Matching Items (26)
Filtering by
- Creators: Arizona State University
Description
Over the last decade, deep neural networks also known as deep learning, combined with large databases and specialized hardware for computation, have made major strides in important areas such as computer vision, computational imaging and natural language processing. However, such frameworks currently suffer from some drawbacks. For example, it is generally not clear how the architectures are to be designed for different applications, or how the neural networks behave under different input perturbations and it is not easy to make the internal representations and parameters more interpretable. In this dissertation, I propose building constraints into feature maps, parameters and and design of algorithms involving neural networks for applications in low-level vision problems such as compressive imaging and multi-spectral image fusion, and high-level inference problems including activity and face recognition. Depending on the application, such constraints can be used to design architectures which are invariant/robust to certain nuisance factors, more efficient and, in some cases, more interpretable. Through extensive experiments on real-world datasets, I demonstrate these advantages of the proposed methods over conventional frameworks.
ContributorsLohit, Suhas Anand (Author) / Turaga, Pavan (Thesis advisor) / Spanias, Andreas (Committee member) / Li, Baoxin (Committee member) / Jayasuriya, Suren (Committee member) / Arizona State University (Publisher)
Created2019
Description
Ultrasound B-mode imaging is an increasingly significant medical imaging modality for clinical applications. Compared to other imaging modalities like computed tomography (CT) or magnetic resonance imaging (MRI), ultrasound imaging has the advantage of being safe, inexpensive, and portable. While two dimensional (2-D) ultrasound imaging is very popular, three dimensional (3-D) ultrasound imaging provides distinct advantages over its 2-D counterpart by providing volumetric imaging, which leads to more accurate analysis of tumor and cysts. However, the amount of received data at the front-end of 3-D system is extremely large, making it impractical for power-constrained portable systems.
In this thesis, algorithm and hardware design techniques to support a hand-held 3-D ultrasound imaging system are proposed. Synthetic aperture sequential beamforming (SASB) is chosen since its computations can be split into two stages, where the output generated of Stage 1 is significantly smaller in size compared to the input. This characteristic enables Stage 1 to be done in the front end while Stage 2 can be sent out to be processed elsewhere.
The contributions of this thesis are as follows. First, 2-D SASB is extended to 3-D. Techniques to increase the volume rate of 3-D SASB through a new multi-line firing scheme and use of linear chirp as the excitation waveform, are presented. A new sparse array design that not only reduces the number of active transducers but also avoids the imaging degradation caused by grating lobes, is proposed. A combination of these techniques increases the volume rate of 3-D SASB by 4\texttimes{} without introducing extra computations at the front end.
Next, algorithmic techniques to further reduce the Stage 1 computations in the front end are presented. These include reducing the number of distinct apodization coefficients and operating with narrow-bit-width fixed-point data. A 3-D die stacked architecture is designed for the front end. This highly parallel architecture enables the signals received by 961 active transducers to be digitalized, routed by a network-on-chip, and processed in parallel. The processed data are accumulated through a bus-based structure. This architecture is synthesized using TSMC 28 nm technology node and the estimated power consumption of the front end is less than 2 W.
Finally, the Stage 2 computations are mapped onto a reconfigurable multi-core architecture, TRANSFORMER, which supports different types of on-chip memory banks and run-time reconfigurable connections between general processing elements and memory banks. The matched filtering step and the beamforming step in Stage 2 are mapped onto TRANSFORMER with different memory configurations. Gem5 simulations show that the private cache mode generates shorter execution time and higher computation efficiency compared to other cache modes. The overall execution time for Stage 2 is 14.73 ms. The average power consumption and the average Giga-operations-per-second/Watt in 14 nm technology node are 0.14 W and 103.84, respectively.
In this thesis, algorithm and hardware design techniques to support a hand-held 3-D ultrasound imaging system are proposed. Synthetic aperture sequential beamforming (SASB) is chosen since its computations can be split into two stages, where the output generated of Stage 1 is significantly smaller in size compared to the input. This characteristic enables Stage 1 to be done in the front end while Stage 2 can be sent out to be processed elsewhere.
The contributions of this thesis are as follows. First, 2-D SASB is extended to 3-D. Techniques to increase the volume rate of 3-D SASB through a new multi-line firing scheme and use of linear chirp as the excitation waveform, are presented. A new sparse array design that not only reduces the number of active transducers but also avoids the imaging degradation caused by grating lobes, is proposed. A combination of these techniques increases the volume rate of 3-D SASB by 4\texttimes{} without introducing extra computations at the front end.
Next, algorithmic techniques to further reduce the Stage 1 computations in the front end are presented. These include reducing the number of distinct apodization coefficients and operating with narrow-bit-width fixed-point data. A 3-D die stacked architecture is designed for the front end. This highly parallel architecture enables the signals received by 961 active transducers to be digitalized, routed by a network-on-chip, and processed in parallel. The processed data are accumulated through a bus-based structure. This architecture is synthesized using TSMC 28 nm technology node and the estimated power consumption of the front end is less than 2 W.
