Matching Items (112)
Filtering by

Clear all filters

157645-Thumbnail Image.png
Description
Disentangling latent spaces is an important research direction in the interpretability of unsupervised machine learning. Several recent works using deep learning are very effective at producing disentangled representations. However, in the unsupervised setting, there is no way to pre-specify which part of the latent space captures specific factors of

Disentangling latent spaces is an important research direction in the interpretability of unsupervised machine learning. Several recent works using deep learning are very effective at producing disentangled representations. However, in the unsupervised setting, there is no way to pre-specify which part of the latent space captures specific factors of variations. While this is generally a hard problem because of the non-existence of analytical expressions to capture these variations, there are certain factors like geometric

transforms that can be expressed analytically. Furthermore, in existing frameworks, the disentangled values are also not interpretable. The focus of this work is to disentangle these geometric factors of variations (which turn out to be nuisance factors for many applications) from the semantic content of the signal in an interpretable manner which in turn makes the features more discriminative. Experiments are designed to show the modularity of the approach with other disentangling strategies as well as on multiple one-dimensional (1D) and two-dimensional (2D) datasets, clearly indicating the efficacy of the proposed approach.
ContributorsKoneripalli Seetharam, Kaushik (Author) / Turaga, Pavan (Thesis advisor) / Papandreou-Suppappola, Antonia (Committee member) / Jayasuriya, Suren (Committee member) / Arizona State University (Publisher)
Created2019
157507-Thumbnail Image.png
Description
A critical problem for airborne, ship board, and land based radars operating in maritime or littoral environments is the detection, identification and tracking of targets against backscattering caused by the roughness of the sea surface. Statistical models, such as the compound K-distribution (CKD), were shown to accurately describe two

A critical problem for airborne, ship board, and land based radars operating in maritime or littoral environments is the detection, identification and tracking of targets against backscattering caused by the roughness of the sea surface. Statistical models, such as the compound K-distribution (CKD), were shown to accurately describe two separate structures of the sea clutter intensity fluctuations. The first structure is the texture that is associated with long sea waves and exhibits long temporal decorrelation period. The second structure is the speckle that accounts for reflections from multiple scatters and exhibits a short temporal decorrelation period from pulse to pulse. Existing methods for estimating the CKD model parameters do not include the thermal noise power, which is critical for real sea clutter processing. Estimation methods that include the noise power are either computationally intensive or require very large data records.



This work proposes two new approaches for accurately estimating all three CKD model parameters, including noise power. The first method integrates, in an iterative fashion, the noise power estimation, using one-dimensional nonlinear curve fitting,

with the estimation of the shape and scale parameters, using closed-form solutions in terms of the CKD intensity moments. The second method is similar to the first except it replaces integer-based intensity moments with fractional moments which have been shown to achieve more accurate estimates of the shape parameter. These new methods can be implemented in real time without requiring large data records. They can also achieve accurate estimation performance as demonstrated with simulated and real sea clutter observation datasets. The work also investigates the numerically computed Cram\'er-Rao lower bound (CRLB) of the variance of the shape parameter estimate using intensity observations in thermal noise with unknown power. Using the CRLB, the asymptotic estimation performance behavior of the new estimators is studied and compared to that of other estimators.
ContributorsNorthrop, Judith (Author) / Papandreou-Suppappola, Antonia (Thesis advisor) / Chakrabarti, Chaitali (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Maurer, Alexander (Committee member) / Arizona State University (Publisher)
Created2019
157934-Thumbnail Image.png
Description
Transportation plays a significant role in every human's life. Numerous factors, such as cost of living, available amenities, work style, to name a few, play a vital role in determining the amount of travel time. Such factors, among others, led in part to an increased need for private transportation and,

Transportation plays a significant role in every human's life. Numerous factors, such as cost of living, available amenities, work style, to name a few, play a vital role in determining the amount of travel time. Such factors, among others, led in part to an increased need for private transportation and, consequently, leading to an increase in the purchase of private cars. Also, road safety was impacted by numerous factors such as Driving Under Influence (DUI), driver’s distraction due to the increase in the use of mobile devices while driving. These factors led to an increasing need for an Advanced Driver Assistance System (ADAS) to help the driver stay aware of the environment and to improve road safety.

