Search results

Title: AN EVOLUTIONARY MULTI-OBJECTIVE APPROACH TO SUSTAINABLE AGRICULTURAL WATER AND NUTRIENT OPTIMIZATION
Creator: Kropp, Ian Meyer
Date: 2018
Collection: Electronic Theses & Dissertations
Description: One of the main problems that society is facing in the 21st century is that agricultural production must keep pace with a rapidly increasing global population in an environmentally sustainable manner. One of the solutions to this global problem is a system approach through the application of optimization techniques to manage farm operations. However, unlike existing agricultural optimization research, this work seeks to optimize multiple agricultural objectives at once via multi-objective...
Show moreOne of the main problems that society is facing in the 21st century is that agricultural production must keep pace with a rapidly increasing global population in an environmentally sustainable manner. One of the solutions to this global problem is a system approach through the application of optimization techniques to manage farm operations. However, unlike existing agricultural optimization research, this work seeks to optimize multiple agricultural objectives at once via multi-objective optimization techniques. Specifically, the algorithm Unified Non-dominated Sorting Genetic Algorithm-III (U-NSGA-III) searched for irrigation and nutrient management practices that minimized combinations of environmental objectives (e.g., total irrigation applied, total nitrogen leached) while maximizing crop yield for maize. During optimization, the crop model named the Decision Support System for Agrotechnology Transfer (DSSAT) calculated the yield and nitrogen leaching for each given management practices. This study also developed a novel bi-level optimization framework to improve the performance of the optimization algorithm, employing U-NSGA-III on the upper level and Monte Carlo optimization on the lower level. The multi-objective optimization framework resulted in groups of equally optimal solutions that each offered a unique trade-off among the objectives. As a result, producers can choose the one that best addresses their needs among these groups of solutions, known as Pareto fronts. In addition, the bi-level optimization framework further improved the number, performance, and diversity of solutions within the Pareto fronts.
Show less

Title: ASSURING THE ROBUSTNESS AND RESILIENCY OF LEARNING-ENABLED AUTONOMOUS SYSTEMS
Creator: Langford, Michael Austin
Date: 2022
Collection: Electronic Theses & Dissertations
Description: As Learning-Enabled Systems (LESs) have become more prevalent in safety-critical applications, addressing the assurance of LESs has become increasingly important. Because machine learning models in LESs are not explicitly programmed like traditional software, developers typically have less direct control over the inferences learned by LESs, relying instead on semantically valid and complete patterns to be extracted from the system’s exposure to the environment. As such, the behavior of an LES...
Show moreAs Learning-Enabled Systems (LESs) have become more prevalent in safety-critical applications, addressing the assurance of LESs has become increasingly important. Because machine learning models in LESs are not explicitly programmed like traditional software, developers typically have less direct control over the inferences learned by LESs, relying instead on semantically valid and complete patterns to be extracted from the system’s exposure to the environment. As such, the behavior of an LES is strongly dependent on the quality of its training experience. However, run-time environments are often noisy or not well-defined. Uncertainty in the behavior of an LES can arise when there is inadequate coverage of relevant training/test cases (e.g., corner cases). It is challenging to assure safety-critical LESs will perform as expected when exposed to run-time conditions that have never been experienced during training or validation. This doctoral research contributes automated methods to improve the robustness and resilience of an LES. For this work, a robust LES is less sensitive to noise in the environment, and a resilient LES is able to self-adapt to adverse run-time contexts in order to mitigate system failure. The proposed methods harness diversity-driven evolution-based methods, machine learning, and software assurance cases to train robust LESs, uncover robust system configurations, and foster resiliency through self-adaptation and predictive behavior modeling. This doctoral work demonstrates these capabilities by applying the proposed framework to deep learning and autonomous cyber-physical systems.
Show less

Title: Achieving reliable distributed systems : through efficient run-time monitoring and predicate detection
Creator: Tekken Valapil, Vidhya
Date: 2020
Collection: Electronic Theses & Dissertations
Description: Runtime monitoring of distributed systems to perform predicate detection is critical as well as a challenging task. It is critical because it ensures the reliability of the system by detecting all possible violations of system requirements. It is challenging because to guarantee lack of violations one has to analyze every possible ordering of system events and this is an expensive task. In this report, wefocus on ordering events in a system run using HLC (Hybrid Logical Clocks) timestamps,...
Show moreRuntime monitoring of distributed systems to perform predicate detection is critical as well as a challenging task. It is critical because it ensures the reliability of the system by detecting all possible violations of system requirements. It is challenging because to guarantee lack of violations one has to analyze every possible ordering of system events and this is an expensive task. In this report, wefocus on ordering events in a system run using HLC (Hybrid Logical Clocks) timestamps, which are O(1) sized timestamps, and present some efficient algorithms to perform predicate detection using HLC. Since, with HLC, the runtime monitor cannot find all possible orderings of systems events, we present a new type of clock called Biased Hybrid Logical Clocks (BHLC), that are capable of finding more possible orderings than HLC. Thus we show that BHLC based predicate detection can find more violations than HLC based predicate detection. Since predicate detection based on both HLC and BHLC do not guarantee detection of all possible violations in a system run, we present an SMT (Satisfiability Modulo Theories) solver based predicate detection approach, that guarantees the detection of all possible violations in a system run. While a runtime monitor that performs predicate detection using SMT solvers is accurate, the time taken by the solver to detect the presence or absence of a violation can be high. To reduce the time taken by the runtime monitor, we propose the use of an efficient two-layered monitoring approach, where the first layer of the monitor is efficient but less accurate and the second layer is accurate but less efficient. Together they reduce the overall time taken to perform predicate detection drastically and also guarantee detection of all possible violations.
Show less

