Matching Items (1,584)
Filtering by
- All Subjects: Computer Science
- All Subjects: Mechanical Engineering
Description
There is intense interest in adopting computer-aided diagnosis (CAD) systems, particularly those developed based on deep learning algorithms, for applications in a number of medical specialties. However, success of these CAD systems relies heavily on large annotated datasets; otherwise, deep learning often results in algorithms that perform poorly and lack generalizability. Therefore, this dissertation seeks to address this critical problem: How to develop efficient and effective deep learning algorithms for medical applications where large annotated datasets are unavailable. In doing so, we have outlined three specific aims: (1) acquiring necessary annotations efficiently from human experts; (2) utilizing existing annotations effectively from advanced architecture; and (3) extracting generic knowledge directly from unannotated images. Our extensive experiments indicate that, with a small part of the dataset annotated, the developed deep learning methods can match, or even outperform those that require annotating the entire dataset. The last part of this dissertation presents the importance and application of imaging in healthcare, elaborating on how the developed techniques can impact several key facets of the CAD system for detecting pulmonary embolism. Further research is necessary to determine the feasibility of applying these advanced deep learning technologies in clinical practice, particularly when annotation is limited. Progress in this area has the potential to enable deep learning algorithms to generalize to real clinical data and eventually allow CAD systems to be employed in clinical medicine at the point of care.
ContributorsZhou, Zongwei (Author) / Liang, Jianming (Thesis advisor) / Shortliffe, Edward H (Committee member) / Greenes, Robert A (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2021
Description
Atmospheric turbulence distorts the path of light passing through the air. When capturing images at long range, the effects of this turbulence can cause substantial geometric distortion and blur in images and videos, degrading image quality. These become more pronounced with greater turbulence, scaling with the refractive index structure constant, Cn2. Removing effects of atmospheric turbulence in images has a range of applications from astronomical imaging to surveillance. Thus, there is great utility in transforming a turbulent image into a ``clean image" undegraded by turbulence. However, as the turbulence is space- and time-variant and statistically random, no closed-form solution exists for a function that performs this transformation. Prior attempts to approximate the solution include spatio-temporal models and lucky frames models, which require many images to provide a good approximation, and supervised neural networks, which rely on large amounts of simulated or difficult-to-acquire real training data and can struggle to generalize. The first contribution in this thesis is an unsupervised neural-network-based model to perform image restoration for atmospheric turbulence with state-of-the-art performance. The model consists of a grid deformer, which produces an estimated distortion field, and an image generator, which estimates the distortion-free image. This model is transferable across different datasets; its efficacy is demonstrated across multiple datasets and on both air and water turbulence. The second contribution is a supervised neural network to predict Cn2 directly from the warp field. This network was trained on a wide range of Cn2 values and estimates Cn2 with relatively good accuracy. When used on the warp field produced by the unsupervised model, this allows for a Cn2 estimate requiring only a few images without any prior knowledge of ground truth or information about the turbulence.
ContributorsWhyte, Cameron (Author) / Jayasuriya, Suren (Thesis advisor) / Espanol, Malena (Thesis advisor) / Speyer, Gil (Committee member) / Arizona State University (Publisher)
Created2021
Description
In this thesis, the problem of designing model discrimination algorithms for unknown nonlinear systems is considered, where only raw experimental data of the system is available. This kind of model discrimination techniques finds one of its application in the estimation of the system or intent models under consideration, where all incompatible models are invalidated using new data that is available at run time. The proposed steps to reach the end goal of the algorithm for intention estimation involves two steps: First, using available experimental data of system trajectories, optimization-based techniques are used to over-approximate/abstract the dynamics of the system by constructing an upper and lower function which encapsulates/frames the true unknown system dynamics. This over-approximation is a conservative preservation of the dynamics of the system, in a way that ensures that any model which is invalidated against this approximation is guaranteed to be invalidated with the actual model of the system. The next step involves the use of optimization-based techniques to investigate the distinguishability of pairs of abstraction/approximated models using an algorithm for 'T-Distinguishability', which gives a finite horizon time 'T', within which the pair of models are guaranteed to be distinguished, and to eliminate incompatible models at run time using a 'Model Invalidation' algorithm. Furthermore, due the large amount of data under consideration, some computation-aware improvements were proposed for the processing of the raw data and the abstraction and distinguishability algorithms.The effectiveness of the above-mentioned algorithms is demonstrated using two examples. The first uses the data collected from the artificial simulation of a swarm of agents, also known as 'Boids', that move in certain patterns/formations, while the second example uses the 'HighD' dataset of naturalistic trajectories recorded on German Highways for vehicle intention estimation.
