Matching Items (13)
Filtering by
- All Subjects: Signal Processing
- All Subjects: deep learning
- Creators: Tepedelenlioğlu, Cihan
Description
The field of education has been immensely benefited by major breakthroughs in technology. The arrival of computers and the internet made student-teacher interaction from different parts of the world viable, increasing the reach of the educator to hitherto remote corners of the world. The arrival of mobile phones in the recent past has the potential to provide the next paradigm shift in the way education is conducted. It combines the universal reach and powerful visualization capabilities of the computer with intimacy and portability. Engineering education is a field which can exploit the benefits of mobile devices to enhance learning and spread essential technical know-how to different parts of the world. In this thesis, I present AJDSP, an Android application evolved from JDSP, providing an intuitive and a easy to use environment for signal processing education. AJDSP is a graphical programming laboratory for digital signal processing developed for the Android platform. It is designed to provide utility; both as a supplement to traditional classroom learning and as a tool for self-learning. The architecture of AJDSP is based on the Model-View-Controller paradigm optimized for the Android platform. The extensive set of function modules cover a wide range of basic signal processing areas such as convolution, fast Fourier transform, z transform and filter design. The simple and intuitive user interface inspired from iJDSP is designed to facilitate ease of navigation and to provide the user with an intimate learning environment. Rich visualizations necessary to understand mathematically intensive signal processing algorithms have been incorporated into the software. Interactive demonstrations boosting student understanding of concepts like convolution and the relation between different signal domains have also been developed. A set of detailed assessments to evaluate the application has been conducted for graduate and senior-level undergraduate students.
ContributorsRanganath, Suhas (Author) / Spanias, Andreas (Thesis advisor) / Tepedelenlioğlu, Cihan (Committee member) / Tsakalis, Konstantinos (Committee member) / Arizona State University (Publisher)
Created2013
Description
This work considers the problem of multiple detection and tracking in two complex time-varying environments, urban terrain and underwater. Tracking multiple radar targets in urban environments is rst investigated by exploiting multipath signal returns, wideband underwater acoustic (UWA) communications channels are estimated using adaptive learning methods, and multiple UWA communications users are detected by designing the transmit signal to match the environment. For the urban environment, a multi-target tracking algorithm is proposed that integrates multipath-to-measurement association and the probability hypothesis density method implemented using particle filtering. The algorithm is designed to track an unknown time-varying number of targets by extracting information from multiple measurements due to multipath returns in the urban terrain. The path likelihood probability is calculated by considering associations between measurements and multipath returns, and an adaptive clustering algorithm is used to estimate the number of target and their corresponding parameters. The performance of the proposed algorithm is demonstrated for different multiple target scenarios and evaluated using the optimal subpattern assignment metric. The underwater environment provides a very challenging communication channel due to its highly time-varying nature, resulting in large distortions due to multipath and Doppler-scaling, and frequency-dependent path loss. A model-based wideband UWA channel estimation algorithm is first proposed to estimate the channel support and the wideband spreading function coefficients. A nonlinear frequency modulated signaling scheme is proposed that is matched to the wideband characteristics of the underwater environment. Constraints on the signal parameters are derived to optimally reduce multiple access interference and the UWA channel effects. The signaling scheme is compared to a code division multiple access (CDMA) scheme to demonstrate its improved bit error rate performance. The overall multi-user communication system performance is finally analyzed by first estimating the UWA channel and then designing the signaling scheme for multiple communications users.
ContributorsZhou, Meng (Author) / Papandreou-Suppappola, Antonia (Thesis advisor) / Tepedelenlioğlu, Cihan (Committee member) / Kovvali, Narayan (Committee member) / Berisha, Visar (Committee member) / Arizona State University (Publisher)
Created2014
Description
Peptide microarrays have been used in molecular biology to profile immune responses and develop diagnostic tools. When the microarrays are printed with random peptide sequences, they can be used to identify antigen antibody binding patterns or immunosignatures. In this thesis, an advanced signal processing method is proposed to estimate epitope antigen subsequences as well as identify mimotope antigen subsequences that mimic the structure of epitopes from random-sequence peptide microarrays. The method first maps peptide sequences to linear expansions of highly-localized one-dimensional (1-D) time-varying signals and uses a time-frequency processing technique to detect recurring patterns in subsequences. This technique is matched to the aforementioned mapping scheme, and it allows for an inherent analysis on how substitutions in the subsequences can affect antibody binding strength. The performance of the proposed method is demonstrated by estimating epitopes and identifying potential mimotopes for eight monoclonal antibody samples.
