Computer Sciences Commons^™

An Optimization Compiler Framework Based On Polyhedron Model For Gpgpus, Lifeng Liu

Browse all Theses and Dissertations

General purpose GPU (GPGPU) is an effective many-core architecture that can yield high throughput for many scientific applications with thread-level parallelism. However, several challenges still limit further performance improvements and make GPU programming challenging for programmers who lack the knowledge of GPU hardware architecture. In this dissertation, we describe an Optimization Compiler Framework Based on Polyhedron Model for GPGPUs to bridge the speed gap between the GPU cores and the off-chip memory and improve the overall performance of the GPU systems. The optimization compiler framework includes a detailed data reuse analyzer based on the extended polyhedron model for GPU kernels, …

Oclep+: One-Class Intrusion Detection Using Length Of Patterns, Sai Kiran Pentukar

Browse all Theses and Dissertations

In an earlier paper, a method called One-class Classification using Length statistics of (jumping) Emerging Patterns (OCLEP) was introduced for masquerader detection. Jumping emerging patterns (JEPs) for a test instance are minimal patterns that match the test instance but they do not match any normal instances. OCLEP was based on the observation that one needs long JEPs to differentiate an instance of one class from instances of the same class, but needs short JEPs to differentiate an instance of one class from instances of a different class. In this thesis, we present OCLEP+, One-class Classification using Length statistics of Emerging …

Conditional Correlation Analysis, Sanjeev Bhatta

Browse all Theses and Dissertations

Correlation analysis is a frequently used statistical measure to examine the relationship among variables in different practical applications. However, the traditional correlation analysis uses an overly simplistic method to do so. It measures how two variables are related in an application by examining only their relationship in the entire underlying data space. As a result, traditional correlation analysis may miss a strong correlation between those variables especially when that relationship exists in the small subpopulation of the larger data space. This is no longer acceptable and may lose a fair share of information in this era of Big Data which …

Rendering Owl In Latex For Improved Readability: Extensions To The Owlapi, Cogan M. Shimizu

Browse all Theses and Dissertations

As ontology engineering is inherently a multidisciplinary process, it is necessary to utilize multiple vehicles to present an ontology to a user. In order to examine the content of an ontology, formal logic renderings of the axioms appear to be a very helpful approach for some. This thesis introduces a number of incremental improvements to the OWLAPI's \LaTeX{} rendering framework in order to improve the readability, concision, and correctness of OWL files translated into Description Logic and First Order Logic. In addition, we examine the efficacy of these renderings as vehicles for understanding an ontology.

Deep Learning Approach For Intrusion Detection System (Ids) In The Internet Of Things (Iot) Network Using Gated Recurrent Neural Networks (Gru), Manoj Kumar Putchala

Browse all Theses and Dissertations

The Internet of Things (IoT) is a complex paradigm where billions of devices are connected to a network. These connected devices form an intelligent system of systems that share the data without human-to-computer or human-to-human interaction. These systems extract meaningful data that can transform human lives, businesses, and the world in significant ways. However, the reality of IoT is prone to countless cyber-attacks in the extremely hostile environment like the internet. The recent hack of 2014 Jeep Cherokee, iStan pacemaker, and a German steel plant are a few notable security breaches. To secure an IoT system, the traditional high-end security …

Portable Motion Lab For Diagnostic And Rehabilitation Processes, Yogesh Laxman Chavan

Browse all Theses and Dissertations

In this thesis research, we have explored the capabilities of a household body-tracking device - Microsoft Xbox Kinect for motion analysis and assessment to assist patient’s rehabilitation after joint replacement and repair surgeries. In particular, we have combined the motion tracking capabilities of Kinect with the 3D modelling of human body for accurate and intuitive movement assessment and feedback. Our prototype system demonstrates the effective and efficient workflow of motion capturing, data processing and analyzing and augmented reality based presentation, resulting in a design which is not only accurate, reliable and robust, but also extremely cost- and space-efficient. Furthermore, we …

