Computer Engineering Commons^™

Extending Structural Learning Paradigms For High-Dimensional Machine Learning And Analysis, Christopher Todd Symons

Doctoral Dissertations

Structure-based machine-learning techniques are frequently used in extensions of supervised learning, such as active, semi-supervised, multi-modal, and multi-task learning. A common step in many successful methods is a structure-discovery process that is made possible through the addition of new information, which can be user feedback, unlabeled data, data from similar tasks, alternate views of the problem, etc. Learning paradigms developed in the above-mentioned fields have led to some extremely flexible, scalable, and successful multivariate analysis approaches. This success and flexibility offer opportunities to expand the use of machine learning paradigms to more complex analyses. In particular, while information is often …

Using Player Profiling To Enhance Dynamic Difficulty Adjustment In Video Games, Aaron Burke

Computer Engineering

Video games have certainly come a long way since the days of pong. From humble beginnings of the first arcade machines they have bloomed into a multi-billion dollar industry and a global force to be reckoned with. Just like with movies there are enough genres out there to fit any demographic of gamer, and that’s not even just the game’s content but also the gameplay.

Unlike other types of media though, games are meant to be interacted with and played, which brings up new issues with accessibility and keeping things interesting for different levels of skill. Dynamic game difficulty adjustment …

The Quickiecomposer Android Application, Brigit Elizabeth Hawley

Liberal Arts and Engineering Studies

The QuickieComposer application is a program intended for use on Android Devices. Designed for the composer on the go, the QuickieComposer app is perfect for those “in the moment” compositions. In the following document, the functionality and development of the first version of the QuickieComposer application is explained.

Amaethon – A Web Application For Farm Management And An Assessment Of Its Utility, Tyler Yero

Master's Theses

Amaethon is a web application that is designed for enterprise farm management. It takes a job typically performed with spreadsheets, paper, or custom software and puts it on the web. Farm administration personnel may use it to schedule farm operations and manage their resources and equipment. A survey was con- ducted to assess Amaethon’s user interface design. Participants in the survey were two groups of students and a small group of agriculture professionals. Among other results, the survey indicated that a calendar interface inside Amaethon was preferred, and statistically no less effective, than a map interface. This is despite the …

Extending The Battery-Powered Operating Time Of A Wireless Environmental Monitoring System, Ross Matthew Butler

Boise State University Theses and Dissertations

Advances in low-power microelectronics and sensor technologies have enabled the creation of sophisticated environmental monitoring systems capable of operating on battery power. Independence from a power outlet connection opens up many new potential applications, but limited battery life still imposes significant restrictions on a monitoring system’s capabilities and the number of systems that can be economically deployed and maintained. These restrictions have motivated much research into reducing monitoring system energy usage, increasing battery capacity, and harnessing alternative energy sources. While most of the research focuses on new system design, there is a need for techniques to extend the battery-powered operating …

Mobile First Web And Content Strategy, Stefanie Havelka, David Stevens

Publications and Research

The paradigm shift from the traditional desktop to the mobile web experience is fast approaching, and providing relevant date, location and time-sensitive content to users via mobile devices becomes an essential piece of the overall web strategy. This presentation demonstrates the concepts, techniques and technologies used to develop both the overall mobile content strategy and user experience, as well as the aggregation and delivery of content to both the desktop and mobile form factors from a single content source.

Is Tech M&A Value-Additive?, Ani Deshmukh

Undergraduate Economic Review

Given rising M&A deal volume across all high-tech subsectors, the ability to measure post-acquisition performance becomes critical. Despite this growth, the relevant academic literature is severely lacking (Kohers and Kohers 2000). Using an event-study approach, I find that acquirers and targets both realize statistically significant day-0 abnormal returns (1.23% [p<0.1] and 8.1% [p<0.01], respectively). As positive stock returns signal positive growth prospects in a semi-strong efficient market, AR regressions found that firms' technological relatedness, deal financing, purchase price premiums, and the relative book to market ratio, explained most variance. Overall, high-tech transactions are value-additive for both targets and acquirers.