Title: Adaptive and Automated Deep Recommender Systems
Creator: Zhao, Xiangyu
Date: 2021
Collection: Electronic Theses & Dissertations
Description: Recommender systems are intelligent information retrieval applications, and have been leveraged in numerous domains such as e-commerce, movies, music, books, and point-of-interests. They play a crucial role in the users' information-seeking process, and overcome the information overload issue by recommending personalized items (products, services, or information) that best match users' needs and preferences. Driven by the recent advances in machine learning theories and the prevalence of deep...
Show moreRecommender systems are intelligent information retrieval applications, and have been leveraged in numerous domains such as e-commerce, movies, music, books, and point-of-interests. They play a crucial role in the users' information-seeking process, and overcome the information overload issue by recommending personalized items (products, services, or information) that best match users' needs and preferences. Driven by the recent advances in machine learning theories and the prevalence of deep learning techniques, there have been tremendous interests in developing deep learning based recommender systems. They have unprecedentedly advanced effectiveness of mining the non-linear user-item relationships and learning the feature representations from massive datasets, which produce great vitality and improvements in recommendations from both academic and industry communities.Despite above prominence of existing deep recommender systems, their adaptiveness and automation still remain under-explored. Thus, in this dissertation, we study the problem of adaptive and automated deep recommender systems. Specifically, we present our efforts devoted to building adaptive deep recommender systems to continuously update recommendation strategies according to the dynamic nature of user preference, which maximizes the cumulative reward from users in the practical streaming recommendation scenarios. In addition, we propose a group of automated and systematic approaches that design deep recommender system frameworks effectively and efficiently from a data-driven manner. More importantly, we apply our proposed models into a variety of real-world recommendation platforms and have achieved promising enhancements of social and economic benefits.
Show less

Title: Advanced Operators for Graph Neural Networks
Creator: Ma, Yao
Date: 2021
Collection: Electronic Theses & Dissertations
Description: Graphs, which encode pairwise relations between entities, are a kind of universal data structure for many real-world data, including social networks, transportation networks, and chemical molecules. Many important applications on these data can be treated as computational tasks on graphs. For example, friend recommendation in social networks can be regarded as a link prediction task and predicting properties of chemical compounds can be treated as a graph classification task. An essential...
Show moreGraphs, which encode pairwise relations between entities, are a kind of universal data structure for many real-world data, including social networks, transportation networks, and chemical molecules. Many important applications on these data can be treated as computational tasks on graphs. For example, friend recommendation in social networks can be regarded as a link prediction task and predicting properties of chemical compounds can be treated as a graph classification task. An essential step to facilitate these tasks is to learn vector representations either for nodes or the entire graphs. Given its great success of representation learning in images and text, deep learning offers great promise for graphs. However, compared to images and text, deep learning on graphs faces immense challenges. Graphs are irregular where nodes are unordered and each of them can have a distinct number of neighbors. Thus, traditional deep learning models cannot be directly applied to graphs, which calls for dedicated efforts for designing novel deep graph models. To help meet this pressing demand, we developed and investigated novel GNN algorithms to generalize deep learning techniques to graph-structured data. Two key operations in GNNs are the graph filtering operation, which aims to refine node representations; and the graph pooling operation, which aims to summarize node representations to obtain a graph representation. In this thesis, we provide deep understandings or develop novel algorithms for these two operations from new perspectives. For graph filtering operations, we propose a unified framework from the perspective of graph signal denoising, which demonstrates that most existing graph filtering operations are conducting feature smoothing. Then, we further investigate what information typical graph filtering operations can capture and how they can be understood beyond feature smoothing. For graph pooling operations, we study the procedure of pooling from the perspective of graph spectral theory and present a novel graph pooling operation. We also propose a technique to downsample nodes considering both mode importance and representativeness, which leads to a novel graph pooling operation.
Show less

Title: Computational methods to investigate connectivity in evolvable systems
Creator: Ackles, Acacia Lee
Date: 2022
Collection: Electronic Theses & Dissertations
Description: Evolution sheds light on all of biology, and evolutionary dynamics underlie some of the most pressing issues we face today. If we can deepen our understanding of evolution, we can better respond to these various challenges. However, studying such processes directly can be difficult; biological data is naturally messy, easily confounded, and often limited. Fortunately, we can use computational modeling to help simplify and systematically untangle complex evolutionary processes. The aim of this...
Show moreEvolution sheds light on all of biology, and evolutionary dynamics underlie some of the most pressing issues we face today. If we can deepen our understanding of evolution, we can better respond to these various challenges. However, studying such processes directly can be difficult; biological data is naturally messy, easily confounded, and often limited. Fortunately, we can use computational modeling to help simplify and systematically untangle complex evolutionary processes. The aim of this dissertation is therefore to develop innovative computational frameworks to describe, quantify, and build intuition about evolutionary phenomena, with a focus on connectivity within evolvable systems. Here I introduce three such computational frameworks which address the importance of connectivity in systems across scales.First, I introduce rank epistasis, a model of epistasis that does not rely on baseline assumptions of genetic interactions. Rank epistasis borrows rank-based comparison testing from parametric statistics to quantify mutational landscapes around a target locus and identify how much that landscape is perturbed by mutation at that locus. This model is able to correctly identify lack of epistasis where existing models fail, thereby providing better insight into connectivity at the genome level.Next, I describe the comparative hybrid method, an approach to piecewise study of complex phenotypes. This model creates hybridized structures of well-known cognitive substrates in order to address what facilitates the evolution of learning. The comparative hybrid model allowed us to identify both connectivity and discretization as important components to the evolution of cognition, as well as demonstrate how both these components interact in different cognitive structures. This approach highlights the importance of recognizing connected components at the level of the phenotype.Finally, I provide an engineering point of view for Tessevolve, a virtual reality enabled system for viewing fitness landscapes in multiple dimensions. While traditional methods have only allowed for 2D visualization, Tessevolve allows the user to view fitness landscapes scaled across 2D, 3D, and 4D. Visualizing these landscapes in multiple dimensions in an intuitive VR-based system allowed us to identify how landscape traversal changes as dimensions increase, demonstrating the way that connections between points across fitness landscapes are affected by dimensionality. As a whole, this dissertation looks at connectivity in computational structures across a broad range of biological scales. These methods and metrics therefore expand our computational toolkit for studying evolution in multiple systems of interest: genotypic, phenotypic, and at the whole landscape level.
Show less

