Electrical & Computer Engineering Theses and Dissertations
Permanent URI for this collectionhttp://hdl.handle.net/1903/2765
Browse
1143 results
Search Results
Item Automated Management of Network Slices with Service Guarantees(2024) Nikolaidis, Panagiotis; Baras, John; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Future mobile networks are expected to support a diverse set of applications including high-throughput video streaming, delay-sensitive augmented reality applications, and critical control traffic for autonomous driving. Unfortunately, existing networks do not have the required management mechanisms to handle this complex mix of traffic efficiently. At the same time, however, there is a significant effort from both industry and academia to make networks more open and programmable, leading to the emergence of software-defined networking, network function virtualization, and packet-forwarding programming languages. Moreover, several organisations such as the Open Networking Foundation were founded to facilitate innovation and lower the entry barriers in the mobile networking industry. In this setting, the concept of network slicing emerged which involves the partitioning of the mobile network into virtual networks that are tailored for specific applications. Each network slice needs to provide premium service to its users as specified in a service level agreement between the mobile network operator and the customer. The deployment of network slices has been largely realized thanks to network function virtualization. However, little progress has been made on mechanisms to efficiently share the network resources among them. In this dissertation, we develop such mechanisms for the licensed spectrum at the base station, a scarce resource that operators obtain through competitive auctions. We propose a system architecture composed of two new network functions; the bandwidth demand estimator and the network slice multiplexer. The bandwidth demand estimator monitors the traffic of the network slice and outputs the amount of bandwidth currently needed to deliver the desired quality of service. The network slice multiplexer decides which bandwidth demands to accept when the available bandwidth does not suffice for all the network slices. A key feature of this architecture is the separation of the demand estimation task from the contention resolution task. This separation makes the architecture scalable for a large number of network slices. It also allows the mobile network operator to charge fairly each customer based on their bandwidth demands. In contrast, the most common approach in the literature is to learn online how to split the available resources among the slices to maximize a total network utility. However, this approach is neither scalable nor suitable for service level agreements. The dissertation contributes several algorithms to realize the proposed architecture and provisioning methods to guarantee the fulfillment of the service level agreements. To satisfypacket delay requirements, we develop a bandwidth demand estimator based on queueing theory and online learning. To share resources efficiently even in the presence of traffic anomalies, we develop a network slice multiplexer based on the Max-Weight algorithm and hypothesis testing. We implement and test the proposed algorithms on network simulators and 5G testbeds to showcase their efficiency in realistic settings. Overall, we present a scalable architecture that is robust to traffic anomalies and reduces the bandwidth needed to serve multiple network slices.Item INTEGRATION OF ATOMIC EMITTERS IN PHOTONIC PLATFORMS FOR CLASSICAL AND QUANTUM INFORMATION APPLICATIONS(2024) Zhao, Yuqi; Waks, Edo; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Integrated photonics provide a powerful toolbox for a wide range of classical and nonclassical applications. In addition to their scalability and significantly lower power consumption, integrated photonic structures enable new design knobs and functionalities that are inaccessible in their bulk counterparts.Solid-state atomic emitters, such as rare-earth ions (REIs) and quantum dots, serve as excellent sources for scalable quantum memories and exhibit strong nonlinear resonant absorption. Integrating atomic emitters with photonic devices enhances light-matter interactions, unlocking new opportunities for advanced optoelectronic systems in both classical and quantum regimes. This thesis tackles two main challenges utilizing the integration of photonic devices and atomic emitters: (1) developing scalable quantum network components, and (2) creating low-power nonlinear components for classical on-chip optical signal processing. Specifically, we focus on a platform of rare-earth ion doped thin-film lithium niobate (TFLN), leveraging the ions’ stable optical transitions with thin-film lithium niobate’s rich toolbox of high-performance photonics. We first demonstrate an integrated atomic frequency comb (AFC) memory in this platform, an essential component for quantum networks. This memory exhibits a broad storage bandwidth exceeding 100 MHz and optical storage time as long as 250 ns. As the first demonstrated integrated AFC memory, it features a significantly enhanced optical confinement compared to the previously demonstrated REI memories based on ion-diffused waveguides, leading to a three orders of magnitude reduction in optical power required for a coherent control. Next, we develop reconfigurable narrowband spectral filters using ring resonators in the REI:TFLN platform. These on-chip optical filters, with linewidths in the MHz and kHz range and extinction ratios of 13 dB – 20 dB, are