Computer Engineering Commons^™

A Framework For Clustering And Adaptive Topic Tracking On Evolving Text And Social Media Data Streams., Gopi Chand Nutakki

Electronic Theses and Dissertations

Recent advances and widespread usage of online web services and social media platforms, coupled with ubiquitous low cost devices, mobile technologies, and increasing capacity of lower cost storage, has led to a proliferation of Big data, ranging from, news, e-commerce clickstreams, and online business transactions to continuous event logs and social media expressions. These large amounts of online data, often referred to as data streams, because they get generated at extremely high throughputs or velocity, can make conventional and classical data analytics methodologies obsolete. For these reasons, the issues of management and analysis of data streams have been researched extensively …

Integrated Environment And Proximity Sensing For Uav Applications, Shawn S. Brackett

Electronic Theses and Dissertations

As Unmanned Aerial Vehicle (UAV), or “drone” applications expand, new methods for sensing, navigating and avoiding obstacles need to be developed. The project applies an Extended Kalman Filter (EKF) to a simulated quadcopter vehicle though Matlab in order to estimate not only the vehicle state but the world state around the vehicle. The EKF integrates multiple sensor readings from range sensors, IMU sensors, and radiation sensors and combines this information to optimize state estimates. The result is an estimated world map to be used in vehicle navigation and obstacle avoidance.

The simulation handles the physics behind the vehicle flight. As …

A Data Science Pipeline For Educational Data : A Case Study Using Learning Catalytics In The Active Learning Classroom., Asuman Cagla Acun Sener

Electronic Theses and Dissertations

This thesis presents an applied data science methodology on a set of University of Louisville, Speed School of Engineering student data. We used data mining and classic statistical techniques to help educational researchers quickly see the data trends and peculiarities. Our data includes scores and information about two Engineering Fundamental Class. The format of these classes is called an inverted classroom model or flipped class. The purpose of this study is to analyze the data in order to uncover potentially hidden information, tell interesting stories about the data, examine student learning behavior and learning performance in an active learning environment, …

Dynamic Adversarial Mining - Effectively Applying Machine Learning In Adversarial Non-Stationary Environments., Tegjyot Singh Sethi

Electronic Theses and Dissertations

While understanding of machine learning and data mining is still in its budding stages, the engineering applications of the same has found immense acceptance and success. Cybersecurity applications such as intrusion detection systems, spam filtering, and CAPTCHA authentication, have all begun adopting machine learning as a viable technique to deal with large scale adversarial activity. However, the naive usage of machine learning in an adversarial setting is prone to reverse engineering and evasion attacks, as most of these techniques were designed primarily for a static setting. The security domain is a dynamic landscape, with an ongoing never ending arms race …

An Interactive Interface For Nursing Robots., Ankita Sahu

Electronic Theses and Dissertations

Physical Human-Robot Interaction (pHRI) is inevitable for a human user while working with assistive robots. There are various aspects of pHRI, such as choosing the interface, type of control schemes implemented and the modes of interaction. The research work presented in this thesis concentrates on a health-care assistive robot called Adaptive Robot Nursing Assistant (ARNA). An assistive robot in a health-care environment has to be able to perform routine tasks and be aware of the surrounding environment at the same time. In order to operate the robot, a teleoperation based interaction would be tedious for some patients as it would …

Spatial Relations And Natural-Language Semantics For Indoor Scenes, Stacy A. Doore

Electronic Theses and Dissertations

Over the past 15 years, there have been increased efforts to represent and communicate spatial information about entities within indoor environments. Automated annotation of information about indoor environments is needed for natural-language processing tasks, such as spatially anchoring events, tracking objects in motion, scene descriptions, and interpretation of thematic places in relationship to confirmed locations. Descriptions of indoor scenes often require a fine granularity of spatial information about the meaning of natural-language spatial utterances to improve human-computer interactions and applications for the retrieval of spatial information. The development needs of these systems provide a rationale as to why—despite an extensive …

Data Driven Discovery Of Materials Properties., Fadoua Khmaissia

Electronic Theses and Dissertations

The high pace of nowadays industrial evolution is creating an urgent need to design new cost efficient materials that can satisfy both current and future demands. However, with the increase of structural and functional complexity of materials, the ability to rationally design new materials with a precise set of properties has become increasingly challenging. This basic observation has triggered the idea of applying machine learning techniques in the field, which was further encouraged by the launch of the Materials Genome Initiative (MGI) by the US government since 2011. In this work, we present a novel approach to apply machine learning …

