Digital Commons Network^™

Wavelet-Based Harmonization Of Local And Global Model Shifts In Federated Learning For Histopathological Images, W. Farzana, A. Temtam, K. M. Iftekharuddin

Electrical & Computer Engineering Faculty Publications

Federated Learning (FL) is a promising machine learning approach for development of data-driven global model using collaborative local models across multiple local institutions. However, the heterogeneity of medical imaging data is one of the challenges within FL. This heterogeneity is caused by the variation in imaging scanner protocols across institutions, which may result in weight shift among local models leading to deterioration in predictive accuracy of global model. The prevailing approaches involve applying different FL averaging techniques to enhance the performance of the global model, ignoring the distinct imaging features of the local domain. In this work, we address both …

Toward Inclusivity: Rethinking Islamophobic Content Classification In The Digital Age, Esraa Aldreabi, Mukul Dev Chhangani, Khawlah M. Harahsheh, Justin M. Lee, Chung-Hao Chen

Electrical & Computer Engineering Faculty Publications

In this paper, we implement a comprehensive three-class system to categorize social media discussions about Islam and Muslims, enhancing the typical binary approach. These classes are: I) General Discourse About Islam and Muslims, II) Criticism of Islamic Teachings and Figures, and III) Comments Against Muslims. These categories are designed to balance the nuances of free speech while protecting diverse groups like Muslims, ex-Muslims, LGBTQ+ communities, and atheists. By utilizing machine learning and employing transformer-based models, we analyze the distribution and characteristics of these classes in social media content. Our findings reveal distinct patterns of user engagement with topics related to …

Runtime Performance Of Gamess Quantum Chemistry Application Offloaded To Gpus, Masha Sosonkina, Gabriel Mateescu, Peng Xu, Tosaporn Sattasathuchana, Buu Pham, Mark S. Gordon, Sarom S. Leang

Electrical & Computer Engineering Faculty Publications

Computational chemistry is at the forefront of solving urgent societal problems, such as polymer upcycling and carbon capture. The complexity of modeling these processes at appropriate length and time scales is mainly manifested in the number and types of chemical species involved in the reactions and may require models of several thousand atoms and large basis sets to accurately capture the chemical complexity and heterogeneity in the physical and chemical processes. The quantum chemistry package General Atomic and Molecular Electronic Structure System (GAMESS) has a wide array of methods that can efficiently and accurately treat complex chemical systems. In this …

Accelerating Cavity Fault Prediction Using Deep Learning At Jefferson Laboratory, Md M. Rahman, A. Carpenter, K. Iftekharuddin, C. Tennant

Electrical & Computer Engineering Faculty Publications

Accelerating cavities are an integral part of the continuous electron beam accelerator facility (CEBAF) at Jefferson Laboratory. When any of the over 400 cavities in CEBAF experiences a fault, it disrupts beam delivery to experimental user halls. In this study, we propose the use of a deep learning model to predict slowly developing cavity faults. By utilizing pre-fault signals, we train a long short-term memory-convolutional neural network binary classifier to distinguish between radio-frequency (RF) signals during normal operation and RF signals indicative of impending faults. We optimize the model by adjusting the fault confidence threshold and implementing a multiple consecutive …

Generalized Functions In The Study Of Signals And Systems, Erik I. Verriest, Gunther Dirr, W. Steven Gray

Electrical & Computer Engineering Faculty Publications

We collect three instances where the theory of generalized functions may still make contributions to the study of signals and systems. In the first, a purely algebraic approach is presented for LTI-ODE's, in terms of two operators, D and T, respectively the differentiation operator and the multiplication-by-the-independent-variable operator. This formalism adds simplicity, a duality theory, and nicely generalizes to other classes of operator equations and their solutions. In the second part we extend the classical bilateral Laplace transform to include Bohl functions with support in ℝ by invoking Sato's hyperfunctions. Finally, in the third case we use the Colombeau algebra …

An Enhanced Real-Time Intrusion Detection Framework Using Federated Transfer Learning In Large-Scale Iot Networks, Khawlah Harahsheh, Malek Alzaqebah, Chung-Hao Chen