crucial for reducing background noise in quantum frequency conversion. By spectral hole burning at 100 mK temperature in a critical-coupled resonance mode, we achieve bandpass filters with a linewidth of as narrow as 681 kHz. Moreover, the cavity enables reconfigurable filtering by varying the cavity coupling rate. Such versatile integrated spectral filters with high extinction ratio and narrow linewidth could serve as fundamental component for optical signal processing and optical memories on-a-chip. We also demonstrate picowatt-threshold power nonlinearity in TFLN, utilizing the strong resonant nonlinear absorption induced by three-level REIs and enhanced by TFLN ring resonators. This work presents three distinct nonlinear transmission functions by adjusting the ring’s coupling strength. The lifetime of the nonlinear transmission is measured to be ~3 ms, determined by the ion’s third-level lifetime. Finally, we propose a novel nonlinear device design based on a different material system and mechanism - an ultrathin optical limiter with low threshold intensity (0.45 kW/cm2), utilizing a 500 nm-thick GaAs zone plate embedded with InAs quantum dots. The optical limiting performance, enabled by the zone plate’s nonlinear focusing behavior, is investigated using FDTD simulations. We also explore the effects of the zone plate’s thickness and radius on its optical limiting performance.Item Representation Learning for Reinforcement Learning: Modeling Non-Gaussian Transition Probabilities with a Wasserstein Critic(2024) Tse, Ryan; Zhang, Kaiqing; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Reinforcement learning algorithms depend on effective state representations when solving complex, high-dimensional environments. Recent methods learn state representations using auxiliary objectives that aim to capture relationships between states that are behaviorally similar, meaning states that lead to similar future outcomes under optimal policies. These methods learn explicit probabilistic state transition models and compute distributional distances between state transition probabilities as part of their measure of behavioral similarity. This thesis presents a novel extension to several of these methods that directly learns the 1-Wasserstein distance between state transition distributions by exploiting the Kantorovich-Rubenstein duality. This method eliminates parametric assumptions about the state transition probabilities while providing a smoother estimator of distributional distances. Empirical evaluation demonstrates improved sample efficiency over some of the original methods and a modest increase in computational cost per sample. The results establish that relaxing theoretical assumptions about state transition modeling leads to more flexible and robust representation learning while maintaining strong performance characteristics.xItem TOWARDS EFFICIENT OCEANIC ROBOT LEARNING WITH SIMULATION(2024) LIN, Xiaomin; Aloimonos, Yiannis; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)In this dissertation, I explore the intersection of machine learning, perception, and simulation-based techniques to enhance the efficiency of underwater robotics, with a focus on oceanic tasks. My research begins with marine object detection using aerial imagery. From there, I address oyster detection using Oysternet, which leverages simulated data and Generative Adversarial Networks for sim-to-real transfer, significantly improving detection accuracy. Next, I present an oyster detection system that integrates diffusion-enhanced synthetic data with the Aqua2 biomimetic hexapedal robot, enabling real-time, on-edge detection in underwater environments. With detection models deployed locally, this system facilitates autonomous exploration. To enhance this capability, I introduce an underwater navigation framework that employs imitation learning, enabling the robot to efficiently navigate over objects of interest, such as rock and oyster reefs, without relying on localization. This approach improves information gathering while ensuring obstacle avoidance. Given that oyster habitats are often in shallow waters, I incorporate a deep learning model for real/virtual image segmentation, allowing the robot to differentiate between actual objects and water surface reflections, ensuring safe navigation. I expand on broader applications of these techniques, including olive detection for yield estimation and industrial object counting for warehouse management, using simulated imagery. In the final chapters, I address unresolved challenges, such as RGB/sonar data integration, and propose directions for future research to enhance underwater robotic learning through digital simulation further. Through these studies, I demonstrate how machine learning models and digital simulations can be used synergistically to address key challenges in underwater robotic tasks. Ultimately, this work advances the capabilities of autonomous systems to monitor and preserve marine ecosystems through efficient and robust digital simulation-based learning.Item FROM PARTS TO WHOLE IN ACTION AND OBJECT UNDERSTANDING(2024) Devaraj, Chinmaya; Aloimonos, Yiannis; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)The traditional paradigm of supervised learning in action or object recognition often relieson a top-down approach, ignoring explicit modeling of what activity or objects consist of. Recent approaches in generative AI research have shown us the ability to generate images and videos using text, indirectly indicating that we have control over the constituents of images and videos. In this dissertation, we explore ways to use the constituents of actions to