Cyber-Physical Modeling Of Implantable Cardiac Medical Devices, Zhihao Jiang, Miroslav Pajic, Rahul Mangharam

Rahul Mangharam

The design of bug-free and safe medical device software is challenging, especially in complex implantable devices that control and actuate organs in unanticipated contexts. Safety recalls of pacemakers and implantable cardioverter defibrillators between 1990 and 2000 affected over 600,000 devices. Of these, 200,000 or 41%, were due to firmware issues and their effect continues to increase in frequency. There is currently no formal methodology or open experimental platform to test and verify the correct operation of medical device software within the closed-loop context of the patient. To this effect, a real-time Virtual Heart Model (VHM) has been developed to model …

From Verification To Implementation: A Model Translation Tool And A Pacemaker Case Study, Miroslav Pajic, Zhihao Jiang, Insup Lee, Oleg Sokolsky, Rahul Mangharam

Rahul Mangharam

Model-Driven Design (MDD) of cyber-physical systems advocates for design procedures that start with formal modeling of the real-time system, followed by the model’s verification at an early stage. The verified model must then be translated to a more detailed model for simulation-based testing and finally translated into executable code in a physical implementation. As later stages build on the same core model, it is essential that models used earlier in the pipeline are valid approximations of the more detailed models developed downstream. The focus of this effort is on the design and development of a model translation tool, UPP2SF, and …

Modeling Cardiac Pacemaker Malfunctions With The Virtual Heart Model, Zhihao Jiang, Rahul Mangharam

Rahul Mangharam

Implantable cardiac devices such as artificial pacemakers deliver therapies according to the timing information from the heart. Such devices work under the assumptions of perfect sensing, which are: (a) the pacemaker leads remain in place, and (b) the pacing therapy in one chamber (e.g. atrium) is insulated from the other chambers (e.g. ventricles). But there are common cases which violate these assumptions and the mechanisms for imperfect sensing cannot be captured by a simple signal generator. In this paper we use the Penn Virtual Heart Model (VHM) to investigate the spatial and temporal aspects of the electrical conduction system of …

Model-Based Closed-Loop Testing Of Implantable Pacemakers, Zhihao Jiang, Miroslav Pajic, Rahul Mangharam

Rahul Mangharam

The increasing complexity of software in implantable medical devices such as cardiac pacemakers and defibrillators accounts for over 40% of device recalls. Testing remains the principal means of verification in the medical device certification regime. Traditional software test generation techniques, where the tests are generated independently of the operational environment, are not effective as the device must be tested within the context of the patient's condition and the current state of the heart. It is necessary for the testing system to observe the system state and conditionally generate the next input to advance the purpose of the test. To this …

Large Scale Processing And Storage Solution: Dna Safeguard Project, Eric Copp

Eric Copp

The DNA Safeguard project involves processing DNA sequence data in order to find nullomer sequences (non-existent short DNA sequences). While the fundamental algorithm for finding nullomer sequences is simple, it is complicated by the amount of data that must be handled. Four methods for handling terabytes of of data are investigated, single instance of a MySQL database, PVFS (Parallel Virtual File System), Hadoop, and a custom MPI (Message Passing Interface) program.

Efficient Algorithms For Improving The Accuracy In Motifs Prediction, Jerlin C. Merlin

Master's Theses

Analysis of sequence homology has always played a major role in the understanding of biological factors such as protein domain identification, gene product relationships, and gene function determination. Short contiguous protein sequences that are conserved across proteins provide important information about such factors, and are of at most 15 residues in length. These segments of proteins are known as minimotifs. Identifying minimotifs has been of much use in the formulation of the hypothesis about the biological functions that otherwise might be uncharacterized. Mechanisms of motif predictions such as Minimotif Miner are widely used for predicting minimotifs. However, due to the …

Contextualized Mobile Support For Learning By Doing In The Real World, Ray Bareiss, Natalie Linnell, Martin L. Griss

Martin L Griss

This research addresses the use of mobile devices with both embedded and external sensors to provide contextualized help, advice, and remediation to learners engaged in real-world learn-by-doing tasks. This work is situated within the context of learning a complex procedure, in particular emergency responders learning to conduct urban search and rescue operations. Research issues include the design and delivery of contextualized performance support and the inferring of learner actions and intentions from sensor data to ensure that the right support is delivered just in time, as it is relevant to what the learner is doing.

