Physical Sciences and Mathematics Commons^™

Controlling For Confounding Network Properties In Hypothesis Testing And Anomaly Detection, Timothy La Fond

Open Access Dissertations

An important task in network analysis is the detection of anomalous events in a network time series. These events could merely be times of interest in the network timeline or they could be examples of malicious activity or network malfunction. Hypothesis testing using network statistics to summarize the behavior of the network provides a robust framework for the anomaly detection decision process. Unfortunately, choosing network statistics that are dependent on confounding factors like the total number of nodes or edges can lead to incorrect conclusions (e.g., false positives and false negatives). In this dissertation we describe the challenges that face …

Data Driven Low-Bandwidth Intelligent Control Of A Jet Engine Combustor, Nathan L. Toner

Open Access Dissertations

This thesis introduces a low-bandwidth control architecture for navigating the input space of an un-modeled combustor system between desired operating conditions while avoiding regions of instability and blow-out. An experimental procedure is discussed for identifying regions of instability and gathering sufficient data to build a data-driven model of the system's operating modes. Regions of instability and blow-out are identified experimentally and a data-driven operating point classifier is designed. This classifier acts as a map of the operating space of the combustor, indicating regions in which the flame is in a "good" or "bad" operating mode. A data-driven predictor is also …

Improving The Eco-System Of Passwords, Weining Yang

Open Access Dissertations

Password-based authentication is perhaps the most widely used method for user authentication. Passwords are both easy to understand and use, and easy to implement. With these advantages, password-based authentication is likely to stay as an important part of security in the foreseeable future. One major weakness of password-based authentication is that many users tend to choose weak passwords that are easy to guess. In this dissertation, we address the challenge and improve the eco-system of passwords in multiple aspects. Firstly, we provide methodologies that help password research. To be more specific, we propose Probability Threshold Graphs, which is superior to …

An Anomaly-Based Intrusion Detection System Based On Artificial Immune System (Ais) Techniques, Harish Valayapalayam Kumaravel

Open Access Theses

Two of the major approaches to intrusion detection are anomaly-based detection and signature-based detection. Anomaly-based approaches have the potential for detecting zero-day and other new forms of attacks. Despite this capability, anomaly-based approaches are comparatively less widely used when compared to signature-based detection approaches. Higher computational overhead, higher false positive rates, and lower detection rates are the major reasons for the same. This research has tried to mitigate this problem by using techniques from an area called the Artificial Immune Systems (AIS). AIS is a collusion of immunology, computer science and engineering and tries to apply a number of techniques …

Using Ubiquitous Data To Improve Smartwatches' Context Awareness, Yuankun Song

Open Access Theses

Nowadays, more and more data is being generated by various software applications, services and smart devices every second. The data contains abundant information about people’s daily lives. This research explored the possibility of improving smartwatches’ context awareness by using common ubiquitous data. The researcher developed a prototype system consisting of an Android application and a web application, and conducted an experiment where 10 participants performed several tasks with the help of a smartwatch. The result showed a significant improvement of the smartwatch’s context awareness running the prototype application, which used ubiquitous data to automatically execute proper actions according to contexts. …

Hardware Accelerated Authentication System For Dynamic Time-Critical Networks, Ankush Singla

Open Access Theses

The secure and efficient operation of time-critical networks, such as vehicular networks, smart-grid and other smart-infrastructures, is of primary importance in today’s society. It is crucial to minimize the impact of security mechanisms over such networks so that the safe and reliable operations of time-critical systems are not being interfered.

Even though there are several security mechanisms, their application to smart-infrastructure and Internet of Things (IoT) deployments may not meet the ubiquitous and time-sensitive needs of these systems. That is, existing security mechanisms either introduce a significant computation and communication overhead, or they are not scalable for a large number …

Packet Filter Performance Monitor (Anti-Ddos Algorithm For Hybrid Topologies), Ibrahim M. Waziri

Open Access Dissertations

DDoS attacks are increasingly becoming a major problem. According to Arbor Networks, the largest DDoS attack reported by a respondent in 2015 was 500 Gbps. Hacker News stated that the largest DDoS attack as of March 2016 was over 600 Gbps, and the attack targeted the entire BBC website.

With this increasing frequency and threat, and the average DDoS attack duration at about 16 hours, we know for certain that DDoS attacks will not be going away anytime soon. Commercial companies are not effectively providing mitigation techniques against these attacks, considering that major corporations face the same challenges. Current security …

Learning Program Specifications From Sample Runs, He Zhu

Open Access Dissertations

With science fiction of yore being reality recently with self-driving cars, wearable computers and autonomous robots, software reliability is growing increasingly important. A critical pre-requisite to ensure the software that controls such systems is correct is the availability of precise specifications that describe a program's intended behaviors. Generating these specifications manually is a challenging, often unsuccessful, exercise; unfortunately, existing static analysis techniques often produce poor quality specifications that are ineffective in aiding program verification tasks.

