement of metal atoms, thus exhibiting superior electrocatalytic activity and durability. However, quantitatively analyzing the ordering degree of IMC and exploring the correlation between the ordering degree and ORR activity remains extremely challenging. Herein, a series of ternary Pt₂NiCo intermetallic catalysts (o-Pt₂NiCo) with different ordering degree were synthesized by annealing temperature modulation. Among them, the o-Pt …