Computer Engineering Commons^™

Support Vector Machines And Artificial Neural Networks: Assessing The Validity Of Using Technical Features For Security Forecasting, James Di Padua

Dissertations

Stock forecasting is an enticing and well studied problem in both finance and machine learning literature with linear based models such as ARIMA and ARCH to nonlinear Artificial Neural Networks (ANN) and Support Vector Machines (SVM). However, these forecasting techniques also use very different input features, some of which are seen by economists as irrational and theoretically unjustified. In this comparative study using ANNs and SVMs for 12 publicly traded companies, derivative price “technicals” are evaluated against macro and microeconomic fundamentals to evaluate the efficacy of model performance. Despite the efficient market hypothesis positing the ill suitability of technicals as …

A Regression Study Of Salary Determinants In Indian Job Markets For Entry Level Engineering Graduates, Rajveer Singh

Dissertations

The economic liberalisation of Indian markets in early 90s boosted the economic growth of the nation in various sectors over the next two decades. One such sector that has seen a massive growth in this time is Information Technology (IT). The IT industry has played a very crucial role in transforming India from a slow moving economy to one of the largest exporters of IT services. This growth created a huge demand in the labour markets for skilled labour, which in turn made engineering one of the top choices of study after high school over the years. In addition, the …

Panoramic Stereovision And Scene Reconstruction, Ashish Nair

Computer Science and Engineering Master's Theses

With advancement of research in robotics and computer vision, an increasingly high number of applications require the understanding of a scene in three dimensions. A variety of systems are deployed to do the same. This thesis explores a novel 3D imaging technique. This involves the use of catadioptric cameras in a stereoscopic arrangement. A secondary system aims to stabilize the system in the event that the cameras are misaligned during operation. The system provides a stark advantage due to it being a cost effective alternative to present day standard state-of-the-art systems that achieve the same goal of 3D imaging. The …

Using Spatialisation To Support Exploratory Search Behaviour, Clement Roux

Dissertations

Information-seekers traditionally interact with digital content through keyword-based search interfaces displaying results in list views. Well-defined lookup search tasks are performed brilliantly with these interfaces, enabling users to find relevant information and develop a relative understanding of the underlying information space. However, it is feasible to suggest that ill-defined and abstract search tasks could be better supported with a different interface that could allow the user to explore a library’s content and develop an appropriate mental model of the information space. One such approach is based on the use of visualisation, an approach to data analysis that aims to reduce …

Investigating The Impact Of Unsupervised Feature-Extraction From Multi-Wavelength Image Data For Photometric Classification Of Stars, Galaxies And Qsos, Annika Lindh

Dissertations

This thesis reviews the current state of photometric classification in Astronomy and identifies two main gaps: a dependence on handcrafted rules, and a lack of interpretability in the more successful classifiers. To address this, Deep Learning and Computer Vision were used to create a more interpretable model, using unsupervised training to reduce human bias.

The main contribution is the investigation into the impact of using unsupervised feature-extraction from multi-wavelength image data for the classification task. The feature-extraction is achieved by implementing an unsupervised Deep Belief Network to extract lower-dimensionality features from the multi-wavelength image data captured by the Sloan Digital …

Routing Algorithm With Uneven Clustering For Energy Heterogeneous Wireless Sensor Networks, Ying Zhang, Wei Xiong, Dezhi Han, Wei Chen, Jun Wang

Computer Science Faculty Research

Aiming at the “hotspots” problem in energy heterogeneous wireless sensor networks, a routing algorithm of heterogeneous sensor network with multilevel energies based on uneven clustering is proposed. In this algorithm, the energy heterogeneity of the nodes is fully reflected in the mechanism of cluster-heads’ election. It optimizes the competition radius of the cluster-heads according to the residual energy of the nodes. This kind of uneven clustering prolongs the lifetime of the cluster-heads with lower residual energies or near the sink nodes. In data transmission stage, the hybrid multihop transmission mode is adopted, and the next-hop routing election fully takes account …