In this dissertation, we present a recent line of work on automated synthesis of specifications that overcome many of the deficiencies that plague existing specification …

Detection Of Communication Over Dnssec Covert Channels, Nicole M. Hands

Open Access Theses

Unauthorized data removal and modification from information systems represents a major and formidable threat in modern computing. Security researchers are engaged in a constant and escalating battle with the writers of malware and other methods of network intrusion to detect and mitigate this threat. Advanced malware behaviors include encryption of communications between the server and infected client machines as well as various strategies for resilience and obfuscation of infrastructure. These techniques evolve to use any and all available mechanisms. As the Internet has grown, DNS has been expanded and has been given security updates. This study analyzed the potential uses …

Monitoring Dbms Activity To Detect Insider Threat Using Query Selectivity, Prajwal B. Hegde

Open Access Theses

The objective of the research presented in this thesis is to evaluate the importance of query selectivity for monitoring DBMS activity and detect insider threat. We propose query selectivity as an additional component to an existing anomaly detection system (ADS). We first look at the advantages of working with this particular ADS. This is followed by a discussion about some existing limitations in the anomaly detection system (ADS) and how it affects its overall performance. We look at what query selectivity is and how it can help improve upon the existing limitations of the ADS. The system is then implemented …

A Usability Assessment For A Career Planning Educational Video Game, Jiaqi Wang

Open Access Theses

This study focused on the design, implementation and usability assessment of an educational 2D iPad job matching game The Place You’ll Go (TPYG), which meant for matching student skill sets with career profiles. The development of the game is conducted in collaboration with Purdue University’s Krannert School of Management and Polytech Institute. A total of 7 subjects, as high school teachers, participated in the usability study. TPYG as one possible solution for job matching data visualization, did not provide players with a good experience. However, conclusions and findings can be used in similar education game development. Based on survey and …

Information Overload In Structured Data, Pinar Yanardag Delul

Open Access Dissertations

Information overload refers to the difficulty of making decisions caused by too much information. In this dissertation, we address information overload problem in two separate structured domains, namely, graphs and text.

Graph kernels have been proposed as an efficient and theoretically sound approach to compute graph similarity. They decompose graphs into certain sub-structures, such as subtrees, or subgraphs. However, existing graph kernels suffer from a few drawbacks. First, the dimension of the feature space associated with the kernel often grows exponentially as the complexity of sub-structures increase. One immediate consequence of this behavior is that small, non-informative, sub-structures occur more …

Zephyr: A Social Psychology-Based Mobile Application For Long-Distance Romantic Partners, Dhiraj Bodicherla

Open Access Theses

Long-distance romantic relationships have become quite common nowadays. With CMC tools advancing day-by-day, their usage among LDRs is proliferating rapidly. Attachment-related anxiety and avoidance can block the ability to enjoy happy relationships. During such situations, remembering happy past moments can be comforting. In this study a mobile chat application that enables LDR couples to reminisce about happy moments was developed. This study primarily focuses on evaluating the usability of this mobile application using survey-based methods. System Usability Scale was considered to discuss the outcome of the study. The overall results provide useful recommendations for further improvements in the design of …

Learning From Minimally Labeled Data With Accelerated Convolutional Neural Networks, Aysegul Dundar

Open Access Dissertations

The main objective of an Artificial Vision Algorithm is to design a mapping function that takes an image as an input and correctly classifies it into one of the user-determined categories. There are several important properties to be satisfied by the mapping function for visual understanding. First, the function should produce good representations of the visual world, which will be able to recognize images independently of pose, scale and illumination. Furthermore, the designed artificial vision system has to learn these representations by itself. Recent studies on Convolutional Neural Networks (ConvNets) produced promising advancements in visual understanding. These networks attain significant …

Optimal Monitoring And Mitigation Of Systemic Risk In Lending Networks, Zhang Li

Open Access Dissertations

This thesis proposes optimal policies to manage systemic risk in financial networks. Given a one-period borrower-lender network in which all debts are due at the same time and have the same seniority, we address the problem of allocating a fixed amount of cash among the nodes to minimize the weighted sum of unpaid liabilities. Assuming all the loan amounts and cash flows are fixed and that there are no bankruptcy costs, we show that this problem is equivalent to a linear program. We develop a duality-based distributed algorithm to solve it which is useful for applications where it is desirable …