develop methods to improve understanding of action. We devise different approaches to utilize the parts of actions, namely object motion, object state changes, and motion descriptions obtained by LLMs in various tasks like in the next active object segmentation, zero-shot action recognition, or video-text retrieval. We show promising benefits in action anticipation, zero-shot action recognition, and text-video retrieval tasks, demonstrating the practical applications of our methods. In the first part of the dissertation, we explore the idea of using the constituents of actions inGCNs for zero-shot human-object action recognition. The main idea is that semantically similar actions (of similar constituents) are closer in feature space. Thus, in our graph, we encode the edges connecting those actions with higher similarity. We introduce a method to visually ground the external knowledge graph using the concept of shared similarity between similar actions. We evaluate the method on the EPIC Kitchens dataset and the Charades dataset showing impressive results over baseline methods. We further show that visually grounding the knowledge graph enhances the performance of GCNs when an adversarial attack corrupts the input graph. In the second part of the thesis, we extend our ideas on human-object interactions in firstpersonvideos. Human actions involving hand manipulations are structured according to the making and breaking of hand-object contact, and human visual understanding of action relies on anticipation of contact, as demonstrated by pioneering work in cognitive science. Taking inspiration from this, we introduce representations and models centered on contact, which we then use in action prediction and anticipation. We train the Anticipation Module, a module producing Contact Anticipation Maps and Next Active Object Segmentations - novel low-level representations providing temporal and spatial characteristics of anticipated near future action. On top of the Anticipation Module, we apply Egocentric Object Manipulation Graphs (Ego- OMG), a framework for action anticipation and prediction. Using the Anticipation Module to aid Ego-OMG produces state-of-the-art results, achieving first and second places on the unseen and seen test sets of the EPIC Kitchens Action Anticipation Challenge and achieving state-of-the-art results on action anticipation and action prediction over EPIC Kitchens. In the same line of thinking of constituents of action, we next focus on investigatinghow motion understanding can be modeled in current video-text models. We introduce motion descriptions generated by GPT4 on three action datasets that capture fine-grained motion descriptions of activities. We evaluated several video-text models on the task of retrieval of motion descriptions and found them to need to catch up to the human expert performance. We introduce a method of improving motion understanding in video-text models by utilizing motion descriptions. This method is demonstrated on two action datasets for the motion description retrieval task. The results draw attention to the need for quality captions involving fine-grained motion information in existing datasets and demonstrate the effectiveness of the proposed pipeline in understanding fine-grained motion during video-text retrieval.Item Efficient learning-based sound propagation for virtual and real-world audio processing applications(2024) Ratnarajah, Anton Jeran; Manocha, Dinesh; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Sound propagation is the process by which sound energy travels through a medium, such as air, to the surrounding environment as sound waves. The room impulse response (RIR) describes this process and is influenced by the positions of the source and listener, the room's geometry, and its materials. Physics-based acoustic simulators have been used for decades to compute accurate RIRs for specific acoustic environments. However, we have encountered limitations with existing acoustic simulators. For example, they require a 3D representation and detailed material knowledge of the environment. To address these limitations, we propose three novel solutions. First, we introduce a learning-based RIR generator that is two orders of magnitude faster than an interactive ray-tracing simulator. Our approach can be trained to input both statistical and traditional parameters directly, and it can generate both monaural and binaural RIRs for both reconstructed and synthetic 3D scenes. Our generated RIRs outperform interactive ray-tracing simulators in speech-processing applications, including Automatic Speech Recognition (ASR), Speech Enhancement, and Speech Separation, by 2.5%, 12%, and 48%, respectively. Secondly, we propose estimating RIRs from reverberant speech signals and visual cues in the absence of a 3D representation of the environment. By estimating RIRs from reverberant speech, we can augment training data to match test data, improving the word error rate of the ASR system. Our estimated RIRs achieve a 6.9% improvement over previous learning-based RIR estimators in real-world far-field ASR tasks. We demonstrate that our audio-visual RIR estimator aids tasks like visual acoustic matching, novel-view acoustic synthesis, and voice dubbing, validated through perceptual evaluation. Finally, we introduce IR-GAN to augment accurate RIRs using real RIRs. IR-GAN parametrically controls acoustic parameters learned from real RIRs to generate new RIRs that imitate different acoustic environments, outperforming Ray-tracing simulators on the Kaldi far-field ASR benchmark by 8.95%.Item NOVEL GRAPHENE HETEROSTRUCTURES FOR SENSITIVE ENVIRONMENTAL AND BIOLOGICAL