The proposed mapping is generalized to express information on a protein's sequence location, structure and function onto a highly localized three-dimensional (3-D) Gaussian waveform. In particular, as analysis of protein homology has shown that incorporating different kinds of information into an alignment process can yield more robust alignment results, a pairwise protein structure alignment method is proposed based on a joint similarity measure of multiple mapped protein attributes. The 3-D mapping allocates protein properties into distinct regions in the time-frequency plane in order to simplify the alignment process by including all relevant information into a single, highly customizable waveform. Simulations demonstrate the improved performance of the joint alignment approach to infer relationships between proteins, and they provide information on mutations that cause changes to both the sequence and structure of a protein.
In addition to the biology-based signal processing methods, a statistical method is considered that uses a physics-based model to improve processing performance. In particular, an externally developed physics-based model for sea clutter is examined when detecting a low radar cross-section target in heavy sea clutter. This novel model includes a process that generates random dynamic sea clutter based on the governing physics of water gravity and capillary waves and a finite-difference time-domain electromagnetics simulation process based on Maxwell's equations propagating the radar signal. A subspace clutter suppression detector is applied to remove dominant clutter eigenmodes, and its improved performance over matched filtering is demonstrated using simulations.
The proposed mapping is generalized to express information on a protein's sequence location, structure and function onto a highly localized three-dimensional (3-D) Gaussian waveform. In particular, as analysis of protein homology has shown that incorporating different kinds of information into an alignment process can yield more robust alignment results, a pairwise protein structure alignment method is proposed based on a joint similarity measure of multiple mapped protein attributes. The 3-D mapping allocates protein properties into distinct regions in the time-frequency plane in order to simplify the alignment process by including all relevant information into a single, highly customizable waveform. Simulations demonstrate the improved performance of the joint alignment approach to infer relationships between proteins, and they provide information on mutations that cause changes to both the sequence and structure of a protein.
In addition to the biology-based signal processing methods, a statistical method is considered that uses a physics-based model to improve processing performance. In particular, an externally developed physics-based model for sea clutter is examined when detecting a low radar cross-section target in heavy sea clutter. This novel model includes a process that generates random dynamic sea clutter based on the governing physics of water gravity and capillary waves and a finite-difference time-domain electromagnetics simulation process based on Maxwell's equations propagating the radar signal. A subspace clutter suppression detector is applied to remove dominant clutter eigenmodes, and its improved performance over matched filtering is demonstrated using simulations.
ContributorsO'Donnell, Brian (Author) / Papandreou-Suppappola, Antonia (Thesis advisor) / Bliss, Daniel (Committee member) / Johnston, Stephen A. (Committee member) / Kovvali, Narayan (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Arizona State University (Publisher)
Created2014
Description
In the late 1960s, Granger published a seminal study on causality in time series, using linear interdependencies and information transfer. Recent developments in the field of information theory have introduced new methods to investigate the transfer of information in dynamical systems. Using concepts from Chaos and Markov theory, much of these methods have evolved to capture non-linear relations and information flow between coupled dynamical systems with applications to fields like biomedical signal processing. This thesis deals with the application of information theory to non-linear multivariate time series and develops measures of information flow to identify significant drivers and response (driven) components in networks of coupled sub-systems with variable coupling in strength and direction (uni- or bi-directional) for each connection. Transfer Entropy (TE) is used to quantify pairwise directional information. Four TE-based measures of information flow are proposed, namely TE Outflow (TEO), TE Inflow (TEI), TE Net flow (TEN), and Average TE flow (ATE). First, the reliability of the information flow measures on models, with and without noise, is evaluated. The driver and response sub-systems in these models are identified. Second, these measures are applied to electroencephalographic (EEG) data from two patients with focal epilepsy. The analysis showed dominant directions of information flow between brain sites and identified the epileptogenic focus as the system component typically with the highest value for the proposed measures (for example, ATE). Statistical tests between pre-seizure (preictal) and post-seizure (postictal) information flow also showed a breakage of the driving of the brain by the focus after seizure onset. The above findings shed light on the function of the epileptogenic focus and understanding of ictogenesis. It is expected that they will contribute to the diagnosis of epilepsy, for example by accurate identification of the epileptogenic focus from interictal periods, as well as the development of better seizure detection, prediction and control methods, for example by isolating pathologic areas of excessive information flow through electrical stimulation.
ContributorsPrasanna, Shashank (Author) / Jassemidis, Leonidas (Thesis advisor) / Tsakalis, Konstantinos (Thesis advisor) / Tepedelenlioğlu, Cihan (Committee member) / Arizona State University (Publisher)
Created2011
Description
Modern machine learning systems leverage data and features from multiple modalities to gain more predictive power. In most scenarios, the modalities are vastly different and the acquired data are heterogeneous in nature. Consequently, building highly effective fusion algorithms is at the core to achieve improved model robustness and inferencing performance. This dissertation focuses on the representation learning approaches as the fusion strategy. Specifically, the objective is to learn the shared latent representation which jointly exploit the structural information encoded in all modalities, such that a straightforward learning model can be adopted to obtain the prediction.
