Matching Items (140)
Description
In this thesis, we consider the problem of fast and efficient indexing techniques for time sequences which evolve on manifold-valued spaces. Using manifolds is a convenient way to work with complex features that often do not live in Euclidean spaces. However, computing standard notions of geodesic distance, mean etc. can get very involved due to the underlying non-linearity associated with the space. As a result a complex task such as manifold sequence matching would require very large number of computations making it hard to use in practice. We believe that one can device smart approximation algorithms for several classes of such problems which take into account the geometry of the manifold and maintain the favorable properties of the exact approach. This problem has several applications in areas of human activity discovery and recognition, where several features and representations are naturally studied in a non-Euclidean setting. We propose a novel solution to the problem of indexing manifold-valued sequences by proposing an intrinsic approach to map sequences to a symbolic representation. This is shown to enable the deployment of fast and accurate algorithms for activity recognition, motif discovery, and anomaly detection. Toward this end, we present generalizations of key concepts of piece-wise aggregation and symbolic approximation for the case of non-Euclidean manifolds. Experiments show that one can replace expensive geodesic computations with much faster symbolic computations with little loss of accuracy in activity recognition and discovery applications. The proposed methods are ideally suited for real-time systems and resource constrained scenarios.
ContributorsAnirudh, Rushil (Author) / Turaga, Pavan (Thesis advisor) / Spanias, Andreas (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2012
Description
Diabetic retinopathy (DR) is a common cause of blindness occurring due to prolonged presence of diabetes. The risk of developing DR or having the disease progress is increasing over time. Despite advances in diabetes care over the years, DR remains a vision-threatening complication and one of the leading causes of blindness among American adults. Recent studies have shown that diagnosis based on digital retinal imaging has potential benefits over traditional face-to-face evaluation. Yet there is a dearth of computer-based systems that can match the level of performance achieved by ophthalmologists. This thesis takes a fresh perspective in developing a computer-based system aimed at improving diagnosis of DR images. These images are categorized into three classes according to their severity level. The proposed approach explores effective methods to classify new images and retrieve clinically-relevant images from a database with prior diagnosis information associated with them. Retrieval provides a novel way to utilize the vast knowledge in the archives of previously-diagnosed DR images and thereby improve a clinician's performance while classification can safely reduce the burden on DR screening programs and possibly achieve higher detection accuracy than human experts. To solve the three-class retrieval and classification problem, the approach uses a multi-class multiple-instance medical image retrieval framework that makes use of spectrally tuned color correlogram and steerable Gaussian filter response features. The results show better retrieval and classification performances than prior-art methods and are also observed to be of clinical and visual relevance.
ContributorsChandakkar, Parag Shridhar (Author) / Li, Baoxin (Thesis advisor) / Turaga, Pavan (Committee member) / Frakes, David (Committee member) / Arizona State University (Publisher)
Created2012
Description
Recent advances in camera architectures and associated mathematical representations now enable compressive acquisition of images and videos at low data-rates. While most computer vision applications of today are composed of conventional cameras, which collect a large amount redundant data and power hungry embedded systems, which compress the collected data for further processing, compressive cameras offer the advantage of direct acquisition of data in compressed domain and hence readily promise to find applicability in computer vision, particularly in environments hampered by limited communication bandwidths. However, despite the significant progress in theory and methods of compressive sensing, little headway has been made in developing systems for such applications by exploiting the merits of compressive sensing. In such a setting, we consider the problem of activity recognition, which is an important inference problem in many security and surveillance applications. Since all successful activity recognition systems involve detection of human, followed by recognition, a potential fully functioning system motivated by compressive camera would involve the tracking of human, which requires the reconstruction of atleast the initial few frames to detect the human. Once the human is tracked, the recognition part of the system requires only the features to be extracted from the tracked sequences, which can be the reconstructed images or the compressed measurements of such sequences. However, it is desirable in resource constrained environments that these features be extracted from the compressive measurements without reconstruction. Motivated by this, in this thesis, we propose a framework for understanding activities as a non-linear dynamical system, and propose a robust, generalizable feature that can be extracted directly from the compressed measurements without reconstructing the original video frames. The proposed feature is termed recurrence texture and is motivated from recurrence analysis of non-linear dynamical systems. We show that it is possible to obtain discriminative features directly from the compressed stream and show its utility in recognition of activities at very low data rates.
ContributorsKulkarni, Kuldeep Sharad (Author) / Turaga, Pavan (Thesis advisor) / Spanias, Andreas (Committee member) / Frakes, David (Committee member) / Arizona State University (Publisher)
Created2012
Description
Contrast agents in medical imaging can help visualize structural details, distributions of particular cell types, or local environment characteristics. Multi-modal imaging techniques have become increasingly popular for their improved sensitivity, resolution, and ability to correlate structural and functional information. This study addresses the development of dual-modality (magnetic resonance/fluorescence) and dual-functional (thermometry/detection) nanoprobes for enhanced tissue imaging.
ContributorsHemzacek, Katherine Leigh (Author) / Kodibagkar, Vikram (Thesis director) / Stabenfeldt, Sarah (Committee member) / Barrett, The Honors College (Contributor) / Harrington Bioengineering Program (Contributor)
Created2015-05
Description
Smart contrast agents allow for noninvasive study of specific events or tissue conditions inside of a patient's body using Magnetic Resonance Imaging (MRI). This research aims to develop and characterize novel smart contrast agents for MRI that respond to temperature changes in tissue microenvironments. Transmission Electron Microscopy, Nuclear Magnetic Resonance, and cell culture growth assays were used to characterize the physical, magnetic, and cytotoxic properties of candidate nanoprobes. The nanoprobes displayed thermosensitve MR properties with decreasing relaxivity with temperature. Future work will be focused on generating and characterizing photo-active analogues of the nanoprobes that could be used for both treatment of tissues and assessment of therapy.