Title: DIGITAL IMAGE FORENSICS IN THE CONTEXT OF BIOMETRICS
Creator: Banerjee, Sudipta
Date: 2020
Collection: Electronic Theses & Dissertations
Description: Digital image forensics entails the deduction of the origin, history and authenticity of a digital image. While a number of powerful techniques have been developed for this purpose, much of the focus has been on images depicting natural scenes and generic objects. In this thesis, we direct our focus on biometric images, viz., iris, ocular and face images.Firstly, we assess the viability of using existing sensor identification schemes developed for visible spectrum images on near-infrared (NIR...
Show moreDigital image forensics entails the deduction of the origin, history and authenticity of a digital image. While a number of powerful techniques have been developed for this purpose, much of the focus has been on images depicting natural scenes and generic objects. In this thesis, we direct our focus on biometric images, viz., iris, ocular and face images.Firstly, we assess the viability of using existing sensor identification schemes developed for visible spectrum images on near-infrared (NIR) iris and ocular images. These schemes are based on estimating the multiplicative sensor noise that is embedded in an input image. Further, we conduct a study analyzing the impact of photometric modifications on the robustness of the schemes. Secondly, we develop a method for sensor de-identificaton, where the sensor noise in an image is suppressed but its biometric utility is retained. This enhances privacy by unlinking an image from its camera sensor and, subsequently, the owner of the camera. Thirdly, we develop methods for constructing an image phylogeny tree from a set of near-duplicate images. An image phylogeny tree captures the relationship between subtly modified images by computing a directed acyclic graph that depicts the sequence in which the images were modified. Our primary contribution in this regard is the use of complex basis functions to model any arbitrary transformation between a pair of images and the design of a likelihood ratio based framework for determining the original and modified image in the pair. We are currently integrating a graph-based deep learning approach with sensor-specific information to refine and improve the performance of the proposed image phylogeny algorithm.
Show less

Title: Detecting and Mitigating Bias in Natural Languages
Creator: Liu, Haochen
Date: 2022
Collection: Electronic Theses & Dissertations
Description: Natural language processing (NLP) is an increasingly prominent subfield of artificial intelligence (AI). NLP techniques enable intelligent machines to understand and analyze natural languages and make it possible for humans and machines to communicate through natural languages. However, more and more evidence indicates that NLP applications show human-like discriminatory bias or make unfair decisions. As NLP algorithms play an increasingly irreplaceable role in promoting the automation of...
Show moreNatural language processing (NLP) is an increasingly prominent subfield of artificial intelligence (AI). NLP techniques enable intelligent machines to understand and analyze natural languages and make it possible for humans and machines to communicate through natural languages. However, more and more evidence indicates that NLP applications show human-like discriminatory bias or make unfair decisions. As NLP algorithms play an increasingly irreplaceable role in promoting the automation of people's lives, bias in NLP is closely related to users' vital interests and demands considerable attention.While there are a growing number of studies related to bias in natural languages, the research on this topic is far from complete. In this thesis, we propose several studies to fill up the gaps in the area of bias in NLP in terms of three perspectives. First, existing studies are mainly confined to traditional and relatively mature NLP tasks, but for certain newly emerging tasks such as dialogue generation, the research on how to define, detect, and mitigate the bias in them is still absent. We conduct pioneering studies on bias in dialogue models to answer these questions. Second, previous studies basically focus on explicit bias in NLP algorithms but overlook implicit bias. We investigate the implicit bias in text classification tasks in our studies, where we propose novel methods to detect, explain, and mitigate the implicit bias. Third, existing research on bias in NLP focuses more on in-processing and post-processing bias mitigation strategies, but rarely considers how to avoid bias being produced in the generation process of the training data, especially in the data annotation phase. To this end, we investigate annotator bias in crowdsourced data for NLP tasks and its group effect. We verify the existence of annotator group bias, develop a novel probabilistic graphical framework to capture it, and propose an algorithm to eliminate its negative impact on NLP model learning.
Show less

Title: Efficient Distributed Algorithms : Better Theory and Communication Compression
Creator: LI, YAO
Date: 2022
Collection: Electronic Theses & Dissertations
Description: Large-scale machine learning models are often trained by distributed algorithms over either centralized or decentralized networks. The former uses a central server to aggregate the information of local computing agents and broadcast the averaged parameters in a master-slave architecture. The latter considers a connected network formed by all agents. The information can only be exchanged with accessible neighbors with a mixing matrix of communication weights encoding the network's topology....
Show moreLarge-scale machine learning models are often trained by distributed algorithms over either centralized or decentralized networks. The former uses a central server to aggregate the information of local computing agents and broadcast the averaged parameters in a master-slave architecture. The latter considers a connected network formed by all agents. The information can only be exchanged with accessible neighbors with a mixing matrix of communication weights encoding the network's topology. Compared with centralized optimization, decentralization facilitates data privacy and reduces the communication burden of the single central agent due to model synchronization, but the connectivity of the communication network weakens the theoretical convergence complexity of the decentralized algorithms. Therefore, there are still gaps between decentralized and centralized algorithms in terms of convergence conditions and rates. In the first part of this dissertation, we consider two decentralized algorithms: EXTRA and NIDS, which both converge linearly with strongly convex objective functions and answer two questions regarding them. \textit{What are the optimal upper bounds for their stepsizes?} \textit{Do decentralized algorithms require more properties on the functions for linear convergence than centralized ones?} More specifically, we relax the required conditions for linear convergence of both algorithms. For EXTRA, we show that the stepsize is comparable to that of centralized algorithms. For NIDS, the upper bound of the stepsize is shown to be exactly the same as the centralized ones. In addition, we relax the requirement for the objective functions and the mixing matrices. We provide the linear convergence results for both algorithms under the weakest conditions.As the number of computing agents and the dimension of the model increase, the communication cost of parameter synchronization becomes the major obstacle to efficient learning. Communication compression techniques have exhibited great potential as an antidote to accelerate distributed machine learning by mitigating the communication bottleneck. In the rest of the dissertation, we propose compressed residual communication frameworks for both centralized and decentralized optimization and design different algorithms to achieve efficient communication. For centralized optimization, we propose DORE, a modified parallel stochastic gradient descent method with a bidirectional residual compression, to reduce over $95\%$ of the overall communication. Our theoretical analysis demonstrates that the proposed strategy has superior convergence properties for both strongly convex and nonconvex objective functions. Existing works mainly focus on smooth problems and compressing DGD-type algorithms for decentralized optimization. The class of smooth objective functions and the sublinear convergence rate under relatively strong assumptions limit these algorithms' application and practical performance. Motivated by primal-dual algorithms, we propose Prox-LEAD, a linear convergent decentralized algorithm with compression, to tackle strongly convex problems with a nonsmooth regularizer. Our theory describes the coupled dynamics of the inexact primal and dual update as well as compression error without assuming bounded gradients. The superiority of the proposed algorithm is demonstrated through the comparison with state-of-the-art algorithms in terms of convergence complexities and numerical experiments. Our algorithmic framework also generally enlightens the compressed communication on other primal-dual algorithms by reducing the impact of inexact iterations.
Show less