SENSING(2024) Pedowitz, Michael Donald; Daniels, Kevin; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)The COVID-19 pandemic has underscored the need for rapid, mobile, and adaptable sensing platforms to respond swiftly to pandemic-level emergencies. Additionally, smog and volatile organic compounds (VOCs), which posed significant health risks during last year’s wildfires, highlight the critical need for environmental air quality monitoring. Graphene, with its high sensitivity and fast response times, shows promise as a powerful sensing platform. However, it faces challenges related to low selectivity and the complexities of device fabrication using conventional chemical vapor-deposited graphene grown on metal foil, which requires exfoliation and transfer to suitable substrates.This dissertation explores the use of epitaxial graphene, which is graphene grown from the sublimation of silicon from silicon carbide, and forming heterostructures with legacy functional materials, such as transition metal oxides and selective capture probes like antibodies and aptamers to develop rapid, ultrasensitive, and selective sensors to address critical environmental and public health challenges. Epitaxial graphene provides a single-crystal, lithography-compatible graphene substrate that retains the desirable electronic properties of graphene without the drawbacks associated with transferred materials. This work focuses on creating heterostructures using traditional functional materials, such as manganese dioxide and antibodies, to develop high-quality, selective sensors for both biological and environmental applications. The practical applications of these sensors are demonstrated and validated using techniques such as Raman spectroscopy, X-ray photoelectron spectroscopy, atomic force microscopy, scanning electron microscopy, and electrical characterization. Additionally, detailed material analysis on producing these heterostructures is provided, emphasizing their ability to be modified without damaging the underlying graphene surface. This highlights epitaxial graphene's robust and versatile nature and its potential for creating high-quality devices with relatively simple designs. Finally, these biosensors are applied to alternate antibody-antigen systems, including influenza, to enhance disease-tracking capabilities. We also explore advanced functional materials, such as protease-peptide systems, which enable the creation of on-chip chemistry systems previously unattainable with current material systems.Item Development of Photonic Reservoir Computers for Radiofrequency Spectrum Awareness(2024) Klimko, Benjamin; Chembo, Yanne K.; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)In this dissertation, we study the use of several optoelectronic oscillator architectures for physical reservoir computing tasks. While optoelectronic oscillator-based reservoir computers have been reported in the literature for over a decade, all reported experimental results have been processed using wideband systems with baseband data sets. Our work focuses on two majorinnovations for physical reservoir computing: (i) narrowband reservoir computers allowing computing tasks to be performed natively on radiofrequency signals and (ii) illustrating that “simplified” optoelectronic oscillators, without external optical modulators, are capable of meeting or exceeding the results from more complex photonic reservoir computers. By their nature, optoelectronic oscillators operate in the radio passband regime and reservoir computers have been shown to be capable on time-series tasks such as waveform prediction and classification data sets. We demonstrated that the optoelectronic oscillator-based reservoir computer can effectively process signals in the radio passband, which is a novel result that could provide an enabling technology for next-generation communication methods such as cognitive networks. The benefits of this innovation would scale with increasing frequency, such as potential use with millimeter-wave cellular networks. In our second physical reservoir innovation, we have shown that external optical modulators, nearly ubiquitous devices in optoelectronic oscillators, may be excluded from the design of a physical reservoir computer without decreasing its accuracy. This is a major result as a reservoir without active optical components could be built on a single integrated circuit using modern semiconductor manufacturing processes. Such integration and miniaturization would be a large step towards photonic reservoir systems that could be more easily put into an operational environment. Up to this point, there has been minimal work on transitioning the optoelectronic oscillator from a benchtop, experimental system to one useful in the real world. Lastly, we investigated the relationship between computational power of the reservoir computer and task error. This is a crucial finding since reservoir computing is often touted as an alternative computing paradigm that is less resource-intensive than other computing methods. By determining a threshold on computational needs for a photonic reservoir computer, we ensure that such systems are utilized efficiently and do not unnecessarily use resources.Item Systematic Analysis of Adversaries' Exploitations of the End-host(2024) Avllazagaj, Erin; Dumitras, Tudor; Kwon, Yonghwi; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)In the pipeline of a cyber attack, the malicious actor will first gain a foothold in the target system through a malware. The malware detection is still a challenging problem, as the malware authors are constantly evolving their techniques to evade detection. Therefore, it