We first consider sensor fusion, a typical multimodal fusion problem critical to building a pervasive computing platform. A systematic fusion technique is described to support both multiple sensors and descriptors for activity recognition. Targeted to learn the optimal combination of kernels, Multiple Kernel Learning (MKL) algorithms have been successfully applied to numerous fusion problems in computer vision etc. Utilizing the MKL formulation, next we describe an auto-context algorithm for learning image context via the fusion with low-level descriptors. Furthermore, a principled fusion algorithm using deep learning to optimize kernel machines is developed. By bridging deep architectures with kernel optimization, this approach leverages the benefits of both paradigms and is applied to a wide variety of fusion problems.
In many real-world applications, the modalities exhibit highly specific data structures, such as time sequences and graphs, and consequently, special design of the learning architecture is needed. In order to improve the temporal modeling for multivariate sequences, we developed two architectures centered around attention models. A novel clinical time series analysis model is proposed for several critical problems in healthcare. Another model coupled with triplet ranking loss as metric learning framework is described to better solve speaker diarization. Compared to state-of-the-art recurrent networks, these attention-based multivariate analysis tools achieve improved performance while having a lower computational complexity. Finally, in order to perform community detection on multilayer graphs, a fusion algorithm is described to derive node embedding from word embedding techniques and also exploit the complementary relational information contained in each layer of the graph.
We first consider sensor fusion, a typical multimodal fusion problem critical to building a pervasive computing platform. A systematic fusion technique is described to support both multiple sensors and descriptors for activity recognition. Targeted to learn the optimal combination of kernels, Multiple Kernel Learning (MKL) algorithms have been successfully applied to numerous fusion problems in computer vision etc. Utilizing the MKL formulation, next we describe an auto-context algorithm for learning image context via the fusion with low-level descriptors. Furthermore, a principled fusion algorithm using deep learning to optimize kernel machines is developed. By bridging deep architectures with kernel optimization, this approach leverages the benefits of both paradigms and is applied to a wide variety of fusion problems.
In many real-world applications, the modalities exhibit highly specific data structures, such as time sequences and graphs, and consequently, special design of the learning architecture is needed. In order to improve the temporal modeling for multivariate sequences, we developed two architectures centered around attention models. A novel clinical time series analysis model is proposed for several critical problems in healthcare. Another model coupled with triplet ranking loss as metric learning framework is described to better solve speaker diarization. Compared to state-of-the-art recurrent networks, these attention-based multivariate analysis tools achieve improved performance while having a lower computational complexity. Finally, in order to perform community detection on multilayer graphs, a fusion algorithm is described to derive node embedding from word embedding techniques and also exploit the complementary relational information contained in each layer of the graph.
ContributorsSong, Huan (Author) / Spanias, Andreas (Thesis advisor) / Thiagarajan, Jayaraman (Committee member) / Berisha, Visar (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Arizona State University (Publisher)
Created2018
Description
The detection and characterization of transients in signals is important in many wide-ranging applications from computer vision to audio processing. Edge detection on images is typically realized using small, local, discrete convolution kernels, but this is not possible when samples are measured directly in the frequency domain. The concentration factor edge detection method was therefore developed to realize an edge detector directly from spectral data. This thesis explores the possibilities of detecting edges from the phase of the spectral data, that is, without the magnitude of the sampled spectral data. Prior work has demonstrated that the spectral phase contains particularly important information about underlying features in a signal. Furthermore, the concentration factor method yields some insight into the detection of edges in spectral phase data. An iterative design approach was taken to realize an edge detector using only the spectral phase data, also allowing for the design of an edge detector when phase data are intermittent or corrupted. Problem formulations showing the power of the design approach are given throughout. A post-processing scheme relying on the difference of multiple edge approximations yields a strong edge detector which is shown to be resilient under noisy, intermittent phase data. Lastly, a thresholding technique is applied to give an explicit enhanced edge detector ready to be used. Examples throughout are demonstrate both on signals and images.
ContributorsReynolds, Alexander Bryce (Author) / Gelb, Anne (Thesis director) / Cochran, Douglas (Committee member) / Viswanathan, Adityavikram (Committee member) / School of Mathematical and Statistical Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
For a sensor array, part of its elements may fail to work due to hardware failures. Then the missing data may distort in the beam pattern or decrease the accuracy of direction-of-arrival (DOA) estimation. Therefore, considerable research has been conducted to develop algorithms that can estimate the missing signal information. On the other hand, through those algorithms, array elements can also be selectively turned off while the missed information can be successfully recovered, which will save power consumption and hardware cost.
Conventional approaches focusing on array element failures are mainly based on interpolation or sequential learning algorithm. Both of them rely heavily on some prior knowledge such as the information of the failures or a training dataset without missing data. In addition, since most of the existing approaches are developed for DOA estimation, their recovery target is usually the co-variance matrix but not the signal matrix.