ContributorsHussain, Khateeb Hyder (Author) / Kodibagkar, Vikram (Thesis director) / Stabenfeldt, Sarah (Committee member) / Barrett, The Honors College (Contributor) / Harrington Bioengineering Program (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2014-05
Description
The objective of the research presented here was to validate the use of kinetic models for the analysis of the dynamic behavior of a contrast agent in tumor tissue and evaluate the utility of such models in determining kinetic properties - in particular perfusion and molecular binding uptake associated with tissue hypoxia - of the imaged tissue, from concentration data acquired with dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) procedure. Data from two separate DCE-MRI experiments, performed in the past, using a standard contrast agent and a hypoxia-binding agent respectively, were analyzed. The results of the analysis demonstrated that the models used may provide novel characterization of the tumor tissue properties. Future research will work to further characterize the physical significance of the estimated parameters, particularly to provide quantitative oxygenation data for the imaged tissue.
ContributorsMartin, Jonathan Michael (Author) / Kodibagkar, Vikram (Thesis director) / Rege, Kaushal (Committee member) / Barrett, The Honors College (Contributor) / Chemical Engineering Program (Contributor) / School of Mathematical and Statistical Sciences (Contributor)
Created2013-12
Description
The main objective of this research is to develop and characterize a targeted contrast agent that will recognize acute neural injury pathology (i.e. fibrin) after traumatic brain injury (TBI). Single chain fragment variable antibodies (scFv) that bind specifically to fibrin have been produced and purified. DSPE-PEG micelles have been produced and the scFv has been conjugated to the surface of the micelles; this nanoparticle system will be used to overcome limitations in diagnosing TBI. The binding and imaging properties will be analyzed in the future to determine functionality of the nanoparticle system in vivo.
ContributorsRumbo, Kailey Michelle (Author) / Stabenfeldt, Sarah (Thesis director) / Kodibagkar, Vikram (Committee member) / Barrett, The Honors College (Contributor) / Harrington Bioengineering Program (Contributor)
Created2014-05
Description
Oxygen delivery is crucial for the development of healthy, functional tissue. Low tissue oxygenation, or hypoxia, is a characteristic that is common in many tumors. Hypoxia contributes to tumor malignancy and can reduce the success of chemotherapy and radiation treatment. There is a current need to noninvasively measure tumor oxygenation or pO2 in patients to determine a personalized treatment method. This project focuses on creating and characterizing nanoemulsions using a pO2 reporter molecule hexamethyldisiloxane (HMDSO) and its longer chain variants as well as assessing their cytotoxicity. We also explored creating multi-modal (MRI/Fluorescence) nanoemulsions.
ContributorsGrucky, Marian Louise (Author) / Kodibagkar, Vikram (Thesis director) / Rege, Kaushal (Committee member) / Stabenfeldt, Sarah (Committee member) / Barrett, The Honors College (Contributor) / Harrington Bioengineering Program (Contributor)
Created2013-05
Description
Five immunocompetent C57BL/6-cBrd/cBrd/Cr (albino C57BL/6) mice were injected with GL261-luc2 cells, a cell line sharing characteristics of human glioblastoma multiforme (GBM). The mice were imaged using magnetic resonance (MR) at five separate time points to characterize growth and development of the tumor. After 25 days, the final tumor volumes of the mice varied from 12 mm3 to 62 mm3, even though mice were inoculated from the same tumor cell line under carefully controlled conditions. We generated hypotheses to explore large variances in final tumor size and tested them with our simple reaction-diffusion model in both a 3-dimensional (3D) finite difference method and a 2-dimensional (2D) level set method. The parameters obtained from a best-fit procedure, designed to yield simulated tumors as close as possible to the observed ones, vary by an order of magnitude between the three mice analyzed in detail. These differences may reflect morphological and biological variability in tumor growth, as well as errors in the mathematical model, perhaps from an oversimplification of the tumor dynamics or nonidentifiability of parameters. Our results generate parameters that match other experimental in vitro and in vivo measurements. Additionally, we calculate wave speed, which matches with other rat and human measurements.
ContributorsRutter, Erica (Author) / Stepien, Tracy (Author) / Anderies, Barrett (Author) / Plasencia, Jonathan (Author) / Woolf, Eric C. (Author) / Scheck, Adrienne C. (Author) / Turner, Gregory H. (Author) / Liu, Qingwei (Author) / Frakes, David (Author) / Kodibagkar, Vikram (Author) / Kuang, Yang (Author) / Preul, Mark C. (Author) / Kostelich, Eric (Author) / College of Liberal Arts and Sciences (Contributor)
Created2017-05-31
Description
Human activity recognition is the task of identifying a person’s movement from sensors in a wearable device, such as a smartphone, smartwatch, or a medical-grade device. A great method for this task is machine learning, which is the study of algorithms that learn and improve on their own with the help of massive amounts of useful data. These classification models can accurately classify activities with the time-series data from accelerometers and gyroscopes. A significant way to improve the accuracy of these machine learning models is preprocessing the data, essentially augmenting data to make the identification of each activity, or class, easier for the model. <br/>On this topic, this paper explains the design of SigNorm, a new web application which lets users conveniently transform time-series data and view the effects of those transformations in a code-free, browser-based user interface. The second and final section explains my take on a human activity recognition problem, which involves comparing a preprocessed dataset to an un-augmented one, and comparing the differences in accuracy using a one-dimensional convolutional neural network to make classifications.
ContributorsLi, Vincent (Author) / Turaga, Pavan (Thesis director) / Buman, Matthew (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2021-05