Data-Driven Abstraction,
2017
Louisiana State University and Agricultural and Mechanical College
Data-Driven Abstraction, Vivian Mankau Ho
LSU Master's Theses
Given a program analysis problem that consists of a program and a property of interest, we use a data-driven approach to automatically construct a sequence of abstractions that approach an ideal abstraction suitable for solving that problem. This process begins with an infinite concrete domain that maps to a finite abstract domain defined by statistical procedures resulting in a clustering mixture model. Given a set of properties expressed as formulas in a restricted and bounded variant of CTL, we can test the success of the abstraction with respect to a predefined performance level. In addition, we can perform iterative abstraction-refinement …
Improving Disciplinary Literacy In An Electronics Course,
2017
CUNY New York City College of Technology
Improving Disciplinary Literacy In An Electronics Course, Ohbong Kwon, Juanita C. But, Sunghoon Jang
Publications and Research
Electronics (EMT1255) is a required course for the Associate Degree in Applied Science (AAS) in Electromechanical Engineering Technology (EMT) at New York City College of Technology. EMT1255 introduces semiconductor devices and their applications in electronic-circuits. Students are expected to understand the structures and principles of semiconductor devices and the configuration and principles of basic electronic circuits. They also learn to analyze and design electronic circuits. In the lab setting, they acquire troubleshooting knowledge and hands-on technical skills. In this reading intensive course, students need to read the lab manual and a textbook of over 700 pages. Therefore, reading and understanding …
Compiler And Runtime Optimization Techniques For Implementation Scalable Parallel Applications,
2017
Louisiana State University and Agricultural and Mechanical College
Compiler And Runtime Optimization Techniques For Implementation Scalable Parallel Applications, Zahra Khatami
LSU Doctoral Dissertations
The compiler is able to detect the data dependencies in an application and is able to analyze the specific sections of code for parallelization potential. However, all of these techniques provided by a compiler are usually applied at compile time, so they rely on static analysis, which is insufficient for achieving maximum parallelism and desired application scalability. These compiler techniques should consider both the static information gathered at compile time and dynamic analysis captured at runtime about the system to generate a safe parallel application. On the other hand, runtime information is often speculative. Solely relying on it doesn't guarantee …
Dynamic Adversarial Mining - Effectively Applying Machine Learning In Adversarial Non-Stationary Environments.,
2017
University of Louisville
Dynamic Adversarial Mining - Effectively Applying Machine Learning In Adversarial Non-Stationary Environments., Tegjyot Singh Sethi
Electronic Theses and Dissertations
While understanding of machine learning and data mining is still in its budding stages, the engineering applications of the same has found immense acceptance and success. Cybersecurity applications such as intrusion detection systems, spam filtering, and CAPTCHA authentication, have all begun adopting machine learning as a viable technique to deal with large scale adversarial activity. However, the naive usage of machine learning in an adversarial setting is prone to reverse engineering and evasion attacks, as most of these techniques were designed primarily for a static setting. The security domain is a dynamic landscape, with an ongoing never ending arms race …
Computer-Aided Detection Of Pathologically Enlarged Lymph Nodes On Non-Contrast Ct In Cervical Cancer Patients For Low-Resource Settings,
2017
The University of Texas MD Anderson Cancer Center UTHealth Graduate School of Biomedical Sciences
Computer-Aided Detection Of Pathologically Enlarged Lymph Nodes On Non-Contrast Ct In Cervical Cancer Patients For Low-Resource Settings, Brian M. Anderson, Laurence E. Court, Ann Klopp, Stephen F. Kry, Jennifer Johnson, Erik Cressman, Arvind Rao, Jinzhong Yang
Dissertations and Theses (Open Access)
The mortality rate of cervical cancer is approximately 266,000 people each year, and 70% of the burden occurs in Low- and Middle- Income Countries (LMICs). Radiation therapy is the primary modality for treatment of locally advanced cervical cancer cases. In the absence of high quality diagnostic imaging needed to identify nodal metastasis, many LMIC sites treat standard pelvic fields, failing to include node metastasis outside of the field and/or to boost lymph nodes in the abdomen and pelvis. The first goal of this project was to create a program which automatically identifies positive cervical cancer lymph nodes on non-contrast daily …
Prediction Of Graduation Delay Based On Student Characterisitics And Performance,
2017
University of New Mexico - Main Campus
Prediction Of Graduation Delay Based On Student Characterisitics And Performance, Tushar Ojha
Electrical and Computer Engineering ETDs
A college student's success depends on many factors including pre-university characteristics and university student support services. Student graduation rates are often used as an objective metric to measure institutional effectiveness. This work studies the impact of such factors on graduation rates, with a particular focus on delay in graduation. In this work, we used feature selection methods to identify a subset of the pre-institutional features with the highest discriminative power. In particular, Forward Selection with Linear Regression, Backward Elimination with Linear Regression, and Lasso Regression were applied. The feature sets were selected in a multivariate fashion. High school GPA, ACT …