ContributorsBhagwat, Mohit Mukul (Author) / Yong, Sze Zheng (Thesis advisor) / Berman, Spring (Committee member) / Xu, Zhe (Committee member) / Arizona State University (Publisher)
Created2021
Description
As technological advancements in silicon, sensors, and actuation continue, the development of robotic swarms is shifting from the domain of science fiction to reality. Many swarm applications, such as environmental monitoring, precision agriculture, disaster response, and lunar prospecting, will require controlling numerous robots with limited capabilities and information to redistribute among multiple states, such as spatial locations or tasks. A scalable control approach is to program the robots with stochastic control policies such that the robot population in each state evolves according to a mean-field model, which is independent of the number and identities of the robots. Using this model, the control policies can be designed to stabilize the swarm to the target distribution. To avoid the need to reprogram the robots for different target distributions, the robot control policies can be defined to depend only on the presence of a “leader” agent, whose control policy is designed to guide the swarm to a particular distribution. This dissertation presents a novel deep reinforcement learning (deep RL) approach to designing control policies that redistribute a swarm as quickly as possible over a strongly connected graph, according to a mean-field model in the form of the discrete-time Kolmogorov forward equation. In the leader-based strategies, the leader determines its next action based on its observations of robot populations and shepherds the swarm over the graph by probabilistically repelling nearby robots. The scalability of this approach with the swarm size is demonstrated with leader control policies that are designed using two tabular Temporal-Difference learning algorithms, trained on a discretization of the swarm distribution. To improve the scalability of the approach with robot population and graph size, control policies for both leader-based and leaderless strategies are designed using an actor-critic deep RL method that is trained on the swarm distribution predicted by the mean-field model. In the leaderless strategy, the robots’ control policies depend only on their local measurements of nearby robot populations. The control approaches are validated for different graph and swarm sizes in numerical simulations, 3D robot simulations, and experiments on a multi-robot testbed.
ContributorsKakish, Zahi Mousa (Author) / Berman, Spring (Thesis advisor) / Yong, Sze Zheng (Committee member) / Marvi, Hamid (Committee member) / Pavlic, Theodore (Committee member) / Pratt, Stephen (Committee member) / Ben Amor, Hani (Committee member) / Arizona State University (Publisher)
Created2021
Description
Computer vision and tracking has become an area of great interest for many reasons, including self-driving cars, identification of vehicles and drivers on roads, and security camera monitoring, all of which are expanding in the modern digital era. When working with practical systems that are constrained in multiple ways, such as video quality or viewing angle, algorithms that work well theoretically can have a high error rate in practice. This thesis studies several ways in which that error can be minimized.This thesis describes an application in a practical system. This project is to detect, track and count people entering different lanes at an airport security checkpoint, using CCTV videos as a primary source. This thesis improves an existing algorithm that is not optimized for this particular problem and has a high error rate when comparing the algorithm counts with the true volume of users.
The high error rate is caused by many people crowding into security lanes at the same time. The camera from which footage was captured is located at a poor angle, and thus many of the people occlude each other and cause the existing algorithm to miss people. One solution is to count only heads; since heads are smaller than a full body, they will occlude less, and in addition, since the camera is angled from above, the heads in back will appear higher and will not be occluded by people in front. One of the primary improvements to the algorithm is to combine both person detections and head detections to improve the accuracy.
The proposed algorithm also improves the accuracy of detections. The existing algorithm used the COCO training dataset, which works well in scenarios where people are visible and not occluded. However, the available video quality in this project was not very good, with people often blocking each other from the camera’s view. Thus, a different training set was needed that could detect people even in poor-quality frames and with occlusion. The new training set is the first algorithmic improvement, and although occasionally performing worse, corrected the error by 7.25% on average.
ContributorsLarsen, Andrei (Author) / Askin, Ronald (Thesis advisor) / Sefair, Jorge (Thesis advisor) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2021
Description
This work explores combining state-of-the-art \gls{mbrl} algorithms focused on learning complex policies with large state-spaces and augmenting them with distributional reward perspective on \gls{rl} algorithms. Distributional \gls{rl} provides a probabilistic reward formulation as opposed to the classic \gls{rl} formulation which models the estimation of this distributional return. These probabilistic reward formulations help the agent choose highly risk-averse actions, which in turn makes the learning more stable. To evaluate this idea, I experiment in simulation on complex high-dimensional environments when subject under different noisy conditions.
ContributorsAgarwal, Nikhil (Author) / Ben Amor, Heni (Thesis advisor) / Phielipp, Mariano (Committee member) / DV, Hemanth (Committee member) / Arizona State University (Publisher)
Created2021
Description
Reverse engineers use decompilers to analyze binaries when their source code is unavailable. A binary decompiler attempts to transform binary programs to their corresponding high-level source code by recovering and inferring the information that was lost during the compilation process. One type of information that is lost during compilation is variable names, which are critical for reverse engineers to analyze and understand programs. Traditional binary decompilers generally use automatically generated, placeholder variable names that are meaningless or have little correlation with their intended semantics. Having correct or meaningful variable names in decompiled code, instead of placeholder variable names, greatly increases the readability of decompiled binary code. Decompiled Identifier Renaming Engine (DIRE) is a state-of-the-art, deep-learning-based solution that automatically predicts variable names in decompiled binary code. However, DIRE's prediction result is far from perfect. The first goal of this research project is to take a close look at the current state-of-the-art solution for automated variable name prediction on decompilation output of binary code, assess the prediction quality, and understand how the prediction result can be improved. Then, as the second goal of this research project, I aim to improve the prediction quality of variable names. With a thorough understanding of DIRE's issues, I focus on improving the quality of training data. This thesis proposes a novel approach to improving the quality of the training data by normalizing variable names and converting their abbreviated forms to their full forms. I implemented and evaluated the proposed approach on a data set of over 10k and 20k binaries and showed improvements over DIRE.