Title: Efficient Transfer Learning for Heterogeneous Machine Learning Domains
Creator: Zhu, Zhuangdi
Date: 2022
Collection: Electronic Theses & Dissertations
Description: Recent advances in deep machine learning hinge on a large amount of labeled data. Such heavy dependence on supervision data impedes the broader application of deep learning in more practical scenarios, where data annotation and labeling can be expensive (e.g. high-frequency trading) or even dangerous (e.g. training autonomous-driving models.) Transfer Learning (TL), equivalently referred to as knowledge transfer, is an effective strategy to confront such challenges. TL, by its definition,...
Show moreRecent advances in deep machine learning hinge on a large amount of labeled data. Such heavy dependence on supervision data impedes the broader application of deep learning in more practical scenarios, where data annotation and labeling can be expensive (e.g. high-frequency trading) or even dangerous (e.g. training autonomous-driving models.) Transfer Learning (TL), equivalently referred to as knowledge transfer, is an effective strategy to confront such challenges. TL, by its definition, distills the external knowledge from relevant domains into the target learning domain, hence requiring fewer supervision resources than learning-from-scratch. TL is beneficial for learning tasks for which the supervision data is limited or even unavailable. It is also an essential property to realize Generalized Artificial Intelligence. In this thesis, we propose sample-efficient TL approaches using limited, sometimes unreliable resources. We take a deep look into the setting of Reinforcement Learning (RL) and Supervised Learning, and derive solutions for the two domains respectively. Especially, for RL, we focus on a problem setting called imitation learning, where the supervision from the environment is either non-available or scarcely provided, and the learning agent must transfer knowledge from exterior resources, such as demonstration examples of a previously trained expert, to learn a good policy. For supervised learning, we consider a distributed machine learning scheme called Federated Learning (FL), which is a more challenging scenario than traditional machine learning, since the training data is distributed and non-sharable during the learning process. Under this distributed setting, it is imperative to enable TL among distributed learning clients to reach a satisfiable generalization performance. We prove by both theoretical support and extensive experiments that our proposed algorithms can facilitate the machine learning process with knowledge transfer to achieve higher asymptotic performance, in a principled and more efficient manner than the prior arts.
Show less

Title: Efficient and Secure Message Passing for Machine Learning
Creator: Liu, Xiaorui
Date: 2022
Collection: Electronic Theses & Dissertations
Description: Machine learning (ML) techniques have brought revolutionary impact to human society, and they will continue to act as technological innovators in the future. To broaden its impact, it is urgent to solve the emerging and critical challenges in machine learning, such as efficiency and security issues. On the one hand, ML models have become increasingly powerful due to big data and models, but it also brings tremendous challenges in designing efficient optimization algorithms to train the big ML...
Show moreMachine learning (ML) techniques have brought revolutionary impact to human society, and they will continue to act as technological innovators in the future. To broaden its impact, it is urgent to solve the emerging and critical challenges in machine learning, such as efficiency and security issues. On the one hand, ML models have become increasingly powerful due to big data and models, but it also brings tremendous challenges in designing efficient optimization algorithms to train the big ML models from big data. The most effective way for large-scale ML is to parallelize the computation tasks on distributed systems composed of many computational devices. However, in practice, the scalability and efficiency of the systems are greatly limited by information synchronization since the message passing between the devices dominates the total running time. In other words, the major bottleneck lies in the high communication cost between devices, especially when the scale of the system and the models becomes larger while the communication bandwidth is relatively limited. This communication bottleneck often limits the practical speedup of distributed ML systems. On the other hand, recent research has generally revealed that many ML models suffer from security vulnerabilities. In particular, deep learning models can be easily deceived by the unnoticeable perturbations in data. Meanwhile, graph is a kind of prevalent data structure for many real-world data that encodes pairwise relations between entities such as social networks, transportation networks, and chemical molecules. Graph neural networks (GNNs) generalize and extend the representation learning power of traditional deep neural networks (DNNs) from regular grids, such as image, video, and text, to irregular graph-structured data through message passing frameworks. Therefore, many important applications on these data can be treated as computational tasks on graphs, such as recommender systems, social network analysis, traffic prediction, etc. Unfortunately, the vulnerability of deep learning models also translates to GNNs, which raises significant concerns about their applications, especially in safety-critical areas. Therefore, it is critical to design intrinsically secure ML models for graph-structured data.The primary objective of this dissertation is to figure out the solutions to solve these challenges via innovative research and principled methods. In particular, we propose multiple distributed optimization algorithms with efficient message passing to mitigate the communication bottleneck and speed up ML model training in distributed ML systems. We also propose multiple secure message passing schemes as the building blocks of graph neural networks aiming to significantly improve the security and robustness of ML models.
Show less