EcoCAR3 is one of the Advanced Vehicle Technology Competitions, sponsored by the United States Department of Energy (DoE) and managed by Argonne National Laboratory in partnership with the North American automotive industry. Students are challenged beyond the traditional classroom environment in these competitions, where they redesign a donated production vehicle to improve energy efficiency and to meet emission standards while maintaining the features that are attractive to the customer, including but not limited to performance, consumer acceptability, safety, and cost.

This thesis presents a driver assistance system interface that was implemented as part of EcoCAR3, including the adopted sensors, hardware and software components, system implementation, validation, and testing. The implemented driver assistance system uses a combination of range measurement sensors to determine the distance, relative location, & the relative velocity of obstacles and surrounding objects together with a computer vision algorithm for obstacle detection and classification. The sensor system and vision system were tested individually and then combined within the overall system. Also, a visual and audio feedback system was designed and implemented to provide timely feedback for the driver as an attempt to enhance situational awareness and improve safety.

Since the driver assistance system was designed and developed as part of a DoE sponsored competition, the system needed to satisfy competition requirements and rules. This work attempted to optimize the system in terms of performance, robustness, and cost while satisfying these constraints.
ContributorsBalaji, Venkatesh (Author) / Karam, Lina J (Thesis advisor) / Papandreou-Suppappola, Antonia (Committee member) / Yu, Hongbin (Committee member) / Arizona State University (Publisher)
Created2019
157982-Thumbnail Image.png
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 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.
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
158768-Thumbnail Image.png
Description
Constant false alarm rate is one of the essential algorithms in a RADAR detection system. It allows the RADAR system to dynamically set thresholds based on the data power level to distinguish targets with interfering noise and clutters.

To have a better acknowledgment of constant false alarm rate approaches performance, three

Constant false alarm rate is one of the essential algorithms in a RADAR detection system. It allows the RADAR system to dynamically set thresholds based on the data power level to distinguish targets with interfering noise and clutters.

To have a better acknowledgment of constant false alarm rate approaches performance, three clutter models, Gamma, Weibull, and Log-normal, have been introduced to evaluate the detection's capability of each constant false alarm rate algorithm.

The order statistical constant false alarm rate approach outperforms other conventional constant false alarm rate methods, especially in clutter evolved environments. However, this method requires high power consumption due to repeat sorting.
In the automotive RADAR system, the computational complexity of algorithms is essential because this system is in real-time. Therefore, the algorithms must be fast and efficient to ensure low power consumption and processing time.

The reduced computational complexity implementations of cell-averaging and order statistic constant false alarm rate were explored. Their big O and processing time has been reduced.
ContributorsChu, Huiwen (Author) / Bliss, Daniel W. (Thesis advisor) / Alkhateeb, Ahmed (Committee member) / Papandreou-Suppappola, Antonia (Committee member) / Arizona State University (Publisher)
Created2020
158864-Thumbnail Image.png
Description
Infants born before 37 weeks of pregnancy are considered to be preterm. Typically, preterm infants have to be strictly monitored since they are highly susceptible to health problems like hypoxemia (low blood oxygen level), apnea, respiratory issues, cardiac problems, neurological problems as well as an increased chance of long-term health

Infants born before 37 weeks of pregnancy are considered to be preterm. Typically, preterm infants have to be strictly monitored since they are highly susceptible to health problems like hypoxemia (low blood oxygen level), apnea, respiratory issues, cardiac problems, neurological problems as well as an increased chance of long-term health issues such as cerebral palsy, asthma and sudden infant death syndrome. One of the leading health complications in preterm infants is bradycardia - which is defined as the slower than expected heart rate, generally beating lower than 60 beats per minute. Bradycardia is often accompanied by low oxygen levels and can cause additional long term health problems in the premature infant.The implementation of a non-parametric method to predict the onset of brady- cardia is presented. This method assumes no prior knowledge of the data and uses kernel density estimation to predict the future onset of bradycardia events. The data is preprocessed, and then analyzed to detect the peaks in the ECG signals, following which different kernels are implemented to estimate the shared underlying distribu- tion of the data. The performance of the algorithm is evaluated using various metrics and the computational challenges and methods to overcome them are also discussed.
It is observed that the performance of the algorithm with regards to the kernels used are consistent with the theoretical performance of the kernel as presented in a previous work. The theoretical approach has also been automated in this work and the various implementation challenges have been addressed.
ContributorsMitra, Sinjini (Author) / Papandreou-Suppappola, Antonia (Thesis advisor) / Moraffah, Bahman (Thesis advisor) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2020
158876-Thumbnail Image.png
Description
Lattice-based Cryptography is an up and coming field of cryptography that utilizes the difficulty of lattice problems to design lattice-based cryptosystems that are resistant to quantum attacks and applicable to Fully Homomorphic Encryption schemes (FHE). In this thesis, the parallelization of the Residue Number System (RNS) and algorithmic efficiency of

