Physical Sciences and Mathematics Commons^™

Automating Deep-Sea Video Annotation Using Machine Learning, Hanson Egbert, Lubomir Stanchev, Benjamin Ruttenberg

Computer Science and Software Engineering

As the world explores opportunities to develop offshore renewable energy capacity, there will be a growing need for pre-construction biological surveys and post-construction monitoring in the challenging marine environment. Underwater video is a powerful tool to facilitate such surveys, but the interpretation of the imagery is costly and time-consuming. Emerging technologies have improved automated analysis of underwater video, but these technologies are not yet accurate or accessible enough for widespread adoption in the scientific community or industries that might benefit from these tools. To address these challenges, we developed a website that allows us to: (1) Quickly play and annotate …

Combining Parts Of Speech, Term Proximity, And Query Expansion For Document Retrieval, Lubomir Stanchev, Eric Labouve

Computer Science and Software Engineering

Document retrieval systems recover documents from a database and order them according to their perceived relevance to a user's search query. This is a difficult task for machines to accomplish because there exists a semantic gap between the meaning of the terms in a user's literal query and a user's true intentions. The main goal of this study is to modify the Okapi BM25 document retrieval system to improve search results for textual queries and unstructured, textual corpora. This research hypothesizes that Okapi BM25 is not taking full advantage of the structure of text inside documents. This structure holds valuable …

Characterizing Mental Health And Wellness In Students Across Engineering Disciplines, Andrew Danowitz, Kacey Beddoes

Computer Science and Software Engineering

Anecdotal evidence has long supported the idea that engineering students have lower levels of mental health and wellness than their peers. It is often posited that the large number of courses, low overall retention, difficult courses, and the abundance of intensive engineering projects lead to an unhealthy work-life balance and eventually lower levels of mental health for this population. To date, however, there has been no comprehensive study on the prevalence and types of mental health conditions that afflict engineering students, or any data on whether certain disciplines within engineering may see a greater prevalence of certain mental health conditions …

Semantic Document Clustering Using Information From Wordnet And Dbpedia, Lubomir Stanchev

Computer Science and Software Engineering

Semantic document clustering is a type of unsupervised learning in which documents are grouped together based on their meaning. Unlike traditional approaches that cluster documents based on common keywords, this technique can group documents that share no words in common as long as they are on the same subject. We compute the similarity between two documents as a function of the semantic similarity between the words and phrases in the documents. We model information from WordNet and DBPedia as a probabilistic graph that can be used to compute the similarity between two terms. We experimentally validate our algorithm on the …

Teaching Systems And Robotics In A Four-Week Summer Short Course, Andrew Danowitz, Bridget Benson, Jeremy Edmonds

Computer Science and Software Engineering

This paper describes a four-week summer short-course designed to introduce students with limited hands-on technical experience to the low-level details of embedded systems and robotics. Students start the course using a Raspberry Pi 3 to learn the basics of Linux and programming, and end the course by competing in a capture-the-flag type competition with the web-configurable GPS-guided autonomous robots they designed and tested in the course. Throughout the course, students are introduced to programming languages including Python and PHP, advanced programming concepts such as using sockets for inter-process communication, data interchange formats such as JSON, basic API development, system concepts …

Group Work Versus Informal Collaborations: Student Perspectives, Andrew Danowitz

Computer Science and Software Engineering

A substantial body of research exists showing that, when implemented correctly, the use of group work in a class can improve student learning outcomes. When implemented incorrectly, however, group-based assignments can lead to dysfunction and inter-personal conflicts that can hamper overall student success. This problem can be especially acute in first and second year engineering fundamentals courses where advanced students who learn the concepts faster may end up completing—and reaping the benefits of—a lions-share of the group work. As the course material starts to build on itself, those students who initially underperformed in their group may lack the understanding to …

Implementing Semantic Document Search Using A Bounded Random Walk In A Probabilistic Graph, Lubomir Stanchev

Computer Science and Software Engineering

Given a set of documents and an input query that is expressed using natural language, the problem of document search is retrieving all relevant documents ordered by the degree of relevance. Semantic document search fetches not only documents that contain words from the input query, but also documents that are semantically relevant. For example, the query "friendly pets" will consider documents that contain the words "dog" and "cat", among others. One way to implement semantic search is to use a probabilistic graph in which the input query is connected to the documents through paths that contain semantically similar words and …

Fine-Tuning An Algorithm For Semantic Document Clustering Using A Similarity Graph, Lubomir Stanchev