Title: Example-Based Parameterization of Linear Blend Skinning for Skinning Decomposition (EP-LBS
Creator: Hopkins, Kayra M.
Date: 2017
Collection: Electronic Theses & Dissertations
Description: This thesis presents Example-based Parameterization of Linear Blend Skinning for Skinning Decomposition (EP-LBS), a unified and robust method for using example data to simplify and improve the development and parameterization of high quality 3D models for animation. Animation and three-dimensional (3D) computer graphics have quickly become a popular medium for education, entertainment and scientific simulation. In addition to film, gaming and research applications, recent advancements in...
Show moreThis thesis presents Example-based Parameterization of Linear Blend Skinning for Skinning Decomposition (EP-LBS), a unified and robust method for using example data to simplify and improve the development and parameterization of high quality 3D models for animation. Animation and three-dimensional (3D) computer graphics have quickly become a popular medium for education, entertainment and scientific simulation. In addition to film, gaming and research applications, recent advancements in augmented reality (AR) and virtual reality (VR) are driving additional demand for 3D content. However, the success of graphics in these arenas depends greatly on the efficiency of model creation and the realism of the animation or 3D image.A common method for figure animation is skeletal animation using linear blend skinning (LBS). In this method, vertices are deformed based on a weighted sum of displacements due to an embedded skeleton. This research addresses the problem that LBS animation parameter computation, including determining the rig (the skeletal structure), identifying influence bones (which bones influence which vertices), and assigning skinning weights (amounts of influence a bone has on a vertex), is a tedious process that is difficult to get right. Even the most skilled animators must work tirelessly to design an effective character model and often find themselves repeatedly correcting flaws in the parameterization. Significant research, including the use of example-data, has focused on simplifying and automating individual components of the LBS deformation process and increasing the quality of resulting animations. However, constraints on LBS animation parameters makes automated analytic computation of the values equally as challenging as traditional 3D animation methods. Skinning decomposition is one such method of computing LBS animation LBS parameters from example data. Skinning decomposition challenges include constraint adherence and computationally efficient determination of LBS parameters.The EP-LBS method presented in this thesis utilizes example data as input to a least-squares non-linear optimization process. Given a model as a set of example poses captured from scan data or manually created, EP-LBS institutes a single optimization equation that allows for simultaneous computation of all animation parameters for the model. An iterative clustering methodology is used to construct an initial parameterization estimate for this model, which is then subjected to non-linear optimization to improve the fitting to the example data. Simultaneous optimization of weights and joint transformations is complicated by a wide range of differing constraints and parameter interdependencies. To address interdependent and conflicting constraints, parameter mapping solutions are presented that map the constraints to an alternative domain more suitable for nonlinear minimization. The presented research is a comprehensive, data-driven solution for automatically determining skeletal structure, influence bones and skinning weights from a set of example data. Results are presented for a range of models that demonstrate the effectiveness of the method.
Show less

Title: Face Anti-Spoofing : Detection, Generalization, and Visualization
Creator: Liu, Yaojie
Date: 2021
Collection: Electronic Theses & Dissertations
Description: Face anti-spoofing is the process of distinguishing genuine faces and face presentation attacks: attackers presenting spoofing faces (e.g. photograph, digital screen, and mask) to the face recognition system and attempting to be authenticated as the genuine user. In recent years, face anti-spoofing has brought increasing attention to the vision community as it is a crucial step to prevent face recognition systems from a security breach. Previous approaches formulate face anti-spoofing as a...
Show moreFace anti-spoofing is the process of distinguishing genuine faces and face presentation attacks: attackers presenting spoofing faces (e.g. photograph, digital screen, and mask) to the face recognition system and attempting to be authenticated as the genuine user. In recent years, face anti-spoofing has brought increasing attention to the vision community as it is a crucial step to prevent face recognition systems from a security breach. Previous approaches formulate face anti-spoofing as a binary classification problem, and many of them struggle to generalize to different conditions(such as pose, lighting, expressions, camera sensors, and unknown spoof types). Moreover, those methods work as a black box and cannot provide interpretation or visualization to their decision. To address those challenges, we investigate face anti-spoofing in 3 stages: detection, generalization and visualization. In the detection stage, we learn a CNN-RNN model to estimate auxiliary tasks of face depth and rPPG signals estimation, which can bring additional knowledge for the spoof detection. In the generalization stage, we investigate the detection of unknown spoof attacks and propose a novel Deep Tree Network (DTN) to well represent the unknown spoof attacks. In the visualization stage, we find “spoof trace, the subtle image pattern in spoof faces (e.g., color distortion, 3D mask edge, and Moire pattern), is effective to explain why a spoof is a spoof. We provide a proper physical modeling of the spoof traces and design a generative model to disentangle the spoof traces from input faces. In addition, we also show that a proper physical modeling can benefit other face problems, such as face shadow detection and removal. A proper shadow modeling can not only detect the shadow region effectively, but also remove the shadow in a visually plausible manner.
Show less

