Computer Sciences Commons^™

Stochastic Multiple Gradient Decent For Inferring Action-Based Network Generators, Qian Wu, Viplove Arora, Mario Ventresca

The Summer Undergraduate Research Fellowship (SURF) Symposium

Networked systems, like the internet, social networks etc., have in recent years attracted the attention of researchers, specifically to develop models that can help us understand or predict the behavior of these systems. A way of achieving this is through network generators, which are algorithms that can synthesize networks with statistically similar properties to a given target network. Action-based Network Generators (ABNG)is one of these algorithms that defines actions as strategies for nodes to form connections with other nodes, hence generating networks. ABNG is parametrized using an action matrix that assigns an empirical probability distribution to vertices for choosing specific …

Haptic Foot Feedback For Kicking Training In Virtual Reality, Hank Huang, Hong Tan

The Summer Undergraduate Research Fellowship (SURF) Symposium

As means to further supplement athletic performances increases, virtual reality is becoming helpful to sports in terms of cognitive training such as reaction, mentality, and game strategies. With the aid of haptic feedback, interaction with virtual objects increases by another dimension, in addition to the presence of visual and auditory feedback. This research presents an integrated system of a virtual reality environment, motion tracking system, and a haptic unit designed for the dorsal foot. The prototype simulates a scenario of virtual kicking and returns haptic response upon collision between the user’s foot and virtual object. The overall system was evaluated …

Classifying Pattern Formation In Materials Via Machine Learning, Lukasz Burzawa, Shuo Liu, Erica W. Carlson

The Summer Undergraduate Research Fellowship (SURF) Symposium

Scanning probe experiments such as scanning tunneling microscopy (STM) and atomic force microscopy (AFM) on strongly correlated materials often reveal complex pattern formation that occurs on multiple length scales. We have shown in two disparate correlated materials that the pattern formation is driven by proximity to a disorder-driven critical point. We developed new analysis concepts and techniques that relate the observed pattern formation to critical exponents by analyzing the geometry and statistics of clusters observed in these experiments and converting that information into critical exponents. Machine learning algorithms can be helpful correlating data from scanning probe experiments to theoretical models …

Gdd(Growth Degree Day) Module For Vinsense Visual Analytics System, Pradeep K. Lam, David Ebert , Phd, Jiawei Zhang

The Summer Undergraduate Research Fellowship (SURF) Symposium

Limited resources and increasing costs require vineyards to develop optimized methods of planting, growing, and harvesting crops in order to ensure max yield and stay competitive in the marketplace. Data from sensors planted within the soil paired with weather reports and observation data from farmers could help develop competitive farming strategies. While automatic computation models are usually a black box that cannot explain how the input data are transformed into output, the farmers require an approach that allows them to interactively manipulate and supervise the computation process. The VinSense project was developed for this purpose. In this paper, we focus …

Analyzing Sports Training Data With Machine Learning Techniques, Rehana Mahfuz, Zeinab Mourad, Aly El Gamal

The Summer Undergraduate Research Fellowship (SURF) Symposium

In the sports industry, there has not been enough effort in analyzing the personalized monitoring data of athletes collected during training sessions. This research is an attempt to find meaningful patterns in the Purdue Women’s Soccer training data that could help the coach design more efficient training sessions. We are specifically interested in studying this problem as an unsupervised learning problem. Our initial attempt is to cluster the players as well as drills into groups using k-means, c-means and spectral clustering algorithms, combined with feature transformation and reduction steps. These basic algorithms serve as a benchmark to measure performance improvements …

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 …

Improving Cloud Middlebox Infrastructure For Online Services, Rohan S. Gandhi

Open Access Dissertations

Middleboxes are an indispensable part of the datacenter networks that provide high availability, scalability and performance to the online services. Using load balancer as an example, this thesis shows that the prevalent scale-out middlebox designs using commodity servers are plagued with three fundamental problems: (1) The server-based layer-4 middleboxes are costly and inflate round-trip-time as much as 2x by processing the packets in software. (2) The middlebox instances cause traffic detouring en route from sources to destinations, which inflates network bandwidth usage by as much as 3.2x and can cause transient congestion. (3) Additionally, existing cloud providers do not support …