An On-Line Diagnostic Method For Open-Circuit Switch Faults In Npc Multilevel Converters, Jiangbiao He, Nabeel Demerdash

Electrical and Computer Engineering Faculty Research and Publications

On-line condition monitoring is of paramount importance for multilevel converters used in safety-critical applications. A novel on-line diagnostic method for detecting open-circuit switch faults in neutral-point-clamped (NPC) multilevel converters is introduced in this paper. The principle of this method is based on monitoring the abnormal variation of the dc-bus neutral-point current in combination with the existing information on instantaneous switching states and phase currents. Advantages of this method include simpler implementation and faster detection speed compared to other existing diagnostic methods in the literature. In this method, only one additional current sensor is required for measuring the dc-bus neutral-point current, …

A Fault-Tolerant T-Type Multilevel Inverter Topology With Soft-Switching Capability Based On Si And Sic Hybrid Phase Legs, Jiangbiao He, Nathan Weise, Ramin Katebi, Lixiang Wei, Nabeel Demerdash

Electrical and Computer Engineering Faculty Research and Publications

The performance of a novel three-phase four-leg fault-tolerant T-Type inverter topology is presented in this paper, which significantly improves the inverter's fault-tolerant capability regarding device switch faults. In this new modular inverter topology, only the redundant leg is composed of Silicon Carbide (SiC) power devices and all other phase legs are constituted by Silicon (Si) devices. The addition of the redundant leg, not only provides fault-tolerant solution to switch faults that could occur in the T-Type inverter, but also can share load current with other phase legs. Moreover, quasi zero-voltage switching (ZVS) and zero-current switching (ZCS) in the Si Insulated-Gate …

An Exploration Of The Impact Of Animal Agriculture On Human Sustainable Development Index And The Child Health Indicator, Hithesan Pandian

Dissertations

Several studies have shown that animal agriculture is one of the major contributors to climate change due to greenhouse gas emissions, deforestation, land degradation, freshwater shortages, general environmental pollution and world hunger. Apart from this, meat consumption is strongly associated with certain fatal health conditions such as cancer, cardiovascular disease and diabetes (Wu, 2014). Although meat production and export could be economically beneficial in the short run, it could lead to over-exploitation of natural resources and in turn the destruction of the environment in the long run. Hence, it is essential for the leaders of a nation to make smart …

Mechanical Design And Optimization Of An Interactive Animatronic Bald Eagle, Eric Burns

Phi Kappa Phi Research Symposium (Archived)

Animatronics is a specialized sub-category of mechatronics, a fusion of mechanical and electrical engineering. The field has grown from small, individual projects into a major industry. As animatronics progress, mechanical engineers are pushed to design internal structures which occupy ever-decreasing spaces and to ensure designs can undergo maintenance and modifications smoothly. This research investigates methods of reducing space required for mechanisms and several other beneficial methods of development as well as varying satisfactions for audiences when exposed to actor-controlled systems rather than pre-scripted functions. The mechanical systems are designed using CAD software available at Georgia Southern. On-campus, resources are used …

Model-Free And Model-Based Active Learning For Regression, Jack O'Neill, Sarah Jane Delany, Brian Macnamee

Conference papers

Training machine learning models often requires large labelled datasets, which can be both expensive and time-consuming to obtain. Active learning aims to selectively choose which data is labelled in order to minimize the total number of labels required to train an effective model. This paper compares model-free and model-based approaches to active learning for regression, finding that model-free approaches, in addition to being less computationally intensive to implement, are more effective in improving the performance of linear regressions than model-based alternatives.

Keeping It Physical: Convergence On A Physicality Requirement For Patentability Of Software-Related Inventions Under The European Patent Convention And United States Law, Kevin Afghani, Duke W. Yee

Georgia Journal of Law & Technology

No abstract provided.

