ASU Electronic Theses and Dissertations
This collection includes most of the ASU Theses and Dissertations from 2011 to present. ASU Theses and Dissertations are available in downloadable PDF format; however, a small percentage of items are under embargo. Information about the dissertations/theses includes degree information, committee members, an abstract, supporting data or media.
In addition to the electronic theses found in the ASU Digital Repository, ASU Theses and Dissertations can be found in the ASU Library Catalog.
Dissertations and Theses granted by Arizona State University are archived and made available through a joint effort of the ASU Graduate College and the ASU Libraries. For more information or questions about this collection contact or visit the Digital Repository ETD Library Guide or contact the ASU Graduate College at gradformat@asu.edu.
Displaying 41 - 50 of 58
Description
Thousands of high-resolution images are generated each day. Segmenting, classifying, and analyzing the contents of these images are the key steps in image understanding. This thesis focuses on image segmentation and classification and its applications in synthetic, texture, natural, biomedical, and industrial images. A robust level-set-based multi-region and texture image segmentation approach is proposed in this thesis to tackle most of the challenges in the existing multi-region segmentation methods, including computational complexity and sensitivity to initialization. Medical image analysis helps in understanding biological processes and disease pathologies. In this thesis, two cell evolution analysis schemes are proposed for cell cluster extraction in order to analyze cell migration, cell proliferation, and cell dispersion in different cancer cell images. The proposed schemes accurately segment both the cell cluster area and the individual cells inside and outside the cell cluster area. The method is currently used by different cell biology labs to study the behavior of cancer cells, which helps in drug discovery. Defects can cause failure to motherboards, processors, and semiconductor units. An automatic defect detection and classification methodology is very desirable in many industrial applications. This helps in producing consistent results, facilitating the processing, speeding up the processing time, and reducing the cost. In this thesis, three defect detection and classification schemes are proposed to automatically detect and classify different defects related to semiconductor unit images. The first proposed defect detection scheme is used to detect and classify the solder balls in the processor sockets as either defective (Non-Wet) or non-defective. The method produces a 96% classification rate and saves 89% of the time used by the operator. The second proposed defect detection scheme is used for detecting and measuring voids inside solder balls of different boards and products. The third proposed defect detection scheme is used to detect different defects in the die area of semiconductor unit images such as cracks, scratches, foreign materials, fingerprints, and stains. The three proposed defect detection schemes give high accuracy and are inexpensive to implement compared to the existing high cost state-of-the-art machines.
ContributorsSaid, Asaad F (Author) / Karam, Lina (Thesis advisor) / Chakrabarti, Chaitali (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Patel, Nital (Committee member) / Arizona State University (Publisher)
Created2010
Description
Dealing with relational data structures is central to a wide-range of applications including social networks, epidemic modeling, molecular chemistry, medicine, energy distribution, and transportation. Machine learning models that can exploit the inherent structural/relational bias in the graph structured data have gained prominence in recent times. A recurring idea that appears in all approaches is to encode the nodes in the graph (or the entire graph) as low-dimensional vectors also known as embeddings, prior to carrying out downstream task-specific learning. It is crucial to eliminate hand-crafted features and instead directly incorporate the structural inductive bias into the deep learning architectures.
In this dissertation, deep learning models that directly operate on graph structured data are proposed for effective representation learning. A literature review on existing graph representation learning is provided in the beginning of the dissertation. The primary focus of dissertation is on building novel graph neural network architectures that are robust against adversarial attacks. The proposed graph neural network models are extended to multiplex graphs (heterogeneous graphs). Finally, a relational neural network model is proposed to operate on a human structural connectome. For every research contribution of this dissertation, several empirical studies are conducted on benchmark datasets. The proposed graph neural network models, approaches, and architectures demonstrate significant performance improvements in comparison to the existing state-of-the-art graph embedding strategies.
