Matching Items (1,580)
Filtering by
- All Subjects: Computer Science
- All Subjects: Mechanical Engineering
Description
Unstructured texts containing biomedical information from sources such as electronic health records, scientific literature, discussion forums, and social media offer an opportunity to extract information for a wide range of applications in biomedical informatics. Building scalable and efficient pipelines for natural language processing and extraction of biomedical information plays an important role in the implementation and adoption of applications in areas such as public health. Advancements in machine learning and deep learning techniques have enabled rapid development of such pipelines. This dissertation presents entity extraction pipelines for two public health applications: virus phylogeography and pharmacovigilance. For virus phylogeography, geographical locations are extracted from biomedical scientific texts for metadata enrichment in the GenBank database containing 2.9 million virus nucleotide sequences. For pharmacovigilance, tools are developed to extract adverse drug reactions from social media posts to open avenues for post-market drug surveillance from non-traditional sources. Across these pipelines, high variance is observed in extraction performance among the entities of interest while using state-of-the-art neural network architectures. To explain the variation, linguistic measures are proposed to serve as indicators for entity extraction performance and to provide deeper insight into the domain complexity and the challenges associated with entity extraction. For both the phylogeography and pharmacovigilance pipelines presented in this work the annotated datasets and applications are open source and freely available to the public to foster further research in public health.
ContributorsMagge, Arjun (Author) / Scotch, Matthew (Thesis advisor) / Gonzalez-Hernandez, Graciela (Thesis advisor) / Greenes, Robert (Committee member) / Arizona State University (Publisher)
Created2019
Description
This dissertation aimed to evaluate the effectiveness and drawbacks of promising fall prevention strategies in individuals with stroke by rigorously analyzing the biomechanics of laboratory falls and compensatory movements required to prevent a fall. Ankle-foot-orthoses (AFOs) and functional electrical stimulators (FESs) are commonly prescribed to treat foot drop. Despite well-established positive impacts of AFOs and FES devices on balance and gait, AFO and FES users fall at a high rate. In chapter 2 (as a preliminary study), solely mechanical impacts of a semi-rigid AFO on the compensatory stepping response of young healthy individuals following trip-like treadmill perturbations were evaluated. It was found that a semi-rigid AFO on the stepping leg diminished the propulsive impulse of the compensatory step which led to decreased trunk movement control, shorter step length, and reduced center of mass (COM) stability. These results highlight the critical role of plantarflexors in generating an effective compensatory stepping response. In chapter 3, the underlying biomechanical mechanisms leading to high fall risk in long-term AFO and FES users with chronic stroke were studied. It was found that AFO and FES users fall more than Non-users because they have a more impaired lower limb that is not fully addressed by AFO/FES, therefore leading to a more impaired compensatory stepping response characterized by increased inability to generate a compensatory step with paretic leg and decreased trunk movement control. An ideal future AFO that provides dorsiflexion assistance during the swing phase and plantarflexion assistance during the push-off phase of gait is suggested to enhance the compensatory stepping response and reduce more falls. In chapter 4, the effects of a single-session trip-specific training on the compensatory stepping response of individuals with stroke were evaluated. Trunk movement control was improved after a single session of training suggesting that this type of training is a viable option to enhance compensatory stepping response and reduce falls in individuals with stroke. Finally, a future powered AFO with plantarflexion assistance complemented by a trip-specific training program is suggested to enhance the compensatory stepping response and decrease falls in individuals with stroke.
ContributorsNevisipour, Masood (Author) / Honeycutt, Claire (Thesis advisor) / Sugar, Thomas (Thesis advisor) / Artemiadis, Panagiotis (Committee member) / Abbas, James (Committee member) / Lee, Hyunglae (Committee member) / Arizona State University (Publisher)
Created2019
Description
Component simulation models, such as agent-based models, may depend on spatial data associated with geographic locations. Composition of such models can be achieved using a Geographic Knowledge Interchange Broker (GeoKIB) enabled with spatial-temporal data transformation functions, each of which is responsible for a set of interactions between two independent models. The use of autonomous interaction models allows model composition without alteration of the composed component models. An interaction model must handle differences in the spatial resolutions between models, in addition to differences in their temporal input/output data types and resolutions.