Detecting Information Leakage In Android Malware Using Static Taint Analysis, Soham P. Kelkar

Browse all Theses and Dissertations

According to Google, Android now runs on 1.4 billion devices. The growing popularity has attracted attackers to use Android as a platform to conduct malicious activities. To achieve these malicious activities some attacker choose to develop malicious Apps to steal information from the Android users. As the modern day smartphones process, a lot of sensitive information, information security, and privacy becoming a potential target for the attacker. The malicious Apps steal information from the infected phone and send this information to the attacker-controlled URLs using various Android sink functions. Therefore, it necessary to protect data as it can prove detrimental …

Harassment Detection On Twitter Using Conversations, Venkatesh Edupuganti

Browse all Theses and Dissertations

Social media has brought people closer than ever before, but the use of social media has also brought with it a risk of online harassment. Such harassment can have a serious impact on a person such as causing low self-esteem and depression. The past research on detecting harassment on social media is primarily based on the content of messages exchanged on social media. The lack of context when relying on a single social media post can result in a high degree of false alarms. In this study, I focus on the reliable detection of harassment on Twitter by better understanding …

Semantic Web Foundations For Representing, Reasoning, And Traversing Contextualized Knowledge Graphs, Vinh Thi Kim Nguyen

Browse all Theses and Dissertations

Semantic Web technologies such as RDF and OWL have become World Wide Web Consortium (W3C) standards for knowledge representation and reasoning. RDF triples about triples, or meta triples, form the basis for a contextualized knowledge graph. They represent the contextual information about individual triples such as the source, the occurring time or place, or the certainty. However, an efficient RDF representation for such meta-knowledge of triples remains a major limitation of the RDF data model. The existing reification approach allows such meta-knowledge of RDF triples to be expressed in RDF by using four triples per reified triple. While reification is …

Automated Rendering Of Schema Diagram For Ontologies, Nazifa Karima

Browse all Theses and Dissertations

Semantic Web extends the current web, using ontologies, metadata and other technologies to establish links between terms and concepts. This enables machines to automatically integrate information across different platforms utilizing the standard definitions. Furthermore, reasoning agents can infer new knowledge by gathering existing information and these additional connections between them. As a result of being designed and maintained independently, data sources exhibit highly heterogeneous nature. This increases the complexity of data integration and hinders interoperability. However, if we can align the overlapping concepts among different domains of knowledge, the prospect of achieving interoperability and integration without having any intermediate reasoning …

Adapting The Search Space While Limiting Damage During Learning In A Simulated Flapping Wing Micro Air Vehicle, Monica Sam

Browse all Theses and Dissertations

Cyber-Physical Systems (CPS) are characterized by closely coupled physical and software components that operate simultaneously on different spatial and temporal scales; exhibit multiple and distinct behavioral modalities; and interact with one another in ways not entirely predictable at the time of design. A commonly appearing type of CPS are systems that contain one or more smart components that adapt locally in response to global measurements of whole system performance. An example of a smart component robotic CPS system is a Flapping Wing Micro Air Vehicle (FW-MAV) that contains wing motion oscillators that control their wing flapping patterns to enable the …

Development Of An Ultra-Portable Non-Contact Wound Measurement System, Anka Babu Billa

Browse all Theses and Dissertations

Continuous monitoring of changes in wound size is key to correctly predict whether wounds will heal readily with conventional treatment or require more aggressive treatment strategies. Unfortunately, existing wound measurement solutions don't meet the clinical demand due to their limitations in accuracy, operating complexity and time, acquisition and operation cost, or reproducibility, resulting in unnecessarily lengthy recovery or extra treatment procedures, incurring an excessively high financial cost, and in many cases extended usage of addictive painkillers. In this thesis, we proposed and developed a low cost, a portable non-contact solution that combines multi-spectral imaging and a portfolio of imaging processing …

