Matching Items (7)
Filtering by
- All Subjects: Machine Learning
- All Subjects: Systems science
- Member of: ASU Electronic Theses and Dissertations
Description
Effective modeling of high dimensional data is crucial in information processing and machine learning. Classical subspace methods have been very effective in such applications. However, over the past few decades, there has been considerable research towards the development of new modeling paradigms that go beyond subspace methods. This dissertation focuses on the study of sparse models and their interplay with modern machine learning techniques such as manifold, ensemble and graph-based methods, along with their applications in image analysis and recovery. By considering graph relations between data samples while learning sparse models, graph-embedded codes can be obtained for use in unsupervised, supervised and semi-supervised problems. Using experiments on standard datasets, it is demonstrated that the codes obtained from the proposed methods outperform several baseline algorithms. In order to facilitate sparse learning with large scale data, the paradigm of ensemble sparse coding is proposed, and different strategies for constructing weak base models are developed. Experiments with image recovery and clustering demonstrate that these ensemble models perform better when compared to conventional sparse coding frameworks. When examples from the data manifold are available, manifold constraints can be incorporated with sparse models and two approaches are proposed to combine sparse coding with manifold projection. The improved performance of the proposed techniques in comparison to sparse coding approaches is demonstrated using several image recovery experiments. In addition to these approaches, it might be required in some applications to combine multiple sparse models with different regularizations. In particular, combining an unconstrained sparse model with non-negative sparse coding is important in image analysis, and it poses several algorithmic and theoretical challenges. A convex and an efficient greedy algorithm for recovering combined representations are proposed. Theoretical guarantees on sparsity thresholds for exact recovery using these algorithms are derived and recovery performance is also demonstrated using simulations on synthetic data. Finally, the problem of non-linear compressive sensing, where the measurement process is carried out in feature space obtained using non-linear transformations, is considered. An optimized non-linear measurement system is proposed, and improvements in recovery performance are demonstrated in comparison to using random measurements as well as optimized linear measurements.
ContributorsNatesan Ramamurthy, Karthikeyan (Author) / Spanias, Andreas (Thesis advisor) / Tsakalis, Konstantinos (Committee member) / Karam, Lina (Committee member) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2013
Description
Feature representations for raw data is one of the most important component in a machine learning system. Traditionally, features are \textit{hand crafted} by domain experts which can often be a time consuming process. Furthermore, they do not generalize well to unseen data and novel tasks. Recently, there have been many efforts to generate data-driven representations using clustering and sparse models. This dissertation focuses on building data-driven unsupervised models for analyzing raw data and developing efficient feature representations.
Simultaneous segmentation and feature extraction approaches for silicon-pores sensor data are considered. Aggregating data into a matrix and performing low rank and sparse matrix decompositions with additional smoothness constraints are proposed to solve this problem. Comparison of several variants of the approaches and results for signal de-noising and translocation/trapping event extraction are presented. Algorithms to improve transform-domain features for ion-channel time-series signals based on matrix completion are presented. The improved features achieve better performance in classification tasks and in reducing the false alarm rates when applied to analyte detection.
Developing representations for multimedia is an important and challenging problem with applications ranging from scene recognition, multi-media retrieval and personal life-logging systems to field robot navigation. In this dissertation, we present a new framework for feature extraction for challenging natural environment sounds. Proposed features outperform traditional spectral features on challenging environmental sound datasets. Several algorithms are proposed that perform supervised tasks such as recognition and tag annotation. Ensemble methods are proposed to improve the tag annotation process.
To facilitate the use of large datasets, fast implementations are developed for sparse coding, the key component in our algorithms. Several strategies to speed-up Orthogonal Matching Pursuit algorithm using CUDA kernel on a GPU are proposed. Implementations are also developed for a large scale image retrieval system. Image-based "exact search" and "visually similar search" using the image patch sparse codes are performed. Results demonstrate large speed-up over CPU implementations and good retrieval performance is also achieved.
Simultaneous segmentation and feature extraction approaches for silicon-pores sensor data are considered. Aggregating data into a matrix and performing low rank and sparse matrix decompositions with additional smoothness constraints are proposed to solve this problem. Comparison of several variants of the approaches and results for signal de-noising and translocation/trapping event extraction are presented. Algorithms to improve transform-domain features for ion-channel time-series signals based on matrix completion are presented. The improved features achieve better performance in classification tasks and in reducing the false alarm rates when applied to analyte detection.