Electrical & Computer Engineering Faculty Publications

The exponential growth of Internet of Things (IoT) devices has introduced critical security challenges, particularly in scalability, privacy, and resource constraints. Traditional centralized intrusion detection systems (IDS) struggle to address these issues effectively. To overcome these limitations, this study proposes a novel Federated Transfer Learning (FTL)-based intrusion detection framework tailored for large-scale IoT networks. By integrating Federated Learning (FL) with Transfer Learning (TL), the framework enhances detection capabilities while ensuring data privacy and reducing communication overhead. The hybrid model incorporates convolutional neural networks (CNNs), bidirectional gated recurrent units (BiGRUs), attention mechanisms, and ensemble learning. To address the class imbalance, Synthetic …

Enhancing Energy Efficiency With A Dynamic Trust Measurement Scheme In Power Distribution Network, Yilei Wang, Xin Sun, Guiping Zheng, Ahmar Rashid, Sami Ullah, Hisham Alasmary, Muhammad Waqas

Research outputs 2022 to 2026

The application of Intelligent Internet of Things (IIoT) in constructing distribution station areas strongly supports platform transformation, upgrade, and intelligent integration. The sensing layer of IIoT comprises the edge convergence layer and the end sensing layer, with the former using intelligent fusion terminals for real-time data collection and processing. However, the influx of multiple low-voltage in the smart grid raises higher demands for the performance, energy efficiency, and response speed of the substation fusion terminals. Simultaneously, it brings significant security risks to the entire distribution substation, posing a major challenge to the smart grid. In response to these challenges, a …

Blind Source Separation And Denoising Of Underwater Acoustic Signals, Ruba Zaheer, Iftekhar Ahmad, Quoc Viet Phung, Daryoush Habibi

Research outputs 2022 to 2026

Due to the addition of new underwater vessels and other natural noise contributors, the underwater environment is becoming congested and noisy. Undersea monitoring sonobuoys receive multiple mixed acoustic signals from different vessels that need to be separated and identified in the presence of underwater noise (UWN). It is extremely challenging to separate highly correlated acoustic signals from a noisy mixture without prior knowledge of mixing process and propagation channel. Also, in many cases, the separated signals from the noisy mixture doesn’t accurately describe the correct signal. This study proposes a novel multi-stage method to separate underwater acoustic source signals from …

Power And Waiting Time Efficiency At Automatic Toll Gates With The Contactless Card Payment Implementation, Ujang Wiharja, Sri Hartanto

ASEAN Journal on Science and Technology for Development

One method of Electronic Toll Collection (ETC) in Automatic Toll Gate (ATG) currently uses contactless transactions using Radio Frequency IDentification (RFID) technology. Tracking and monitoring objects (the car) with RFID is carried out in real-time and is required to keep up with the speed of an object (the car). The On-Board Unit (OBU) transponder installed on the car's windshield and the Road Side Unit (RSU) installed on the ATG are the main components of the Dedicated Short-Range Communication (DSRC) system, which allows the car and ATG to communicate with each other and carry out transactions, including online toll payments, without …

Application Of Fusion Based Deep Learning Models To Improve Millimeter Wave Beamforming, Abishek Subramanian

Dissertations, Master's Theses and Master's Reports

This study addresses the challenge of selecting millimeter Wave (mmWave) beamforming pairs for vehicle-to-infrastructure (V2I) communication, to mitigate latency in highly dynamic vehicular environments. We investigate the use of out-of-band sensor data as side information to model mmWave ray tracing paths and predicting a subset of top-K optimal beamforming pairs for efficient and low-latency searches. Unimodal-Fusion Deep Learning (F-DL) networks was applied to enhance mmWave beamforming process. We started by first investigating the centralized architecture, and then explored a novel distributed architecture through federated learning to minimize resource and latency overheads. The distributed architecture incorporates two biased client selection strategies: …

The Integration Of Neuromorphic Computing In Autonomous Robotic Systems, Md Abu Bakr Siddique

Dissertations, Master's Theses and Master's Reports

Deep Neural Networks (DNNs) have come a long way in many cognitive tasks by training on large, labeled datasets. However, this method has problems in places with limited data and energy, like when planetary robots are used or when edge computing is used [1]. In contrast to this data-heavy approach, animals demonstrate an innate ability to learn by communicating with their environment and forming associative memories among events and entities, a process known as associative learning [2-4]. For instance, rats in a T-maze learn to associate different stimuli with outcomes through exploration without needing labeled data [5]. This learning paradigm …

Modeling Of Inverter-Based Resources For Hardware In The Loop Testing Of Protection And Control Schemes, Md Aamir Rahmani