Preliminary Investigation Of Walking Motion Using A Combination Of Image And Signal Processing, Bradley Schneider, Tanvi Banerjee

Kno.e.sis Publications

We present the results of analyzing gait motion in first-person video taken from a commercially available wearable camera embedded in a pair of glasses. The video is analyzed with three different computer vision methods to extract motion vectors from different gait sequences from four individuals for comparison against a manually annotated ground truth dataset. Using a combination of signal processing and computer vision techniques, gait features are extracted to identify the walking pace of the individual wearing the camera as well as validated using the ground truth dataset. Our preliminary results indicate that the extraction of activity from the video …

Analyzing Clinical Depressive Symptoms In Twitter, Amir Hossein Yazdavar, Hussein S. Al-Olimat, Tanvi Banerjee, Krishnaprasad Thirunarayan, Amit P. Sheth

Kno.e.sis Publications

350 million people are suffering from clinical depression worldwide.

What Motivates High School Students To Take Precautions Against The Spread Of Influenza? A Data Science Approach To Latent Modeling Of Compliance With Preventative Practice, William L. Romine, Tanvi Banerjee, William R. Folk, Lloyd H. Barrow

Kno.e.sis Publications

– This study focuses on a central question: What key behavioral factors influence high school students’ compliance with preventative measures against the transmission of influenza? We use multilevel logistic regression to equate logit measures for eight precautions to students’ latent compliance levels on a common scale. Using linear regression, we explore the efficacy of knowledge of influenza, affective perceptions about influenza and its prevention, prior illness, and gender in predicting compliance. Hand washing and respiratory etiquette are the easiest precautions for students, and hand sanitizer use and keeping the hands away from the face are the most difficult. Perceptions of …

Semantic, Cognitive, And Perceptual Computing: Paradigms That Shape Human Experience, Amit P. Sheth, Pramod Anantharam, Cory Henson

Kno.e.sis Publications

Unlike machine-centric computing, in which efficient data processing takes precedence over contextual tailoring, human-centric computation provides a personalized data interpretation that most users find highly relevant to their needs. The authors show how semantic, cognitive, and perceptual computing paradigms work together to produce actionable information.

Educational Methods For Inverted-Lecture Computer Science And Engineering Classrooms To Overcome Common Barriers To Stem Student Success, Kathleen Timmerman

Browse all Theses and Dissertations

New educational pedagogies are emerging in an effort to increase the number of new engineers available to enter the workforce in the coming years. One of the re-occurring themes in these pedagogies is variations of the flipped classroom. Often the additional classroom time gained from flipping is used to reinforce learning objectives. It is hypothesized that it might be more beneficial to students if a portion of that time is used to address common non-cognitive barriers that prevent students from succeeding in the major. In a freshman Introductory Computer Science course, three different pedagogies are compared: a hybrid lecture-active learning …

A Hybrid Approach To Aerial Video Image Registration, Karol T. Salva

Browse all Theses and Dissertations

Many video processing applications, such as motion detection and tracking, rely on accurate and robust alignment between consecutive video frames. Traditional approaches to video image registration, such as pyramidal Kanade-Lucas-Tomasi (KLT) feature detection and tracking are fast and subpixel accurate, but are not robust to large inter-frame displacements due to rotation, scale, or translation. This thesis presents an alternative hybrid approach using normalized gradient correlation (NGC) in the frequency domain and normalized cross-correlation (NCC) in the spatial domain that is fast, accurate, and robust to large displacements. A scale space search is incorporated into NGC to enable more consistent recovery …

Super-Resolution Reconstruction Of Mri, Sara Gharabaghi, Thomas Wischgoll, Nasser H. Kashou

Computer Science and Engineering Faculty Publications

Magnetic Resonance Imaging (MRI) is a non-invasive technique that is used in clinical applications such as diseases diagnosis and monitoring and treatment progress. Although, MRI scans typically have high in-plane resolution but they have very poor resolution in slice direction. Furthermore, in some applications with limited acquisition time or where the subject is moving, increased slice thickness or inter-slice space (slice gaps) may be used which results in poor resolution MRI.