Developing representations for multimedia is an important and challenging problem with applications ranging from scene recognition, multi-media retrieval and personal life-logging systems to field robot navigation. In this dissertation, we present a new framework for feature extraction for challenging natural environment sounds. Proposed features outperform traditional spectral features on challenging environmental sound datasets. Several algorithms are proposed that perform supervised tasks such as recognition and tag annotation. Ensemble methods are proposed to improve the tag annotation process.
To facilitate the use of large datasets, fast implementations are developed for sparse coding, the key component in our algorithms. Several strategies to speed-up Orthogonal Matching Pursuit algorithm using CUDA kernel on a GPU are proposed. Implementations are also developed for a large scale image retrieval system. Image-based "exact search" and "visually similar search" using the image patch sparse codes are performed. Results demonstrate large speed-up over CPU implementations and good retrieval performance is also achieved.
ContributorsSattigeri, Prasanna S (Author) / Spanias, Andreas (Thesis advisor) / Thornton, Trevor (Committee member) / Goryll, Michael (Committee member) / Tsakalis, Konstantinos (Committee member) / Arizona State University (Publisher)
Created2014
Description
Following the success in incorporating perceptual models in audio coding algorithms, their application in other speech/audio processing systems is expanding. In general, all perceptual speech/audio processing algorithms involve minimization of an objective function that directly/indirectly incorporates properties of human perception. This dissertation primarily investigates the problems associated with directly embedding an auditory model in the objective function formulation and proposes possible solutions to overcome high complexity issues for use in real-time speech/audio algorithms. Specific problems addressed in this dissertation include: 1) the development of approximate but computationally efficient auditory model implementations that are consistent with the principles of psychoacoustics, 2) the development of a mapping scheme that allows synthesizing a time/frequency domain representation from its equivalent auditory model output. The first problem is aimed at addressing the high computational complexity involved in solving perceptual objective functions that require repeated application of auditory model for evaluation of different candidate solutions. In this dissertation, a frequency pruning and a detector pruning algorithm is developed that efficiently implements the various auditory model stages. The performance of the pruned model is compared to that of the original auditory model for different types of test signals in the SQAM database. Experimental results indicate only a 4-7% relative error in loudness while attaining up to 80-90 % reduction in computational complexity. Similarly, a hybrid algorithm is developed specifically for use with sinusoidal signals and employs the proposed auditory pattern combining technique together with a look-up table to store representative auditory patterns. The second problem obtains an estimate of the auditory representation that minimizes a perceptual objective function and transforms the auditory pattern back to its equivalent time/frequency representation. This avoids the repeated application of auditory model stages to test different candidate time/frequency vectors in minimizing perceptual objective functions. In this dissertation, a constrained mapping scheme is developed by linearizing certain auditory model stages that ensures obtaining a time/frequency mapping corresponding to the estimated auditory representation. This paradigm was successfully incorporated in a perceptual speech enhancement algorithm and a sinusoidal component selection task.
ContributorsKrishnamoorthi, Harish (Author) / Spanias, Andreas (Thesis advisor) / Papandreou-Suppappola, Antonia (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Tsakalis, Konstantinos (Committee member) / Arizona State University (Publisher)
Created2011
Description
VTOL drones were designed and built at the beginning of the 20th century for military applications due to easy take-off and landing operations. Many companies like Lockheed, Convair, NASA and Bell Labs built their own aircrafts but only a few from them came in to the market. Usually, flight automation starts from first principles modeling which helps in the controller design and dynamic analysis of the system.
In this project, a VTOL drone with a shape similar to a Convair XFY-1 is studied and the primary focus is stabilizing and controlling the flight path of the drone in
its hover and horizontal flying modes. The model of the plane is obtained using first principles modeling and controllers are designed to stabilize the yaw, pitch and roll rotational motions.
The plane is modeled for its yaw, pitch and roll rotational motions. Subsequently, the rotational dynamics of the system are linearized about the hover flying mode, hover to horizontal flying mode, horizontal flying mode, horizontal to hover flying mode for ease of implementation of linear control design techniques. The controllers are designed based on an H∞ loop shaping procedure and the results are verified on the actual nonlinear model for the stability of the closed loop system about hover flying, hover to horizontal transition flying, horizontal flying, horizontal to hover transition flying. An experiment is conducted to study the dynamics of the motor by recording the PWM input to the electronic speed controller as input and the rotational speed of the motor as output. A theoretical study is also done to study the thrust generated by the propellers for lift, slipstream velocity analysis, torques acting on the system for various thrust profiles.
