Engineering Commons^™

Quantifying Balance: Computational And Learning Frameworks For The Characterization Of Balance In Bipedal Systems, Kubra Akbas

Dissertations

In clinical practice and general healthcare settings, the lack of reliable and objective balance and stability assessment metrics hinders the tracking of patient performance progression during rehabilitation; the assessment of bipedal balance plays a crucial role in understanding stability and falls in humans and other bipeds, while providing clinicians important information regarding rehabilitation outcomes. Bipedal balance has often been examined through kinematic or kinetic quantities, such as the Zero Moment Point and Center of Pressure; however, analyzing balance specifically through the body's Center of Mass (COM) state offers a holistic and easily comprehensible view of balance and stability.

Building upon …

One-Stage Blind Source Separation Via A Sparse Autoencoder Framework, Jason Anthony Dabin

Dissertations

Blind source separation (BSS) is the process of recovering individual source transmissions from a received mixture of co-channel signals without a priori knowledge of the channel mixing matrix or transmitted source signals. The received co-channel composite signal is considered to be captured across an antenna array or sensor network and is assumed to contain sparse transmissions, as users are active and inactive aperiodically over time. An unsupervised machine learning approach using an artificial feedforward neural network sparse autoencoder with one hidden layer is formulated for blindly recovering the channel matrix and source activity of co-channel transmissions. The BSS sparse autoencoder …

A Self-Learning Intersection Control System For Connected And Automated Vehicles, Ardeshir Mirbakhsh

Dissertations

This study proposes a Decentralized Sparse Coordination Learning System (DSCLS) based on Deep Reinforcement Learning (DRL) to control intersections under the Connected and Automated Vehicles (CAVs) environment. In this approach, roadway sections are divided into small areas; vehicles try to reserve their desired area ahead of time, based on having a common desired area with other CAVs; the vehicles would be in an independent or coordinated state. Individual CAVs are set accountable for decision-making at each step in both coordinated and independent states. In the training process, CAVs learn to minimize the overall delay at the intersection. Due to the …

Local Learning Algorithms For Stochastic Spiking Neural Networks, Bleema Rosenfeld

Dissertations

This dissertation focuses on the development of machine learning algorithms for spiking neural networks, with an emphasis on local three-factor learning rules that are in keeping with the constraints imposed by current neuromorphic hardware. Spiking neural networks (SNNs) are an alternative to artificial neural networks (ANNs) that follow a similar graphical structure but use a processing paradigm more closely modeled after the biological brain in an effort to harness its low power processing capability. SNNs use an event based processing scheme which leads to significant power savings when implemented in dedicated neuromorphic hardware such as Intel’s Loihi chip.

This work …

Un-Fair Trojan: Targeted Backdoor Attacks Against Model Fairness, Nicholas Furth

Theses

Machine learning models have been shown to be vulnerable against various backdoor and data poisoning attacks that adversely affect model behavior. Additionally, these attacks have been shown to make unfair predictions with respect to certain protected features. In federated learning, multiple local models contribute to a single global model communicating only using local gradients, the issue of attacks become more prevalent and complex. Previously published works revolve around solving these issues both individually and jointly. However, there has been little study on the effects of attacks against model fairness. Demonstrated in this work, a flexible attack, which we call Un-Fair …

A Practical Approach To Automated Software Correctness Enhancement, Aleksandr Zakharchenko

Dissertations

To repair an incorrect program does not mean to make it correct; it only means to make it more-correct, in some sense, than it is. In the absence of a concept of relative correctness, i.e. the property of a program to be more-correct than another with respect to a specification, the discipline of program repair has resorted to various approximations of absolute (traditional) correctness, with varying degrees of success. This shortcoming is concealed by the fact that most program repair tools are tested on basic cases, whence making them absolutely correct is not clearly distinguishable from making them relatively more-correct. …

Gradient Free Sign Activation Zero One Loss Neural Networks For Adversarially Robust Classification, Yunzhe Xue

Dissertations

The zero-one loss function is less sensitive to outliers than convex surrogate losses such as hinge and cross-entropy. However, as a non-convex function, it has a large number of local minima, andits undifferentiable attribute makes it impossible to use backpropagation, a method widely used in training current state-of-the-art neural networks. When zero-one loss is applied to deep neural networks, the entire training process becomes challenging. On the other hand, a massive non-unique solution probably also brings different decision boundaries when optimizing zero-one loss, making it possible to fight against transferable adversarial examples, which is a common weakness in deep learning …

Towards Adversarial Robustness With 01 Lossmodels, And Novel Convolutional Neural Netsystems For Ultrasound Images, Meiyan Xie

Dissertations

This dissertation investigates adversarial robustness with 01 loss models and a novel convolutional neural net systems for vascular ultrasound images.

In the first part, the dissertation presents stochastic coordinate descent for 01 loss and its sensitivity to adversarial attacks. The study here suggests that 01 loss may be more resilient to adversarial attacks than the hinge loss and further work is required.