In this research, we propose a novel Super Resolution (SR) technique for reconstructing High-Resolution (HR) MRI using a sequence of orthogonal Low-Resolution (LR) MRI scans.

The resolution of this …

Uncertainty-Awareness In Open Source Visualization Solutions, Christina Gillmann, Thomas Wischgoll, Hans Hagen

Computer Science and Engineering Faculty Publications

The popularity of open source tools is constantly increasing, as they offer the possibility to quickly create and use visualizations of arbitrary data sources. As the positive effects of uncertainty communication to all kinds of visualizations were discussed over the past years in the academic world, this work examines the uncertaintyawareness of open source solutions. Through a categorization and classification of available tools, this paper identifies the problems in uncertainty-awareness of available open source solutions. To solve this problem, a new paradigm of data handling that extends raw datasets by its uncertainty is suggested

Knowledge Driven Search Intent Mining, Ashutosh Jadhav

Browse all Theses and Dissertations

Understanding users' latent intents behind search queries is essential for satisfying a user's search needs. Search intent mining can help search engines to enhance its ranking of search results, enabling new search features like instant answers, personalization, search result diversification, and the recommendation of more relevant ads. Hence, there has been increasing attention on studying how to effectively mine search intents by analyzing search engine query logs. While state-of-the-art techniques can identify the domain of the queries (e.g. sports, movies, health), identifying domain-specific intent is still an open problem. Among all the topics available on the Internet, health is one …

A Performance Analysis Framework For Coreference Resolution Algorithms, Chandankumar Johakhim Patel

Browse all Theses and Dissertations

This thesis entitled A Performance Analysis Framework for Coreference Resolution Algorithms, focuses on the topic of coreference resolution of semantic datasets. In order for Big Data analytics to be effective, it is essential to develop automated algorithms capable of integrating multiple datasets that contain data about a particular person or other entity. Accomplishing this necessitates coreference resolution; for example, determining that J. Doe in one dataset refers to the same person as Jonathan Doe Jr. in another dataset. There are many existing coreference resolution algorithms, but there are only a few basic design decisions to be made by such systems …

Openthinning: Fast 3d Thinning Based On Local Neighborhood Lookups, Tobias Post, Christina Gillmann, Thomas Wischgoll, Hans Hagen

Computer Science and Engineering Faculty Publications

3D Thinning is an often required image processing task in order to perform shape analysis in various applications. For researchers in these domains, a fast, flexible and easy to access implementation is required. Open source solutions, as the Insights Segmentation and Registration Toolkit (ITK), are often used for image processing and visualization tasks, due to their wide range of provided algorithms. Unfortunately, ITK’s thinning implementation is computational expensive and allows solely one specific thinning approach. Therefore, this work presents OpenThinning, an open source thinning solution for 3D image data. The implemented algorithm evaluates a moving local neighborhood to find deletable …

Cardiovascular Dieseases: From Data Generation To Analysis, Thomas Wischgoll

Computer Science and Engineering Faculty Publications

Cardiovascular diseases remain the leading cause of death in Western societies. This presentation will provide insight into the use of expert knowledge and models to derive diagnostic tools that have the potential to aid in the diagnosis of diffuse cardiovascular diseases that tend to be more difficult to detect in CT angiograms. In order to develop these methods more basic research is needed to prove the validity of the approach, including validation of accuracy as well as approach itself. For that, specimens of porcine hearts were prepared and then analyzed followed by a statistical comparison between computed and optical measurements. …

A Semi-Automated Computer Program For Assessment Of Skeletal Maturity In Children, Sara Gharabaghi, Thomas Wischgoll

Computer Science and Engineering Faculty Publications

In pediatric patients, skeletal maturity is an important tool for detection of hormonal, growth or genetic disorders. The Fels method is a well-known visual assessment method in which the skeletal age is estimated by grading 98 skeletal indicators in the hand-wrist radiographic (x-ray) image. These indicators are features that reflect the three-dimensional shape of the bones and change during the maturation process. Generally, the Fels indicators could be categorized into three main groups of the status of ossification, the ratios of bone widths, and epiphysealdiaphyseal fusion.