In this thesis, a new signal recovery method based on matrix completion (MC) theory is introduced. It aims to directly refill the absent entries in the signal matrix without any prior knowledge. We proposed a novel overlapping reshaping method to satisfy the applying conditions of MC algorithms. Compared to other existing MC based approaches, our proposed method can provide us higher probability of successful recovery. The thesis describes the principle of the algorithms and analyzes the performance of this method. A few application examples with simulation results are also provided.
Conventional approaches focusing on array element failures are mainly based on interpolation or sequential learning algorithm. Both of them rely heavily on some prior knowledge such as the information of the failures or a training dataset without missing data. In addition, since most of the existing approaches are developed for DOA estimation, their recovery target is usually the co-variance matrix but not the signal matrix.
In this thesis, a new signal recovery method based on matrix completion (MC) theory is introduced. It aims to directly refill the absent entries in the signal matrix without any prior knowledge. We proposed a novel overlapping reshaping method to satisfy the applying conditions of MC algorithms. Compared to other existing MC based approaches, our proposed method can provide us higher probability of successful recovery. The thesis describes the principle of the algorithms and analyzes the performance of this method. A few application examples with simulation results are also provided.
ContributorsFan, Jie (Author) / Spanias, Andreas (Thesis advisor) / Tepedelenlioğlu, Cihan (Committee member) / Tsakalis, Konstantinos (Committee member) / Arizona State University (Publisher)
Created2016
Description
Compressed sensing (CS) is a novel approach to collecting and analyzing data of all types. By exploiting prior knowledge of the compressibility of many naturally-occurring signals, specially designed sensors can dramatically undersample the data of interest and still achieve high performance. However, the generated data are pseudorandomly mixed and must be processed before use. In this work, a model of a single-pixel compressive video camera is used to explore the problems of performing inference based on these undersampled measurements. Three broad types of inference from CS measurements are considered: recovery of video frames, target tracking, and object classification/detection. Potential applications include automated surveillance, autonomous navigation, and medical imaging and diagnosis.
Recovery of CS video frames is far more complex than still images, which are known to be (approximately) sparse in a linear basis such as the discrete cosine transform. By combining sparsity of individual frames with an optical flow-based model of inter-frame dependence, the perceptual quality and peak signal to noise ratio (PSNR) of reconstructed frames is improved. The efficacy of this approach is demonstrated for the cases of \textit{a priori} known image motion and unknown but constant image-wide motion.
Although video sequences can be reconstructed from CS measurements, the process is computationally costly. In autonomous systems, this reconstruction step is unnecessary if higher-level conclusions can be drawn directly from the CS data. A tracking algorithm is described and evaluated which can hold target vehicles at very high levels of compression where reconstruction of video frames fails. The algorithm performs tracking by detection using a particle filter with likelihood given by a maximum average correlation height (MACH) target template model.
Motivated by possible improvements over the MACH filter-based likelihood estimation of the tracking algorithm, the application of deep learning models to detection and classification of compressively sensed images is explored. In tests, a Deep Boltzmann Machine trained on CS measurements outperforms a naive reconstruct-first approach.
Taken together, progress in these three areas of CS inference has the potential to lower system cost and improve performance, opening up new applications of CS video cameras.
Recovery of CS video frames is far more complex than still images, which are known to be (approximately) sparse in a linear basis such as the discrete cosine transform. By combining sparsity of individual frames with an optical flow-based model of inter-frame dependence, the perceptual quality and peak signal to noise ratio (PSNR) of reconstructed frames is improved. The efficacy of this approach is demonstrated for the cases of \textit{a priori} known image motion and unknown but constant image-wide motion.
Although video sequences can be reconstructed from CS measurements, the process is computationally costly. In autonomous systems, this reconstruction step is unnecessary if higher-level conclusions can be drawn directly from the CS data. A tracking algorithm is described and evaluated which can hold target vehicles at very high levels of compression where reconstruction of video frames fails. The algorithm performs tracking by detection using a particle filter with likelihood given by a maximum average correlation height (MACH) target template model.
Motivated by possible improvements over the MACH filter-based likelihood estimation of the tracking algorithm, the application of deep learning models to detection and classification of compressively sensed images is explored. In tests, a Deep Boltzmann Machine trained on CS measurements outperforms a naive reconstruct-first approach.
Taken together, progress in these three areas of CS inference has the potential to lower system cost and improve performance, opening up new applications of CS video cameras.
ContributorsBraun, Henry Carlton (Author) / Turaga, Pavan K (Thesis advisor) / Spanias, Andreas S (Thesis advisor) / Tepedelenlioğlu, Cihan (Committee member) / Berisha, Visar (Committee member) / Arizona State University (Publisher)
Created2016
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