Vehicle Make And Model Recognition For Intelligent Transportation Monitoring And Surveillance., Faezeh Tafazzoli

Electronic Theses and Dissertations

Vehicle Make and Model Recognition (VMMR) has evolved into a significant subject of study due to its importance in numerous Intelligent Transportation Systems (ITS), such as autonomous navigation, traffic analysis, traffic surveillance and security systems. A highly accurate and real-time VMMR system significantly reduces the overhead cost of resources otherwise required. The VMMR problem is a multi-class classification task with a peculiar set of issues and challenges like multiplicity, inter- and intra-make ambiguity among various vehicles makes and models, which need to be solved in an efficient and reliable manner to achieve a highly robust VMMR system. In this dissertation, …

Using A Multi Variate Pattern Analysis (Mvpa) Approach To Decode Fmri Responses To Fear And Anxiety., Sajjad Torabian Esfahani

Electronic Theses and Dissertations

This study analyzed fMRI responses to fear and anxiety using a Multi Variate Pattern Analysis (MVPA) approach. Compared to conventional univariate methods which only represent regions of activation, MVPA provides us with more detailed patterns of voxels. We successfully found different patterns for fear and anxiety through separate classification attempts in each subject’s representational space. Further, we transformed all the individual models into a standard space to do group analysis. Results showed that subjects share a more common fear response. Also, the amygdala and hippocampus areas are more important for differentiating fear than anxiety.

Peeking Into The Other Half Of The Glass : Handling Polarization In Recommender Systems., Mahsa Badami

Electronic Theses and Dissertations

This dissertation is about filtering and discovering information online while using recommender systems. In the first part of our research, we study the phenomenon of polarization and its impact on filtering and discovering information. Polarization is a social phenomenon, with serious consequences, in real-life, particularly on social media. Thus it is important to understand how machine learning algorithms, especially recommender systems, behave in polarized environments. We study polarization within the context of the users' interactions with a space of items and how this affects recommender systems. We first formalize the concept of polarization based on item ratings and then relate …

Uncovering Exceptional Predictions Using Exploratory Analysis Of Second Stage Machine Learning., Aneseh Alvanpour

Electronic Theses and Dissertations

Nowadays, algorithmic systems for making decisions are widely used to facilitate decisions in a variety of fields such as medicine, banking, applying for universities or network security. However, many machine learning algorithms are well-known for their complex mathematical internal workings which turn them into black boxes and makes their decision-making process usually difficult to understand even for experts. In this thesis, we try to develop a methodology to explain why a certain exceptional machine learned decision was made incorrectly by using the interpretability of the decision tree classifier. Our approach can provide insights about potential flaws in feature definition or …

Towards High-Efficiency Data Management In The Next-Generation Persistent Memory System, Xunchao Chen

Electronic Theses and Dissertations

For the sake of higher cell density while achieving near-zero standby power, recent research progress in Magnetic Tunneling Junction (MTJ) devices has leveraged Multi-Level Cell (MLC) configurations of Spin-Transfer Torque Random Access Memory (STT-RAM). However, in order to mitigate the write disturbance in an MLC strategy, data stored in the soft bit must be restored back immediately after the hard bit switching is completed. Furthermore, as the result of MTJ feature size scaling, the soft bit can be expected to become disturbed by the read sensing current, thus requiring an immediate restore operation to ensure the data reliability. In this …

End To End Brain Fiber Orientation Estimation Using Deep Learning, Nandakishore Puttashamachar

Electronic Theses and Dissertations

In this work, we explore the various Brain Neuron tracking techniques, one of the most significant applications of Diffusion Tensor Imaging. Tractography is a non-invasive method to analyze underlying tissue micro-structure. Understanding the structure and organization of the tissues facilitates a diagnosis method to identify any aberrations which can occur within tissues due to loss of cell functionalities, provides acute information on the occurrences of brain ischemia or stroke, the mutation of certain neurological diseases such as Alzheimer, multiple sclerosis and so on. Under all these circumstances, accurate localization of the aberrations in efficient manner can help save a life. …