A generalized GeoKIB was designed that regulates unidirectional spatially-based interactions between composed models. Different input and output data types are used for the interaction model, depending on whether data transfer should be passive or active. Synchronization of time-tagged input/output values is made possible with the use of dependency on a discrete simulation clock. An algorithm supporting spatial conversion is developed to transform any two-dimensional geographic data map between different region specifications. Maps belonging to the composed models can have different regions, map cell sizes, or boundaries. The GeoKIB can be extended based on the model specifications to be composed and the target application domain.
Two separate, simplistic models were created to demonstrate model composition via the GeoKIB. An interaction model was created for each of the two directions the composed models interact. This exemplar is developed to demonstrate composition and simulation of geographic-based component models.
A generalized GeoKIB was designed that regulates unidirectional spatially-based interactions between composed models. Different input and output data types are used for the interaction model, depending on whether data transfer should be passive or active. Synchronization of time-tagged input/output values is made possible with the use of dependency on a discrete simulation clock. An algorithm supporting spatial conversion is developed to transform any two-dimensional geographic data map between different region specifications. Maps belonging to the composed models can have different regions, map cell sizes, or boundaries. The GeoKIB can be extended based on the model specifications to be composed and the target application domain.
Two separate, simplistic models were created to demonstrate model composition via the GeoKIB. An interaction model was created for each of the two directions the composed models interact. This exemplar is developed to demonstrate composition and simulation of geographic-based component models.
ContributorsBoyd, William Angelo (Author) / Sarjoughian, Hessam S. (Thesis advisor) / Maciejewski, Ross (Committee member) / Sarwat, Mohamed (Committee member) / Arizona State University (Publisher)
Created2019
Description
In recent years, Convolutional Neural Networks (CNNs) have been widely used in not only the computer vision community but also within the medical imaging community. Specifically, the use of pre-trained CNNs on large-scale datasets (e.g., ImageNet) via transfer learning for a variety of medical imaging applications, has become the de facto standard within both communities.
However, to fit the current paradigm, 3D imaging tasks have to be reformulated and solved in 2D, losing rich 3D contextual information. Moreover, pre-trained models on natural images never see any biomedical images and do not have knowledge about anatomical structures present in medical images. To overcome the above limitations, this thesis proposes an image out-painting self-supervised proxy task to develop pre-trained models directly from medical images without utilizing systematic annotations. The idea is to randomly mask an image and train the model to predict the missing region. It is demonstrated that by predicting missing anatomical structures when seeing only parts of the image, the model will learn generic representation yielding better performance on various medical imaging applications via transfer learning.
The extensive experiments demonstrate that the proposed proxy task outperforms training from scratch in six out of seven medical imaging applications covering 2D and 3D classification and segmentation. Moreover, image out-painting proxy task offers competitive performance to state-of-the-art models pre-trained on ImageNet and other self-supervised baselines such as in-painting. Owing to its outstanding performance, out-painting is utilized as one of the self-supervised proxy tasks to provide generic 3D pre-trained models for medical image analysis.
However, to fit the current paradigm, 3D imaging tasks have to be reformulated and solved in 2D, losing rich 3D contextual information. Moreover, pre-trained models on natural images never see any biomedical images and do not have knowledge about anatomical structures present in medical images. To overcome the above limitations, this thesis proposes an image out-painting self-supervised proxy task to develop pre-trained models directly from medical images without utilizing systematic annotations. The idea is to randomly mask an image and train the model to predict the missing region. It is demonstrated that by predicting missing anatomical structures when seeing only parts of the image, the model will learn generic representation yielding better performance on various medical imaging applications via transfer learning.