Title: Fast edit distance calculation methods for NGS sequence similarity
Creator: Islam, A. K. M. Tauhidul
Date: 2020
Collection: Electronic Theses & Dissertations
Description: Sequence fragments generated from targeted regions of phylogenetic marker genes provide valuable insight in identifying and classifying organisms and inferring taxonomic hierarchies. In recent years, significant development in targeted gene fragment sequencing through Next Generation Sequencing (NGS) technologies has increased the necessity of efficient sequence similarity computation methods for very large numbers of pairs of NGS sequences.The edit distance has been widely used to determine...
Show moreSequence fragments generated from targeted regions of phylogenetic marker genes provide valuable insight in identifying and classifying organisms and inferring taxonomic hierarchies. In recent years, significant development in targeted gene fragment sequencing through Next Generation Sequencing (NGS) technologies has increased the necessity of efficient sequence similarity computation methods for very large numbers of pairs of NGS sequences.The edit distance has been widely used to determine the dissimilarity between pairs of strings. All the known methods for the edit distance calculation run in near quadratic time with respect to string lengths, and it may take days or weeks to compute distances between such large numbers of pairs of NGS sequences. To solve the performance bottleneck problem, faster edit distance approximation and bounded edit distance calculation methods have been proposed. Despite these efforts, the existing edit distance calculation methods are not fast enough when computing larger numbers of pairs of NGS sequences. In order to further reduce the computation time, many NGS sequence similarity methods have been proposed using matching k-mers. These methods extract all possible k-mers from NGS sequences and compare similarity between pairs of sequences based on the shared k-mers. However, these methods reduce the computation time at the cost accuracy.In this dissertation, our goal is to compute NGS sequence similarity using edit distance based methods while reducing the computation time. We propose a few edit distance prediction methods using dataset independent reference sequences that are distant from each other. These reference sequences convert sequences in datasets into feature vectors by computing edit distances between the sequence and each of the reference sequences. Given sequences A, B and a reference sequence r, the edit distance, ed(A.B) 2265 (ed(A, r) 0303ed(B, r)). Since each reference sequence is significantly different from each other, with sufficiently large number of reference sequences and high similarity threshold, the differences of edit distances of A and B with respect to the reference sequences are close to the ed(A,B). Using this property, we predict edit distances in the vector space based on the Euclidean distances and the Chebyshev distances. Further, we develop a small set of deterministically generated reference sequences with maximum distance between each of them to predict higher edit distances more efficiently. This method predicts edit distances between corresponding sub-sequences separately and then merges the partial distances to predict the edit distances between the entire sequences. The computation complexity of this method is linear with respect to sequence length. The proposed edit distance prediction methods are significantly fast while achieving very good accuracy for high similarity thresholds. We have also shown the effectiveness of these methods on agglomerative hierarchical clustering.We also propose an efficient bounded exact edit distance calculation method using the trace [1]. For a given edit distance threshold d, only letters up to d positions apart can be part of an edit operation. Hence, we generate pairs of sub-sequences up to length difference d so that no edit operation is spilled over to the adjacent pairs of sub-sequences. Then we compute the trace cost in such a way that the number of matching letters between the sub-sequences are maximized. This technique does not guarantee locally optimal edit distance, however, it guarantees globally optimal edit distance between the entire sequences for distance up to d. The bounded exact edit distance calculation method is an order of magnitude faster than that of the dynamic programming edit distance calculation method.
Show less

Title: GENERATIVE SIGNAL PROCESSING THROUGH MULTILAYER MULTISCALE WAVELET MODELS
Creator: He, Jieqian
Date: 2021
Collection: Electronic Theses & Dissertations
Description: Wavelet analysis and deep learning are two popular fields for signal processing. The scattering transform from wavelet analysis is a recently proposed mathematical model for convolution neural networks. Signals with repeated patterns can be analyzed using the statistics from such models. Specifically, signals from certain classes can be recovered from related statistics. We first focus on recovering 1D deterministic dirac signals from multiscale statistics. We prove a dirac signal can be...
Show moreWavelet analysis and deep learning are two popular fields for signal processing. The scattering transform from wavelet analysis is a recently proposed mathematical model for convolution neural networks. Signals with repeated patterns can be analyzed using the statistics from such models. Specifically, signals from certain classes can be recovered from related statistics. We first focus on recovering 1D deterministic dirac signals from multiscale statistics. We prove a dirac signal can be recovered from multiscale statistics up to a translation and reflection. Then we switch to a stochastic version, modeled using Poisson point processes, and prove wavelet statistics at small scales capture the intensity parameter of Poisson point processes. We also design a scattering generative adversarial network (GAN) to generate new Poisson point samples from statistics of multiple given samples. Next we consider texture images. We successfully synthesize new textures given one sample from the texture class through multiscale, multilayer wavelet models. Finally, we analyze and prove why the multiscale multilayer model is essential for signal recovery, especially natural texture images.
Show less

Title: IMPROVED DETECTION AND MANAGEMENT OF PHYTOPHTHORA SOJAE
Creator: McCoy, Austin Glenn
Date: 2022
Collection: Electronic Theses & Dissertations
Description: Phytophthora spp. cause root and stem rots, leaf blights and fruit rots on agricultural and economically important plant species. Symptoms of Phytophthora infected plants, particularly root rots, can be difficult to distinguish from other oomycete and fungal pathogens and often result in devastating losses. Phytophthora spp. can lie dormant for many years in the oospore stage, making long-term management of these diseases difficult. Phytophthora sojae is an important and prevalent pathogen of...
Show morePhytophthora spp. cause root and stem rots, leaf blights and fruit rots on agricultural and economically important plant species. Symptoms of Phytophthora infected plants, particularly root rots, can be difficult to distinguish from other oomycete and fungal pathogens and often result in devastating losses. Phytophthora spp. can lie dormant for many years in the oospore stage, making long-term management of these diseases difficult. Phytophthora sojae is an important and prevalent pathogen of soybean (Glycine max L.) worldwide, causing Phytophthora stem and root rot (PRR). PRR disease management during the growing season relies on an integrated pest management approach using a combination of host resistance, chemical compounds (fungicides; oomicides) and cultural practices for successful management. Therefore, this dissertation research focuses on improving the detection and management recommendations for Phytophthora sojae. In Chapter 1 I provide background and a review of the current literature on Phytophthora sojae management, including genetic resistance, chemical control compounds (fungicides; oomicides) and cultural practices used to mitigate losses to PRR. In my second chapter I validate the sensitivity and specificity of a preformulated Recombinase Polymerase Amplification assay for Phytophthora spp. This assay needs no refrigeration, does not require extensive DNA isolation, can be used in the field, and different qPCR platforms could reliably detect down to 3.3-330.0 pg of Phytophthora spp. DNA within plant tissue in under 30 minutes. Based on the limited reagents needed, ease of use, and reliability, this assay would be of benefit to diagnostic labs and inspectors monitoring regulated and non-regulated Phytophthora spp. Next, I transitioned the Habgood-Gilmour Spreadsheet (‘HaGiS’) from Microsoft Excel format to the subsequent R package ‘hagis’ and improved upon the analyses readily available to compare pathotypes from different populations of P. sojae (Chapter 3; ‘hagis’ beta-diversity). I then implemented the R package ‘hagis’ in my own P. sojae pathotype and fungicide sensitivity survey in the state of Michigan, identifying effective resistance genes and seed treatment compounds for the management of PRR. This study identified a loss of Rps1c and Rps1k, the two most widely plant Phytophthora sojae resistance genes, as viable management tools in Michigan and an increase in pathotype complexity, as compared to a survey conducted twenty years ago in Michigan (Chapter 4). In Chapter 5 I led a multi-state integrated pest management field trial that was performed in Michigan, Indiana, and Minnesota to study the effects of partial resistance and seed treatments with or without ethaboxam and metalaxyl on soybean stand, plant dry weights, and final yields under P. sojae pressure. This study found that oomicide treated seed protects stand across three locations in the Midwest, but the response of soybean varieties based on seed treatment, was variety and year specific. Significant yield benefits from using oomicide treated seed were only observed in one location and year. The effects of partial resistance were inconclusive and highlighted the need for a more informative and reliable rating system for soybean varieties partial resistance to P. sojae. Finally, in Chapter 6 I present conclusions and impacts on the studies presented in this dissertation. Overall, the studies presented provide an improvement to the detection, virulence data analysis, and integrated pest management recommendations for Phytophthora sojae.
Show less