ContributorsShanthamallu, Uday Shankar (Author) / Spanias, Andreas (Thesis advisor) / Thiagarajan, Jayaraman J (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Berisha, Visar (Committee member) / Arizona State University (Publisher)
Created2021
Description
Quantum computing has the potential to revolutionize the signal-processing field by providing more efficient methods for analyzing signals. This thesis explores the application of quantum computing in signal analysis synthesis for compression applications. More specifically, the study focuses on two key approaches: quantum Fourier transform (QFT) and quantum linear prediction (QLP). The research is motivated by the potential advantages offered by quantum computing in massive signal processing tasks and presents novel quantum circuit designs for QFT, quantum autocorrelation, and QLP, enabling signal analysis synthesis using quantum algorithms. The two approaches are explained as follows. The Quantum Fourier transform (QFT) demonstrates the potential for improved speed in quantum computing compared to classical methods. This thesis focuses on quantum encoding of signals and designing quantum algorithms for signal analysis synthesis, and signal compression using QFTs. Comparative studies are conducted to evaluate quantum computations for Fourier transform applications, considering Signal-to-Noise-Ratio results. The effects of qubit precision and quantum noise are also analyzed. The QFT algorithm is also developed in the J-DSP simulation environment, providing hands-on laboratory experiences for signal-processing students. User-friendly simulation programs on QFT-based signal analysis synthesis using peak picking, and perceptual selection using psychoacoustics in the J-DSP are developed. Further, this research is extended to analyze the autocorrelation of the signal using QFTs and develop a quantum linear prediction (QLP) algorithm for speech processing applications. QFTs and IQFTs are used to compute the quantum autocorrelation of the signal, and the HHL algorithm is modified and used to compute the solutions of the linear equations using quantum computing. The performance of the QLP algorithm is evaluated for system identification, spectral estimation, and speech analysis synthesis, and comparisons are performed for QLP and CLP results. The results demonstrate the following: effective quantum circuits for accurate QFT-based speech analysis synthesis, evaluation of performance with quantum noise, design of accurate quantum autocorrelation, and development of a modified HHL algorithm for efficient QLP. Overall, this thesis contributes to the research on quantum computing for signal processing applications and provides a foundation for further exploration of quantum algorithms for signal analysis synthesis.
ContributorsSharma, Aradhita (Author) / Spanias, Andreas (Thesis advisor) / Tepedelenlioğlu, Cihan (Committee member) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2023
Description
Software-defined radio provides users with a low-cost and flexible platform for implementing and studying advanced communications and remote sensing applications. Two such applications include unmanned aerial system-to-ground communications channel and joint sensing and communication systems. In this work, these applications are studied.
In the first part, unmanned aerial system-to-ground communications channel models are derived from empirical data collected from software-defined radio transceivers in residential and mountainous desert environments using a small (< 20 kg) unmanned aerial system during low-altitude flight (< 130 m). The Kullback-Leibler divergence measure was employed to characterize model mismatch from the empirical data. Using this measure the derived models accurately describe the underlying data.
In the second part, an experimental joint sensing and communications system is implemented using a network of software-defined radio transceivers. A novel co-design receiver architecture is presented and demonstrated within a three-node joint multiple access system topology consisting of an independent radar and communications transmitter along with a joint radar and communications receiver. The receiver tracks an emulated target moving along a predefined path and simultaneously decodes a communications message. Experimental system performance bounds are characterized jointly using the communications channel capacity and novel estimation information rate.
In the first part, unmanned aerial system-to-ground communications channel models are derived from empirical data collected from software-defined radio transceivers in residential and mountainous desert environments using a small (< 20 kg) unmanned aerial system during low-altitude flight (< 130 m). The Kullback-Leibler divergence measure was employed to characterize model mismatch from the empirical data. Using this measure the derived models accurately describe the underlying data.
In the second part, an experimental joint sensing and communications system is implemented using a network of software-defined radio transceivers. A novel co-design receiver architecture is presented and demonstrated within a three-node joint multiple access system topology consisting of an independent radar and communications transmitter along with a joint radar and communications receiver. The receiver tracks an emulated target moving along a predefined path and simultaneously decodes a communications message. Experimental system performance bounds are characterized jointly using the communications channel capacity and novel estimation information rate.