Reducing The Overhead Of Memory Space, Network Communication And Disk I/O For Analytic Frameworks In Big Data Ecosystem, Xuhong Zhang

Electronic Theses and Dissertations

To facilitate big data processing, many distributed analytic frameworks and storage systems such as Apache Hadoop, Apache Hama, Apache Spark and Hadoop Distributed File System (HDFS) have been developed. Currently, many researchers are conducting research to either make them more scalable or enabling them to support more analysis applications. In my PhD study, I conducted three main works in this topic, which are minimizing the communication delay in Apache Hama, minimizing the memory space and computational overhead in HDFS and minimizing the disk I/O overhead for approximation applications in Hadoop ecosystem. Specifically, In Apache Hama, communication delay makes up a …

Load-Balancing In Local And Metro-Area Networks With Mptcp And Openflow, Austin Jerome

Electronic Theses and Dissertations

In this thesis, a novel load-balancing technique for local or metro-area traffic is proposed in mesh-style topologies. The technique uses Software Defined Networking (SDN) architecture with virtual local area network (VLAN) setups typically seen in a campus or small-to-medium enterprise environment. This was done to provide a possible solution or at least a platform to expand on for the load-balancing dilemma that network administrators face today. The transport layer protocol Multi-Path TCP (MPTCP) coupled with IP aliasing is also used. The trait of MPTCP of forming multiple subflows from sender to receiver depending on the availability of IP addresses at …

Energy-Aware Data Movement In Non-Volatile Memory Hierarchies, Navid Khoshavi Najafabadi

Electronic Theses and Dissertations

While technology scaling enables increased density for memory cells, the intrinsic high leakage power of conventional CMOS technology and the demand for reduced energy consumption inspires the use of emerging technology alternatives such as eDRAM and Non-Volatile Memory (NVM) including STT-MRAM, PCM, and RRAM. The utilization of emerging technology in Last Level Cache (LLC) designs which occupies a signifcant fraction of total die area in Chip Multi Processors (CMPs) introduces new dimensions of vulnerability, energy consumption, and performance delivery. To be specific, a part of this research focuses on eDRAM Bit Upset Vulnerability Factor (BUVF) to assess vulnerable portion of …

A Dynamic Scaling Methodology For Improving Performance Of Big Data Systems, Nashmiah Alhamdawi

Electronic Theses and Dissertations

The continuous growth of data volume in various fields such as, healthcare, sciences, economics, and business has caused an overwhelming flow of data in the last decade. The overwhelming flow of data has raised challenges in processing, analyzing, and storing data, which lead many systems to face an issue in performance. Poor performance of systems creates negative impact such as delays, unprocessed data, and increasing response time. Processing huge amounts of data demands a powerful computational infrastructure to ensure that data processing and analysis success [7]. However, the architectures of these systems are not suitable to process that quantity of …

Optimized Multilayer Perceptron With Dynamic Learning Rate To Classify Breast Microwave Tomography Image, Chulwoo Pack

Electronic Theses and Dissertations

Most recently developed Computer Aided Diagnosis (CAD) systems and their related research is based on medical images that are usually obtained through conventional imaging techniques such as Magnetic Resonance Imaging (MRI), x-ray mammography, and ultrasound. With the development of a new imaging technology called Microwave Tomography Imaging (MTI), it has become inevitable to develop a CAD system that can show promising performance using new format of data. The platform can have a flexibility on its input by adopting Artificial Neural Network (ANN) as a classifier. Among the various phases of CAD system, we have focused on optimizing the classification phase …

Improving The Performance Of Data-Intensive Computing On Cloud Platforms, Wei Dai

Electronic Theses and Dissertations

Big Data such as Terabyte and Petabyte datasets are rapidly becoming the new norm for various organizations across a wide range of industries. The widespread data-intensive computing needs have inspired innovations in parallel and distributed computing, which has been the effective way to tackle massive computing workload for decades. One significant example is MapReduce, which is a programming model for expressing distributed computations on huge datasets, and an execution framework for data-intensive computing on commodity clusters as well. Since it was originally proposed by Google, MapReduce has become the most popular technology for data-intensive computing. While Google owns its proprietary …

