Matching Items (1,033)
Filtering by

Clear all filters

161804-Thumbnail Image.png
Description
The field of Computer Vision has seen great accomplishments in the last decade due to the advancements in Deep Learning. With the advent of Convolutional Neural Networks, the task of image classification has achieved unimaginable success when perceived through the traditional Computer Vision lens. With that being said, the

The field of Computer Vision has seen great accomplishments in the last decade due to the advancements in Deep Learning. With the advent of Convolutional Neural Networks, the task of image classification has achieved unimaginable success when perceived through the traditional Computer Vision lens. With that being said, the state-of-the-art results in the image classification task were produced under a closed set assumption i.e. the input samples and the target datasets have knowledge of class labels in the testing phase. When any real-world scenario is considered, the model encounters unknown instances in the data. The task of identifying these unknown instances is called Open-Set Classification. This dissertation talks about the detection of unknown classes and the classification of the known classes. The problem is approached by using a neural network architecture called Deep Hierarchical Reconstruction Nets (DHRNets). It is dealt with by leveraging the reconstruction part of the DHRNets to identify the known class labels from the data. Experiments were also conducted on Convolutional Neural Networks (CNN) on the basis of softmax probability, Autoencoders on the basis of reconstruction loss, and Mahalanobis distance on CNN's to approach this problem.
ContributorsAinala, Kalyan (Author) / Turaga, Pavan (Thesis advisor) / Moraffah, Bahman (Committee member) / Demakethepalli Venkateswara, Hemanth Kumar (Committee member) / Arizona State University (Publisher)
Created2021
161894-Thumbnail Image.png
Description
Heterogenous SoCs are in development that marry multiple architectural patterns together. In order for software to be run on such a platform, it must be broken down into its constituent parts, kernels, and scheduled for execution on the hardware. Although this can be done by hand, it would be arduous

Heterogenous SoCs are in development that marry multiple architectural patterns together. In order for software to be run on such a platform, it must be broken down into its constituent parts, kernels, and scheduled for execution on the hardware. Although this can be done by hand, it would be arduous and time consuming; rather, a tool should be developed that analyzes the source binary, extracts the kernels, schedules the kernels, and optimizes the scheduled kernels for their target component. This dissertation proposes a decidable kernel definition that enables an algorithmic approach to detecting kernels from arbitrary programs. This definition is built upon four constraints that can be tested using basic graph theory. In addition, two algorithms are proposed that successfully extract kernels based upon runtime information. The first utilizes dynamic traces, which are generated using a collection of novel optimizations. The second utilizes a simple affinity matrix, which has no runtime overhead during program execution. Finally, a Dense Neural Network is proposed that is capable of detecting a kernel's archetype based upon only the composition of the source program and the number of times individual basic blocks execute. The contributions proposed in this dissertation provide the necessary infrastructure to perform a litany of other optimizations on kernels. By detecting kernels algorithmically, any program can be analyzed and optimized with techniques that have heretofore required kernels be written in a compatible form. Computational kernels can be extracted from any program with no constraints. The innovations describes here will form the foundation for automated kernel optimization in the future, helping optimize the code of the future.
ContributorsUhrie, Richard Lawrence (Author) / Brunhaver, John (Thesis advisor) / Chakrabarti, Chaitali (Committee member) / Shrivastiva, Aviral (Committee member) / Wu, Carole-Jean (Committee member) / Arizona State University (Publisher)
Created2021
161901-Thumbnail Image.png
Description
The need of effective forecasting models for multi-variate time series has been underlined by the integration of sensory technologies into essential applications such as building energy optimizations, flight monitoring, and health monitoring. To meet this requirement, time series prediction techniques have been expanded from uni-variate to multi-variate. However, due to