The extensive experiments demonstrate that the proposed proxy task outperforms training from scratch in six out of seven medical imaging applications covering 2D and 3D classification and segmentation. Moreover, image out-painting proxy task offers competitive performance to state-of-the-art models pre-trained on ImageNet and other self-supervised baselines such as in-painting. Owing to its outstanding performance, out-painting is utilized as one of the self-supervised proxy tasks to provide generic 3D pre-trained models for medical image analysis.
ContributorsSodha, Vatsal Arvindkumar (Author) / Liang, Jianming (Thesis advisor) / Devarakonda, Murthy (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2020
Description
Convolutional Neural Network (CNN) has achieved state-of-the-art performance in numerous applications like computer vision, natural language processing, robotics etc. The advancement of High-Performance Computing systems equipped with dedicated hardware accelerators has also paved the way towards the success of compute intensive CNNs. Graphics Processing Units (GPUs), with massive processing capability, have been of general interest for the acceleration of CNNs. Recently, Field Programmable Gate Arrays (FPGAs) have been promising in CNN acceleration since they offer high performance while also being re-configurable to support the evolution of CNNs. This work focuses on a design methodology to accelerate CNNs on FPGA with low inference latency and high-throughput which are crucial for scenarios like self-driving cars, video surveillance etc. It also includes optimizations which reduce the resource utilization by a large margin with a small degradation in performance thus making the design suitable for low-end FPGA devices as well.
FPGA accelerators often suffer due to the limited main memory bandwidth. Also, highly parallel designs with large resource utilization often end up achieving low operating frequency due to poor routing. This work employs data fetch and buffer mechanisms, designed specifically for the memory access pattern of CNNs, that overlap computation with memory access. This work proposes a novel arrangement of the systolic processing element array to achieve high frequency and consume less resources than the existing works. Also, support has been extended to more complicated CNNs to do video processing. On Intel Arria 10 GX1150, the design operates at a frequency as high as 258MHz and performs single inference of VGG-16 and C3D in 23.5ms and 45.6ms respectively. For VGG-16 and C3D the design offers a throughput of 66.1 and 23.98 inferences/s respectively. This design can outperform other FPGA 2D CNN accelerators by up to 9.7 times and 3D CNN accelerators by up to 2.7 times.
FPGA accelerators often suffer due to the limited main memory bandwidth. Also, highly parallel designs with large resource utilization often end up achieving low operating frequency due to poor routing. This work employs data fetch and buffer mechanisms, designed specifically for the memory access pattern of CNNs, that overlap computation with memory access. This work proposes a novel arrangement of the systolic processing element array to achieve high frequency and consume less resources than the existing works. Also, support has been extended to more complicated CNNs to do video processing. On Intel Arria 10 GX1150, the design operates at a frequency as high as 258MHz and performs single inference of VGG-16 and C3D in 23.5ms and 45.6ms respectively. For VGG-16 and C3D the design offers a throughput of 66.1 and 23.98 inferences/s respectively. This design can outperform other FPGA 2D CNN accelerators by up to 9.7 times and 3D CNN accelerators by up to 2.7 times.
