Digital Commons Network^™

Hatt-Flow: Hierarchical Attention-Flow Mechanism For Group-Activity Scene Graph Generation In Videos, Naga Venkata Sai Raviteja Chappa, Pha Nguyen, Thi Hoang Ngan Le, Page Daniel Dobbs, Khoa Luu

Electrical Engineering and Computer Science Faculty Publications and Presentations

Group-activity scene graph (GASG) generation is a challenging task in computer vision, aiming to anticipate and describe relationships between subjects and objects in video sequences. Traditional video scene graph generation (VidSGG) methods focus on retrospective analysis, limiting their predictive capabilities. To enrich the scene-understanding capabilities, we introduced a GASG dataset extending the JRDB dataset with nuanced annotations involving appearance, interaction, position, relationship, and situation attributes. This work also introduces an innovative approach, a Hierarchical Attention–Flow (HAtt-Flow) mechanism, rooted in flow network theory to enhance GASG performance. Flow–attention incorporates flow conservation principles, fostering competition …

Sensorless Control Of Low Inductance Coreless Afpm Machines For Fault-Tolerant Operation Of Propulsion Systems, Yaser Chulaee, Ali Mohammadi, Aaron M. Cramer, Dan M. Ionel

Electrical and Computer Engineering Graduate Research

In motor-drive systems utilized in safety-critical applications and demanding conditions like electric aircraft propulsion systems, the reliability of the system is greatly affected by position sensors, given their susceptibility within the motor drive system. Consequently, there is a need to eliminate sensors in vector-controlled motor drives to decrease overall hardware complexity and expenses, bolster the mechanical durability and dependability of the drive system. In this paper, a fault-tolerant sensorless control system for low inductance coreless axial flux PM (AFPM) machines, integrated into electric aircraft propulsion systems, is introduced. The proposed control system spans a wide operating range, from zero to …

Multi-Hop And Automated Testing Of Wide-Area Network Radio Systems, Zachary C. Numa, Joseph S. Nuccio

Electrical Engineering

Requests for low-power and versatile wide-area Internet-of-Things (IoT) networks are becoming more prevalent with upcoming research in low-data rate ad-hoc mesh networks. Connections to terrestrial satellites have proven promising methods for increasing range capabilities for wide area networks (WAN). As research in communication with IoT networks and satellites progresses, reliable multi-hop mesh networks for Earth-based communication are still necessary to develop the base for satellite communication. These multi-hop communication mesh networks are being developed to allow communication where Line-of-Sight (LOS) from A to B is incapable due to environmental barriers. Hence, communication is possible without LOS by providing an intermediate …

Autonomous Apple Harvester Robot, Jack Ryan Cline, Tyus Green, Devon Woolston

Electrical Engineering

As agricultural demands rise and manual labor costs increase, there has become a dire need to automate apple harvesting. However, the precision and speed necessary for cost-efficient apple harvesting pose a significant challenge for robotic automation. To maintain cost-effective production, a harvester must be able to operate fast enough and long enough to compete with human labor. It must also be able to navigate and traverse apple orchards autonomously and pick apples without damaging the fruit or tree. This project presents an apple harvesting robot that uses a Mask R-CNN vision system with an RGB-D camera to detect the location …

Impact Of Operational Ladar Occlusions On Point Cloud Instance Segmentation, Andrew D. Gibson

Theses and Dissertations

Data exploitation techniques are the enabler for technological advancements in military ISR applications of ladar ISR. By identifying instances of military objects in observed scenes, point cloud deep learning models can unlock new standards of real-time information delivery to warfighters. Although current deep learning training datasets do not include real-world collection occlusions consistent with military applications, this research characterizes SPT model performance by adding occlusions to the DALESObjects dataset via artificial flyby simulations.We find that a baseline model trained on unoccluded data suffers performance degradation on both semantic and instance segmentation tasks when evaluated on occluded data, but that the …

Remote Profiling Of Atmospheric Turbulence: Enhanced Resolution With Stacked Rayleigh Beacons In Tardis, Benjamin C. Wilson

Theses and Dissertations

A stacked beacon turbulence profiling methodology has been introduced and applied to have increased profiling on the Turbulence and Aerosol Research and Investigation System (TARDIS). The model was derived and demonstrated the applicability through discussion on data processing and inversion processes. The methodology was applied for two different nighttime experiments, one in Summer and one in Fall. C 2 n profiles were derived into the 1300 m altitude ranges for both nights and the summer experiment was compared to a co-located DELTA Sky measurements and LEEDR generated Climatological profiles. The comparison implied promise in the methodology with additional work needed …

Gps/Imu Board, Luke Chen, Steve Tran

Electrical Engineering

Providing information on a vehicle’s location during a competition can be used to provide greater insight to progress the car is making or what portion of the track caused failure. As a result, we will be designing a board that includes a Global Positioning System (GPS) and Inertial Measurement Unit (IMU) module to provide position coordinates, which is driven by an STM32 processor to feed into the DAQ through Controller Area Network (CAN) protocol.