ContributorsBajaj, Ati Priya (Author) / Wang, Ruoyu (Thesis advisor) / Baral, Chitta (Committee member) / Shoshitaishvili, Yan (Committee member) / Arizona State University (Publisher)
Created2021
Description
This dissertation studies the methods to enhance the performance of foldable robots manufactured by laminated techniques. This class of robots are unique in their manufacturing process, which involves cutting and staking up thin layers of different materials with various stiffness. While inheriting the advantages of soft robots -- low weight, affordable manufacturing cost and a fast prototyping process -- a wider range of actuators is available to these mechanisms, while modeling their behavior requires less computational cost.The fundamental question this dissertation strives to answer is how to decode and leverage the effect of material stiffness in these robots. These robots' stiffness is relatively limited due to their slender design, specifically at larger scales. While compliant robots may have inherent advantages such as being safer to work around, this low rigidity makes modeling more complex. This complexity is mostly contained in material deformation since the conventional actuators such as servo motors can be easily leveraged in these robots. As a result, when introduced to real-world environments, efficient modeling and control of these robots are more achievable than conventional soft robots.
Various approaches have been taken to design, model, and control a variety of laminate robot platforms by investigating the effect of material deformation in prototypes while they interact with their working environments. The results obtained show that data-driven approaches such as experimental identification and machine learning techniques are more reliable in modeling and control of these mechanisms. Also, machine learning techniques for training robots in non-ideal experimental setups that encounter the uncertainties of real-world environments can be leveraged to find effective gaits with high performance. Our studies on the effect of stiffness of thin, curved sheets of materials has evolved into introducing a new class of soft elements which we call Soft, Curved, Reconfigurable, Anisotropic Mechanisms (SCRAMs). Like bio-mechanical systems, SCRAMs are capable of re-configuring the stiffness of curved surfaces to enhance their performance and adaptability. Finally, the findings of this thesis show promising opportunities for foldable robots to become an alternative for conventional soft robots since they still offer similar advantages in a fraction of computational expense.
ContributorsSharifzadeh, Mohammad (Author) / Aukes, Daniel (Thesis advisor) / Sugar, Thomas (Committee member) / Zhang, Wenlong (Committee member) / Arizona State University (Publisher)
Created2021
Description
One persisting problem in Massive Open Online Courses (MOOCs) is the issue of student dropout from these courses. The prediction of student dropout from MOOC courses can identify the factors responsible for such an event and it can further initiate intervention before such an event to increase student success in MOOC. There are different approaches and various features available for the prediction of student’s dropout in MOOC courses.In this research, the data derived from the self-paced math course ‘College Algebra and Problem Solving’ offered on the MOOC platform Open edX offered by Arizona State University (ASU) from 2016 to 2020 was considered. This research aims to predict the dropout of students from a MOOC course given a set of features engineered from the learning of students in a day. Machine Learning (ML) model used is Random Forest (RF) and this model is evaluated using the validation metrics like accuracy, precision, recall, F1-score, Area Under the Curve (AUC), Receiver Operating Characteristic (ROC) curve. The average rate of student learning progress was found to have more impact than other features. The model developed can predict the dropout or continuation of students on any given day in the MOOC course with an accuracy of 87.5%, AUC of 94.5%, precision of 88%, recall of 87.5%, and F1-score of 87.5% respectively. The contributing features and interactions were explained using Shapely values for the prediction of the model. The features engineered in this research are predictive of student dropout and could be used for similar courses to predict student dropout from the course. This model can also help in making interventions at a critical time to help students succeed in this MOOC course.
ContributorsDominic Ravichandran, Sheran Dass (Author) / Gary, Kevin (Thesis advisor) / Bansal, Ajay (Committee member) / Cunningham, James (Committee member) / Sannier, Adrian (Committee member) / Arizona State University (Publisher)
Created2021
Description
Accurate knowledge and understanding of thermal conductivity is very important in awide variety of applications both at microscopic and macroscopic scales. Estimation,however varies widely with respect to scale and application. At a lattice level, calcu-lation of thermal conductivity of any particular alloy require very heavy computationeven for a relatively small number of atoms. This thesis aims to run conventionalmolecular dynamic simulations for a particular supercell and then employ a machinelearning based approach and compare the two in hopes of developing a method togreatly reduce computational costs as well as increase the scale and time frame ofthese systems. Conventional simulations were run using interatomic potentials basedon density function theory-basedab initiocalculations. Then deep learning neuralnetwork based interatomic potentials were used run similar simulations to comparethe two approaches.
ContributorsDabir, Anirudh (Author) / Zhuang, Houlong (Thesis advisor) / Nian, Qiong (Committee member) / Jiao, Yang (Committee member) / Arizona State University (Publisher)
Created2021