The need of effective forecasting models for multi-variate time series has been underlined by the integration of sensory technologies into essential applications such as building energy optimizations, flight monitoring, and health monitoring. To meet this requirement, time series prediction techniques have been expanded from uni-variate to multi-variate. However, due to the extended models’ poor ability to capture the intrinsic relationships among variates, naïve extensions of prediction approaches result in an unwanted rise in the cost of model learning and, more critically, a significant loss in model performance. While recurrent models like Long Short-Term Memory (LSTM) and Recurrent Neural Network Network (RNN) are designed to capture the temporal intricacies in data, their performance can soon deteriorate. First, I claim in this thesis that (a) by exploiting temporal alignments of variates to quantify the importance of the recorded variates in relation to a target variate, one can build a more accurate forecasting model. I also argue that (b) traditional time series similarity/distance functions, such as Dynamic Time Warping (DTW), which require that variates have similar absolute patterns are fundamentally ill-suited for this purpose, and that should instead quantify temporal correlation in terms of temporal alignments of key “events” impacting these series, rather than series similarity. Further, I propose that (c) while learning a temporal model with recurrence-based techniques (such as RNN and LSTM – even when leveraging attention strategies) is challenging and expensive, the better results can be obtained by coupling simpler CNNs with an adaptive variate selection strategy. Putting these together, I introduce a novel Selego framework for variate selection based on these arguments, and I experimentally evaluate the performance of the proposed approach on various forecasting models, such as LSTM, RNN, and CNN, for different top-X% percent variates and different forecasting time in the future (lead), on multiple real-world data sets. Experiments demonstrate that the proposed framework can reduce the number of recorded variates required to train predictive models by 90 - 98% while also increasing accuracy. Finally, I present a fault onset detection technique that leverages the precise baseline forecasting models trained using the Selego framework. The proposed, Selego-enabled Fault Detection Framework (FDF-Selego) has been experimentally evaluated within the context of detecting the onset of faults in the building Heating, Ventilation, and Air Conditioning (HVAC) system.
ContributorsTiwaskar, Manoj (Author) / Candan, K. Selcuk (Thesis advisor) / Sapino, Maria Luisa (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Created2021
161906-Thumbnail Image.png
Description
In many real-world machine learning classification applications, well labeled training data can be difficult, expensive, or even impossible to obtain. In such situations, it is sometimes possible to label a small subset of data as belonging to the class of interest though it is impractical to manually label all data

In many real-world machine learning classification applications, well labeled training data can be difficult, expensive, or even impossible to obtain. In such situations, it is sometimes possible to label a small subset of data as belonging to the class of interest though it is impractical to manually label all data not of interest. The result is a small set of positive labeled data and a large set of unknown and unlabeled data. This is known as the Positive and Unlabeled learning (PU learning) problem, a type of semi-supervised learning. In this dissertation, the PU learning problem is rigorously defined, several common assumptions described, and a literature review of the field provided. A new family of effective PU learning algorithms, the MLR (Modified Logistic Regression) family of algorithms, is described. Theoretical and experimental justification for these algorithms is provided demonstrating their success and flexibility. Extensive experimentation and empirical evidence are provided comparing several new and existing PU learning evaluation estimation metrics in a wide variety of scenarios. The surprisingly clear advantage of a simple recall estimate as the best estimate for overall PU classifier performance is described. Finally, an application of PU learning to the field of solar fault detection, an area not previously explored in the field, demonstrates the advantage and potential of PU learning in new application domains.
ContributorsJaskie, Kristen P (Author) / Spanias, Andreas (Thesis advisor) / Blain-Christen, Jennifer (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Thiagarajan, Jayaraman (Committee member) / Arizona State University (Publisher)
Created2021
161863-Thumbnail Image.png
Description
The field of computer vision has achieved tremendous progress over recent years with innovations in deep learning and neural networks. The advances have unprecedentedly enabled an intelligent agent to understand the world from its visual observations, such as recognizing an object, detecting the object's position, and estimating the distance to

The field of computer vision has achieved tremendous progress over recent years with innovations in deep learning and neural networks. The advances have unprecedentedly enabled an intelligent agent to understand the world from its visual observations, such as recognizing an object, detecting the object's position, and estimating the distance to the object. It then comes to a question of how such visual understanding can be used to support the agent's decisions over its actions to perform a task. This dissertation aims to study this question in which several methods are presented to address the challenges in learning a desirable action policy from the agent's visual inputs for the agent to perform a task well. Specifically, this dissertation starts with learning an action policy from high dimensional visual observations by improving the sample efficiency. The improved sample efficiency is achieved through a denser reward function defined upon the visual understanding of the task, and an efficient exploration strategy equipped with a hierarchical policy. It further studies the generalizable action policy learning problem. The generalizability is achieved for both a fully observable task with local environment dynamic captured by visual representations, and a partially observable task with global environment dynamic captured by a novel graph representation. Finally, this dissertation explores learning from human-provided priors, such as natural language instructions and demonstration videos for better generalization ability.
ContributorsYe, Xin (Author) / Yang, Yezhou YY (Thesis advisor) / Ren, Yi YR (Committee member) / Pavlic, Theodore TP (Committee member) / Fan, Deliang DF (Committee member) / Srivastava, Siddharth SS (Committee member) / Arizona State University (Publisher)
Created2021
161829-Thumbnail Image.png
Description
The use of spatial data has become very fundamental in today's world. Ranging from fitness trackers to food delivery services, almost all application records users' location information and require clean geospatial data to enhance various application features. As spatial data flows in from heterogeneous sources various problems arise. The study