Lattice-based Cryptography is an up and coming field of cryptography that utilizes the difficulty of lattice problems to design lattice-based cryptosystems that are resistant to quantum attacks and applicable to Fully Homomorphic Encryption schemes (FHE). In this thesis, the parallelization of the Residue Number System (RNS) and algorithmic efficiency of the Number Theoretic Transform (NTT) are combined to tackle the most significant bottleneck of polynomial ring multiplication with the hardware design of an optimized RNS-based NTT polynomial multiplier. The design utilizes Negative Wrapped Convolution, the NTT, RNS Montgomery reduction with Bajard and Shenoy extensions, and optimized modular 32-bit channel arithmetic for nine RNS channels to accomplish an RNS polynomial multiplication. In addition to a full software implementation of the whole system, a pipelined and optimized RNS-based NTT unit with 4 RNS butterflies is implemented on the Xilinx Artix-7 FPGA(xc7a200tlffg1156-2L) for size and delay estimates. The hardware implementation achieves an operating frequency of 47.043 MHz and utilizes 13239 LUT's, 4010 FF's, and 330 DSP blocks, allowing for multiple simultaneously operating NTT units depending on FGPA size constraints.
ContributorsBrist, Logan Alan (Author) / Chakrabarti, Chaitali (Thesis advisor) / Papandreou-Suppappola, Antonia (Committee member) / Bliss, Daniel (Committee member) / Arizona State University (Publisher)
Created2020
158425-Thumbnail Image.png
Description
The inverse problem in electroencephalography (EEG) is the determination of form and location of neural activity associated to EEG recordings. This determination is of interest in evoked potential experiments where the activity is elicited by an external stimulus. This work investigates three aspects of this problem: the use of forward

The inverse problem in electroencephalography (EEG) is the determination of form and location of neural activity associated to EEG recordings. This determination is of interest in evoked potential experiments where the activity is elicited by an external stimulus. This work investigates three aspects of this problem: the use of forward methods in its solution, the elimination of artifacts that complicate the accurate determination of sources, and the construction of physical models that capture the electrical properties of the human head.

Results from this work aim to increase the accuracy and performance of the inverse solution process.

The inverse problem can be approached by constructing forward solutions where, for a know source, the scalp potentials are determined. This work demonstrates that the use of two variables, the dissipated power and the accumulated charge at interfaces, leads to a new solution method for the forward problem. The accumulated charge satisfies a boundary integral equation. Consideration of dissipated power determines bounds on the range of eigenvalues of the integral operators that appear in this formulation. The new method uses the eigenvalue structure to regularize singular integral operators thus allowing unambiguous solutions to the forward problem.

A major problem in the estimation of properties of neural sources is the presence of artifacts that corrupt EEG recordings. A method is proposed for the determination of inverse solutions that integrates sequential Bayesian estimation with probabilistic data association in order to suppress artifacts before estimating neural activity. This method improves the tracking of neural activity in a dynamic setting in the presence of artifacts.

Solution of the inverse problem requires the use of models of the human head. The electrical properties of biological tissues are best described by frequency dependent complex conductivities. Head models in EEG analysis, however, usually consider head regions as having only constant real conductivities. This work presents a model for tissues as composed of confined electrolytes that predicts complex conductivities for macroscopic measurements. These results indicate ways in which EEG models can be improved.
ContributorsSolis, Francisco Jr. (Author) / Papandreou-Suppappola, Antonia (Thesis advisor) / Berisha, Visar (Committee member) / Bliss, Daniel (Committee member) / Moraffah, Bahman (Committee member) / Arizona State University (Publisher)
Created2020
158254-Thumbnail Image.png
Description
Detecting areas of change between two synthetic aperture radar (SAR) images of the same scene, taken at different times is generally performed using two approaches. Non-coherent change detection is performed using the sample variance ratio detector, and displays a good performance in detecting areas of significant changes. Coherent change detection

