Pattern recognition algorithms have been proposed as a way to control powered lower limb prostheses, specifically for transitioning between the different pre-programmed locomotion modes of the prosthesis (e.g., level ground walking, stair ascent, etc.). However, these algorithms cannot track changes in the statistical characteristics of input signals, and do not...
The impacts of many important technologies are limited by the availability of better-performing materials. One factor limiting the ability of engineers to develop better materials is the speed at which they can search through possible formulations and processing schemes. Recently, machine learning algorithms have emerged as a possible route to...
Social media such as Twitter has risen as a powerful new communication medium for disseminating information on news, personal interests, experiences, and opinions. On social media, people talk about their lifestyle, health conditions and symptoms, search information on treatment options, and connect with people who have been through similar medical...
A central question in neuroscience is how the brain plans movements. Here, I apply neural data analysis and machine learning methods to better understand both eye and arm movement planning, in particular focusing on naturalistic settings. First, I built encoding models to investigate the factors that led to neural activity...
In this work, we explore the utility of the three main types of neural networks: feed forward, convolutional, and recurrent. While using these networks, we develop a new way to model multiagent trajectory data, explore the use of multiple activation functions for neurons at each layer of a neural network,...
Machine learning and symbolic reasoning have been two main approaches to build intelligent systems. Symbolic reasoning has been used in many applications by making use of expressive symbolic representations to encode prior knowledge, conduct complex reasoning and provide explanations. Recently, machine learning has enabled various successful applications by learning from...
Heterogeneous materials have been emerging and playing essential roles in various engineering and scientific fields. They usually include multiple phases of materials to create unique properties that are not accessible to their homogeneous counterparts. The traditional design approach in the material science community is to use trial-and-error iteratively, which is...
Connecting structure and function in nanoscale engineered materials and devices relies on the analysis of the fundamental arrangement of matter, frequently under dynamic conditions. The demand to image structures at fundamental length scales has touched inorganic materials, biology, and frequently hybrid hard/soft materials with unique phenomena driven by heterogeneous components....
The theory of how humans and machines control and communicate with each other is at the core of the scientific field known as Human-Robot Interaction (HRI). Researchers in this sub-discipline of robotics are therefore particularly interested in developing methods to chuppahreduce the inherent friction in this communication and control channel....
Annual age-adjusted breast cancer incidence rates in the United States have been static for decades. More recently, the development of massively parallel, high throughput DNA sequencing has enabled the cataloging of somatic mutations in cancer. Mutations are non-random and occur within sequence motifs. These motifs provide us with evidence to...
Connected and automated vehicle (CAV) technology is a disruptive transportation development with potentially transformative impacts on society and the economy. CAV systems promise to significantly reduce human-caused road crashes, improve traffic flow performance, and lower pollutant emissions. However, realizing those benefits requires strategic planning for the deployment of CAV systems...
Soft materials such as colloids and polymers often exhibit a variety of mesoscopic structures that are governed merely by weak physical interactions. Due to these intermediate structures, they can be easily taken out of thermal equilibrium by introducing external stimuli such as a shear flow and electromagnetic fields. This thesis...
Supervised learning model is one of the most fundamental machine learning models. It can provide powerful capability of prediction by learning complex patterns hidden in many, sometimes thousands, predictors. It can also be used as a building block of other machine learning tasks, like unsupervised learning and reinforcement learning. Such...
Deep neural networks have achieved remarkable success in the past decade on tasks that were out of reach prior to the era of deep learning. Amongst the myriad reasons for these successes are powerful computational resources, large datasets, new optimization algorithms, and modern architecture designs. Most of the reasons are...
The world is awash in data and much of artificial intelligence focuses on learning models of the underlying structure in this data or the mechanisms governing its evolution. Both neural and symbolic models have weaknesses that make these models sub-optimal from a use perspective. Much of this data is in...
The study of employee engagement and its consequences in the workplace has gained traction in the business world over the past decade, with dramatic claims of the direct consequences of engagement including lower absenteeism, higher sales, improved productivity, and increased profitability for organizations that are more engaged (The Gallup Organization,...
While optimization has received much attention in the machine learning community, most of them consider unconstrained supervised learning models such as neural networks and support vector machine. In this dissertation, we introduce a new class of optimization problems called scale invariant problems that include interesting unsupervised learning models such as...
This thesis focuses on applications of recurrent neural networks (RNNs) for three aspects of sequential classification. In the first chapter, a novel method to generate synthetic minority data generation to improve imbalanced classification is discussed. Generative Adversarial Networks (GANs) have been used in many different applications to generate realistic synthetic...
Radiofrequency ablation is a minimally-invasive treatment method that aims to destroy undesired tissue by exposing it to alternating current in the 100 kHz to 800 kHz frequency range and heating it until it is destroyed via coagulative necrosis. Ablation treatment is gaining momentum especially in cancer research, where the undesired...
Mammalian transcriptional regulation is well-known to be complex and highly context dependent. Different genetic and epigenetic features, including single nucleotide polymorphisms (SNPs) that function as cis- or trans-expression quantitative trait loci (eQTLs), transcription factor (TF) interaction profile with cis-regulatory elements (CREs), methylation of CpG dinucleotide sequences, and histone modification that...