Dissertations, Master's Theses and Master's Reports

High penetration of inverter-based resources (IBR) may cause the misoperation of protective relays due to the dynamic nature of fault currents fed by the IBR during short-circuit faults. Misoperation may cause damage to power system equipment and affect the reliability of the power system. This dissertation presents an in-depth investigation into the modeling of IBR in the context of transmission line fault scenarios to understand and analyze the characteristics of fault currents fed by the IBR. The research objectives encompass the development of reliable IBR models capable of accurately replicating fault current behaviors, designing IBR operation control schemes, and implementing …

V2i-Based Adaptive Collision Avoidance For Safety And Traffic Efficiency, Vaishnavi Balambeed

Dissertations, Master's Theses and Master's Reports

To leverage the growing communication and connectivity among modern vehicles, Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) systems are increasingly being used to implement active safety applications. However, current research often overlooks the impact of algorithms such as collision avoidance on traffic flow efficiency. This work investigates the adaptation of a collision avoidance algorithm implemented in V2I to incorporate a variable time headway and spacing control strategy. The proposed approach aims to maintain higher average speeds among vehicles, lower individual vehicle’s waiting, and travel times in the vicinity of the infrastructural unit while simultaneously avoiding collisions; thereby enhancing both safety and traffic …

Implementing Associative Learning Using Neuromorphic Robot, Vinay Kumar Pillalamarri

Dissertations, Master's Theses and Master's Reports

Associative learning, a key cognitive process seen across the animal kingdom, enables organisms to form connections between stimuli and adapt their behaviors based on past experiences. A particularly powerful example is fear conditioning, where animals learn to associate a neutral stimulus with an aversive one, allowing them to predict and avoid potential threats. Inspired by this mechanism, this project implements associative learning on an unmanned ground vehicle (UGV) to develop adaptive behavior through neuromorphic principles. Utilizing Nengo for neural modeling, the UGV learns to associate visual (red color) and tactile (vibration) stimuli through Hebbian learning, a biologically inspired synaptic adaptation …

Particle Accelerator Spin-Transparent Storage Rings For Beyond State-Of-The-Art Science, R. Suleiman, Y. Derbenev, M. Grau, V. Morozov

Physics Faculty Publications

We will describe spin-transparent storage rings that exhibit spin-coherence times of several hours and store a large number of particles and their use in novel applications. For example, these rings can be used to directly measure the electric dipole moment of the electron, relevant to CP violation and matter-antimatter asymmetry in the universe, and to search for dark energy and ultra-light dark matter*. These rings can also serve as a compelling platform for quantum computing. In this presentation, we will describe how spin-transparent rings can be used in conjunction with ion traps to enhance scalability and increase quantum coherence times …

5g New Radio Access And Core Network Slicing For Next-Generation Network Services And Management, Abdullah Ridwan Hossain

Dissertations

In recent years, fifth-generation New Radio (5G NR) has attracted much attention owing to its potential in enhancing mobile access networks and enabling better support for heterogeneous services and applications. Network slicing has garnered substantial focus as it promises to offer a higher degree of isolation between subscribers with diverse quality-of-service requirements. Integrating 5G NR technologies, specifically the mmWave waveform and numerology schemes, with network slicing can unlock unparalleled performance so crucial to meeting the demands of high throughput and sub-millisecond latency constraints.

While conceding that optimizing next-generation access network performance is extremely important, it needs to be acknowledged that …

Distributed Intelligence: Exploring Federated Paradigms Across Computing And Networking On The Edge, Yang Deng

Dissertations

Computer Graphics (CG) revolves around virtual content creation using computational methods, spanning applications from games to visual effects. Typically, the creation of CG content is led by expert practitioners who guide computational algorithms towards satisfactory results. Thus, creating CG content often requires manual iterations encompassing algorithm design, parameter tuning, and aesthetic feedback. This work investigates how to leverage crowd-sourcing to streamline such creation processes, focusing on animation and simulation. In animation, a novel crowd-sourcing framework is proposed for combat animation, enabling users to analyze motion similarities, and retrieve matching motions using novel crowd-sourced motion features. Such features enable quantifying previously …

Comparison Of Dc Motor Speed Calculation Efficiency Between Inductive Proximity Sensor And Rotary Encoder, Dino Dwi Aryanto, S. Sukir

Elinvo (Electronics, Informatics, and Vocational Education)