In this project, a VTOL drone with a shape similar to a Convair XFY-1 is studied and the primary focus is stabilizing and controlling the flight path of the drone in
its hover and horizontal flying modes. The model of the plane is obtained using first principles modeling and controllers are designed to stabilize the yaw, pitch and roll rotational motions.
The plane is modeled for its yaw, pitch and roll rotational motions. Subsequently, the rotational dynamics of the system are linearized about the hover flying mode, hover to horizontal flying mode, horizontal flying mode, horizontal to hover flying mode for ease of implementation of linear control design techniques. The controllers are designed based on an H∞ loop shaping procedure and the results are verified on the actual nonlinear model for the stability of the closed loop system about hover flying, hover to horizontal transition flying, horizontal flying, horizontal to hover transition flying. An experiment is conducted to study the dynamics of the motor by recording the PWM input to the electronic speed controller as input and the rotational speed of the motor as output. A theoretical study is also done to study the thrust generated by the propellers for lift, slipstream velocity analysis, torques acting on the system for various thrust profiles.
ContributorsRAGHURAMAN, VIGNESH (Author) / Tsakalis, Konstantinos (Thesis advisor) / Rodriguez, Armando (Committee member) / Yong, Sze Zheng (Committee member) / Arizona State University (Publisher)
Created2018
Description
In this dissertation, we present a H-infinity based multivariable control design methodology that can be used to systematically address design specifications at distinct feedback loop-breaking points. It is well understood that for multivariable systems, obtaining good/acceptable closed loop properties at one loop-breaking point does not mean the same at another. This is especially true for multivariable systems that are ill-conditioned (having high condition number and/or relative gain array and/or scaled condition number). We analyze the tradeoffs involved in shaping closed loop properties at these distinct loop-breaking points and illustrate through examples the existence of pareto optimal points associated with them. Further, we study the limitations and tradeoffs associated with shaping the properties in the presence of right half plane poles/zeros, limited available bandwidth and peak time-domain constraints. To address the above tradeoffs, we present a methodology for designing multiobjective constrained H-infinity based controllers, called Generalized Mixed Sensitivity (GMS), to effectively and efficiently shape properties at distinct loop-breaking points. The methodology accommodates a broad class of convex frequency- and time-domain design specifications. This is accomplished by exploiting the Youla-Jabr-Bongiorno-Kucera parameterization that transforms the nonlinear problem in the controller to an affine one in the Youla et al. parameter. Basis parameters that result in efficient approximation (using lesser number of basis terms) of the infinite-dimensional parameter are studied. Three state-of-the-art subgradient-based non-differentiable constrained convex optimization solvers, namely Analytic Center Cutting Plane Method (ACCPM), Kelley's CPM and SolvOpt are implemented and compared.
The above approach is used to design controllers for and tradeoff between several control properties of longitudinal dynamics of 3-DOF Hypersonic vehicle model -– one that is unstable, non-minimum phase and possesses significant coupling between channels. A hierarchical inner-outer loop control architecture is used to exploit additional feedback information in order to significantly help in making reasonable tradeoffs between properties at distinct loop-breaking points. The methodology is shown to generate very good designs –- designs that would be difficult to obtain without our presented methodology. Critical control tradeoffs associated are studied and compared with other design methods (e.g., classically motivated, standard mixed sensitivity) to further illustrate its power and transparency.
The above approach is used to design controllers for and tradeoff between several control properties of longitudinal dynamics of 3-DOF Hypersonic vehicle model -– one that is unstable, non-minimum phase and possesses significant coupling between channels. A hierarchical inner-outer loop control architecture is used to exploit additional feedback information in order to significantly help in making reasonable tradeoffs between properties at distinct loop-breaking points. The methodology is shown to generate very good designs –- designs that would be difficult to obtain without our presented methodology. Critical control tradeoffs associated are studied and compared with other design methods (e.g., classically motivated, standard mixed sensitivity) to further illustrate its power and transparency.