Computer Science and Software Engineering

In this article, we examine an algorithm for document clustering using a similarity graph. The graph stores words and common phrases from the English language as nodes and it can be used to compute the degree of semantic similarity between any two phrases. One application of the similarity graph is semantic document clustering, that is, grouping documents based on the meaning of the words in them. Since our algorithm for semantic document clustering relies on multiple parameters, we examine how fine-tuning these values affects the quality of the result. Specifically, we use the Reuters-21578 benchmark, which contains 11,362 newswire stories …

Leveraging The Final Project To Improve Student Motivation In Introductory Digital Design Courses, Andrew Danowitz

Computer Science and Software Engineering

Student retention rates in engineering, especially among traditionally underrepresented groups, remain an obstacle to training a large, diverse engineering workforce. The NSF's Science and Engineering Indicators 2016 indicate that of students entering college with an intent to major in engineering, only 63% graduate with an engineering degree [1]. With research suggesting that misperceptions or a lack of knowledge about what work in a certain field is like can deter students from studying that discipline [2], [3], it is possible that providing a meaningful project experience at the introductory level could provide a strong positive impact on retention rates. This could …

Creating A Probabilistic Model For Wordnet, Lubomir Stanchev

Computer Science and Software Engineering

We present a probabilistic model for extracting and storing information from WordNet and the British National Corpus. We map the data into a directed probabilistic graph that can be used to compute the conditional probability between a pair of words from the English language. For example, the graph can be used to deduce that there is a 10% probability that someone who is interested in dogs is also interested in the word “canine”. We propose three ways for computing this probability, where the best results are achieved when performing multiple random walks in the graph. Unlike existing approaches that only …

Leveraging New Platforms To Provide Students With A Realistic Soc Design Experience, Andrew Danowitz, Antonio M. Leija

Computer Science and Software Engineering

Recently there have been a slew of digital design products released that promise to simplify the task of giving students a real-world System-on-Chip (SoC) design experience. These “programmable SoCs” from companies such as Xilinx, Cypress, and Altera combine modern multi-core ARM processors connected to an FPGA through a widely used SoC interconnect standard. This paper discusses a Real Time Embedded System Course I designed that uses the Xilinx Zynq platform to give students first-hand experience with modern System-on-Chip design methodologies and the challenges that designers face in both hardware and software bring-up for a modern IP-based design.

The first portion …

Creating A Probabilistic Graph For Wordnet Using Markov Logic Network, Lubomir Stanchev

Computer Science and Software Engineering

The paper shows how to create a probabilistic graph for WordNet. A node is created for every word and phrase in WordNet. An edge between two nodes is labeled with the probability that a user that is interested in the source concept will also be interested in the destination concept. For example, an edge with weight 0.3 between “canine” and “dog” indicates that there is a 30% probability that a user who searches for “canine” will be interested in results that contain the word “dog”. We refer to the graph as probabilistic because we enforce the constraint that the sum …

Semantic Document Clustering Using A Similarity Graph, Lubomir Stanchev

Computer Science and Software Engineering

Document clustering addresses the problem of identifying groups of similar documents without human supervision. Unlike most existing solutions that perform document clustering based on keywords matching, we propose an algorithm that considers the meaning of the terms in the documents. For example, a document that contains the words "dog" and "cat" multiple times may be placed in the same category as a document that contains the word "pet" even if the two documents share only noise words in common. Our semantic clustering algorithm is based on a similarity graph that stores the degree of semantic relationship between terms (extracted from …

Building Conflict-Free Fft Schedules, Stephen Richardson, Dejan Markovic, Andrew Danowitz, John Brunhaver, Mark Horowitz

Computer Science and Software Engineering

A conflict-free schedule lets an FFT run to completion without ever having to pause for memory-conflict resolution. We show how to build such schedules for FFTs having any number of butterfly units B operating at any radix R, transforming any number of datapoints D. Our algorithm works for FFT datapaths with or without pipeline overlap, and for memory banks having any number of access ports. Specifically, it enables construction of conflict-free schedules using single-ported memory banks, which require less area than more traditional multi-ported designs.