ContributorsRavi, Pravin Kumar (Author) / Zhao, Ming (Thesis advisor) / Li, Baoxin (Committee member) / Ren, Fengbo (Committee member) / Arizona State University (Publisher)
Created2020
Description
Polyurea is a highly versatile material used in coatings and armor systems to protect against extreme conditions such as ballistic impact, cavitation erosion, and blast loading. However, the relationships between microstructurally-dependent deformation mechanisms and the mechanical properties of polyurea are not yet fully understood, especially under extreme conditions. In this work, multi-scale coarse-grained models are developed to probe molecular dynamics across the wide range of time and length scales that these fundamental deformation mechanisms operate. In the first of these models, a high-resolution coarse-grained model of polyurea is developed, where similar to united-atom models, hydrogen atoms are modeled implicitly. This model was trained using a modified iterative Boltzmann inversion method that dramatically reduces the number of iterations required. Coarse-grained simulations using this model demonstrate that multiblock systems evolve to form a more interconnected hard phase, compared to the more interrupted hard phase composed of distinct ribbon-shaped domains found in diblock systems. Next, a reactive coarse-grained model is developed to simulate the influence of the difference in time scales for step-growth polymerization and phase segregation in polyurea. Analysis of the simulated cured polyurea systems reveals that more rapid reaction rates produce a smaller diameter ligaments in the gyroidal hard phase as well as increased covalent bonding connecting the hard domain ligaments as evidenced by a larger fraction of bridging segments and larger mean radius of gyration of the copolymer chains. The effect that these processing-induced structural variations have on the mechanical properties of the polymer was tested by simulating uniaxial compression, which revealed that the higher degree of hard domain connectivity leads to a 20% increase in the flow stress. A hierarchical multiresolution framework is proposed to fully link coarse-grained molecular simulations across a broader range of time scales, in which a family of coarse-grained models are developed. The models are connected using an incremental reverse–mapping scheme allowing for long time scale dynamics simulated at a highly coarsened resolution to be passed all the way to an atomistic representation.
ContributorsLiu, Minghao (Author) / Oswald, Jay (Thesis advisor) / Muhich, Christopher (Committee member) / Jiang, Hanqing (Committee member) / Peralta, Pedro (Committee member) / Jiao, Yang (Committee member) / Arizona State University (Publisher)
Created2020
Description
The use of reactive security mechanisms in enterprise networks can, at times, provide an asymmetric advantage to the attacker. Similarly, the use of a proactive security mechanism like Moving Target Defense (MTD), if performed without analyzing the effects of security countermeasures, can lead to security policy and service level agreement violations. In this thesis, I explore the research questions 1) how to model attacker-defender interactions for multi-stage attacks? 2) how to efficiently deploy proactive (MTD) security countermeasures in a software-defined environment for single and multi-stage attacks? 3) how to verify the effects of security and management policies on the network and take corrective actions?
I propose a Software-defined Situation-aware Cloud Security framework, that, 1) analyzes the attacker-defender interactions using an Software-defined Networking (SDN) based scalable attack graph. This research investigates Advanced Persistent Threat (APT) attacks using a scalable attack graph. The framework utilizes a parallel graph partitioning algorithm to generate an attack graph quickly and efficiently. 2) models single-stage and multi-stage attacks (APTs) using the game-theoretic model and provides SDN-based MTD countermeasures. I propose a Markov Game for modeling multi-stage attacks. 3) introduces a multi-stage policy conflict checking framework at the SDN network's application plane. I present INTPOL, a new intent-driven security policy enforcement solution. INTPOL provides a unified language and INTPOL grammar that abstracts the network administrator from the underlying network controller's lexical rules. INTPOL develops a bounded formal model for network service compliance checking, which significantly reduces the number of countermeasures that needs to be deployed. Once the application-layer policy conflicts are resolved, I utilize an Object-Oriented Policy Conflict checking (OOPC) framework that identifies and resolves rule-order dependencies and conflicts between security policies.
I propose a Software-defined Situation-aware Cloud Security framework, that, 1) analyzes the attacker-defender interactions using an Software-defined Networking (SDN) based scalable attack graph. This research investigates Advanced Persistent Threat (APT) attacks using a scalable attack graph. The framework utilizes a parallel graph partitioning algorithm to generate an attack graph quickly and efficiently. 2) models single-stage and multi-stage attacks (APTs) using the game-theoretic model and provides SDN-based MTD countermeasures. I propose a Markov Game for modeling multi-stage attacks. 3) introduces a multi-stage policy conflict checking framework at the SDN network's application plane. I present INTPOL, a new intent-driven security policy enforcement solution. INTPOL provides a unified language and INTPOL grammar that abstracts the network administrator from the underlying network controller's lexical rules. INTPOL develops a bounded formal model for network service compliance checking, which significantly reduces the number of countermeasures that needs to be deployed. Once the application-layer policy conflicts are resolved, I utilize an Object-Oriented Policy Conflict checking (OOPC) framework that identifies and resolves rule-order dependencies and conflicts between security policies.