ContributorsGutierrez, Richard (Author) / Bliss, Daniel W (Thesis advisor) / Papandreou-Suppappola, Antonia (Committee member) / Ogras, Umit Y. (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Arizona State University (Publisher)
Created2018
Description
With the rapid development of reflect-arrays and software-defined meta-surfaces, reconfigurable intelligent surfaces (RISs) have been envisioned as promising technologies for next-generation wireless communication and sensing systems. These surfaces comprise massive numbers of nearly-passive elements that interact with the incident signals in a smart way to improve the performance of such systems. In RIS-aided communication systems, designing this smart interaction, however, requires acquiring large-dimensional channel knowledge between the RIS and the transmitter/receiver. Acquiring this knowledge is one of the most crucial challenges in RISs as it is associated with large computational and hardware complexity. For RIS-aided sensing systems, it is interesting to first investigate scene depth perception based on millimeter wave (mmWave) multiple-input multiple-output (MIMO) sensing. While mmWave MIMO sensing systems address some critical limitations suffered by optical sensors, realizing these systems possess several key challenges: communication-constrained sensing framework design, beam codebook design, and scene depth estimation challenges. Given the high spatial resolution provided by the RISs, RIS-aided mmWave sensing systems have the potential to improve the scene depth perception, while imposing some key challenges too. In this dissertation, for RIS-aided communication systems, efficient RIS interaction design solutions are proposed by leveraging tools from compressive sensing and deep learning. The achievable rates of these solutions approach the upper bound, which assumes perfect channel knowledge, with negligible training overhead. For RIS-aided sensing systems, a mmWave MIMO based sensing framework is first developed for building accurate depth maps under the constraints imposed by the communication transceivers. Then, a scene depth estimation framework based on RIS-aided sensing is developed for building high-resolution accurate depth maps. Numerical simulations illustrate the promising performance of the proposed solutions, highlighting their potential for next-generation communication and sensing systems.
ContributorsTaha, Abdelrahman (Author) / Alkhateeb, Ahmed (Thesis advisor) / Bliss, Daniel (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Michelusi, Nicolò (Committee member) / Arizona State University (Publisher)
Created2023
Description
The past decade witnessed the success of deep learning models in various applications of computer vision and natural language processing. This success can be predominantly attributed to the (i) availability of large amounts of training data; (ii) access of domain aware knowledge; (iii) i.i.d assumption between the train and target distributions and (iv) belief on existing metrics as reliable indicators of performance. When any of these assumptions are violated, the models exhibit brittleness producing adversely varied behavior. This dissertation focuses on methods for accurate model design and characterization that enhance process reliability when certain assumptions are not met. With the need to safely adopt artificial intelligence tools in practice, it is vital to build reliable failure detectors that indicate regimes where the model must not be invoked. To that end, an error predictor trained with a self-calibration objective is developed to estimate loss consistent with the underlying model. The properties of the error predictor are described and their utility in supporting introspection via feature importances and counterfactual explanations is elucidated. While such an approach can signal data regime changes, it is critical to calibrate models using regimes of inlier (training) and outlier data to prevent under- and over-generalization in models i.e., incorrectly identifying inliers as outliers and vice-versa. By identifying the space for specifying inliers and outliers, an anomaly detector that can effectively flag data of varying semantic complexities in medical imaging is next developed. Uncertainty quantification in deep learning models involves identifying sources of failure and characterizing model confidence to enable actionability. A training strategy is developed that allows the accurate estimation of model uncertainties and its benefits are demonstrated for active learning and generalization gap prediction. This helps identify insufficiently sampled regimes and representation insufficiency in models. In addition, the task of deep inversion under data scarce scenarios is considered, which in practice requires a prior to control the optimization. By identifying limitations in existing work, data priors powered by generative models and deep model priors are designed for audio restoration. With relevant empirical studies on a variety of benchmarks, the need for such design strategies is demonstrated.