This study examines the level of effectiveness and efficiency of a sensor on the calculation of the rotational speed (RPM) of a DC motor, considering that the calculation of the rotational speed of an electric motor, both AC motors and DC motors, greatly influences the output of the system. the speed of motor rotation is very influential in several fields, such as power generation, which will affect the output voltage that will be generated. There are many methods for measuring the rotational speed of a motor, including using an inductive proximity sensor and a rotary encoder combined with a PLC …

Gen-Acceleration: Pioneering Work For Hardware Accelerator Generation Using Large Language Models, Durga Lakshmi Venkata Deepak Vungarala

Theses

Optimizing computational power is critical in the age of data-intensive applications and Artificial Intelligence (AI)/Machine Learning (ML). While facing challenging bottlenecks, conventional Von-Neumann architecture with implementing such huge tasks looks seemingly impossible. Hardware Accelerators are critical in efficiently deploying these technologies and have been vastly explored in edge devices. This study explores a state-of-the-art hardware accelerator; Gemmini is studied; we leveraged the open-sourced tool. Furthermore, we developed a Hardware Accelerator in the study we compared with the Non-Von-Neumann architecture. Gemmini is renowned for efficient matrix multiplication, but configuring it for specific tasks requires manual effort and expertise. We propose implementing …

Towards Digital Twins For Optimizing Metrics In Distributed Storage Systems - A Review, May Itani, Layal Abu Daher, Ahmad Hammoud

BAU Journal - Science and Technology

With the exponential data growth, there is a crucial need for highly available, scalable, reliable, and cost-effective Distributed Storage Systems (DSSs). To ensure such efficient and fault tolerant systems, replication and erasure coding techniques are typically used in traditional DSSs. However, these systems are prone to failure and require different failure prevention and recovery algorithms. Failure recovery of DSS and data reconstruction techniques take into consideration different performance metrics optimization in the recovery process. In this paper, DSS performance metrics are introduced. Several recent papers related to adopting erasure coding in DSSs are surveyed together with highlighting related performance metrics …

Adaptation Algorithm For Self-Tuning Of Parameters Of Models Of Multi-Stage Flotation Processes, Nilufar Sharifzhanova, Maksadhan Yakubov, Francesco Gregoretti

Technical science and innovation

Modern methods for solving problems of planning the execution of batches of tasks in multi-stage systems are characterized by the presence of restrictions on their dimensionality, the impossibility of guaranteed obtaining better results in comparison with fixed packages for different values of the input parameters of the problem. In the article, the author solved the problem of optimizing the composition of job packages running in multi-stage systems using the branch and bound method. Research has been carried out on various ways to form package execution orders tasks in multi-stage systems (heuristic rules for ordering packages tasks in the sequence of …

Potential Applications Of Encoders, Erkin Uljaev, Utkirjon Murodillayevich Ubaydullaev

Technical science and innovation

This article explores the applicability of diverse sensor types—such as optical, magnetic incremental encoder and potentiometric sensors—for controlling the turning angle of tractor steering wheels, specifically addressing the control challenges faced by semi-mounted cotton pickers. The discussion encompasses fundamental principles, operational aspects, advantages, and limitations of turning angle sensors prevalent in the industry. Emphasizing advancements in sensor technology, the article recommends sensor options for controlling the steering wheel's turning angle, crucial for enhanced maneuverability and operational efficiency of semi-mounted cotton pickers. Various sensor types, including optical and magnetic encoders and potentiometers, are evaluated for their suitability in this context. Optical …

Indicators Affecting Passenger Service Processes And Their Scientific Interpretation, Maxliyoxon Madaminova Maxamatjon Qizi, Saidazim Amanullayevich Ganihodjayev

Technical science and innovation

Many traffic flow parameters affect the performance of the road network at high voltage. These are low vehicle speeds, high vehicle distances relative to road capacity, and density per unit time (lane occupancy). In turn, a number of factors affect the decrease in traffic speed: the presence of slow-moving vehicles in the stream; pedestrians crossing the road irregularly; increase in traffic flow, etc. The issues of public transportation depend on many factors, each of which requires a separate approach and a complex solution. In large cities around the world, the quality indicators of public transport services, including the issues of …

Multi-Mode Regulation Of The Drying Process Of Industrial Gas, Isamidin Xakimovich Sidikov Pr, Nashvandova Gulruxsor Murot Qizi Phd