Detecting areas of change between two synthetic aperture radar (SAR) images of the same scene, taken at different times is generally performed using two approaches. Non-coherent change detection is performed using the sample variance ratio detector, and displays a good performance in detecting areas of significant changes. Coherent change detection can be implemented using the classical coherence estimator, which does better at detecting subtle changes, like vehicle tracks. A two-stage detector was proposed by Cha et al., where the sample variance ratio forms the first stage, and the second stage comprises of Berger's alternative coherence estimator.

A modification to the first stage of the two-stage detector is proposed in this study, which significantly simplifies the analysis of the this detector. Cha et al. have used a heuristic approach to determine the thresholds for this two-stage detector. In this study, the probability density function for the modified two-stage detector is derived, and using this probability density function, an approach for determining the thresholds for this two-dimensional detection problem has been proposed. The proposed method of threshold selection reveals an interesting behavior shown by the two-stage detector. With the help of theoretical receiver operating characteristic analysis, it is shown that the two-stage detector gives a better detection performance as compared to the other three detectors. However, the Berger's estimator proves to be a simpler alternative, since it gives only a slightly poorer performance as compared to the two-stage detector. All the four detectors have also been implemented on a SAR data set, and it is shown that the two-stage detector and the Berger's estimator generate images where the areas showing change are easily visible.
ContributorsBondre, Akshay Sunil (Author) / Richmond, Christ D (Thesis advisor) / Papandreou-Suppappola, Antonia (Committee member) / Bliss, Daniel W (Committee member) / Arizona State University (Publisher)
Created2020
158202-Thumbnail Image.png
Description
Complex dynamical systems are the kind of systems with many interacting components that usually have nonlinear dynamics. Those systems exist in a wide range of disciplines, such as physical, biological, and social fields. Those systems, due to a large amount of interacting components, tend to possess very high dimensionality. Additionally,

Complex dynamical systems are the kind of systems with many interacting components that usually have nonlinear dynamics. Those systems exist in a wide range of disciplines, such as physical, biological, and social fields. Those systems, due to a large amount of interacting components, tend to possess very high dimensionality. Additionally, due to the intrinsic nonlinear dynamics, they have tremendous rich system behavior, such as bifurcation, synchronization, chaos, solitons. To develop methods to predict and control those systems has always been a challenge and an active research area.

My research mainly concentrates on predicting and controlling tipping points (saddle-node bifurcation) in complex ecological systems, comparing linear and nonlinear control methods in complex dynamical systems. Moreover, I use advanced artificial neural networks to predict chaotic spatiotemporal dynamical systems. Complex networked systems can exhibit a tipping point (a “point of no return”) at which a total collapse occurs. Using complex mutualistic networks in ecology as a prototype class of systems, I carry out a dimension reduction process to arrive at an effective two-dimensional (2D) system with the two dynamical variables corresponding to the average pollinator and plant abundances, respectively. I demonstrate that, using 59 empirical mutualistic networks extracted from real data, our 2D model can accurately predict the occurrence of a tipping point even in the presence of stochastic disturbances. I also develop an ecologically feasible strategy to manage/control the tipping point by maintaining the abundance of a particular pollinator species at a constant level, which essentially removes the hysteresis associated with tipping points.

Besides, I also find that the nodal importance ranking for nonlinear and linear control exhibits opposite trends: for the former, large degree nodes are more important but for the latter, the importance scale is tilted towards the small-degree nodes, suggesting strongly irrelevance of linear controllability to these systems. Focusing on a class of recurrent neural networks - reservoir computing systems that have recently been exploited for model-free prediction of nonlinear dynamical systems, I uncover a surprising phenomenon: the emergence of an interval in the spectral radius of the neural network in which the prediction error is minimized.
ContributorsJiang, Junjie (Author) / Lai, Ying-Cheng (Thesis advisor) / Papandreou-Suppappola, Antonia (Committee member) / Wang, Xiao (Committee member) / Zhang, Yanchao (Committee member) / Arizona State University (Publisher)
Created2020