ContributorsNarayanaswamy, Vivek Sivaraman (Author) / Spanias, Andreas (Thesis advisor) / J. Thiagarajan, Jayaraman (Committee member) / Berisha, Visar (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Arizona State University (Publisher)
Created2023
Description
In the recent years, deep learning has gained popularity for its ability to be utilized for several computer vision applications without any apriori knowledge. However, to introduce better inductive bias incorporating prior knowledge along with learnedinformation is critical. To that end, human intervention including choice of algorithm, data and model in deep learning pipelines can be considered a prior. Thus, it is extremely important to select effective priors for a given application. This dissertation explores different aspects of a deep learning pipeline and provides insights as to why a particular prior is effective for the corresponding application. For analyzing the effect of model priors, three applications which involvesequential modelling problems i.e. Audio Source Separation, Clinical Time-series (Electroencephalogram (EEG)/Electrocardiogram(ECG)) based Differential Diagnosis and Global Horizontal Irradiance Forecasting for Photovoltaic (PV) Applications are chosen. For data priors, the application of image classification is chosen and a new algorithm titled,“Invenio” that can effectively use data semantics for both task and distribution shift scenarios is proposed. Finally, the effectiveness of a data selection prior is shown using the application of object tracking wherein the aim is to maintain the tracking performance while prolonging the battery usage of image sensors by optimizing the data selected for reading from the environment. For every research contribution of this dissertation, several empirical studies are conducted on benchmark datasets. The proposed design choices demonstrate significant performance improvements in comparison to the existing application specific state-of-the-art deep learning strategies.
ContributorsKatoch, Sameeksha (Author) / Spanias, Andreas (Thesis advisor) / Turaga, Pavan (Thesis advisor) / Thiagarajan, Jayaraman J. (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Arizona State University (Publisher)
Created2022
Description
Increased demand on bandwidth has resulted in wireless communications and radar systems sharing spectrum. As signal transmissions from both modalities coexist, methodologies must be designed to reduce the induced interference from each system. This work considers the problem of tracking an object using radar measurements embedded in noise and corrupted from transmissions of multiple communications users. Radar received signals in low noise can be successively processed to estimate object parameters maximum likelihood estimation. For linear frequency-modulated (LFM) signals, such estimates can be efficiently computed by integrating the Wigner distribution along lines in the time-frequency (TF) plane. However, the presence of communications interference highly reduces estimation performance.This thesis proposes a new approach to increase radar estimation performance by integrating a highly-localized TF method with data clustering. The received signal is first decomposed into highly localized Gaussians using the iterative matching pursuit decomposition (MPD). As the MPD is iterative, high noise levels can be reduced by appropriately selecting the algorithm’s stopping criteria. The decomposition also provides feature vectors of reduced dimensionality that can be used for clustering using a Gaussian mixture model (GMM). The proposed estimation method integrates along lines of a modified Wigner distribution of the Gaussian clusters in the TF plane. Using simulations, the object parameter estimation performance of the MPD is shown to highly improve when the MPD is integrated with GMM clustering.
ContributorsZhang, Yiming (Author) / Papandreou-Suppappola, Antonia (Thesis advisor) / Moraffah, Bahman (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Arizona State University (Publisher)
Created2022
Description
There has been a lot of work on the characterization of capacity and achievable rate regions, and rate region outer-bounds for various multi-user channels of interest. Parallel to the developed information theoretic results, practical codes have also been designed for some multi-user channels such as multiple access channels, broadcast channels and relay channels; however, interference channels have not received much attention and only a limited amount of work has been conducted on them. With this motivation, in this dissertation, design of practical and implementable channel codes is studied focusing on multi-user channels with special emphasis on interference channels; in particular, irregular low-density-parity-check codes are exploited for a variety of cases and trellis based codes for short block length designs are performed.
Novel code design approaches are first studied for the two-user Gaussian multiple access channel. Exploiting Gaussian mixture approximation, new methods are proposed wherein the optimized codes are shown to improve upon the available designs and off-the-shelf point-to-point codes applied to the multiple access channel scenario. The code design is then examined for the two-user Gaussian interference channel implementing the Han-Kobayashi encoding and decoding strategy. Compared with the point-to-point codes, the newly designed codes consistently offer better performance. Parallel to this work, code design is explored for the discrete memoryless interference channels wherein the channel inputs and outputs are taken from a finite alphabet and it is demonstrated that the designed codes are superior to the single user codes used with time sharing. Finally, the code design principles are also investigated for the two-user Gaussian interference channel employing trellis-based codes with short block lengths for the case of strong and mixed interference levels.