The GPS module will produce an initial positioning and will continue to do so unless it is unable to create a solution, possibly due to over-arching …

Prescribed-Time Nash Equilibrium Seeking For Pursuit-Evasion Game, Lei Xue, Jianfeng Ye, Yongbao Wu, Jian Liu, D. C. Wunsch

Electrical and Computer Engineering Faculty Research & Creative Works

Dear Editor, this letter is concerned with prescribed-time Nash equilibrium (PTNE) seeking problem in a pursuit-evasion game (PEG) involving agents with second-order dynamics. In order to achieve the prior given and user-defined convergence time for the PEG, a PTNE seeking algorithm has been developed to facilitate collaboration among multiple pursuers for capturing the evader without the need for any global information. Then, it is theoretically proved that the prescribed-time convergence of the designed algorithm for achieving Nash equilibrium of PEG. Eventually, the effectiveness of the PTNE method was validated by numerical simulation results.

Performance Analysis Of Underground-To-Aboveground Communication In Agricultural Iot Networks, Irfana Ilyas Manzil

Theses

This thesis investigates the potential of LoRa, a low-power, wide-area networking technology, for establishing reliable communication between underground sensors and aboveground infrastructure. We comprehensively analyze LoRa's performance in both single-hop and multi-hop configurations, considering the impact of diverse environmental factors such as soil composition, moisture content, underground transmission distance, and path loss on signal propagation. We delve into the crucial role of the spreading factor (SF) within the LoRa communication system, analyzing its influence on network performance. Furthermore, we develop a comprehensive mathematical model for bit error rate (BER) under various channel conditions, including additive white Gaussian noise (AWGN) and …

Unconventional Computing With Photonic Oscillator Networks, Mostafa Honari Latifpour

Dissertations, Theses, and Capstone Projects

The ever-increasing demand for data processing and the challenges in scaling traditional computing architectures are driving intensive research into alternative computing paradigms. Optical computing has garnered renewed attention since the 2010s, driven by its potential to accelerate specialized computational tasks such as combinatorial optimization and neural networks.

Coherent light sources including lasers and parametric oscillators have been around for decades and become indispensable tools in modern technology, but these photonic oscillators are also nonlinear dynamical systems that can exhibit emergent, complex phenomena, especially when coupled in arrays. These nonlinear optical systems have recently been shown to be capable of doing …

Network Slicing And Noma Enabled Mobile Edge Computing For Next-Generation Networks, Mohammad Arif Hossain

Dissertations

The advent of next-generation wireless networks ushers in a new era of potential, harnessing cutting-edge technologies like mobile edge computing (MEC), non-orthogonal multiple access (NOMA), and network slicing as pivotal drivers of transformation. Within this landscape, an innovative approach is proposed by introducing a NOMA-enabled network slicing technique within MEC networks. This approach aims to achieve multiple objectives: meeting stringent quality of service requirements, minimizing service latency, and enhancing spectral efficiency. By seamlessly integrating NOMA with network slicing in edge computing environments, significant reductions in overall latency are achieved, alongside ensuring optimal resource allocation for NOMA users. To address these …

Integrating Laser Charging And Drones For Secure Edge Computing, Weiqi Liu

Dissertations

Drone-mounted base stations (DBSs) have emerged as a promising solution to enhance the flexibility and coverage of wireless networks, potentially revolutionizing communication systems. This dissertation explores the integration of DBSs into 5G and beyond networks, focusing on methodologies to optimize their deployment and performance. A laser charging-enabled DBS framework is proposed to extend flight time and enhance network coverage. By leveraging laser charging technology, the DBS can receive continuous energy transmission from a ground-based charging station while providing communication services to users. The framework is formulated as an optimization problem to jointly maximize flight time and communication data rate, while …