The use of spatial data has become very fundamental in today's world. Ranging from fitness trackers to food delivery services, almost all application records users' location information and require clean geospatial data to enhance various application features. As spatial data flows in from heterogeneous sources various problems arise. The study of entity matching has been a fervent step in the process of producing clean usable data. Entity matching is an amalgamation of various sub-processes including blocking and matching. At the end of an entity matching pipeline, we get deduplicated records of the same real-world entity. Identifying various mentions of the same real-world locations is known as spatial entity matching. While entity matching received significant interest in the field of relational entity matching, the same cannot be said about spatial entity matching. In this dissertation, I build an end-to-end Geospatial Entity Matching framework, GEM, exploring spatial entity matching from a novel perspective. In the current state-of-the-art systems spatial entity matching is only done on one type of geometrical data variant. Instead of confining to matching spatial entities of only point geometry type, I work on extending the boundaries of spatial entity matching to match the more generic polygon geometry entities as well. I propose a methodology to provide support for three entity matching scenarios across different geometrical data types: point X point, point X polygon, polygon X polygon. As mentioned above entity matching consists of various steps but blocking, feature vector creation, and classification are the core steps of the system. GEM comprises an efficient and lightweight blocking technique, GeoPrune, that uses the geohash encoding mechanism to prune away the obvious non-matching spatial entities. Geohashing is a technique to convert a point location coordinates to an alphanumeric code string. This technique proves to be very effective and swift for the blocking mechanism. I leverage the Apache Sedona engine to create the feature vectors. Apache Sedona is a spatial database management system that holds the capacity of processing spatial SQL queries with multiple geometry types without compromising on their original coordinate vector representation. In this step, I re-purpose the spatial proximity operators (SQL queries) in Apache Sedona to create spatial feature dimensions that capture the proximity between a geospatial entity pair. The last step of an entity matching process is matching or classification. The classification step in GEM is a pluggable component, which consumes the feature vector for a spatial entity pair and determines whether the geolocations match or not. The component provides 3 machine learning models that consume the same feature vector and provide a label for the test data based on the training. I conduct experiments with the three classifiers upon multiple large-scale geospatial datasets consisting of both spatial and relational attributes. Data considered for experiments arrives from heterogeneous sources and we pre-align its schema manually. GEM achieves an F-measure of 1.0 for a point X point dataset with 176k total pairs, which is 42% higher than a state-of-the-art spatial EM baseline. It achieves F-measures of 0.966 and 0.993 for the point X polygon dataset with 302M total pairs, and the polygon X polygon dataset with 16M total pairs respectively.
ContributorsShah, Setu Nilesh (Author) / Sarwat, Mohamed (Thesis advisor) / Pedrielli, Giulia (Committee member) / Boscovic, Dragan (Committee member) / Arizona State University (Publisher)
Created2021
161833-Thumbnail Image.png
Description
The meteoric rise of Deep Neural Networks (DNN) has led to the development of various Machine Learning (ML) frameworks (e.g., Tensorflow, PyTorch). Every ML framework has a different way of handling DNN models, data types, operations involved, and the internal representations stored on disk or memory. There have been initiatives