Measuring The Strength Of The Semantic Relationship Between Words, Lubomir Stanchev

Computer Science and Software Engineering

We propose a novel way for extracting the strength of the semantic relationship between words from semi-structured sources, such as WordNet. Unlike existing approaches that only explore the structured information (e.g., the hypernym relationship in WordNet), we present a framework that allows us to utilize all available information, including natural text descriptions. Our approach constructs a similarity graph that stores the strength of the semantic relationship between words. Specifically, an edge between two words describes the probability that someone who is interested in resources about the first word will be also interested in resources about the second word. Note that …

Semantic Search Using A Similarity Graph, Lubomir Stanchev

Computer Science and Software Engineering

Given a set of documents and an input query that is expressed in a natural language, the problem of document search is retrieving the most relevant documents. Unlike most existing systems that perform document search based on keywords matching, we propose a search method that considers the meaning of the words in the query and the document. As a result, our algorithm can return documents that have no words in common with the input query as long as the documents are relevant. For example, a document that contains the words “Ford”, “Chrysler” and “General Motors” multiple times is surely relevant …

A Heterogeneous Compute Solution For Optimized Genomic Selection Analysis, Trevor Devore, Scott Kenneth Winkleblack, Bruce Golden, Chris Lupo

Computer Science and Software Engineering

This paper presents a heterogeneous computing solution for an optimized genetic selection analysis tool, GenSel. GenSel can be used to efficiently infer the effects of genetic markers on a desired trait or to determine the genomic estimated breeding values (GEBV) of genotyped individuals. To predict which genetic markers are informational, GenSel performs Bayesian inference using Gibbs sampling, a Markov Chain Monte Carlo (MCMC) algorithm. Parallelizing this algorithm proves to be a technically challenging problem because there exists a loop carried dependence between each iteration of the Markov chain. The approach presented in this paper exploits both task-level parallelism (TLP) and …

Exploring Abstract Interfaces In System-On-Chip Integration, Andrew Danowitz

Computer Science and Software Engineering

Modern mobile devices are marvels of computation. They can encode high defnition video, processing and compressing over 350MB/s of image data in real time. They have no trouble driving displays with as much resolution as a full laptop, and smartphone manufacturers boast of running games with "console quality" graphics. Mobile devices pack all of this computational power into a 12\ handheld package by integrating a number of specialized hardware accelerators (IP) along with conventional CPU and GPUs in a system on chip (SoC). Unfortunately, creating these specialized systems is becoming increasingly expensive. Since hardware accelerators come from a number of …

Creating A Phrase Similarity Graph From Wikipedia, Lubomir Stanchev

Computer Science and Software Engineering

The paper addresses the problem of modeling the relationship between phrases in English using a similarity graph. The mathematical model stores data about the strength of the relationship between phrases expressed as a decimal number. Both structured data from Wikipedia, such as that the Wikipedia page with title “Dog” belongs to theWikipedia category “Domesticated animals”, and textual descriptions, such as that the Wikipedia page with title “Dog” contains the word “wolf” thirty one times are used in creating the graph. The quality of the graph data is validated by comparing the similarity of pairs of phrases using our software that …

Twill: A Hybrid Microcontroller-Fpga Framework For Parallelizing Single-Threaded C Programs, Douglas S. Gallatin, Aaron Keen, Chris Lupo, John Y. Oliver

Computer Science and Software Engineering

Increasingly System-On-A-Chip platforms which incorporate both microprocessors and re-programmable logic are being utilized across several fields ranging from the automotive industry to network infrastructure. Unfortunately, the development tools accompanying these products leave much to be desired, requiring knowledge of both traditional embedded systems languages like C and hardware description languages like Verilog. We propose to bridge this gap with Twill, a truly automatic hybrid compiler that can take advantage of the parallelism inherent in these platforms. Twill can extract long-running threads from single threaded C code and distribute these threads across the hardware and software domains to more fully utilize …

Chapter 1 Engineering Justice, Joe Grimes, Mark Grimes

Computer Science and Software Engineering

No abstract provided.

Chapter 20 The Hybrid Course: Facilitating Learning Through Social Interaction Technologies, Lorraine D. Jackson, Joe Grimes

Computer Science and Software Engineering

This chapter surveys the benefits and challenges of hybrid courses, which blend face-to-face instruction with online learning, and opportunities provided by the introduction of Web-based social interaction technologies. It discusses the pedagogical implications of various Web 2.0 tools: that is, asynchronous discussion boards, blogs, wikis, podcasts, RSS, e-portfolios, folksonomies, educational gaming, data mashups, and simulations. The authors argue that as hybrid courses continue to evolve to meet the needs of students, instructors, and institutions of higher learning, the integration of Web 2.0 applications in a hybrid model requires thoughtful course design, clear educational objectives, and carefully planned activities.

Chapter 13 Access Within The Classroom Through Universal Design For Learning And Key Learning Elements, Joe Grimes, Mark Grimes

Computer Science and Software Engineering

No abstract provided.