Project Daedalus: An Additive Manufacturing Vending Machine, Paul A. Galarnyk, Roxanna Stein, Priscilla Mcdonald, Sky Comarsh White, Matthew Caixeiro, Alexander Seifans, Chris Hays, Benjamin Sallick, Katherine Mcbrayer, Skyler Singleton, Scott Wt Kent

Student Works

The project was a research endeavor focused on designing and building a vending machine for 3D-printed parts. It also had the secondary objective of catalyzing leadership qualities among its membership by emphasizing individual responsibility and forward thinking. The project began in the spring of 2015, when the topic of autonomous 3D-printing was chosen, funding was secured, and the majority of the leadership was brought on. Over the summer and into the fall semester the team developed project requirements and infrastructure, and gathered members from the parent organization. By December of 2015 most of the machine design had been completed, and …

Improving Gold/Gold Microcontact Performance And Reliability Under Low-Frequency Ac Through Circuit Loading, T. Laurvick, Ronald A. Coutu Jr.

Electrical and Computer Engineering Faculty Research and Publications

This paper investigates the performance and reliability of microcontacts under low-frequency and low-amplitude ac test conditions. Current microcontact theory is based on dc tests adapted to RF applications. To help better apply dc theory to RF applications, frequencies between 100 Hz to 100 kHz were experimentally investigated. Microcontacts designed to conduct performance and reliability measurements were used, which in prior dc testing typically lasted for 100 million cycles or more. Under ac loads, at similar power levels, eight devices were tested under cold-switching conditions, and only one was still operational at 10 million cycles. The effect of external circuitry on …

Fall 2016

In The Loop

Dean David Miller and CDM Through the Years; The New ABCs of Digital Literacy; The Younger Generation: Computer Scientists of the Future; The Final Hurdle: Thesis Talk; Telling Stories in Cuba with Abbas Kiarostami with James Choi; Collegiate Cyber Defense Competition; TEDxDePaulUniversity Conference; Tim Nedow, Olympian; Omnibus Crowdfunded Game; News Briefs; The Social Technocrat: Andrew Ruginis; When Computing and Biology Collide; Tori Meschino: Campus Leader and All-Around Superstar; Degrees Offered at CDM

Towards Efficient Resource Provisioning In Mapreduce, Peter Nghiem, Silvia M. Figueira

Computer Science and Engineering

The paper presents a novel approach and algorithm with mathematical formula for obtaining the exact optimal number of task resources for any workload running on HadoopMapReduce. In the era of Big Data, energy efficiency has become an important issue for the ubiquitous Hadoop MapReduce framework. However, the question of what is the optimal number of tasks required for a job to get the most efficient performance from MapReduce still has no definite answer. Our algorithm for optimal resource provisioning allows users to identify the best trade-off point between performance and energy efficiency on the runtime elbow curve …

Real-Time Monitoring Of Sand And Dust Storm Winds Using Wireless Sensor Technology, Hana Mohammed Mujlid

Theses and Dissertations

This dissertation proposes an empirical model for prediction of the radio path loss in Wireless Sensor Networks (WSNs). The model applies to WSNs that are deployed in environments with dust and sand storms. It is developed as a result of statistical analysis of the measured data collected during dust and sand storms. The measured data were obtained at 2.4GHz and for different levels of the storm severity. For the purpose of data collection a custom measurement system based on Xbee air interface was developed. The proposed model shows a very good agreement with the measured data. It is also demonstrated …

An Inductive Ethnographic Study In Elderly Woman Technology Adoption And The Role Of Her Children, Noshad Rahimi, Antonie J, Jetter, Charles M. Weber

Engineering and Technology Management Faculty Publications and Presentations

Elderly woman strives to have a streamlined life surrounded by ease and familiarity. As she is aging, her desire for simplicity grows, her self-efficacy weakens, her prudency intensifies and her overall inclination toward status quo strengthens. As a result, she delays, or refuses, making any decision that might bring complexity and disrupt the continuity in her life, particularly new and unfamiliar technologies (which often bring complexity, before providing ease). Consequently, her technology adoption has a much lower rate than that of other demographics. To open the black box of elderly woman technology adoption process, this study focuses on the role …

Activist: A New Framework For Dataset Labelling, Jack O'Neill, Sarah Jane Delany, Brian Macnamee