Title: IMPROVING THE PREDICTABILITY OF HYDROLOGIC INDICES IN ECOHYDROLOGICAL APPLICATIONS
Creator: Hernandez Suarez, Juan Sebastian
Date: 2021
Collection: Electronic Theses & Dissertations
Description: Monitoring freshwater ecosystems allow us to better understand their overall ecohydrological condition within large and diverse watersheds. Due to the significant costs associated with biological monitoring, hydrological modeling is widely used to calculate ecologically relevant hydrologic indices (ERHIs) for stream health characterization in locations with lacking data. However, the reliability and applicability of these models within ecohydrological frameworks are major concerns....
Show moreMonitoring freshwater ecosystems allow us to better understand their overall ecohydrological condition within large and diverse watersheds. Due to the significant costs associated with biological monitoring, hydrological modeling is widely used to calculate ecologically relevant hydrologic indices (ERHIs) for stream health characterization in locations with lacking data. However, the reliability and applicability of these models within ecohydrological frameworks are major concerns. Particularly, hydrologic modeling’s ability to predict ERHIs is limited, especially when calibrating models by optimizing a single objective function or selecting a single optimal solution. The goal of this research was to develop model calibration strategies based on multi-objective optimization and Bayesian parameter estimation to improve the predictability of ERHIs and the overall representation of the streamflow regime. The research objectives were to (1) evaluate the predictions of ERHIs using different calibration techniques based on widely used performance metrics, (2) develop performance and signature-based calibration strategies explicitly constraining or targeting ERHIs, and (3) quantify the modeling uncertainty of ERHIs using the results from multi-objective model calibration and Bayesian inference. The developed strategies were tested in an agriculture-dominated watershed in Michigan, US, using the Unified Non-dominated Sorting Algorithm III (U-NSGA-III) for multi-objective calibration and the Soil and Water Assessment Tool (SWAT) for hydrological modeling. Performance-based calibration used objective functions based on metrics calculated on streamflow time series, whereas signature-based calibration used ERHIs values for objective functions’ formulation. For uncertainty quantification purposes, a lumped error model accounting for heteroscedasticity and autocorrelation was considered and the multiple-try Differential Evolution Adaptive Metropolis (ZS) (MT-DREAM(ZS)) algorithm was implemented for Markov Chain Monte Carlo (MCMC) sampling. In relation to the first objective, the results showed that using different sets of solutions instead of a single optimal introduces more flexibility in the predictability of various ERHIs. Regarding the second objective, both performance-based and signature-based model calibration strategies were successful in representing most of the selected ERHIs within a +/-30% relative error acceptability threshold while yielding consistent runoff predictions. The performance-based strategy was preferred since it showed a lower dispersion of near-optimal Pareto solutions when representing the selected indices and other hydrologic signatures based on water balance and Flow Duration Curve characteristics. Finally, regarding the third objective, using near-optimal Pareto parameter distributions as prior knowledge in Bayesian calibration generally reduced both the bias and variability ranges in ERHIs prediction. In addition, there was no significant loss in the reliability of streamflow predictions when targeting ERHIs, while improving precision and reducing the bias. Moreover, parametric uncertainty drastically shrank when linking multi-objective calibration and Bayesian parameter estimation. Still, the representation of low flow magnitude and timing, rate of change, and duration and frequency of extreme flows were limited. These limitations, expressed in terms of bias and interannual variability, were mainly attributed to the hydrological model’s structural inadequacies. Therefore, future research should involve revising hydrological models to better describe the ecohydrological characteristics of riverine systems.
Show less