High Performance Regional Ocean Modeling With Gpu Acceleration, Ian Panzer, Spencer Lines, Jason Mak, Paul Choboter, Chris Lupo

Computer Science and Software Engineering

The Regional Ocean Modeling System (ROMS) is an open-source, free-surface, primitive equation ocean model used by the scientific community for a diverse range of applications [1]. ROMS employs sophisticated numerical techniques, including a split-explicit time-stepping scheme that treats the fast barotropic (2D) and slow baroclinic (3D) modes separately for improved efficiency [2]. ROMS also contains a suite of data assimilation tools that allow the user to improve the accuracy of a simulation by incorporating observational data. These tools are based on four dimensional variational methods [3], which generate reliable results, but require more computational resources than without any assimilation of …

Towards Three-Dimensional Underwater Mapping Without Odometry, Alistair Dobke, Joshua Vasquez, Lauren Lieu, Ben Chasnov, Christopher Clark, Ian Dunn, Zoë J. Wood, Timothy Gambin

Computer Science and Software Engineering

This paper presents a method for the creation of three-dimensional maps of underwater cisterns and wells using a submersible robot equipped with two scanning sonars and a compass. Previous work in this area utilized a particle filter to perform offline simultaneous localization and mapping (SLAM) in two dimensions using a single sonar [11]. This work utilizes scan matching and incorporates an additional sonar that scans in a perpendicular plane. Given a set of overlapping horizontal and vertical sonar scans, an algorithm was implemented to map underwater chambers by matching sets of scans using a weighted iterative closest point (ICP) method. …

Wireless Cloud Architecture Based On Thin Clients And Ontologies, Todor Cooklev, Lubomir Stanchev, Chao Chen

Computer Science and Software Engineering

Recently, several researchers have discovered the need for radios to use description techniques for the objects in the wireless realm. The concept of RF field-programmable analog array (FPAA) was also proposed recently and the lack of hardware abstractions was identified as a problem. We propose a hardware abstraction for RF FPAAs, which enables an open RF-digital interface. We advance the concept of wireless thin clients. These clients are connected to the cloud using the open RF-digital interface. We describe the architecture of a comprehensive wireless ontology.

An Evaluation Of Interactive Test-Driven Labs With Webide In Cs0, David S. Janzen, John Clements, Michael Hilton

Computer Science and Software Engineering

WebIDE is a framework that enables instructors to develop and deliver online lab content with interactive feedback. The ability to create lock-step labs enables the instructor to guide students through learning experiences, demonstrating mastery as they proceed. Feedback is provided through automated evaluators that vary from simple regular expression evaluation to syntactic parsers to applications that compile and run programs and unit tests. This paper describes WebIDE and its use in a CS0 course that taught introductory Java and Android programming using a test-driven learning approach. We report results from a controlled experiment that compared the use of dynamic WebIDE …

Breaking Weak 1024-Bit Rsa Keys Using Cuda, Kerry Scharfglass, Darrin Weng, Joseph White, Christopher Lupo

Computer Science and Software Engineering

An exploit involving the greatest common divisor (GCD) of RSA moduli was recently discovered [1]. This paper presents a tool that can efficiently and completely compare a large number of 1024-bit RSA public keys, and identify any keys that are susceptible to this weakness. NVIDIA's graphics processing units (GPU) and the CUDA massively-parallel programming model are powerful tools that can be used to accelerate this tool. Our method using CUDA has a measured performance speedup of 27.5 compared to a sequential CPU implementation, making it a more practical method to compare large sets of keys. A computation for finding GCDs …

Pyroprinting Sensitivity Analysis On The Gpu, Douglas Brandt, Aldrin Montana, Bob Somers, Alex Dekhtyar, Christopher Lupo, Michael Black, Anya Goodman, Christopher Kitts

Computer Science and Software Engineering

Microbial Source Tracking (MST) is a field in which microbial strains are identified and associated with a specific host source (e.g., human, canine, avian, etc). Identifying the hosts of microbial strains lies at the heart of many studies of bacterial contamination in the environment. Being able to determine which host species is responsible, e.g., for fecal contamination of a creek, allows the parties involved to develop specific measures for addressing the contamination. The paper presents an in-silico study to investigate the sensitivity of the pyroprinting method. Given a collection of possible DNA sequences that can be found in the sequenced …

Building Semantic Corpus From Wordnet, Lubomir Stanchev

Computer Science and Software Engineering

We propose a novel methodology for extracting semantic similarity knowledge from semi-structured sources, such as WordNet. Unlike existing approaches that only explore the structured information (e.g., the hypernym relationship in WordNet), we present a framework that allows us to utilize all available information, including natural language descriptions. Our approach constructs a semantic corpus. It is represented using a graph that models the relationship between phrases using numbers. The data in the semantic corpus can be used to measure the similarity between phrases, the similarity between documents, or to perform a semantic search in a set of documents that uses the …