Personalized And Adaptive Semantic Information Filtering For Social Media, Pavan Kapanipathi

Browse all Theses and Dissertations

Social media has experienced immense growth in recent times. These platforms are becoming increasingly common for information seeking and consumption, and as part of its growing popularity, information overload pose a significant challenge to users. For instance, Twitter alone generates around 500 million tweets per day and it is impractical for users to have to parse through such an enormous stream to find information that are interesting to them. This situation necessitates efficient personalized filtering mechanisms for users to consume relevant, interesting information from social media. Building a personalized filtering system involves understanding users' interests and utilizing these interests to …

Detecting Php-Based Cross-Site Scripting Vulnerabilities Using Static Program Analysis, Steven M. Kelbley

Browse all Theses and Dissertations

With the widespread adoption of dynamic web applications in recent years, a number of threats to the security of these applications have emerged as significant challenges for application developers. The security of developed applications has become a higher priority for both developers and their employers as cyber attacks become increasingly more prevalent and damaging. Some of the most used web application frameworks are written in PHP and have become major targets due to the large number of servers running these applications worldwide. A number of tools exist to evaluate PHP code for issues, however most of these applications are not …

Miniatured Inertial Motion And Position Tracking And Visualization Systems Using Android Wear Platform, Dhruvkumar Navinchandra Patel

Browse all Theses and Dissertations

In this thesis, we have designed and developed a motion tracking and visualization system using the latest motion tracking sensory technologies. It is one of the enabling technologies for our novel visual-inertial odometer and human anatomy based 3D Locating, Mapping and Navigation system for endoscopy and drug delivery capsules used inside GI tract. In particular, we have: i) designed and completed a cloud-based sensory data collecting, processing and storage system to provide the reliable computing and storage platform; ii) explored different data processing methods to obtain improved-quality motion results from extremely noisy raw data, e.g., by using a low pass …

Hpc Enabled Data Analytics For High-Throughput High-Content Cellular Analysis, Ross A. Smith, Rhonda J. Vickery, Jack Harris, Sara Gharabaghi, Thomas Wischgoll, David Short, Robert Trevino, Steven A. Kawamoto, Thomas J. Lamkin, Kevin Schoen, Eric E. Bardes, Scott C. Tabar, Bruce J. Aronow

Computer Science and Engineering Faculty Publications

Biologists doing high-throughput high-content cellular analysis are generally not computer scientists or high performance computing (HPC) experts, and they want their workflow to support their science without having to be. We describe a new HPC enabled data analytics workflow with a web interface, HPC pipeline for analysis, and both traditional and new analytics tools to help them transition from a single workstation mode of operation to power HPC users. This allows the processing of multiple plates over a short period of time to ensure timely query and analysis to match potential countermeasures to individual responses.

A Study Of Social Web Data On Buprenorphine Abuse Using Semantic Web Technology, Raminta Daniulaityte, Amit P. Sheth

Kno.e.sis Publications

The Specific Aims of this application are to use a paradigmatic approach that combines Semantic Web technology, Natural Language Processing and Machine Learning techniques to:

1) Describe drug users’ knowledge, attitudes, and behaviors related to the non-medical use of Suboxone and Subutex as discussed on Web-based forums.
2) Identify and describe temporal patterns of non-medical use of Suboxone and Subutex as discussed on Web-based forums.

The research was carried out by an interdisciplinary team of members of the Center for Interventions, Treatment and Addictions Research (CITAR) and the Ohio Center of Excellence in Knowledge- enabled Computing (Kno.e.sis) at Wright State …