The meteoric rise of Deep Neural Networks (DNN) has led to the development of various Machine Learning (ML) frameworks (e.g., Tensorflow, PyTorch). Every ML framework has a different way of handling DNN models, data types, operations involved, and the internal representations stored on disk or memory. There have been initiatives such as the Open Neural Network Exchange (ONNX) for a more standardized approach to machine learning for better interoperability between the various popular ML frameworks. Model Serving Platforms (MSP) (e.g., Tensorflow Serving, Clipper) are used for serving DNN models to applications and edge devices. These platforms have gained widespread use for their flexibility in serving DNN models created by various ML frameworks. They also have additional capabilities such as caching, automatic ensembling, and scheduling. However, few of these frameworks focus on optimizing the storage of these DNN models, some of which may take up to ∼130GB storage space(“Turing-NLG: A 17-billion-parameter language model by Microsoft” 2020). These MSPs leave it to the ML frameworks for optimizing the DNN model with various model compression techniques, such as quantization and pruning. This thesis investigates the viability of automatic cross-model compression using traditional deduplication techniques and storage optimizations. Scenarios are identified where different DNN models have shareable model weight parameters. “Chunking” a model into smaller pieces is explored as an approach for deduplication. This thesis also proposes a design for storage in a Relational Database Management System (RDBMS) that allows for automatic cross-model deduplication.
ContributorsDas, Amitabh (Author) / Zou, Jia (Thesis advisor) / Zhao, Ming (Thesis advisor) / Yang, Yingzhen (Committee member) / Arizona State University (Publisher)
Created2021
161835-Thumbnail Image.png
Description
To optimize solar cell performance, it is necessary to properly design the doping profile in the absorber layer of the solar cell. For CdTe solar cells, Cu is used for providing p-type doping. Hence, having an estimator that, given the diffusion parameter set (time and Temperature) and the doping concentration

To optimize solar cell performance, it is necessary to properly design the doping profile in the absorber layer of the solar cell. For CdTe solar cells, Cu is used for providing p-type doping. Hence, having an estimator that, given the diffusion parameter set (time and Temperature) and the doping concentration at the junction, gives the junction depth of the absorber layer, is essential in the design process of CdTe solar cells (and other cell technologies). In this work it is called a forward (direct) estimation process. The backward (inverse) problem then is the one in which, given the junction depth and the desired concentration of Cu doping at the CdTe/CdS heterointerface, the estimator gives the time and/or the Temperature needed to achieve the desired doping profiles. This is called a backward (inverse) estimation process. Such estimators, both forward and backward, do not exist in the literature for solar cell technology. To train the Machine Learning (ML) estimator, it is necessary to first generate a large set of data that are obtained by using the PVRD-FASP Solver, which has been validated via comparison with experimental values. Note that this big dataset needs to be generated only once. Next, one uses Machine Learning (ML), Deep Learning (DL) and Artificial Intelligence (AI) to extract the actual Cu doping profiles that result from the process of diffusion, annealing, and cool-down in the fabrication sequence of CdTe solar cells. Two deep learning neural network models are used: (1) Multilayer Perceptron Artificial Neural Network (MLPANN) model using a Keras Application Programmable Interface (API) with TensorFlow backend, and (2) Radial Basis Function Network (RBFN) model to predict the Cu doping profiles for different Temperatures and durations of the annealing process. Excellent agreement between the simulated results obtained with the PVRD-FASP Solver and the predicted values is obtained. It is important to mention here that it takes a significant amount of time to generate the Cu doping profiles given the initial conditions using the PVRD-FASP Solver, because solving the drift-diffusion-reaction model is mathematically a stiff problem and leads to numerical instabilities if the time steps are not small enough, which, in turn, affects the time needed for completion of one simulation run. The generation of the same with Machine Learning (ML) is almost instantaneous and can serve as an excellent simulation tool to guide future fabrication of optimal doping profiles in CdTe solar cells.
ContributorsSalman, Ghaith (Author) / Vasileska, Dragica (Thesis advisor) / Goodnick, Stephen M. (Thesis advisor) / Ringhofer, Christian (Committee member) / Banerjee, Ayan (Committee member) / Arizona State University (Publisher)
Created2021
161838-Thumbnail Image.png
Description
Visual question answering (VQA) is a task that answers the questions by giving an image, and thus involves both language and vision methods to solve, which make the VQA tasks a frontier interdisciplinary field. In recent years, as the great progress made in simple question tasks (e.g. object recognition), researchers

