Computer Engineering Commons^™

Eliciting Knowledge Bases With Defeasible Reasoning: A Comparative Analysis With Machine Learning, Peter Keogh

Dissertations

This thesis compares the ability of an implementation of Defeasible Reasoning (via Argumentation Theory) to model a construct (mental workload) with Machine Learning. In order to perform this comparison a defeasible reasoning system was designed and implemented in software. This software was used to elicit a knowledge base from an expert in an experiment which was then compared with machine learning. The central findings of this thesis were that the knowledge based approach was better at predicting an objective performance measure, time, than machine learning. However, machine learning was better equiped to identify another object measure task membership. The knowledge …

Maturity Of Cloud Application Interoperability Frameworks For Small To Medium Enterprises, John Warde

Dissertations

Cloud computing has many benefits and organisations have bought into the cost effective and elastic solutions provided by major players in the market. However, cloud computing and Cloud Service Providers (CSP) are still evolving, hence there are differences in how customers connect with each provider to the orchestrate application lifecycle management. A lack of standards can create vendor lock-in. This work investigates current research and possible solutions to the vendor lock-in problem through the use of Cloud Interoperability or multi-cloud frameworks. Software developers and organisations can use these frameworks which abstract the differences between CSPs and mitigate vendor lock-in. A …

An Evaluation Of The Use Of Diversity To Improve The Accuracy Of Predicted Ratings In Recommender Systems, Gillian Browne

Dissertations

The diversity; versus accuracy trade off, has become an important area of research within recommender systems as online retailers attempt to better serve their customers and gain a competitive advantage through an improved customer experience. This dissertation attempted to evaluate the use of diversity measures in predictive models as a means of improving predicted ratings. Research literature outlines a number of influencing factors such as personality, taste, mood and social networks in addition to approaches to the diversity challenge post recommendation. A number of models were applied included DecisionStump, Linear Regression, J48 Decision Tree and Naive Bayes. Various evaluation metrics …

Investigating The Relationship Between Organizational Innovation Capability And Firm Performance With Irish Smes, Maryam Bukhamsin

Dissertations

The topic of innovation capability and its relationship with performance has been examined by several previous studies. The purpose of this thesis is to investigate the relationship between innovation capability aspects proposed by the Innovation Value Institute (IVI) and firms’ overall performance. IVI is specialised in developing organizational and innovation capability in order to improve firms’ performance. In addition, this study presents the most important aspects of innovation capability that are directly and positively associated with firms’ overall financial and operational performance. This empirical study was conducted on small- and medium-sized enterprises (SMEs) in Ireland; the data was collected from …

Non-Invasive Detection Of Moving And Stationary Human With Wifi, Chenshu Wu, Zheng Yang, Zimu Zhou, Xuefeng Liu, Yunhao Liu, Jiannong Cao

Research Collection School Of Computing and Information Systems

Non-invasive human sensing based on radio signals has attracted a great deal of research interest and fostered a broad range of innovative applications of localization, gesture recognition, smart health-care, etc., for which a primary primitive is to detect human presence. Previous works have studied the detection of moving humans via signal variations caused by human movements. For stationary people, however, existing approaches often employ a prerequisite scenario-tailored calibration of channel profile in human-free environments. Based on in-depth understanding of human motion induced signal attenuation reflected by PHY layer channel state information (CSI), we propose DeMan, a unified scheme for non-invasive …

Motion In The Field: A Study Of Movement In Computer Science, Catherine Martin

Renée Crown University Honors Thesis Projects - All

In this project, I use a system that combines the use of a motion controller to obtain information about physical motion of a user with the transmission of outputs to a quadcopter that interacts with the physical environment. In the manual mode, the user sends commands to the quadcopter using hand controls. I utilized an existing system but increased usability to prevent accidental flight and created commands that are more intuitive for the user. In the automatic mode, the user gives a single command to the motion controller and it runs the A* path planning algorithm over a representation of …

Naturalized Communication And Testing, Marly Roncken, Swetha Mettala Gilla, Hoon Park, Navaneeth Prasannakumar Jamadagni, Christopher Cowan, Ivan Sutherland

Computer Science Faculty Publications and Presentations

We ”naturalize” the handshake communication links of a self-timed system by assigning the capabilities of filling and draining a link and of storing its full or empty status to the link itself. This contrasts with assigning these capabilities to the joints, the modules connected by the links, as was previously done. Under naturalized communication, the differences between Micropipeline, GasP, Mousetrap, and Click circuits are seen only in the links — the joints become identical; past, present, and future link and joint designs become interchangeable. We also “naturalize” the actions of a self-timed system, giving actions status equal to states — …