ContributorsChowdhary, Ankur (Author) / Huang, Dijiang (Thesis advisor) / Kambhampati, Subbarao (Committee member) / Doupe, Adam (Committee member) / Bao, Youzhi (Committee member) / Arizona State University (Publisher)
Created2020
Description
Information exists in various forms and a better utilization of the available information can benefit the system awareness and response predictions. The focus of this dissertation is on the fusion of different types of information using Bayesian-Entropy method. The Maximum Entropy method in information theory introduces a unique way of handling information in the form of constraints. The Bayesian-Entropy (BE) principle is proposed to integrate the Bayes’ theorem and Maximum Entropy method to encode extra information. The posterior distribution in Bayesian-Entropy method has a Bayesian part to handle point observation data, and an Entropy part that encodes constraints, such as statistical moment information, range information and general function between variables. The proposed method is then extended to its network format as Bayesian Entropy Network (BEN), which serves as a generalized information fusion tool for diagnostics, prognostics, and surrogate modeling.
The proposed BEN is demonstrated and validated with extensive engineering applications. The BEN method is first demonstrated for diagnostics of gas pipelines and metal/composite plates for damage diagnostics. Both empirical knowledge and physics model are integrated with direct observations to improve the accuracy for diagnostics and to reduce the training samples. Next, the BEN is demonstrated in prognostics and safety assessment in air traffic management system. Various information types, such as human concepts, variable correlation functions, physical constraints, and tendency data, are fused in BEN to enhance the safety assessment and risk prediction in the National Airspace System (NAS). Following this, the BE principle is applied in surrogate modeling. Multiple algorithms are proposed based on different type of information encoding, such as Bayesian-Entropy Linear Regression (BELR), Bayesian-Entropy Semiparametric Gaussian Process (BESGP), and Bayesian-Entropy Gaussian Process (BEGP) are demonstrated with numerical toy problems and practical engineering analysis. The results show that the major benefits are the superior prediction/extrapolation performance and significant reduction of training samples by using additional physics/knowledge as constraints. The proposed BEN offers a systematic and rigorous way to incorporate various information sources. Several major conclusions are drawn based on the proposed study.
The proposed BEN is demonstrated and validated with extensive engineering applications. The BEN method is first demonstrated for diagnostics of gas pipelines and metal/composite plates for damage diagnostics. Both empirical knowledge and physics model are integrated with direct observations to improve the accuracy for diagnostics and to reduce the training samples. Next, the BEN is demonstrated in prognostics and safety assessment in air traffic management system. Various information types, such as human concepts, variable correlation functions, physical constraints, and tendency data, are fused in BEN to enhance the safety assessment and risk prediction in the National Airspace System (NAS). Following this, the BE principle is applied in surrogate modeling. Multiple algorithms are proposed based on different type of information encoding, such as Bayesian-Entropy Linear Regression (BELR), Bayesian-Entropy Semiparametric Gaussian Process (BESGP), and Bayesian-Entropy Gaussian Process (BEGP) are demonstrated with numerical toy problems and practical engineering analysis. The results show that the major benefits are the superior prediction/extrapolation performance and significant reduction of training samples by using additional physics/knowledge as constraints. The proposed BEN offers a systematic and rigorous way to incorporate various information sources. Several major conclusions are drawn based on the proposed study.