Distributed Knowledge Discovery For Diverse Data,
2017
University of New Mexico
Distributed Knowledge Discovery For Diverse Data, Hossein Hamooni
Computer Science ETDs
In the era of new technologies, computer scientists deal with massive data of size hundreds of terabytes. Smart cities, social networks, health care systems, large sensor networks, etc. are constantly generating new data. It is non-trivial to extract knowledge from big datasets because traditional data mining algorithms run impractically on such big datasets. However, distributed systems have come to aid this problem while introducing new challenges in designing scalable algorithms. The transition from traditional algorithms to the ones that can be run on a distributed platform should be done carefully. Researchers should design the modern distributed algorithms based on the …
One-To-Cloud One-Time Pad Data Encryption: Introducing Virtual Prototyping With Pspice,
2017
Technological University Dublin
One-To-Cloud One-Time Pad Data Encryption: Introducing Virtual Prototyping With Pspice, Paul Tobin, Lee Tobin, Roberto Gandia Blanquer Dr, Michael Mckeever, Jonathan Blackledge
Conference papers
In this paper, we examine the design and application of a one-time pad encryption system for protecting data stored in the Cloud. Personalising security using a one-time pad generator at the client-end protects data from break-ins, side-channel attacks and backdoors in public encryption algorithms. The one-time pad binary sequences were obtained from modified analogue chaos oscillators initiated by noise and encoded client data locally. Specific ``one-to-Cloud'' storage applications returned control back to the end user but without the key distribution problem normally associated with one-time pad encryption. Development of the prototype was aided by ``Virtual Prototyping'' in the latest version …
Multiple-Phase Modeling Of Degradation Signal For Condition Monitoring And Remaining Useful Life Prediction,
2017
Chapman University
Multiple-Phase Modeling Of Degradation Signal For Condition Monitoring And Remaining Useful Life Prediction, Yuxin Wen, Jianguo Wu, Yuan Yuan
Engineering Faculty Articles and Research
Remaining useful life prediction plays an important role in ensuring the safety, availability, and efficiency of various engineering systems. In this paper, we propose a flexible Bayesian multiple-phase modeling approach to characterize degradation signals for prognosis. The priors are specified with a novel stochastic process and the multiple-phase model is formulated to a novel state-space model to facilitate online monitoring and prediction. A particle filtering algorithm with stratified sampling and partial Gibbs resample-move strategy is developed for online model updating and residual life prediction. The advantages of the proposed method are demonstrated through extensive numerical studies and real case studies.
A Survey Of Addictive Software Design,
2017
California Polytechnic State University at San Luis Obispo
A Survey Of Addictive Software Design, Chauncey J. Neyman
Computer Science and Software Engineering
The average smartphone owner checks their phone more than 150 times per day. As of 2015, 62% of smartphone users had used their phone to look up information about a health condition, while 57% had used their phone to do online banking. Mobile platforms have become the dominant medium of human-computer interaction. So how have these devices established themselves as our go to connection to the Internet? The answer lies in addictive design. Software designers have become well versed in creating software that captivates us at a primal level. In this article, we survey addictive software design strategies, their bases …
Djukebox: A Mobile Application Senior Project,
2017
California Polytechnic State University, San Luis Obispo
Djukebox: A Mobile Application Senior Project, Alexander M. Mitchell
Computer Science and Software Engineering
I’m going to discuss the process used to research, design, and develop a mobile application to handle song requests from patrons to disc jockeys. The research phase was completed in the first half of the project, during CSC-491, along with much of the design. The rest of the design and all of the development was completed during CSC-492. Once development began there were times when reverting back to the design phase was needed, which became apparent as more was learned about the mobile platform chosen for development, Android, and the backend server utilized, Google Firebase. Ultimately the project was purely …
Slither.Io Deep Learning Bot,
2017
California Polytechnic State University, San Luis Obispo
Slither.Io Deep Learning Bot, James Caudill
Computer Engineering
Recent advances in deep learning and computer vision techniques and algorithms have inspired me to create a model application. The game environment used is Slither.io. The system has no previous understanding of the game and is able to learn its surroundings through feature detection and deep learning. Contrary to other agents, my bot is able to dynamically learn and react to its environment. It operates extremely well in early game, with little enemy encounters. It has difficulty transitioning to middle and late game due to limited training time. I will continue to develop this algorithm.