In the second part, this dissertation proposes sign activation network with a novel gradient-free stochastic coordinate descent algorithm and its ensembling model. The study here finds that the ensembling model gives a high minimum distortion (as measured by …

Data-Driven Learning For Robot Physical Intelligence, Leidi Zhao

Dissertations

The physical intelligence, which emphasizes physical capabilities such as dexterous manipulation and dynamic mobility, is essential for robots to physically coexist with humans. Much research on robot physical intelligence has achieved success on hyper robot motor capabilities, but mostly through heavily case-specific engineering. Meanwhile, in terms of robot acquiring skills in a ubiquitous manner, robot learning from human demonstration (LfD) has achieved great progress, but still has limitations handling dynamic skills and compound actions. In this dissertation, a composite learning scheme which goes beyond LfD and integrates robot learning from human definition, demonstration, and evaluation is proposed. This method tackles …

Deep Learning On Image Forensics And Anti-Forensics, Zhangyi Shen

Dissertations

Image forensics protect the authenticity and integrity of digital images. On the contrary, as the countermeasures of digital forensics, anti-forensics is applied to expose the vulnerability of forensics tools. Consequently, forensics researchers could develop forensics tools against possible new attacks. This dissertation investigation demonstrates two image forensics methods based on convolutional neural network (CNN) and two image anti-forensics methods based on generative adversarial network (GAN).

Detecting unsharp masking (USM) sharpened image is the first study in this dissertation. A CNN architecture comprises four convolutional layers and a classification module is proposed to discriminate sharpened images and unsharpened images. The results …

A Deep Machine Learning Approach For Predicting Freeway Work Zone Delay Using Big Data, Abdullah Shabarek

Dissertations

The introduction of deep learning and big data analytics may significantly elevate the performance of traffic speed prediction. Work zones become one of the most critical factors causing congestion impact, which reduces the mobility as well as traffic safety. A comprehensive literature review on existing work zone delay prediction models (i.e., parametric, simulation and non-parametric models) is conducted in this research. The research shows the limitations of each model. Moreover, most previous modeling approaches did not consider user delay for connected freeways when predicting traffic speed under work zone conditions. This research proposes Deep Artificial Neural Network (Deep ANN) and …

Efficient Hardware Implementations Of Bio-Inspired Networks, Anakha Vasanthakumaribabu

Dissertations

The human brain, with its massive computational capability and power efficiency in small form factor, continues to inspire the ultimate goal of building machines that can perform tasks without being explicitly programmed. In an effort to mimic the natural information processing paradigms observed in the brain, several neural network generations have been proposed over the years. Among the neural networks inspired by biology, second-generation Artificial or Deep Neural Networks (ANNs/DNNs) use memoryless neuron models and have shown unprecedented success surpassing humans in a wide variety of tasks. Unlike ANNs, third-generation Spiking Neural Networks (SNNs) closely mimic biological neurons by operating …

Model-Based Deep Siamese Autoencoder For Clustering Single Cell Rna-Seq Data, Zixia Meng

Theses

In the biological field, the smallest unit of organisms in most biological systems is the single cell, and the classification of cells is an everlasting problem. A central task for analysis of single-cell RNA-seq data is to identify and characterize novel cell types. Currently, there are several classical methods, such as K-means algorithm, spectral clustering, and Gaussian Mixture Models (GMMs), which are widely used to cluster the cells. Furthermore, typical dimensional reduction methods such as PCA, t-SNE, and ZIDA have been introduced to overcome “the curse of dimensionality”. A more recent method scDeepCluster has demonstrated improved and promising performances in …

Bio-Inspired Learning And Hardware Acceleration With Emerging Memories, Shruti R. Kulkarni

Dissertations

Machine Learning has permeated many aspects of engineering, ranging from the Internet of Things (IoT) applications to big data analytics. While computing resources available to implement these algorithms have become more powerful, both in terms of the complexity of problems that can be solved and the overall computing speed, the huge energy costs involved remains a significant challenge. The human brain, which has evolved over millions of years, is widely accepted as the most efficient control and cognitive processing platform. Neuro-biological studies have established that information processing in the human brain relies on impulse like signals emitted by neurons called …

Optimal Sampling Paths For Autonomous Vehicles In Uncertain Ocean Flows, Andrew J. De Stefan

Dissertations

Despite an extensive history of oceanic observation, researchers have only begun to build a complete picture of oceanic currents. Sparsity of instrumentation has created the need to maximize the information extracted from every source of data in building this picture. Within the last few decades, autonomous vehicles, or AVs, have been employed as tools to aid in this research initiative. Unmanned and self-propelled, AVs are capable of spending weeks, if not months, exploring and monitoring the oceans. However, the quality of data acquired by these vehicles is highly dependent on the paths along which they collect their observational data. The …

Probabilistic Spiking Neural Networks : Supervised, Unsupervised And Adversarial Trainings, Alireza Bagheri

Dissertations

Spiking Neural Networks (SNNs), or third-generation neural networks, are networks of computation units, called neurons, in which each neuron with internal analogue dynamics receives as input and produces as output spiking, that is, binary sparse, signals. In contrast, second-generation neural networks, termed as Artificial Neural Networks (ANNs), rely on simple static non-linear neurons that are known to be energy-intensive, hindering their implementations on energy-limited processors such as mobile devices. The sparse event-based characteristics of SNNs for information transmission and encoding have made them more feasible for highly energy-efficient neuromorphic computing architectures. The most existing training algorithms for SNNs are based …