Energy Efficiency In Data Collection Wireless Sensor Networks, Miquel Andres Navarro Patino

Open Access Dissertations

This dissertation studies the problem of energy efficiency in resource constrained and heterogeneous wireless sensor networks (WSNs) for data collection applications in real-world scenarios. The problem is addressed from three different perspectives: network routing, node energy profiles, and network management. First, the energy efficiency in a WSN is formulated as a load balancing problem, where the routing layer can diagnose and exploit the WSN topology redundancy to reduce the data traffic processed in critical nodes, independent of their hardware platform, improving their energy consumption and extending the network lifetime. We propose a new routing strategy that extends traditional cost-based routing …

Social Customer Relationship Management In Higher Education, Victorian A. Farnsworth

Open Access Theses

Customer Relationship Management is a concept that has become a requirement for any successful entity to attract and retain desired constituents. It is a set of processes and tools that help track, analyze, and act upon customer related data. Over the last decade, the toolsets have evolved to include social media as another source of information and connection. Nowhere is this information and connection more important than in higher education where globalization and tighter budgets have created a competitive market. This research evaluated the use of this most recent social toolset and its effectiveness in a higher education institution, all …

Hardware Accelerated Redundancy Elimination In Network System, Kelu Diao

Open Access Theses

With the tremendous growth in the amount of information stored on remote locations and cloud systems, many service providers are seeking ways to reduce the amount of redundant information sent across networks by using data de-duplication techniques. Data de-duplication can reduce network traffic without the loss of information, and consequently increase available network bandwidth by reducing redundant traffic. However, due to the heavy computation required for detecting and reducing redundant data transmission, de-duplication itself can become a bottleneck in high capacity links. We completed two parts of work in this research study, Hardware Accelerated Redundancy Elimination in Network Systems (HARENS) …

Extracting Cng Tls/Ssl Artifacts From Lsass Memory, Jacob M. Kambic

Open Access Theses

Currently, there is no publicly accessible, reliable, automated way to forensically decrypt Secure Socket Layer (SSL)/Transport Layer Security (TLS) connections that leverage ephemeral key negotiations as implemented by the modern Windows operating system. This thesis explores the Local Security Authority Sub-System (LSASS) process used for Key Isolation within the Windows 10 operating system in pursuit of identifying artifacts that would allow a solution to that problem, along with any other connection artifacts that could provide forensic value. The end result was the identication of TLS/SSL secrets from the key exchange and contextual artifacts that provide identication of the other party …

User-Centric Workload Analytics: Towards Better Cluster Management, Suhas Raveesh Javagal

Open Access Theses

Effective management of computing clusters and providing a high quality customer support is not a trivial task. Due to rise of community clusters there is an increase in the diversity of workloads and the user demographic. Owing to this and privacy concerns of the user, it is difficult to identify performance issues, reduce resource wastage and understand implicit user demands. In this thesis, we perform in-depth analysis of user behavior, performance issues, resource usage patterns and failures in the workloads collected from a university-wide community cluster and two clusters maintained by a government lab. We also introduce a set of …

Bridging Statistical Learning And Formal Reasoning For Cyber Attack Detection, Kexin Pei

Open Access Theses

Current cyber-infrastructures are facing increasingly stealthy attacks that implant malicious payloads under the cover of benign programs. Current attack detection approaches based on statistical learning methods may generate misleading decision boundaries when processing noisy data with such a mixture of benign and malicious behaviors. On the other hand, attack detection based on formal program analysis may lack completeness or adaptivity when modeling attack behaviors. In light of these limitations, we have developed LEAPS, an attack detection system based on supervised statistical learning to classify benign and malicious system events. Furthermore, we leverage control flow graphs inferred from the system event …

Implementation And Validation Of A Probabilistic Open Source Baseball Engine (Posbe): Modeling Hitters And Pitchers, Rhett Tracy Schaefer

Open Access Theses

This manuscript details the implementation and validation of an open source probabilistic baseball engine (POSBE) that focuses on the hitter and pitcher model of the simulation. The simulation produced outcomes that parallel those observed in actual professional Major League Baseball games. The observed data were taken from the nineteen games played between the New York Yankees (NYY) and Boston Red Sox (BOS) during the 2015 season. The potential hitter/pitcher outcomes of interest were singles, doubles, triples, homeruns, walks, hit-by-pitch, and strikeouts. The nineteen game series was simulated 1000 times, resulting in a total of 19,000 simulations. The eighteen hitters and …

Unsupervised Learning Framework For Large-Scale Flight Data Analysis Of Cockpit Human Machine Interaction Issues, Abhishek B. Vaidya