Technical science and innovation

Currently, much attention is paid to the issue of energy efficiency of gas processing enterprises. The continuous growth of world prices for energy resources requires constant improvement of the management system, providing the most optimal conditions for the flow of technological processes. A conceptual model of the heat-mass transfer process occurring in the absorber as an object of research has been developed, which characterizes the relationship of the variables involved in the drying process of natural gas, control, measurable and immeasurable, as well as controlled parameters have been selected, which are used to develop and study a mathematical model of …

Reducing Food Scarcity: The Benefits Of Urban Farming, S.A. Claudell, Emilio Mejia

Journal of Nonprofit Innovation

Urban farming can enhance the lives of communities and help reduce food scarcity. This paper presents a conceptual prototype of an efficient urban farming community that can be scaled for a single apartment building or an entire community across all global geoeconomics regions, including densely populated cities and rural, developing towns and communities. When deployed in coordination with smart crop choices, local farm support, and efficient transportation then the result isn’t just sustainability, but also increasing fresh produce accessibility, optimizing nutritional value, eliminating the use of ‘forever chemicals’, reducing transportation costs, and fostering global environmental benefits.

Imagine Doris, who is …

Application Of Quantum Algorithms In The Synthesis Of Dynamic Objects, Noilakhon Yakubova

Chemical Technology, Control and Management

Around the world, the food industry is focusing on achieving energy and resource efficiency. One of the main challenges in the field of process automation is the creation of effective control systems using intelligent technologies to improve the quality of processes and achieve the production of high-quality products with less energy and resources. Therefore, it is necessary to work with a large amount of data. Particular attention is paid to the development of computational algorithms for automated high-speed computational analysis systems for processing this data at high speed. Therefore, the article discusses the use of quantum computing methods in controlling …

Energy Efficiency And Fault Tolerance In Open Ran And Future Internet, Saish Urumkar, Byrav Ramamurthy, Sachin Sharma

Conference papers

Open Radio Access Networks (Open RAN) repre- sent a promising technological advancement within the realm of the future internet. Research efforts are currently directed towards enhancing energy efficiency and fault tolerance, which are critical aspects for both Open RAN and the future internet landscape. In the context of energy saving in Open RAN, there exists a spectrum of methods for achieving energy efficiency. These methods include the toggling of on/off states for different hardware resources such as base station units, distributed units, and radio units. Conversely, for enhancing fault tolerance in Open RAN, Software-Defined Networking (SDN) and OpenFlow based techniques …

Improving Energy Efficiency In Open Ran Through Dynamic Cpu Scheduling, Saish Urumkar, Byrav Ramamurthy, Sachin Sharma

Conference papers

Open RAN is a promising cellular technology that is currently undergoing extensive research for future wireless radio access networks. Achieving optimal energy efficiency in Open RAN poses a significant challenge. This paper introduces a CPU scheduling algorithm that specifically targets this chal- lenge by optimizing energy consumption at the base station while maintaining optimal performance levels. With the goal of minimizing energy consumption, the proposed algorithm dynamically adjusts the CPU core states, seamlessly switching between active and sleep modes based on the load conditions. To evaluate the algorithm’s effectiveness in terms of energy saving and performance, experimental testing is conducted …

Design And Fabrication Of A Low Power 7.2 Terabit Transmitter For Exascale Computing, Scott Mcwilliams

Electrical Engineering Theses and Dissertations

Enhanced Coupled Strength (ECS) gratings fabricated into III-V based devices offer high reflected power per unit length and broad band reflectivity as compared to conventional 1st order gratings, desired qualities for short-haul high speed transmitters that can be implemented without the need for chip-level temperature control, contributing to the low power per transmitted bit. For commercial DBR lasers, the grating reflectivity results in an extremely narrow reflectivity spectrum, which is highly desired for most/many applications, but requires a power hungry thermo-electric cooler to maintain a fixed frequency. The proposed LEAM (laser electro-absorption modulator) requires a broad reflectivity spectrum, which, by …

Series Aperture Coupled Fed Phased Array Antenna, Guang Yang

Electrical Engineering Theses and Dissertations

Phased arrays are employed in a wide range of civil and Military contexts, including RADAR, cellular communications, and satellite communications. However, modern phased-array antennas require complex design and bulky structure at high costs, hindering their implementation in many applications. The critical aspect of a phased array design lies in power splitting with a proper phase to each radiating element. Conventional power splitters such as quarter-wavelength or Wilkinson power splitters suffer problems associated with complex array network and high power dissipation. Furthermore, popular phase shifters such as MEMS switch, ferrite-based or PIN diode have drawbacks of low power-handling capability, expensive packaging, …