Computational Microscopy For Biomedical Imaging With Deep Learning Assisted Image Analysis, Yuwei Liu

Dissertations

Microscopy plays a crucial role across various scientific fields by enabling structural and functional imaging with microscopic resolution. In biomedicine, microscopy contributes to basic research and clinical diagnosis. Conventionally, optical microscopy derives its contrast from the amplitude of the optical wave and provides visualization of the physical structure of the sample qualitatively. To understand the function at the cellular or tissue level, there is a need to characterize the sample quantitatively and explore contrast mechanisms other than light intensity. Image enhancement or reconstruction from microscopic imaging systems is known as computational microscopy, and it involves the application of computational techniques …

Interaction Of Particles With Plasma And Shock Produced By Pulsed Spark Discharge, Shomik Mukhopadhyay

Dissertations

Interactions of powders with high-temperature plasma and shockwaves occur in diverse scenarios, such as nuclear blasts, accidental industrial dust explosions, solid propellant combustion in explosive charges and when removing contaminants from surfaces. Electrostatic Discharge (ESD), known for generating shock and plasma, is a promising lab-scale technique for simulating these interactions. Studies with ESD involved placing powders near a spark-producing gap between electrodes and observing mechanical and chemical processes like particle motion and ignition. A limited range of spark conditions and material properties have been tested, which facilitated the development and validation of preliminary computational models describing this system. Significant gaps …

Machine Learning-Based Design Of Doppler Tolerant Radar, Kyle Peter Wensell

Dissertations

In this work, machine learning theory is applied to the design of a radar detector in order to train a machine learning-based detector that is robust against Doppler shifts. The radar system is designed to work with data that would be otherwise intractable to conventional optimal detector design, such as transmitted noise waveforms and the effects of one-bit quantization at the receiver. The detection performance of the one-bit receiver is shown to match the performance of the derived square-law sign correlator detector. The resulting learning-based detector also introduces Doppler tolerance to the system, which allows for the successful detection of …

Information Theoretic Bounds For Capacity And Bayesian Risk, Ian Zieder

Dissertations

In this dissertation, the problem of finding lower error bounds on the minimum mean-squared error (MMSE) and the maximum capacity achieving distribution for a specific channel is addressed. Presented are two parts, a new lower bound on the MMSE and upper and lower bounds on the capacity achieving distribution for a Binomial noise channel. The new lower bound on the MMSE is achieved via use of the Poincare inequality. It is compared to the performance of the well known Ziv-Zakai error bound. The second part considers a binomial noise channel and is concerned with the properties of the capacity-achieving distribution. …

Graph-Based Modeling And Optimization Of Wpt Systems For Evs, Matthew J. Hansen, Greg Droge, Abhilash Kamineni

Electrical and Computer Engineering Student Research

A model of a system of wireless power transfer (WPT) pads is developed, where each WPT pad is modeled as a node and the coupling between pads is modeled as graph edges. This modeling approach is generalized to admit primary, secondary, and booster coils, where power can flow among the pads and a pad can fill multiple roles. An excitation in one pad induces voltage and current in all neighboring pads, causing each pad to act as both a booster coil and either a transmitter or a receiver. Power flow through the entire system can be modeled with the graph …

The Next Strike: Pioneering Forward-Thinking Attack Techniques With Rowhammer In Dram Technologies, Nakul Kochar

Theses

In the realm of DRAM technologies this study investigates RowHammer vulnerabilities in DDR4 DRAM memory across various manufacturers, employing advanced multi-sided fault injection techniques to impose attack strategies directly on physical memory rows. Our novel approach, diverging from traditional victim-focused methods, involves strategically allocating virtual memory rows to their physical counterparts for more potent attacks. These attacks, exploiting the inherent weaknesses in DRAM design, are capable of inducing bit flips in a controlled manner to undermine system integrity. We employed a strategy that compromised system integrity through a nuanced approach of targeting rows situated at a distance of two rows …

Marking Estimation In Petri Nets Using Dynamic Mode Decomposition, Aditya Kale

Theses

Petri Nets (PNs) are a well-established framework for modeling and analyzing complex systems with interacting, concurrent processes. This thesis extends traditional Petri Net methodologies by integrating Dynamic Mode Decomposition (DMD), a technique originally developed for fluid dynamics, to analyze Continuous Petri Nets (CPNs). By applying DMD to CPN marking evolution, this research constructs a reduced-order model that captures its dynamics through dynamic modes and eigenvalues, enabling prediction of future markings without detailed knowledge of transition firings or underlying deterministic models. The principal contribution of this research is extending the kit of tools available for analysis of CPN dynamics, providing insights …