ContributorsWang, Yuhao (Author) / Liu, Yongming (Thesis advisor) / Chattopadhyay, Aditi (Committee member) / Mignolet, Marc (Committee member) / Yan, Hao (Committee member) / Ren, Yi (Committee member) / Arizona State University (Publisher)
Created2020
Description
Almost all mechanical and electro-mechanical products are assemblies of multiple parts, either because of requirements for relative motion, or use of different materials, shape/size differences. Thus, assembly design is the very crux of engineering design. In addition to nominal design of an assembly, there is also tolerance design to determine allowable manufacturing variations to ensure proper functioning and assemblability. Most of the flexible assemblies are made by stamping sheet metal. Sheet metal stamping process involves plastically deforming sheet metals using dies. Sub-assemblies of two or more components are made with either spot-welding or riveting operations. Various sub-assemblies are finally joined, using spot-welds or rivets, to create the desired assembly. When two components are brought together for assembly, they do not align exactly; this causes gaps and irregularities in assemblies. As multiple parts are stacked, errors accumulate further. Stamping leads to variable deformations due to residual stresses and elastic recovery from plastic strain of metals; this is called as the ‘spring-back’ effect. When multiple components are stacked or assembled using spot welds, input parameters variations, such as sheet metal thickness, number and order of spot welds, cause variations in the exact shape of the final assembly in its free state. It is essential to understand the influence of these input parameters on the geometric variations of both the individual components and the assembly created using these components. Design of Experiment is used to generate principal effect study which evaluates the influence of input parameters on output parameters. The scope of this study is to quantify the geometric variations for a flexible assembly and evaluate their dependence on specific input variables. The 3 input variables considered are the thickness of the sheet material, the number of spot welds used and the spot-welding order to create the assembly. To quantify the geometric variations, sprung-back nodal points along lines, circular arcs, a combination of these, and a specific profile are reduced to metrologically simulated features.
ContributorsJoshi, Abhishek (Author) / Ren, Yi (Thesis advisor) / Davidson, Joseph (Committee member) / Shah, Jami (Committee member) / Arizona State University (Publisher)
Created2020
Description
Thermal Energy Storage (TES) is of great significance for many engineering applications as it allows surplus thermal energy to be stored and reused later, bridging the gap between requirement and energy use. Phase change materials (PCMs) are latent heat-based TES which have the ability to store and release heat through phase transition processes over a relatively narrow temperature range. PCMs have a wide range of operating temperatures and therefore can be used in various applications such as stand-alone heat storage in a renewable energy system, thermal storage in buildings, water heating systems, etc. In this dissertation, various PCMs are incorporated and investigated numerically and experimentally with different applications namely a thermochemical metal hydride (MH) storage system and thermal storage in buildings. In the second chapter, a new design consisting of an MH reactor encircled by a cylindrical sandwich bed packed with PCM is proposed. The role of the PCM is to store the heat released by the MH reactor during the hydrogenation process and reuse it later in the subsequent dehydrogenation process. In such a system, the exothermic and endothermic processes of the MH reactor can be utilized effectively by enhancing the thermal exchange between the MH reactor and the PCM bed. Similarly, in the third chapter, a novel design that integrates the MH reactor with cascaded PCM beds is proposed. In this design, two different types of PCMs with different melting temperatures and enthalpies are arranged in series to improve the heat transfer rate and consequently shorten the time duration of the hydrogenation and dehydrogenation processes. The performance of the new designs (in chapters 2 and 3) is investigated numerically and compared with the conventional designs in the literature. The results indicate that the new designs can significantly enhance the time duration of MH reaction (up to 87%). In the fourth chapter, organic coconut oil PCM (co-oil PCM) is explored experimentally and numerically for the first time as a thermal management tool in building applications. The results show that co-oil PCM can be a promising solution to improve the indoor thermal environment in semi-arid regions.
ContributorsAlqahtani, Talal (Author) / Phelan, Patrick E (Thesis advisor) / Shuaib, Abdelrahman (Committee member) / Mellouli, Sofiene (Committee member) / Wang, Robert (Committee member) / Mu, Bin (Committee member) / Arizona State University (Publisher)
Created2020