Conference papers

Acquiring labels for large datasets can be a costly and time-consuming process. This has motivated the development of the semi-supervised learning problem domain, which makes use of unlabelled data — in conjunction with a small amount of labelled data — to infer the correct labels of a partially labelled dataset. Active Learning is one of the most successful approaches to semi-supervised learning, and has been shown to reduce the cost and time taken to produce a fully labelled dataset. In this paper we present Activist; a free, online, state-of-the-art platform which leverages active learning techniques to improve the efficiency …

Developers’ Perceptions On Object-Oriented Design And Architectural Roles, Maurício Aniche, Marco Aurélio Gerosa, Christoph Treude

Research Collection School Of Computing and Information Systems

Software developers commonly rely on well-known software architecture patterns, such as MVC, to build their applications. In many of these patterns, classes play specific roles in the system, such as Controllers or Entities, which means that each of these classes has specific characteristics in terms of object-oriented class design and implementation. Indeed, as we have shown in a previous study, architectural roles are different from each other in terms of code metrics. In this paper, we present a study in a software development company in which we captured developers’ perceptions on object-oriented design aspects of the architectural roles in their …

Generalizing Effective Spatial Bandwidth For Pole Location In Mas: The Elliptic Cylinder, James Richie

Electrical and Computer Engineering Faculty Research and Publications

The location of poles in the method of auxiliary sources for 2-D scatterers can be assisted using the effective spatial bandwidth (EBW) of the incident and scattered fields. Previously, only circular boundaries were considered. Here, EBW is extended to noncircular boundaries. Calculations presented for a cylinder with elliptical cross section verify EBW as an additional tool for pole placement for more general geometries.

Thermal Management Using Mems Bimorph Cantilever Beams, Ronald A. Coutu Jr., R. S. Lafleur, J. P.K. Walton, Lavern A. Starman

Electrical and Computer Engineering Faculty Research and Publications

This paper examines a passive cooling technique using microelectromechanical systems (MEMS) for localized thermal management of electronic devices. The prototype was designed using analytic equations, simulated using finite element methods (FEM), and fabricated using the commercial PolyMUMPs™ process. The system consisted of an electronic device simulator (EDS) and MEMS bimorph cantilever beams (MBCB) array with beams lengths of 200, 250, and 300 μm that were tested to characterize deflection and thermal behavior. The specific beam lengths were chosen to actuate in response to heating associated with the EDS (i.e. the longest beams actuated first corresponding to the hottest portion of …

Large-Scale Design Optimization Of Pm Machines Over A Target Operating Cycle, Alireza Fatemi, Nabeel Demerdash, Thomas W. Nehl, Dan M. Ionel

Electrical and Computer Engineering Faculty Research and Publications

A large-scale finite element model-based design optimization algorithm is developed for improving the drive-cycle efficiency of permanent magnet (PM) synchronous machines with wide operating ranges such as those used in traction propulsion motors. The load operating cycle is efficiently modeled by using a systematic k-means clustering method to identify the operating points representing the high-energy-throughput zones in the torque-speed plane. The machine performance is evaluated over these cyclic representative points using a recently introduced computationally efficient finite element analysis, which is upgraded to include both constant torque and field-weakening operations in the evaluation of the machine performance metrics. In contrast …

Indoor Localization Via Multi-Modal Sensing On Smartphones, Han Xu, Zheng Yang, Zimu Zhou, Longfei Shangguan, Ke Yi, Yunhao Liu

Research Collection School Of Computing and Information Systems

Indoor localization is of great importance to a wide range ofapplications in shopping malls, office buildings and publicplaces. The maturity of computer vision (CV) techniques andthe ubiquity of smartphone cameras hold promise for offering sub-meter accuracy localization services. However, pureCV-based solutions usually involve hundreds of photos andpre-calibration to construct image database, a labor-intensiveoverhead for practical deployment. We present ClickLoc, anaccurate, easy-to-deploy, sensor-enriched, image-based indoor localization system. With core techniques rooted insemantic information extraction and optimization-based sensor data fusion, ClickLoc is able to bootstrap with few images. Leveraging sensor-enriched photos, ClickLoc also enables user localization with a single photo of the …