Novel code design approaches are first studied for the two-user Gaussian multiple access channel. Exploiting Gaussian mixture approximation, new methods are proposed wherein the optimized codes are shown to improve upon the available designs and off-the-shelf point-to-point codes applied to the multiple access channel scenario. The code design is then examined for the two-user Gaussian interference channel implementing the Han-Kobayashi encoding and decoding strategy. Compared with the point-to-point codes, the newly designed codes consistently offer better performance. Parallel to this work, code design is explored for the discrete memoryless interference channels wherein the channel inputs and outputs are taken from a finite alphabet and it is demonstrated that the designed codes are superior to the single user codes used with time sharing. Finally, the code design principles are also investigated for the two-user Gaussian interference channel employing trellis-based codes with short block lengths for the case of strong and mixed interference levels.
ContributorsSharifi, Shahrouz (Author) / Duman, Tolga M. (Thesis advisor) / Zhang, Junshan (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Reisslein, Martin (Committee member) / Arizona State University (Publisher)
Created2015
Description
The power of science lies in its ability to infer and predict the
existence of objects from which no direct information can be obtained
experimentally or observationally. A well known example is to
ascertain the existence of black holes of various masses in different
parts of the universe from indirect evidence, such as X-ray emissions.
In the field of complex networks, the problem of detecting
hidden nodes can be stated, as follows. Consider a network whose
topology is completely unknown but whose nodes consist of two types:
one accessible and another inaccessible from the outside world. The
accessible nodes can be observed or monitored, and it is assumed that time
series are available from each node in this group. The inaccessible
nodes are shielded from the outside and they are essentially
``hidden.'' The question is, based solely on the
available time series from the accessible nodes, can the existence and
locations of the hidden nodes be inferred? A completely data-driven,
compressive-sensing based method is developed to address this issue by utilizing
complex weighted networks of nonlinear oscillators, evolutionary game
and geospatial networks.
Both microbes and multicellular organisms actively regulate their cell
fate determination to cope with changing environments or to ensure
proper development. Here, the synthetic biology approaches are used to
engineer bistable gene networks to demonstrate that stochastic and
permanent cell fate determination can be achieved through initializing
gene regulatory networks (GRNs) at the boundary between dynamic
attractors. This is experimentally realized by linking a synthetic GRN
to a natural output of galactose metabolism regulation in yeast.
Combining mathematical modeling and flow cytometry, the
engineered systems are shown to be bistable and that inherent gene expression
stochasticity does not induce spontaneous state transitioning at
steady state. By interfacing rationally designed synthetic
GRNs with background gene regulation mechanisms, this work
investigates intricate properties of networks that illuminate possible
regulatory mechanisms for cell differentiation and development that
can be initiated from points of instability.
existence of objects from which no direct information can be obtained
experimentally or observationally. A well known example is to
ascertain the existence of black holes of various masses in different
parts of the universe from indirect evidence, such as X-ray emissions.
In the field of complex networks, the problem of detecting
hidden nodes can be stated, as follows. Consider a network whose
topology is completely unknown but whose nodes consist of two types:
one accessible and another inaccessible from the outside world. The
accessible nodes can be observed or monitored, and it is assumed that time
series are available from each node in this group. The inaccessible
nodes are shielded from the outside and they are essentially
``hidden.'' The question is, based solely on the
available time series from the accessible nodes, can the existence and
locations of the hidden nodes be inferred? A completely data-driven,
compressive-sensing based method is developed to address this issue by utilizing
complex weighted networks of nonlinear oscillators, evolutionary game
and geospatial networks.
Both microbes and multicellular organisms actively regulate their cell
fate determination to cope with changing environments or to ensure
proper development. Here, the synthetic biology approaches are used to
engineer bistable gene networks to demonstrate that stochastic and
permanent cell fate determination can be achieved through initializing
gene regulatory networks (GRNs) at the boundary between dynamic
attractors. This is experimentally realized by linking a synthetic GRN
to a natural output of galactose metabolism regulation in yeast.
Combining mathematical modeling and flow cytometry, the
engineered systems are shown to be bistable and that inherent gene expression
stochasticity does not induce spontaneous state transitioning at
steady state. By interfacing rationally designed synthetic
GRNs with background gene regulation mechanisms, this work
investigates intricate properties of networks that illuminate possible
regulatory mechanisms for cell differentiation and development that
can be initiated from points of instability.
ContributorsSu, Ri-Qi (Author) / Lai, Ying-Cheng (Thesis advisor) / Wang, Xiao (Thesis advisor) / Bliss, Daniel (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Arizona State University (Publisher)
Created2015