Segmentation Of Pulmonary Nodules In Computed Tomography Using A Regression Neural Network Approach And Its Application To The Lung Image Database Consortium And Image Database Resource Initiative Dataset, Temesguen Messay, Russell C. Hardie, Timothy R. Tuinstra

Electrical and Computer Engineering Faculty Publications

We present new pulmonary nodule segmentation algorithms for computed tomography (CT). These include a fully-automated (FA) system, a semi-automated (SA) system, and a hybrid system. Like most traditional systems, the new FA system requires only a single user-supplied cue point. On the other hand, the SA system represents a new algorithm class requiring 8 user-supplied control points. This does increase the burden on the user, but we show that the resulting system is highly robust and can handle a variety of challenging cases. The proposed hybrid system starts with the FA system.

If improved segmentation results are needed, the SA …

Object Tracking Through The Use Of Color Hue Image Processing, Zachary R. Sabey

Electrical Engineering Undergraduate Honors Theses

Many industrial and commercial applications today are beginning to use autonomous systems to increase productivity and cut costs in production and manpower. Most of these applications are only semi autonomous; they still need assistance from a human to either start up or receive continual instructions. With the improvement of image processing techniques, camera processing capabilities and more efficient vehicles, a new wave of fully autonomous vehicles can be implemented. A simple system that uses a dedicated image processor connected to an RC vehicle can be developed to provide an example for the new techniques currently available. The Pixycam, a dedicated …

Tweetement: Pseudo-Relevance Feedback For Twitter Search, Kanatbay Bektemirov

Computer Science and Computer Engineering Undergraduate Honors Theses

Microblogging platforms such as Twitter let users communicate with short messages. Due to the messages’ short content and the users’ tendency to type short queries while searching, it is particularly challenging to locate useful tweets that match user queries. The fundamental problems of word mismatch due to ambiguity are especially acute. To solve this problem, this thesis explores and compares multiple automatic query expansion methods that involve the most frequent hashtags and keywords. We built a Web service that provides real-time Twitter Search results incorporating automatic query expansion. Six pseudo-relevance feedback methods were studied and the numbers indicate that results …

An Island-Based Approach For Rna-Seq Differential Expression Analysis., Abdallah Eteleeb

Electronic Theses and Dissertations

High-throughput mRNA sequencing (also known as RNA-Seq) promises to be the technique of choice for studying transcriptome profiles, offering several advantages over old techniques such as microarrays. This technique provides the ability to develop precise methodologies for a variety of RNA-Seq applications including gene expression quantification, novel transcript and exon discovery, differential expression (DE) and splice variant detection. The detection of significantly changing features (e.g. genes, transcript isoforms, exons) in expression across biological samples is a primary application of RNA-Seq. Uncovering which features are significantly differentially expressed between samples can provide insight into their functions. One major limitation with the …

Design, Programming, And User-Experience, Kaila G. Manca

Honors Scholar Theses

This thesis is a culmination of my individualized major in Human-Computer Interaction. As such, it showcases my knowledge of design, computer engineering, user-experience research, and puts into practice my background in psychology, com- munications, and neuroscience.

I provided full-service design and development for a web application to be used by the Digital Media and Design Department and their students.This process involved several iterations of user-experience research, testing, concepting, branding and strategy, ideation, and design. It lead to two products.

The first product is full-scale development and optimization of the web appli- cation.The web application adheres to best practices. It was …

Vcare: A Personal Emergency Response System To Promote Safe And Independent Living Among Elders Staying By Themselves In Community Or Residential Settings, Priyankar Bhattacharjee

Department of Computer Electronics and Engineering: Dissertations, Theses, and Student Research

‘Population aging’ is a growing concern for most of us living in the twenty first century, primarily because many of us in the next few years will have a senior person to care for - spending money towards their healthcare expenditures AND/OR having to balance a full-time job with the responsibility of care-giving, travelling from another city to be with this elderly citizen who might be our parent, grand-parent or even community elders. As informal care-givers, if somehow we were able to monitor the day-to-day activities of our elderly dependents, and be alerted when wrong happens to them that would …

Energy Harvesting And Storage: The Catalyst To The Power Constraint For Leveraging Internet Of Things (Iot) On Trains, Kelechi Nwogu

Department of Computer Electronics and Engineering: Dissertations, Theses, and Student Research

The success of Wireless Sensor Networks is heavily constrained by its reliance on storage technology like batteries, which are a finite resource. Whilst the number of transistors in an IC doubles every 18 months, the energy density of batteries is relatively flat during the same time period. This is a key challenge in leveraging the Internet of Things on trains.