Abstraction Hierarchies For Multi-Agent Pathfinding, Aaron R. Kraft

Electronic Theses and Dissertations

Multi-Agent Pathfinding is an NP-Complete search problem with a branching factor that is exponential in the number of agents. Because of this exponential feature, it can be difficult to solve optimally using traditional search techniques, even for relatively small problems. Many recent optimal solvers have attempted to reduce the complexity of the problem by resolving the conflicts between agent paths separately. Very little of this research has focused on creating quality heuristics to help solve the problem. In this thesis, we create heuristics using sub-problems created by removing agents from a complete problem instance. We combine this with the Independence …

Explaining The Performance Of Bidirectional Dijkstra And A* On Road Networks, Sneha Sawlani

Electronic Theses and Dissertations

The heuristic search community traditionally uses A* as the baseline algorithm for their research methods. Research papers in the road networks community, however, often build upon Dijkstra's algorithm and use Bidirectional Dijkstra's algorithm as their baseline. This thesis investigates the performance of A* and Bidirectional Dijkstra in road networks to see how they compare and to see if there is a principled explanation for the different approaches. Our analysis reveals why Bidirectional Dijkstra can perform well in this domain, but also shows a simple mistake that can be made when building test problems that hurts the performance of A*.

Optimized Trajectory Generation For Car-Like Robots On A Closed Loop Track, Tyler Friedl

Electronic Theses and Dissertations

This thesis presents a method for generating an optimized path through a given track. The path is generated by choosing waypoints throughout the track then iteratively optimizing the position of these waypoints. The waypoints are then connected by optimized paths represented by curvature polynomials. The end result is a path through the track represented as a spline of curvature polynomials. This method is applied to multiple simulated tracks and the results are presented. By generating and representing the paths in the continuous domain, the method has improved computational efficiency from many of the discrete methods used to generate an optimal …

System Identification Of A Circulation Control Unmanned Aerial Vehicle, Mohammed Agha

Electronic Theses and Dissertations

The advancement in automation and sensory systems in recent years has led to an increase the demand of UAV missions. Due to this increase in demand, the research community has gained interest in investigating UAV performance enhancing systems. Circulation Control (CC), which is an active control flow method used to enhance UAV lift, is a performance enhancing system currently studied. In prior research, experimental studies have shown that Circulation Control wings (CCW) implemented on class-I UAVs can reduce take-off distance by 54%. Wind tunnel tests reveal that CC improves aircraft payload capabilities through lift enhancement. Increasing aircraft payload capabilities causes …

Reducing Side-Sweep Accidents With Vehicle-To-Vehicle Communications, Gamini Bulumulle

Electronic Theses and Dissertations

This dissertation present contributions to the understanding of the causes of a side-sweep accidents on multi-lane highways using computer simulation. Side-sweep accidents are one of the major causes of loss of life and property damage on highways. This type of accident is caused by a driver initiating a lane change while another vehicle is blocking the road in the target lane. Our objective in the research described in this dissertation was to understand and simulate the different factors which affect the likelihood of side sweep accidents. For instance, we know that blind spots, parts of the road that are not …

Wind Turbine Noise And Wind Speed Prediction, Tyler H. Blanchard

Electronic Theses and Dissertations

In order to meet the US Department of Energy projected target of 35% of US energy coming from wind by 2050, there is a strong need to study the management and development of wind turbine technology and its impact on human health, wildlife and environment. The prediction of wind turbine noise and its propagation is very critical to study the impacts of wind turbine noise for long term adoption and acceptance by neighboring communities. The prediction of wind speed is critical in the assessment of feasibility of a potential wind turbine site. This work presents a study on prediction of …

Ego-Localization Navigation For Intelligent Vehicles Using 360° Lidar Sensor For Point Cloud Mapping, Tyler Naes

Electronic Theses and Dissertations

With its prospects of reducing vehicular accidents and traffic in highly populated urban areas by taking the human error out of driving, the future in automobiles is leaning towards autonomous navigation using intelligent vehicles. Autonomous navigation via Light Detection And Ranging (LIDAR) provides very accurate localization within a predefined, a priori, point cloud environment that is not possible with Global Positioning System (GPS) and video camera technology. Vehicles may be able to follow paths in the point cloud environment if the baseline paths it must follow are known in that environment by referencing objects detected in the point cloud …