Title: INTERPRETABLE ARTIFICIAL INTELLIGENCE USING NONLINEAR DECISION TREES
Creator: Dhebar, Yashesh Deepakkumar
Date: 2020
Collection: Electronic Theses & Dissertations
Description: The recent times have observed a massive application of artificial intelligence (AI) to automate tasks across various domains. The back-end mechanism with which automation occurs is generally black-box. Some of the popular black-box AI methods used to solve an automation task include decision trees (DT), support vector machines (SVM), artificial neural networks (ANN), etc. In the past several years, these black-box AI methods have shown promising performance and have been widely applied and...
Show moreThe recent times have observed a massive application of artificial intelligence (AI) to automate tasks across various domains. The back-end mechanism with which automation occurs is generally black-box. Some of the popular black-box AI methods used to solve an automation task include decision trees (DT), support vector machines (SVM), artificial neural networks (ANN), etc. In the past several years, these black-box AI methods have shown promising performance and have been widely applied and researched across industries and academia. While the black-box AI models have been shown to achieve high performance, the inherent mechanism with which a decision is made is hard to comprehend. This lack of interpretability and transparency of black-box AI methods makes them less trustworthy. In addition to this, the black-box AI models lack in their ability to provide valuable insights regarding the task at hand. Following these limitations of black-box AI models, a natural research direction of developing interpretable and explainable AI models has emerged and has gained an active attention in the machine learning and AI community in the past three years. In this dissertation, we will be focusing on interpretable AI solutions which are being currently developed at the Computational Optimization and Innovation Laboratory (COIN Lab) at Michigan State University. We propose a nonlinear decision tree (NLDT) based framework to produce transparent AI solutions for automation tasks related to classification and control. The recent advancement in non-linear optimization enables us to efficiently derive interpretable AI solutions for various automation tasks. The interpretable and transparent AI models induced using customized optimization techniques show similar or better performance as compared to complex black-box AI models across most of the benchmarks. The results are promising and provide directions to launch future studies in developing efficient transparent AI models.
Show less

Title: Iris Recognition : Enhancing Security and Improving Performance
Creator: Sharma, Renu
Date: 2022
Collection: Electronic Theses & Dissertations
Description: Biometric systems recognize individuals based on their physical or behavioral traits, viz., face, iris, and voice. Iris (the colored annular region around the pupil) is one of the most popular biometric traits due to its uniqueness, accuracy, and stability. However, its widespread usage raises security concerns against various adversarial attacks. Another challenge is to match iris images with other compatible biometric modalities (i.e., face) to increase the scope of human identification....
Show moreBiometric systems recognize individuals based on their physical or behavioral traits, viz., face, iris, and voice. Iris (the colored annular region around the pupil) is one of the most popular biometric traits due to its uniqueness, accuracy, and stability. However, its widespread usage raises security concerns against various adversarial attacks. Another challenge is to match iris images with other compatible biometric modalities (i.e., face) to increase the scope of human identification. Therefore, the focus of this thesis is two-fold: firstly, enhance the security of the iris recognition system by detecting adversarial attacks, and secondly, accentuate its performance in iris-face matching.To enhance the security of the iris biometric system, we work over two types of adversarial attacks - presentation and morph attacks. A presentation attack (PA) occurs when an adversary presents a fake or altered biometric sample (plastic eye, cosmetic contact lens, etc.) to a biometric system to obfuscate their own identity or impersonate another identity. We propose three deep learning-based iris PA detection frameworks corresponding to three different imaging modalities, namely NIR spectrum, visible spectrum, and Optical Coherence Tomography (OCT) imaging inputting a NIR image, visible-spectrum video, and cross-sectional OCT image, respectively. The techniques perform effectively to detect known iris PAs as well as generalize well across unseen attacks, unseen sensors, and multiple datasets. We also presented the explainability and interpretability of the results from the techniques. Our other focuses are robustness analysis and continuous update (retraining) of the trained iris PA detection models. Another burgeoning security threat to biometric systems is morph attacks. A morph attack entails the generation of an image (morphed image) that embodies multiple different identities. Typically, a biometric image is associated with a single identity. In this work, we first demonstrate the vulnerability of iris recognition techniques to morph attacks and then develop techniques to detect the morphed iris images.The second focus of the thesis is to improve the performance of a cross-modal system where iris images are matched against face images. Cross-modality matching involves various challenges, such as cross-spectral, cross-resolution, cross-pose, and cross-temporal. To address these challenges, we extract common features present in both images using a multi-channel convolutional network and also generate synthetic data to augment insufficient training data using a dual-variational autoencoder framework. The two focus areas of this thesis improve the acceptance and widespread usage of the iris biometric system.
Show less

Title: Learning to Detect Language Markers
Creator: Tang, Fengyi
Date: 2021
Collection: Electronic Theses & Dissertations
Description: In the world of medical informatics, biomarkers play a pivotal role in determining the physical state of human beings, distinguishing the pathologic from the clinically normal. In recent years, behavioral markers, due to their availability and low cost, have attracted a lot of attention as a potential supplement to biomarkers. “Language markers” such as spoken words and lexical preference have been shown to be both cost-effective as well as predictive of complex diseases such as mild...
Show moreIn the world of medical informatics, biomarkers play a pivotal role in determining the physical state of human beings, distinguishing the pathologic from the clinically normal. In recent years, behavioral markers, due to their availability and low cost, have attracted a lot of attention as a potential supplement to biomarkers. “Language markers” such as spoken words and lexical preference have been shown to be both cost-effective as well as predictive of complex diseases such as mild cognitive impairment (MCI).However, language markers, although universal, do not possess many of the favorable properties that characterize traditional biomakers. For example, different people may exhibit similar use of language under certain conversational contexts (non-unique), and a person's lexical preferences may change over time (non-stationary). As a result, it is unclear whether any set of language markers can be measured in a consistent manner. My thesis projects provide solutions to some of the limitations of language markers: (1) We formalize the problem of learning a dialog policy to measure language markers as an optimization problem which we call persona authentication. We provide a learning algorithm for finding such a dialog policy that can generalize to unseen personalities. (2) We apply our dialog policy framework on real-world data for MCI prediction and show that the proposed pipeline improves prediction against supervised learning baselines. (3) To address non-stationarity, we introduce an effective way to do temporally-dependent and non-i.i.d. feature selection through an adversarial learning framework which we call precision sensing. (4) Finally, on the prediction side, we propose a method for improving the sample efficiency of classifiers by retaining privileged information (auxiliary features available only at training time).
Show less

MSU Libraries

Digital Repository

Enabled Filters

Pages

Pages

MSU Libraries

Digital Repository

You are here

Search results

Pages

Pages