Diy Grip Tape Website,
2017
California Polytechnic State University, San Luis Obispo
Diy Grip Tape Website, Jason E. Krein
Computer Science and Software Engineering
The goal of this senior project was to create an easy to use website that will allow people to design and order their own custom skateboard grip tape. Custom skateboard decks are a large business, however the top, more visible, part of the board is largely ignored by custom shops. With the help of a local entrepreneur, I aim to enable skateboarders the ability to get custom grip tape shapes that they can stick on their board to spice it up from the normal black tape that everyone uses. The website was completed over the course of 4 months, in …
Gridiron-Gurus Final Report: Fantasy Football Performance Prediction,
2017
California Polytechnic State University, San Luis Obispo
Gridiron-Gurus Final Report: Fantasy Football Performance Prediction, Kyle Tanemura, Michael Li, Erica Dorn, Ryan Mckinney
Computer Science and Software Engineering
Gridiron Gurus is a desktop application that allows for the creation of custom AI profiles to help advise and compete against in a Fantasy Football setting. Our AI are capable of performing statistical prediction of players on both a season long and week to week basis giving them the ability to both draft and manage a fantasy football team throughout a season.
Underwater Computer Vision - Fish Recognition,
2017
California Polytechnic State University, San Luis Obispo
Underwater Computer Vision - Fish Recognition, Spencer Chang, Austin Otto
Computer Engineering
The Underwater Computer Vision – Fish Recognition project includes the design and implementation of a device that can withstand staying underwater for a duration of time, take pictures of underwater creatures, such as fish, and be able to identify certain fish. The system is meant to be cheap to create, yet still able to process the images it takes and identify the objects in the pictures with some accuracy. The device can output its results to another device or an end user.
Multispectral Identification Array,
2017
California Polytechnic State University, San Luis Obispo
Multispectral Identification Array, Zachary D. Eagan
Computer Engineering
The Multispectral Identification Array is a device for taking full image spectroscopy data via the illumination of a subject with sixty-four unique spectra. The array combines images under the illumination spectra to produce an approximate reflectance graph for every pixel in a scene. Acquisition of an entire spectrum allows the array to differentiate objects based on surface material. Spectral graphs produced are highly approximate and should not be used to determine material properties, however the output is sufficiently consistent to allow differentiation and identification of previously sampled subjects. While not sufficiently advanced for use as a replacement to spectroscopy the …
Sublimesurf,
2017
California Polytechnic State University, San Luis Obispo
Sublimesurf, Nathan Sfard, Karis Russell
Computer Engineering
Surf conditions change rapidly day to day and location to location, which forces modern day surfers to utilize online forecasts and obtain a detailed knowledge of the places they want to surf. To ease this pain, we are developing SublimeSurf, an iOS application that will keep track of the current surf conditions and allow users to rate aspects of the surf. We plan to use this rating data in combination with surf forecast data available online to notify a user when conditions look favorable, based on their previous ratings. We also intend to mine the data submitted by all users …
Farmbot Rfid Integration,
2017
California Polytechnic State University, San Luis Obispo
Farmbot Rfid Integration, Laura R. Swart
Computer Engineering
The purpose of this project is to assist the company FarmBot improve their product by adding RFID tracking to the FarmBot robot. RFID tracking will allow the robot to select and pick up tool heads without any user interference.
Daily Dose,
2017
California Polytechnic State University, San Luis Obispo
Daily Dose, Ken H. Yasui, Joey M. Angeja
Computer Engineering
The project goal is to develop a medication and vitamin management device that will sort and dispense pre-configured amounts of pills at designated times . The main clientele of this device is the elderly community with a secondary client base of the general public. The entire system is designed from scratch, powered by US standard line voltage. The main functionalities of the device are the ability to store multiple types of pills and the ability to accurately handle user input and data transfer. The two engineering specifications that were not met included the desired pill pick up rate and dimensions …
Micro-Spi Sediment Profile Imaging Micro-Inspector,
2017
California Polytechnic State University, San Luis Obispo
Micro-Spi Sediment Profile Imaging Micro-Inspector, Andrew P. Corvin, Caleb T. Davies, Matt R. Ferrari
Mechanical Engineering
This project was proposed by Dr. Brian Paavo through a desire to more easily study the benthic sediment layers of the ocean. To do so, he asked us to build a simple and compact machine for use in sediment profile imagery (SPI). Although devices like this already exist, they are all large scale devices that require a ship with a crane to deploy, which is expensive and time consuming. Instead, he desired a “micro” SPI, which is capable of being deployed from a small vessel that can easily navigate shallow waters. Our interpretation of these requirements was as follows: a …