The gravity of this problem is increased by an order of magnitude when the network is to be scaled up to hundreds or thousands of nodes. Comprehensive research and development efforts have been devoted to building ultra-low power sensors. These …

Using A Nearest Neighbor Algorithm And Logistic Regression To Assess Hazard Identification In The U.S. Army Risk Management Process, Heath L. Mccormick

Theses and Dissertations

This research considers whether a person's demographic and experiential attributes play a significant role in how they perceive the presence or absence of hazards in a given situation. The goal of the research is to show that participants with enlisted military experience, prior to being commissioned as a junior officer, would be more successful at identifying the hazards presented in military scenarios than those who had only been trained on the process via their pre-commissioning and initial entry courses of instruction. The research study involves the use of two surveys with realistic military scenarios including both Foot March and Maintenance …

Using Unrestricted Mobile Sensors To Infer Tapped And Traced User Inputs, Trang Duyen Nguyen

Theses and Dissertations

As of January 2014, 58% of Americans over the age of 18 own a smart phone. Of these smart phones, Android devices provide some security by requiring that third-party application developers declare to users which components and features their applications will access. However, many of the real-time environmental sensors on devices are exempt from this requirement. We evaluate the possibility of exploiting this freedom to discretely use these sensors and expand on previous work by developing an application that can use the gyroscope and accelerometer to interpret what the user has written, even of trace input is used. Trace input …

Novel Bioinformatic Approaches For Analyzing Next-Generation Sequencing Data, Yan Peng

Dissertations

In general, DNA reconstruction is deemed as the key of molecular biology since it makes people realize how genotype affects phenotypes. The DNA sequencing technology emerged exactly towards this and has greatly promoted molecular biology’s development. The traditional method, "Sanger," is effective but extremely expensive on a cost-per-base basis. This shortcoming of Sanger method leads to the rapid development of next-generation sequencing technologies. The NGS technologies are widely used by virtue of their low-cost, high-throughput, and fast nature. However, they still face major drawbacks such as huge amounts of data as well as relatively short read length compared with traditional …

Experimental Boss Design And Testing, Joseph P. Mistretta

Undergraduate Honors Theses

Over the years, gaming has developed rapidly from simple pixel-based experiences to fully blown three-dimensional worlds. As developing technologies improve, so does the complexity and flexibility of what can be created. Encounters, along with all aspects of any gaming experience, have evolved along with the technologies that create them. These intense combat instances, often times referred to as “bosses”, represent a chance for the developer to challenge player skill, cooperation, and coordination. In addition to being major challenges, encounters also allow players to feel a sense of progression as they learn and adapt to mechanics incorporated within an encounter’s design. …

Segmentation Of Pulmonary Nodules In Computed Tomography Using A Regression Neural Network Approach And Its Application To The Lung Image Database Consortium And Image Database Resource Initiative Dataset, Temesguen Messay, Russell C. Hardie, Timothy R. Tuinstra

Electrical and Computer Engineering Faculty Publications

We present new pulmonary nodule segmentation algorithms for computed tomography (CT). These include a fully-automated (FA) system, a semi-automated (SA) system, and a hybrid system. Like most traditional systems, the new FA system requires only a single user-supplied cue point. On the other hand, the SA system represents a new algorithm class requiring 8 user-supplied control points. This does increase the burden on the user, but we show that the resulting system is highly robust and can handle a variety of challenging cases. The proposed hybrid system starts with the FA system. If improved segmentation results are needed, the SA …

Developing An Application For Evolutionary Search For Computational Models Of Cellular Development, Nicolas Scott Cornia

Boise State University Theses and Dissertations

VPEvolve is a free and open source application that utilizes a Visual Programming Environment (VPE) for the setup of the Genetic Algorithm (GA), for optimization of computational models. Specifically, the User Interface uses connected glyphs to represent the genetic operators of mutation, reproduction, fitness and selection. These glyphs give the user an intuitive way to set the parameters for the GA, and better visualization of the population's flow through these operators.

VPEvolve is currently being developed alongside research being done in Biocomputing to create models of cellular regeneration based on the regenerative properties of Planaria or flatworms. Since these models …