is important for us to understand why that is the case and what can the defenders do to improve the detection of the malware. In this thesis, I explore the behavior of the malware in the real users’ machines and how it changes across different executions. I show that the malware exhibits more variability than benign samples and that certain actions are often more prone to variability than others. This is the first study that quantitatively analyzes the behavior of the malware in the wildI leverage an observation from the first project, where variability in the malware samples happens due to running privilege escalation exploits. The variability in behavior is due to the fact that the malware sometimes runs in non-privileged mode and tries to run an exploit to escalate its privileges. For these reasons, I propose a new methodology to systematically discover sensitive memory corruption targets that cause privilege escalation. At last, I explore the sensitive memory corruption targets in the Linux kernel. Specifically, I propose a methodology to systematically discover sensitive fields in the Linux kernel that, when corrupted, lead the system into an exploitable state. This system, called SCAVY, is based on a novel definition of the exploitable state that allows the attacker to read and write into files and memory locations that they would normally. SCAVY explores the exploitable states based on the threat model of a local unprivileged attacker with the ability to issue system calls and with the capability to read/write into a limited location in the kernel memory. The framework revealed that there are 17 sensitive fields across 12 Linux kernel C structs that, when overwritten with the correct value, lead the system into an exploitable state. In this definition, unlike prior work, I consider the system to be in an exploitable state when the weird machine allows the attacker to read and/or write into files and memory locations that they would normally not be able to. This state can be used to write into sensitive files such as //etc//passwd where the exploit author can create a new root account on the vulnerable host and log in as that. Additionally, if the attacker can read unreadable files such as //etc//shadow they can leak passwords of root accounts, de-hash them and log in as the root account. I utilize these targets to develop 6 exploits for 5 CVE vulnerabilities. I also demonstrated the severity of these fields and the applicability of the exploitable state by exploiting CVE-2022-27666. I overwrote the f mapping pointer in struct file and caused a write into //etc//passwd. Unlike the original exploit, ours didn’t need to break KASLR, modify global variables or require support of FUSE-fs from the vulnerable host. This makes our methodology more extensible and more stable, since the exploit requires fewer corruption in the kernel memory and it doesn’t rely on the need to have the addresses of the kernel’s symbols for calculating the KASLR offset. Additionally, our exploit doesn’t modify global variables, which makes it more stable and less likely to crash the kernel, during its runtime. Our findings show that new memory corruption targets can change the security implications of vulnerabilities, urging researchers to proactively discover memory corruption targets.Item ML-ENABLED SOLAR PV ELECTRICITY GENERATION PROJECTION FOR A LARGE ACADEMIC CAMPUS TO REDUCE ONSITE CO2 EMISSIONS(2024) Zargarzadeh, Sahar; Babadi, Behtash; Ohadi, Michael; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Mitigating CO2 emissions is crucial in reducing climate change, as these emissions contribute to global warming and its adverse impacts on ecosystems. According to statistics, photovoltaic electricity is 15 times less carbon-intensive than natural gas and 30 times less than coal, making Solar Photovoltaic an attractive option among various methods of reducing electricity demand. This study aims to apply Machine Learning to predict future impact of solar PV-Generated electricity in reducing CO2 emissions based. The primary utility data source is from the University of Maryland's campus; with over half of the campus's energy consumption derived from electricity, therefore reducing electricity consumption to mitigate carbon emissions is paramount. 153 buildings on the campus were investigated, spanning the years 2015-2022. This study was conducted in four key phases. In the first phase, an open source tool, PVWatts was used to gather data to predict PV-generated energy. This served as the foundation for phase II, where a novel tree-based ensemble learning model was developed to predict monthly PV-generated electricity on any period of time, leveraging machine learning to capture complex patterns in energy data for more accurate forecasts. The SHAP (SHapley Additive exPlanations) technique was incorporated into the proposed framework to enhance model explainability. Phase III involved calculating historical CO2 emissions based on past energy consumption data, providing a baseline for comparison. A meta-learning algorithm was implemented in the phase IV to project future CO2 emissions post-solar PV installation. This comparison facilitated the evaluation of different machine learning techniques for projecting emissions and assessing the university’s progress toward Maryland’s sustainability objectives. The ML-based tool developed in this study demonstrated that solar PV implementation could potentially reduce the campus’s footprint by approximately 18% for the studied clusters of buildings with the uncertainty level of about 1.7%, contributing to sustainability objectives and the promotion of cleaner energy use.