ContributorsPuttannaiah, Karan (Author) / Rodriguez, Armando A. (Thesis advisor) / Berman, Spring M. (Committee member) / Mittelmann, Hans D. (Committee member) / Tsakalis, Konstantinos (Committee member) / Arizona State University (Publisher)
Created2018
Description
Multi-segment manipulators and mobile robot collectives are examples of multi-agent robotic systems, in which each segment or robot can be considered an agent. Fundamental motion control problems for such systems include the stabilization of one or more agents to target configurations or trajectories while preventing inter-agent collisions, agent collisions with obstacles, and deadlocks. Despite extensive research on these control problems, there are still challenges in designing controllers that (1) are scalable with the number of agents; (2) have theoretical guarantees on collision-free agent navigation; and (3) can be used when the states of the agents and the environment are only partially observable. Existing centralized and distributed control architectures have limited scalability due to their computational complexity and communication requirements, while decentralized control architectures are often effective only under impractical assumptions that do not hold in real-world implementations. The main objective of this dissertation is to develop and evaluate decentralized approaches for multi-agent motion control that enable agents to use their onboard sensors and computational resources to decide how to move through their environment, with limited or absent inter-agent communication and external supervision. Specifically, control approaches are designed for multi-segment manipulators and mobile robot collectives to achieve position and pose (position and orientation) stabilization, trajectory tracking, and collision and deadlock avoidance. These control approaches are validated in both simulations and physical experiments to show that they can be implemented in real-time while remaining computationally tractable. First, kinematic controllers are proposed for position stabilization and trajectory tracking control of two- or three-dimensional hyper-redundant multi-segment manipulators. Next, robust and gradient-based feedback controllers are presented for individual holonomic and nonholonomic mobile robots that achieve position stabilization, trajectory tracking control, and obstacle avoidance. Then, nonlinear Model Predictive Control methods are developed for collision-free, deadlock-free pose stabilization and trajectory tracking control of multiple nonholonomic mobile robots in known and unknown environments with obstacles, both static and dynamic. Finally, a feedforward proportional-derivative controller is defined for collision-free velocity tracking of a moving ground target by multiple unmanned aerial vehicles.
ContributorsSalimi Lafmejani, Amir (Author) / Berman, Spring (Thesis advisor) / Tsakalis, Konstantinos (Thesis advisor) / Papandreou-Suppappola, Antonia (Committee member) / Marvi, Hamidreza (Committee member) / Arizona State University (Publisher)
Created2022
Description
Gas turbine engine for aircraft propulsion represents one of the most physics-complex and safety-critical systems in the world. Its failure diagnostic is challenging due to the complexity of the model system, difficulty involved in practical testing and the infeasibility of creating homogeneous diagnostic performance evaluation criteria for the diverse engine makes.
NASA has designed and publicized a standard benchmark problem for propulsion engine gas path diagnostic that enables comparisons among different engine diagnostic approaches. Some traditional model-based approaches and novel purely data-driven approaches such as machine learning, have been applied to this problem.
This study focuses on a different machine learning approach to the diagnostic problem. Some most common machine learning techniques, such as support vector machine, multi-layer perceptron, and self-organizing map are used to help gain insight into the different engine failure modes from the perspective of big data. They are organically integrated to achieve good performance based on a good understanding of the complex dataset.
The study presents a new hierarchical machine learning structure to enhance classification accuracy in NASA's engine diagnostic benchmark problem. The designed hierarchical structure produces an average diagnostic accuracy of 73.6%, which outperforms comparable studies that were most recently published.
NASA has designed and publicized a standard benchmark problem for propulsion engine gas path diagnostic that enables comparisons among different engine diagnostic approaches. Some traditional model-based approaches and novel purely data-driven approaches such as machine learning, have been applied to this problem.
This study focuses on a different machine learning approach to the diagnostic problem. Some most common machine learning techniques, such as support vector machine, multi-layer perceptron, and self-organizing map are used to help gain insight into the different engine failure modes from the perspective of big data. They are organically integrated to achieve good performance based on a good understanding of the complex dataset.
The study presents a new hierarchical machine learning structure to enhance classification accuracy in NASA's engine diagnostic benchmark problem. The designed hierarchical structure produces an average diagnostic accuracy of 73.6%, which outperforms comparable studies that were most recently published.
ContributorsWu, Qiyu (Author) / Si, Jennie (Thesis advisor) / Wu, Teresa (Committee member) / Tsakalis, Konstantinos (Committee member) / Arizona State University (Publisher)
Created2015