Hard And Soft Error Resilience For One-Sided Dense Linear Algebra Algorithms, Peng Du

Doctoral Dissertations

Dense matrix factorizations, such as LU, Cholesky and QR, are widely used by scientific applications that require solving systems of linear equations, eigenvalues and linear least squares problems. Such computations are normally carried out on supercomputers, whose ever-growing scale induces a fast decline of the Mean Time To Failure (MTTF). This dissertation develops fault tolerance algorithms for one-sided dense matrix factorizations, which handles Both hard and soft errors.

For hard errors, we propose methods based on diskless checkpointing and Algorithm Based Fault Tolerance (ABFT) to provide full matrix protection, including the left and right factor that are normally seen in …

A Comparative Study Of User Preferences Of A Personalized Academic Website, Dipti U. Desai

Purdue Polytechnic Masters Theses

ABSTRACT

There has been a growing concern over the enrollment by American students into Science, Technology, Engineering and Mathematic (STEM) fields of study. Following globalization there is a direct competition for jobs in the United States with lower-wage workers around the globe and the US, thereby, is on the verge of losing its global technological competitiveness (Committee on Prospering in the Global Economy of the 21st Century: An Agenda for American Science and Technology, National Academy of Sciences, National Academy of Engineering, Institute of Medicine, 2007). Governmental as well as non-profit organizations are constantly searching for ideas, programs and initiatives …

Extended Pcr Rules For Dynamic Frames, Florentin Smarandache, Jean Dezert

Branch Mathematics and Statistics Faculty and Staff Publications

In most of classical fusion problems modeled from belief functions, the frame of discernment is considered as static. This means that the set of elements in the frame and the underlying integrity constraints of the frame are fixed forever and they do not change with time. In some applications, like in target tracking for example, the use of such invariant frame is not very appropriate because it can truly change with time. So it is necessary to adapt the Proportional Conflict Redistribution fusion rules (PCR5 and PCR6) for working with dynamical frames. In this paper, we propose an extension of …

The Dancer's Friend - A Wearable Electronics Investigation, Paul Case

Computer Engineering

This project is an initial investigation into the use of wearable electronics for wireless gesture detection, with the end goal of an application of augmenting dance performance through the use of gesture controlled sound. Though the system developed is not as yet of practical use to a dance performer, it lays the groundwork for future development and expansion, in both hardware and software design. In particular, it provides an in-depth overview of the lessons learned regarding the special hardware development considerations in wearable electronics to help ensure the success of future developments.

Mac's Fiesta: A Foreign Language Game For The Sifteo Platform, Karina Cordon

Computer Engineering

Mac’s Fiesta is a Spanish learning game designed on the Sifteo gaming platform for children ages four and up. The Sifteo gaming platform provides a new way of interacting with computers by giving users a set of tangible and interactive cubes. Each Sifteo cube has a clickable colored screen and can sense motion and adjacent blocks. Games on this platform are designed to encourage the development of core thinking skills. This project aims to explore how Sifteo cubes can be used for language learning as well as observe how effective they are as educational tools.

Pier Portal, Andrew Belis, Andrew (Andy) Crafts, Jeremy Depangher, Aaron Hein, Michael Machado, Aaron Poulos

Computer Engineering

This project constitutes the design, build, and test of a camera system that runs on a track along the length of a pier piling at the Cal Poly pier in Avila Beach. The goal of the camera system is to observe the abundant sea life active on the surface of the piling underwater and in the tidal zone. The camera system will stream live video to the internet, record HD video, and be controllable remotely. The track is mounted to the piling with brackets and extends from the sea floor to a few feet above the pier deck. The camera, …

Cal Poly Xpress Project: Exploring Interactive Storytelling Through Digital Multimedia Platforms, Eugene Bistolas

Computer Engineering

No abstract provided.