Tool Comparison Of Semantic Parsers, Robert Hinh

Open Access Theses

Natural Language Processing (NLP) is a vital aspect for artificial intelligence systems to achieve integration into human lives, which has been a goal for researchers in this industry. While NLP focuses on an array of problems, semantic parsing will be specifically focused on throughout this paper. These parsers have been considerably targeted for improvement through the scientific community and demand for semantic parsers that achieve high accuracy has increased. There have been many approaches developed for this specific purpose and in this paper, a deep analysis was performed to compare the performance of semantic parsing systems. The implications of this …

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 …

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. …

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 …

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 …

A Study Of Security Issues Of Mobile Apps In The Android Platform Using Machine Learning Approaches, Lei Cen

Open Access Dissertations

Mobile app poses both traditional and new potential threats to system security and user privacy. There are malicious apps that may do harm to the system, and there are mis-behaviors of apps, which are reasonable and legal when not abused, yet may lead to real threats otherwise. Moreover, due to the nature of mobile apps, a running app in mobile devices may be only part of the software, and the server side behavior is usually not covered by analysis. Therefore, direct analysis on the app itself may be incomplete and additional sources of information are needed. In this dissertation, we …

Knowledge Modeling Of Phishing Emails, Courtney Falk

Open Access Dissertations

This dissertation investigates whether or not malicious phishing emails are detected better when a meaningful representation of the email bodies is available. The natural language processing theory of Ontological Semantics Technology is used for its ability to model the knowledge representation present in the email messages. Known good and phishing emails were analyzed and their meaning representations fed into machine learning binary classifiers. Unigram language models of the same emails were used as a baseline for comparing the performance of the meaningful data. The end results show how a binary classifier trained on meaningful data is better at detecting phishing …

Interactive Logical Analysis Of Planning Domains, Rajesh Kalyanam

Open Access Dissertations

Humans exhibit a significant ability to answer a wide range of questions about previously unencountered planning domains, and leverage this ability to construct “general-purpose'' solution plans for the domain.

The long term vision of this research is to automate this ability, constructing a system that utilizes reasoning to automatically verify claims about a planning domain. The system would use this ability to automatically construct and verify a generalized plan to solve any planning problem in the domain. The goal of this thesis is to start with baseline results from the interactive verification of claims about planning domains and develop the …

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 …

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 …

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 …

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 …

Texture Modelling Using Convolutional Neural Networks, Leon A. Gatys, Alexander S. Ecker, Matthias Bethge

MODVIS Workshop

We introduce a new model of natural textures based on the feature spaces of convolutional neural networks optimised for object recognition. Samples from the model are of high perceptual quality demonstrating the generative power of neural networks trained in a purely discriminative fashion. Within the model, textures are represented by the correlations between feature maps in several layers of the network. We show that across layers the texture representations increasingly capture the statistical properties of natural images while making object information more and more explicit. Extending this framework to texture transfer, we introduce A Neural Algorithm of Artistic Style that …

Focusing On Selection For Fixation, John K. Tsotsos, Calden Wloka, Yulia Kotseruba

MODVIS Workshop

Building on our presentation at MODVIS 2015, we continue in our quest to discover a functional, computational, explanation of the relationship among visual attention, interpretation of visual stimuli, and eye movements, and how these produce visual behavior. Here, we focus on one component, how selection is accomplished for the next fixation. The popularity of saliency map models drives the inference that this is solved; we suggested otherwise at MODVIS 2015. Here, we provide additional empirical and theoretical arguments. We then develop arguments that a cluster of complementary, conspicuity representations drive selection, modulated by task goals and history, leading to a …

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 …

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 …

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 …

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 …

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 …

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 …

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 …