Finally, the Stage 2 computations are mapped onto a reconfigurable multi-core architecture, TRANSFORMER, which supports different types of on-chip memory banks and run-time reconfigurable connections between general processing elements and memory banks. The matched filtering step and the beamforming step in Stage 2 are mapped onto TRANSFORMER with different memory configurations. Gem5 simulations show that the private cache mode generates shorter execution time and higher computation efficiency compared to other cache modes. The overall execution time for Stage 2 is 14.73 ms. The average power consumption and the average Giga-operations-per-second/Watt in 14 nm technology node are 0.14 W and 103.84, respectively.
ContributorsZhou, Jian (Author) / Chakrabarti, Chaitali (Thesis advisor) / Papandreou-Suppappola, Antonia (Committee member) / Wenisch, Thomas F. (Committee member) / Ogras, Umit Y. (Committee member) / Arizona State University (Publisher)
Created2019
Description
The availability of data for monitoring and controlling the electrical grid has increased exponentially over the years in both resolution and quantity leaving a large data footprint. This dissertation is motivated by the need for equivalent representations of grid data in lower-dimensional feature spaces so that machine learning algorithms can be employed for a variety of purposes. To achieve that, without sacrificing the interpretation of the results, the dissertation leverages the physics behind power systems, well-known laws that underlie this man-made infrastructure, and the nature of the underlying stochastic phenomena that define the system operating conditions as the backbone for modeling data from the grid.
The first part of the dissertation introduces a new framework of graph signal processing (GSP) for the power grid, Grid-GSP, and applies it to voltage phasor measurements that characterize the overall system state of the power grid. Concepts from GSP are used in conjunction with known power system models in order to highlight the low-dimensional structure in data and present generative models for voltage phasors measurements. Applications such as identification of graphical communities, network inference, interpolation of missing data, detection of false data injection attacks and data compression are explored wherein Grid-GSP based generative models are used.
The second part of the dissertation develops a model for a joint statistical description of solar photo-voltaic (PV) power and the outdoor temperature which can lead to better management of power generation resources so that electricity demand such as air conditioning and supply from solar power are always matched in the face of stochasticity. The low-rank structure inherent in solar PV power data is used for forecasting and to detect partial-shading type of faults in solar panels.
The first part of the dissertation introduces a new framework of graph signal processing (GSP) for the power grid, Grid-GSP, and applies it to voltage phasor measurements that characterize the overall system state of the power grid. Concepts from GSP are used in conjunction with known power system models in order to highlight the low-dimensional structure in data and present generative models for voltage phasors measurements. Applications such as identification of graphical communities, network inference, interpolation of missing data, detection of false data injection attacks and data compression are explored wherein Grid-GSP based generative models are used.
The second part of the dissertation develops a model for a joint statistical description of solar photo-voltaic (PV) power and the outdoor temperature which can lead to better management of power generation resources so that electricity demand such as air conditioning and supply from solar power are always matched in the face of stochasticity. The low-rank structure inherent in solar PV power data is used for forecasting and to detect partial-shading type of faults in solar panels.
ContributorsRamakrishna, Raksha (Author) / Scaglione, Anna (Thesis advisor) / Cochran, Douglas (Committee member) / Spanias, Andreas (Committee member) / Vittal, Vijay (Committee member) / Zhang, Junshan (Committee member) / Arizona State University (Publisher)
Created2020
Description
Aortic aneurysms and dissections are life threatening conditions addressed by replacing damaged sections of the aorta. Blood circulation must be halted to facilitate repairs. Ischemia places the body, especially the brain, at risk of damage. Deep hypothermia circulatory arrest (DHCA) is employed to protect patients and provide time for surgeons to complete repairs on the basis that reducing body temperature suppresses the metabolic rate. Supplementary surgical techniques can be employed to reinforce the brain's protection and increase the duration circulation can be suspended. Even then, protection is not completely guaranteed though. A medical condition that can arise early in recovery is postoperative delirium, which is correlated with poor long term outcome. This study develops a methodology to intraoperatively monitor neurophysiology through electroencephalography (EEG) and anticipate postoperative delirium. The earliest opportunity to detect occurrences of complications through EEG is immediately following DHCA during warming. The first observable electrophysiological activity after being completely suppressed is a phenomenon known as burst suppression, which is related to the brain's metabolic state and recovery of nominal neurological function. A metric termed burst suppression duty cycle (BSDC) is developed to characterize the changing electrophysiological dynamics. Predictions of postoperative delirium incidences are made by identifying deviations in the way these dynamics evolve. Sixteen cases are examined in this study. Accurate predictions can be made, where on average 89.74% of cases are correctly classified when burst suppression concludes and 78.10% when burst suppression begins. The best case receiver operating characteristic curve has an area under its convex hull of 0.8988, whereas the worst case area under the hull is 0.7889. These results demonstrate the feasibility of monitoring BSDC to anticipate postoperative delirium during burst suppression. They also motivate a further analysis on identifying footprints of causal mechanisms of neural injury within BSDC. Being able to raise warning signs of postoperative delirium early provides an opportunity to intervene and potentially avert neurological complications. Doing so would improve the success rate and quality of life after surgery.