Visual question answering (VQA) is a task that answers the questions by giving an image, and thus involves both language and vision methods to solve, which make the VQA tasks a frontier interdisciplinary field. In recent years, as the great progress made in simple question tasks (e.g. object recognition), researchers start to shift their interests to the questions that require knowledge and reasoning. Knowledge-based VQA requires answering questions with external knowledge in addition to the content of images. One dataset that is mostly used in evaluating knowledge-based VQA is OK-VQA, but it lacks a gold standard knowledge corpus for retrieval. Existing work leverages different knowledge bases (e.g., ConceptNet and Wikipedia) to obtain external knowledge. Because of varying knowledge bases, it is hard to fairly compare models' performance. To address this issue, this paper collects a natural language knowledge base that can be used for any question answering (QA) system. Moreover, a Visual Retriever-Reader pipeline is proposed to approach knowledge-based VQA, where the visual retriever aims to retrieve relevant knowledge, and the visual reader seeks to predict answers based on given knowledge. The retriever is constructed with two versions: term based retriever which uses best matching 25 (BM25), and neural based retriever where the latest dense passage retriever (DPR) is introduced. To encode the visual information, the image and caption are encoded separately in the two kinds of neural based retriever: Image-DPR and Caption-DPR. There are also two styles of readers, classification reader and extraction reader. Both the retriever and reader are trained with weak supervision. The experimental results show that a good retriever can significantly improve the reader's performance on the OK-VQA challenge.
ContributorsZeng, Yankai (Author) / Baral, Chitta (Thesis advisor) / Yang, Yezhou (Committee member) / Ghayekhloo, Samira (Committee member) / Arizona State University (Publisher)
Created2021
161846-Thumbnail Image.png
Description
Complex systems appear when interaction among system components creates emergent behavior that is difficult to be predicted from component properties. The growth of Internet of Things (IoT) and embedded technology has increased complexity across several sectors (e.g., automotive, aerospace, agriculture, city infrastructures, home technologies, healthcare) where the paradigm of cyber-physical

Complex systems appear when interaction among system components creates emergent behavior that is difficult to be predicted from component properties. The growth of Internet of Things (IoT) and embedded technology has increased complexity across several sectors (e.g., automotive, aerospace, agriculture, city infrastructures, home technologies, healthcare) where the paradigm of cyber-physical systems (CPSs) has become a standard. While CPS enables unprecedented capabilities, it raises new challenges in system design, certification, control, and verification. When optimizing system performance computationally expensive simulation tools are often required, and search algorithms that sequentially interrogate a simulator to learn promising solutions are in great demand. This class of algorithms are black-box optimization techniques. However, the generality that makes black-box optimization desirable also causes computational efficiency difficulties when applied real problems. This thesis focuses on Bayesian optimization, a prominent black-box optimization family, and proposes new principles, translated in implementable algorithms, to scale Bayesian optimization to highly expensive, large scale problems. Four problem contexts are studied and approaches are proposed for practically applying Bayesian optimization concepts, namely: (1) increasing sample efficiency of a highly expensive simulator in the presence of other sources of information, where multi-fidelity optimization is used to leverage complementary information sources; (2) accelerating global optimization in the presence of local searches by avoiding over-exploitation with adaptive restart behavior; (3) scaling optimization to high dimensional input spaces by integrating Game theoretic mechanisms with traditional techniques; (4) accelerating optimization by embedding function structure when the reward function is a minimum of several functions. In the first context this thesis produces two multi-fidelity algorithms, a sample driven and model driven approach, and is implemented to optimize a serial production line; in the second context the Stochastic Optimization with Adaptive Restart (SOAR) framework is produced and analyzed with multiple applications to CPS falsification problems; in the third context the Bayesian optimization with sample fictitious play (BOFiP) algorithm is developed with an implementation in high-dimensional neural network training; in the last problem context the minimum surrogate optimization (MSO) framework is produced and combined with both Bayesian optimization and the SOAR framework with applications in simultaneous falsification of multiple CPS requirements.
ContributorsMathesen, Logan (Author) / Pedrielli, Giulia (Thesis advisor) / Candan, Kasim (Committee member) / Fainekos, Georgios (Committee member) / Gel, Esma (Committee member) / Montgomery, Douglas (Committee member) / Zabinsky, Zelda (Committee member) / Arizona State University (Publisher)
Created2021