Open Access Theses

As the level of automation within an aircraft increases, the interactions between the pilot and autopilot play a crucial role in its proper operation. Issues with human machine interactions (HMI) have been cited as one of the main causes behind many aviation accidents. Due to the complexity of such interactions, it is challenging to identify all possible situations and develop the necessary contingencies. In this thesis, we propose a data-driven analysis tool to identify potential HMI issues in large-scale Flight Operational Quality Assurance (FOQA) dataset. The proposed tool is developed using a multi-level clustering framework, where a set of basic …

Enhancing The Campus Experience: Helping International Students To Adapt To North American Campus Life, Qiaoying Wang

Open Access Theses

This thesis investigates how culture adaption topic can be applied to a design solution by enhancing international students experience on North American campus. Each year more than half a million international students enroll in American colleges and universities. Many will spend several years on a campus working toward their degree. Most of them arrive with clear academic goals, but they may have no clue what their social lives will be like. In that case, a common phenomenon that most of the international students need to get along with is called “Culture Shock”, which involves culture and academic adapting difficulties, limited …

Learning In Vision And Robotics, Daniel P. Barrett

Open Access Dissertations

I present my work on learning from video and robotic input. This is an important problem, with numerous potential applications. The use of machine learning makes it possible to obtain models which can handle noise and variation without explicitly programming them. It also raises the possibility of robots which can interact more seamlessly with humans rather than only exhibiting hard-coded behaviors. I will present my work in two areas: video action recognition, and robot navigation. First, I present a video action recognition method which represents actions in video by sequences of retinotopic appearance and motion detectors, learns such models automatically …

Grounding Robot Motion In Natural Language And Visual Perception, Scott Alan Bronikowski

Open Access Dissertations

The current state of the art in military and first responder ground robots involves heavy physical and cognitive burdens on the human operator while taking little to no advantage of the potential autonomy of robotic technology. The robots currently in use are rugged remote-controlled vehicles. Their interaction modalities, usually utilizing a game controller connected to a computer, require a dedicated operator who has limited capacity for other tasks.

I present research which aims to ease these burdens by incorporating multiple modes of robotic sensing into a system which allows humans to interact with robots through a natural-language interface. I conduct …

On The 3d Point Cloud For Human-Pose Estimation, Kai-Chi Chan

Open Access Dissertations

This thesis aims at investigating methodologies for estimating a human pose from a 3D point cloud that is captured by a static depth sensor. Human-pose estimation (HPE) is important for a range of applications, such as human-robot interaction, healthcare, surveillance, and so forth. Yet, HPE is challenging because of the uncertainty in sensor measurements and the complexity of human poses. In this research, we focus on addressing challenges related to two crucial components in the estimation process, namely, human-pose feature extraction and human-pose modeling.

In feature extraction, the main challenge involves reducing feature ambiguity. We propose a 3D-point-cloud feature called …

A Study Of How Chinese Ink Painting Features Can Be Applied To 3d Scenes And Models In Real-Time Rendering, Muning Cao

Open Access Theses

Past research findings addressed mature techniques for non-photorealistic rendering. However, research findings indicate that there is little information dealing with efficient methods to simulate Chinese ink painting features in rendering 3D scenes. Considering that Chinese ink painting has achieved many worldwide awards, the potential to effectively and automatically develop 3D animations and games in this style indicates a need for the development of appropriate technology for the future market.

The goal of this research is about rendering 3D meshes in a Chinese ink painting style which is both appealing and realistic. Specifically, how can the output image appear similar to …

Gesture Based Non-Obstacle Interaction On Mobile Computing Devices For Dirty Working Environment, William B. Huynh

Open Access Theses

The dominant way of interacting with tablets, smartphones, or wearable devices are through touchscreen or touchpad, which requires the user to physically touch the device’s screen. However, in certain situation, for example, a dirty working environment, touching is not ideal or feasible. This study examined a new method that allows for a non-touch interaction by using the devices’ back camera along with simple gesture to simulate mouse clicking. Cameras are used to capture motion-based gestures coupled with object detection, achieving a non-touch interaction. With human subject evaluation, the researcher found that using the back camera on mobile devices for gesture …

A Faster Version Of Louvain Method For Community Detection For Efficient Modeling And Analytics Of Cyber Systems, Sunanda Vivek Shanbhaq

Open Access Theses

Cyber networks are complex networks with various hosts forming the entities of the network and the communication between them forming the edges of the network. Most cyber networks exhibit a community structure. A community is a group of nodes that are densely connected with each other as compared to other nodes in the network. Representing an IP network in the form of communities helps in viewing the network from different levels of granularity and makes the visualization of the network cleaner and more pleasing to the eye. This will help significantly in cyber attack detection in large scale cyber networks. …