ContributorsMa, Owen (Author) / Bliss, Daniel W (Thesis advisor) / Berisha, Visar (Committee member) / Kosut, Oliver (Committee member) / Brewer, Gene (Committee member) / Arizona State University (Publisher)
Created2020
Description
The continuous time-tagging of photon arrival times for high count rate sources isnecessary for applications such as optical communications, quantum key encryption,
and astronomical measurements. Detection of Hanbury-Brown and Twiss (HBT) single
photon correlations from thermal sources, such as stars, requires a combination of high
dynamic range, long integration times, and low systematics in the photon detection
and time tagging system. The continuous nature of the measurements and the need
for highly accurate timing resolution requires a customized time-to-digital converter
(TDC). A custom built, two-channel, field programmable gate array (FPGA)-based
TDC capable of continuously time tagging single photons with sub clock cycle timing
resolution was characterized. Auto-correlation and cross-correlation measurements
were used to constrain spurious systematic effects in the pulse count data as a function
of system variables. These variables included, but were not limited to, incident
photon count rate, incoming signal attenuation, and measurements of fixed signals.
Additionally, a generalized likelihood ratio test using maximum likelihood estimators
(MLEs) was derived as a means to detect and estimate correlated photon signal
parameters. The derived GLRT was capable of detecting correlated photon signals in
a laboratory setting with a high degree of statistical confidence. A proof is presented
in which the MLE for the amplitude of the correlated photon signal is shown to be the
minimum variance unbiased estimator (MVUE). The fully characterized TDC was used
in preliminary measurements of astronomical sources using ground based telescopes.
Finally, preliminary theoretical groundwork is established for the deep space optical
communications system of the proposed Breakthrough Starshot project, in which
low-mass craft will travel to the Alpha Centauri system to collect scientific data from
Proxima B. This theoretical groundwork utilizes recent and upcoming space based
optical communication systems as starting points for the Starshot communication
system.
ContributorsHodges, Todd Michael William (Author) / Mauskopf, Philip (Thesis advisor) / Trichopoulos, George (Thesis advisor) / Papandreou-Suppappola, Antonia (Committee member) / Bliss, Daniel (Committee member) / Arizona State University (Publisher)
Created2022
Description
The propagation of waves in solids, especially when characterized by dispersion, remains a topic of profound interest in the field of signal processing. Dispersion represents a phenomenon where wave speed becomes a function of frequency and results in multiple oscillatory modes. Such signals find application in structural healthmonitoring for identifying potential damage sensitive features in complex materials.
Consequently, it becomes important to find matched time-frequency representations
for characterizing the properties of the multiple frequency-dependent modes of propagation in dispersive material. Various time-frequency representations have been
used for dispersive signal analysis. However, some of them suffered from poor timefrequency localization or were designed to match only specific dispersion modes with
known characteristics, or could not reconstruct individual dispersive modes. This
thesis proposes a new time-frequency representation, the nonlinear synchrosqueezing
transform (NSST) that is designed to offer high localization to signals with nonlinear time-frequency group delay signatures. The NSST follows the technique used
by reassignment and synchrosqueezing methods to reassign time-frequency points of
the short-time Fourier transform and wavelet transform to specific localized regions
in the time-frequency plane. As the NSST is designed to match signals with third
order polynomial phase functions in the frequency domain, we derive matched group
delay estimators for the time-frequency point reassignment. This leads to a highly localized representation for nonlinear time-frequency characteristics that also allow for
the reconstruction of individual dispersive modes from multicomponent signals. For
the reconstruction process, we propose a novel unsupervised learning approach that
does not require prior information on the variation or number of modes in the signal.
We also propose a Bayesian group delay mode merging approach for reconstructing
modes that overlap in time and frequency. In addition to using simulated signals, we demonstrate the performance of the new NSST, together with mode extraction, using
real experimental data of ultrasonic guided waves propagating through a composite
plate.
ContributorsIkram, Javaid (Author) / Papandreou-Suppappola, Antonia (Thesis advisor) / Chattopadhyay, Aditi (Thesis advisor) / Bertoni, Mariana (Committee member) / Sinha, Kanu (Committee member) / Arizona State University (Publisher)
Created2023