Design And Implementation Of Non-Isolated High Gain Dc-Dc Converter For Photovoltaic Application, Rajesh R

Theses and Dissertations

Fossil fuel-based power plants emit 25% of greenhouse gases and 40% of carbon emissions globally. Therefore, several countries focus on deploying RES-based electricity production (such as solar and wind). As per the International Energy Agency report, solar PV might be the lowest-cost option for generating electricity in the future. Solar energy is highly emission-free, but it is still a key challenge in procuring the maximum amount of energy from solar PV due to its non–linear characteristics. Therefore, a DC-DC converter must integrate with solar PV to increase the output voltage level. Many existing topologies exist in the literature, but the …

Coordination Of Srf-Pll And Grid Forming Inverter Control In Microgrid With Solar Pv And Energy Storage, V. Vignesh Babu, J. Preetha Roselyn, Prabha Sundaravadivel

Electrical Engineering Faculty Publications and Presentations

Recently, there has been a huge advancement in renewable energy integration in power systems. Power converters with grid-forming or grid-following topologies are typically employed to link these decentralized power sources to the grid. However, because distributed generation has less inertia than synchronous generators, their use of renewable energy sources threatens the electrical grid's reliability. Suitable control approaches for ensuring frequency and voltage stability in the grid-connected form of operation are established in this study, which offers dynamic, seamless power switching in the islanded mode of operation. In this research, effective Phase Locked Loop (PLL) techniques for grid-forming (GFM) and grid-following …

Unveiling Anomalies: A Survey On Xai-Based Anomaly Detection For Iot, Esin Eren, Feyza Yildirim Okay, Suat Özdemi̇r

Turkish Journal of Electrical Engineering and Computer Sciences

In recent years, the rapid growth of the Internet of Things (IoT) has raised concerns about the security and reliability of IoT systems. Anomaly detection is vital for recognizing potential risks and ensuring the optimal functionality of IoT networks. However, traditional anomaly detection methods often lack transparency and interpretability, hindering the understanding of their decisions. As a solution, Explainable Artificial Intelligence (XAI) techniques have emerged to provide human-understandable explanations for the decisions made by anomaly detection models. In this study, we present a comprehensive survey of XAI-based anomaly detection methods for IoT. We review and analyze various XAI techniques, including …

Text-To-Sql: A Methodical Review Of Challenges And Models, Ali Buğra Kanburoğlu, Faik Boray Tek

Turkish Journal of Electrical Engineering and Computer Sciences

This survey focuses on Text-to-SQL, automated translation of natural language queries into SQL queries. Initially, we describe the problem and its main challenges. Then, by following the PRISMA systematic review methodology, we survey the existing Text-to-SQL review papers in the literature. We apply the same method to extract proposed Text-to-SQL models and classify them with respect to used evaluation metrics and benchmarks. We highlight the accuracies achieved by various models on Text-to-SQL datasets and discuss execution-guided evaluation strategies. We present insights into model training times and implementations of different models. We also explore the availability of Text-to-SQL datasets in non-English …

Security Fusion Method Of Physical Fitness Training Data Based On The Internet Of Things, Bin Zhou

Turkish Journal of Electrical Engineering and Computer Sciences

Physical fitness training, an important way to improve physical fitness, is the basic guarantee for forming combat effectiveness. At present, the evaluation types of physical fitness training are mostly conducted manually. It has problems such as low efficiency, high consumption of human and material resources, and subjective factors affecting the evaluation results. ”Internet+” has greatly expanded the traditional network from the perspective of technological convergence and network coverage objects. It has expedited and promoted the rapid development of Internet of Things (IoT) technology and its applications. The IoT with many sensor nodes shows the characteristics of acquisition information redundancy, node …

Dpafy-Gcaps: Denoising Patch-And-Amplify Gabor Capsule Network For The Recognition Of Gastrointestinal Diseases, Henrietta Adjei Pokuaa, Adeboya Felix Adekoya, Benjamin Asubam Weyori, Owusu Nyarko-Boateng