Metaflow: A Scalable Metadata Lookup Service For Distributed File Systems In Data Centers, Peng Sun, Yonggang Wen, Nguyen Binh Duong Ta, Haiyong Xie

Research Collection School Of Computing and Information Systems

In large-scale distributed file systems, efficient metadata operations are critical since most file operations have to interact with metadata servers first. In existing distributed hash table (DHT) based metadata management systems, the lookup service could be a performance bottleneck due to its significant CPU overhead. Our investigations showed that the lookup service could reduce system throughput by up to 70%, and increase system latency by a factor of up to 8 compared to ideal scenarios. In this paper, we present MetaFlow, a scalable metadata lookup service utilizing software-defined networking (SDN) techniques to distribute lookup workload over network components. MetaFlow tackles …

Design And Application Research Of Maritime Casualty Investigation Simulation Base On Unity 3d, Mingzhong Wen

Maritime Safety & Environment Management Dissertations (Dalian)

No abstract provided.

Mems-Based Terahertz Photoacoustic Chemical Sensing System, Nathan Glauvitz, Ronald A. Coutu Jr., Ivan R. Medvedev, Douglas T. Petkie

Electrical and Computer Engineering Faculty Research and Publications

Advancements in microelectromechanical system (MEMS) technology over the last several decades has been a driving force behind miniaturizing and improving sensor designs. In this work, a specialized cantilever pressure sensor was designed, modeled, and fabricated to investigate the photoacoustic (PA) response of gases to terahertz (THz) radiation under low-vacuum conditions associated with high-resolution spectroscopy. Microfabricated cantilever devices made using silicon-on-insulator (SOI) wafers were tested in a custom-built test chamber in this first ever demonstration of a cantilever-based PA chemical sensor and spectroscopy system in the THz frequency regime. The THz radiation source was amplitude modulated to excite acoustic waves in …

Surface Feature Engineering Through Nanosphere Lithography, Tod V. Laurvick, Ronald A. Coutu Jr., James M. Sattler, Robert A. Lake

Electrical and Computer Engineering Faculty Research and Publications

How surface geometries can be selectively manipulated through nanosphere lithography (NSL) is discussed. Self-assembled monolayers and multilayers of nanospheres have been studied for decades and have been applied to lithography for almost as long. When compared to the most modern, state-of-the-art techniques, NSL offers comparable feature resolution with many advantages over competing technologies. Several high-resolution alternatives require scan-based implementation (i.e., focused ion beams and e-beam lithography) while NSL is much more of a batch operation, allowing for full wafer or possibly even multiple wafer processing, potentially saving time and increasing throughput in a manufacturing environment. Additionally, NSL has continued to …

Gpu-Arraysort: A Parallel, In-Place Algorithm For Sorting Large Number Of Arrays, Muaaz Awan, Fahad Saeed

Parallel Computing and Data Science Lab Technical Reports

Modern day analytics deals with big datasets from diverse fields. For many application the data is in the form of an array which consists of large number of smaller arrays. Existing techniques focus on sorting a single large array and cannot be used for sorting large number of smaller arrays in an efficient manner. Currently no such algorithm is available which can sort such large number of arrays utilizing the massively parallel architecture of GPU devices. In this paper we present a highly scalable parallel algorithm, called GPU-ArraySort, for sorting large number of arrays using a GPU. Our algorithm performs …

Code Girl, Amanda Holl

Computer Science and Engineering Master's Theses

Despite the growing importance of technology and computing, fewer than one percent of women in college today choose to major in computer science. Educational programs and games created to interest girls in computing, such as Girls Who Code and Made With Code, have been successful in engaging girls with interactive and creative learning environments, but they are too advanced for young girls to benefit from. To address the lack of educational, computer science games designed specifically for young girls, we developed a web-based application called Code Girl for girls age five to eight to customize their own avatars using Blockly, …