Frg Turbojet, Tyler Vitti

Computer Engineering

Members of the Cal Poly SLO campus club FRG work together with students of several different disciplines to build a functional turbojet engine. Engineering approaches include design, fabrication, testing, and computer sensing, control, and integration. The goal of the project is to produce a running turbojet engine monitored and controlled by embedded hardware and specialized PC software. This project is to be used by later groups for further research and development.

Real World Computer Forensics, Jessica Riccio

Liberal Arts and Engineering Studies

No abstract provided.

Controlling Virus Infections In Internet And Web Servers A Triz Based Analysis, Umakant Mishra

Umakant Mishra

The viruses not only infect the stand-alone machines or client machines but also infect the web servers. When the web servers are infected with viruses, they disseminate infected content and thereby infect the client computers. The conventional anti-virus programs can run only on one machine. There is no way that an anti-virus in the client machine can determine whether the content of a website is virus safe or not. Hence, different methods are implemented to prevent the client computer from being infected by the infected content of a web server.

One proposed efficient method is to get scanned by the …

Inventions On Generic Detection Of Computer Viruses -A Triz Based Analysis, Umakant Mishra

Umakant Mishra

The conventional methods of signature scanning and heuristic testing depend on prior knowledge of individual virus signatures and virus behaviors. Hence these methods are capable of detecting only the known viruses or viruses behaving in known ways. Hence, these methods cannot detect the viruses unless they are created, released and infected the innocent users. This situation creates the need for generic detectors that can detect even the new and unknown viruses.

The generic scanning methods, in contrast, don’t depend on individual virus signatures or behaviors. Hence they are better applicable to detect the new and unknown viruses and viruses of …

Lottery Scheduling In The Linux Kernel: A Closer Look, David Zepp

Master's Theses

This paper presents an implementation of a lottery scheduler, presented from design through debugging to performance testing. Desirable characteristics of a general purpose scheduler include low overhead, good overall system performance for a variety of process types, and fair scheduling behavior. Testing is performed, along with an analysis of the results measuring the lottery scheduler against these characteristics. Lottery scheduling is found to provide better than average control over the relative execution rates of processes. The results show that lottery scheduling functions as a good mechanism for sharing the CPU fairly between users that are competing for the resource. While …

A Crowdsourcing Approach To Labelling A Mood Induced Speech Corpus, John Snel, Alexey Tarasov, Charlie Cullen, Sarah Jane Delany

Conference papers

This paper demonstrates the use of crowdsourcing to accumulate ratings from na ̈ıve listeners as a means to provide labels for a naturalistic emotional speech dataset. In order to do so, listening tasks are performed with a rating tool, which is delivered via the web. The rating requirements are based on the classical dimensions, activation and evaluation, presented to the participant as two discretised 5-point scales. Great emphasis is placed on the participant’s overall understanding of the task, and on the ease-of-use of the tool so that labelling accuracy is reinforced. The accumulation process is ongoing with a goal to …

A Critical Perfomance Analysis Of Thin Client Platforms, Faith J. Shimba, Renatus Michael

Faith Joel Shimba

The nature of operation of Thin Client computing makes their performance to be affected by both the quality of the network and the terminals. For the past few years, there are few analyses on the performance of Thin Clients that can produce reliable, valid, and up-to-date results collected in a well designed and evaluated experiment based research. This paper analyses the performance of Thin Clients through experiment based research. The approach is to use benchmark application which is designed specifically for measurement of desktop computers by inserting delays in the visual elements of such benchmark application. In this technique, packet’s …

Meal Helper, Jacob Taylor Peek, David Prenshaw, Matthew Burnett, Ian Harmon

Chancellor’s Honors Program Projects

No abstract provided.

Deep Machine Learning With Spatio-Temporal Inference, Thomas Paul Karnowski

Doctoral Dissertations

Deep Machine Learning (DML) refers to methods which utilize hierarchies of more than one or two layers of computational elements to achieve learning. DML may draw upon biomemetic models, or may be simply biologically-inspired. Regardless, these architectures seek to employ hierarchical processing as means of mimicking the ability of the human brain to process a myriad of sensory data and make meaningful decisions based on this data. In this dissertation we present a novel DML architecture which is biologically-inspired in that (1) all processing is performed hierarchically; (2) all processing units are identical; and (3) processing captures both spatial and …