Turkish Journal of Electrical Engineering and Computer Sciences

Deep learning (DL) models have performed tremendously well in image classification. This good performance can be attributed to the availability of massive data in most domains. However, some domains are known to have few datasets, especially the health sector. This makes it difficult to develop domain-specific high-performing DL algorithms for these fields. The field of health is critical and requires accurate detection of diseases. In the United States Gastrointestinal diseases are prevalent and affect 60 to 70 million people. Ulcerative colitis, polyps, and esophagitis are some gastrointestinal diseases. Colorectal polyps is the third most diagnosed malignancy in the world. This …

Joint Control Of A Flying Robot And A Ground Vehicle Using Leader-Follower Paradigm, Ayşen Süheyla Bağbaşi, Ali Emre Turgut, Kutluk Bilge Arikan

Turkish Journal of Electrical Engineering and Computer Sciences

In this study, a novel control framework for the collaboration of an aerial robot and a ground vehicle that is connected via a taut tether is proposed. The framework is based on a leader-follower paradigm. The leader follows a desired trajectory while the motion of the follower is controlled by an admittance controller using an extended state observer to estimate the tether force. Additionally, a velocity estimator is also incorporated to accurately assess the leader’s velocity. An essential feature of our system is its adaptability, enabling role switching between the robots when needed. Furthermore, the synchronization performance of the robots …

Stereo-Image-Based Ground-Line Prediction And Obstacle Detection, Emre Güngör, Ahmet Özmen

Turkish Journal of Electrical Engineering and Computer Sciences

In recent years, vision systems have become essential in the development of advanced driver assistance systems or autonomous vehicles. Although deep learning methods have been the center of focus in recent years to develop fast and reliable obstacle detection solutions, they face difficulties in complex and unknown environments where objects of varying types and shapes are present. In this study, a novel non-AI approach is presented for finding the ground-line and detecting the obstacles in roads using v-disparity data. The main motivation behind the study is that the ground-line estimation errors cause greater deviations at the output. Hence, a novel …

Deep Learning-Based Breast Cancer Diagnosis With Multiview Of Mammography Screening To Reduce False Positive Recall Rate, Meryem Altın Karagöz, Özkan Ufuk Nalbantoğlu, Derviş Karaboğa, Bahriye Akay, Alper Baştürk, Halil Ulutabanca, Serap Doğan, Damla Coşkun, Osman Demi̇r

Turkish Journal of Electrical Engineering and Computer Sciences

Breast cancer is the most prevalent and crucial cancer type that should be diagnosed early to reduce mortality. Therefore, mammography is essential for early diagnosis owing to high-resolution imaging and appropriate visualization. However, the major problem of mammography screening is the high false positive recall rate for breast cancer diagnosis. High false positive recall rates psychologically affect patients, leading to anxiety, depression, and stress. Moreover, false positive recalls increase costs and create an unnecessary expert workload. Thus, this study proposes a deep learning based breast cancer diagnosis model to reduce false positive and false negative rates. The proposed model has …

Signer-Independent Sign Language Recognition With Feature Disentanglement, İnci̇ Meli̇ha Baytaş, İpek Erdoğan

Turkish Journal of Electrical Engineering and Computer Sciences

Learning a robust and invariant representation of various unwanted factors in sign language recognition (SLR) applications is essential. One of the factors that might degrade the sign recognition performance is the lack of signer diversity in the training datasets, causing a dependence on the singer’s identity during representation learning. Consequently, capturing signer-specific features hinders the generalizability of SLR systems. This study proposes a feature disentanglement framework comprising a convolutional neural network (CNN) and a long short-term memory (LSTM) network based on adversarial training to learn a signer-independent sign language representation that might enhance the recognition of signs. We aim to …

Ri2ap: Robust And Interpretable 2d Anomaly Prediction In Assembly Pipelines, Chathurangi Shyalika, Kaushik Roy, Renjith Prasad, Fadi El Kalach, Yuxin Zi, Priya Mittal, Vignesh Narayanan, Ramy Harik, Amit Sheth

Publications

Predicting anomalies in manufacturing assembly lines is crucial for reducing time and labor costs and improving processes. For instance, in rocket assembly, premature part failures can lead to significant financial losses and labor inefficiencies. With the abundance of sensor data in the Industry 4.0 era, machine learning (ML) offers potential for early anomaly detection. However, current ML methods for anomaly prediction have limitations, with F1 measure scores of only 50% and 66% for prediction and detection, respectively. This is due to challenges like the rarity of anomalous events, scarcity of high-fidelity simulation data (actual data are expensive), and the complex …