Computer Engineering Commons^™

A Study Of Activation Functions For Neural Networks, Meenakshi Manavazhahan

Computer Science and Computer Engineering Undergraduate Honors Theses

Artificial neural networks are function-approximating models that can improve themselves with experience. In order to work effectively, they rely on a nonlinearity, or activation function, to transform the values between each layer. One question that remains unanswered is, “Which non-linearity is optimal for learning with a particular dataset?” This thesis seeks to answer this question with the MNIST dataset, a popular dataset of handwritten digits, and vowel dataset, a dataset of vowel sounds. In order to answer this question effectively, it must simultaneously determine near-optimal values for several other meta-parameters, including the network topology, the optimization algorithm, and the number …

On The Simulation And Mitigation Of Anisoplanatic Optical Turbulence For Long Range Imaging, Russell C. Hardie, Daniel A. Lemaster

Electrical and Computer Engineering Faculty Publications

We describe a numerical wave propagation method for simulating long range imaging of an extended scene under anisoplanatic conditions. Our approach computes an array of point spread functions (PSFs) for a 2D grid on the object plane. The PSFs are then used in a spatially varying weighted sum operation, with an ideal image, to produce a simulated image with realistic optical turbulence degradation. To validate the simulation we compare simulated outputs with the theoretical anisoplanatic tilt correlation and differential tilt variance. This is in addition to comparing the long- and short-exposure PSFs, and isoplanatic angle. Our validation analysis shows an …

Automation In Entertainment: Concept, Design, And Application, Ryan Thally

Undergraduate Honors Theses

The focus of this thesis is to explore the automation technology used in the modern entertainment industry. Upon completion of my thesis, I will deliver a working prototype of the chosen technology and present its capabilities in a choreographed show.

Sparse Coding On Stereo Video For Object Detection, Sheng Y. Lundquist, Melanie Mitchell, Garrett T. Kenyon

Computer Science Faculty Publications and Presentations

Deep Convolutional Neural Networks (DCNN) require millions of labeled training examples for image classification and object detection tasks, which restrict these models to domains where such a dataset is available. We explore the use of unsupervised sparse coding applied to stereo-video data to help alleviate the need for large amounts of labeled data. In this paper, we show that unsupervised sparse coding is able to learn disparity and motion sensitive basis functions when exposed to unlabeled stereo-video data. Additionally, we show that a DCNN that incorporates unsupervised learning exhibits better performance than fully supervised networks. Furthermore, finding a sparse representation …

Evaluating A Personal Stress Monitoring System, Sneha Gogineni

Theses and Dissertations

Now-a-days, Life is generally much more stressful than in the past. "Stress" is the word that we use when we feel that we are overloaded mentally in our thoughts and wonder whether we can really cope with those placed upon us. Sometimes, stress gets us going and they are good for us but at other times, it could be the cause to undermine both our mental and physical health. The way we respond to a challenge can be considered as a kind of stress. Part of our response to a challenge is physiological and affects our own physical state. When …

Models For Pedestrian Trajectory Prediction And Navigation In Dynamic Environments, Jeremy N. Kerfs

Master's Theses

Robots are no longer constrained to cages in factories and are increasingly taking on roles alongside humans. Before robots can accomplish their tasks in these dynamic environments, they must be able to navigate while avoiding collisions with pedestrians or other robots. Humans are able to move through crowds by anticipating the movements of other pedestrians and how their actions will influence others; developing a method for predicting pedestrian trajectories is a critical component of a robust robot navigation system. A current state-of-the-art approach for predicting pedestrian trajectories is Social-LSTM, which is a recurrent neural network that incorporates information about neighboring …

Dsrc Performance Analysis In Foggy Environment For Intelligent Vehicles System, Mostafa El-Said, Samah Mansour, Alexander Arendsen

Peer-Reviewed Publications

Advanced Driver Assistance System (ADAS) is one of the fastest growing areas in the Intelligent Transportation Systems (ITS). Research efforts has focused on developing a driver assistant alert system to warn driver in foggy environment. However, there is a lack of which effective V2V/V2I communication technology would be the best to extend and disseminate this information to nearby vehicles. In this paper, we examine the use of Dedicated Short Range Communications (DSRC) as a V2V communication mechanism to share the foggy conditions to nearby vehicles. The study also investigates the effect of changing the fog/air density on the DSRC performance …

Software Updates To A Multiple Autonomous Quadcopter Search System (Maqss), Jared Speck, Toby Chan

Computer Engineering

A series of performance-based and feature implementation software updates to an existing multiple vehicle autonomous target search system is outlined in this paper. The search system, MAQSS, is designed to address a computational power constraint found on modern autonomous aerial platforms by separating real-time and computationally expensive tasks through delegation to multiple multirotor vehicles. A Ground Control Station (GCS) is also described as part of the MAQSS system to perform the delegation and provide a low workload user interface. Ultimately, the changes to MAQSS noted in this paper helped to improve the performance of the autonomous search mission, the accuracy …

Expierience, Seong Bo Chang, Albert Chen, Emily Nguyen

Computer Engineering

The name of this project is called “exPIERience” and the technological field of focus is virtual reality. We will be working on creating a virtual reality experience using the Oculus Rift for the Center of Coastal Marine Sciences (CCMS). The purpose of this system is to enable people to experience diving at the Cal Poly Pier even during nonoptimal diving conditions which occur frequently. CCMS hopes to attract further interest and possible momentum in future outreach such as a “Live Dive” program, where live videos of divers under the pier can be streamed. A 360° video from the diver’s perspective …

A Hybrid Partially Reconfigurable Overlay Supporting Just-In-Time Assembly Of Custom Accelerators On Fpgas, Zeyad Tariq Aklah

Graduate Theses and Dissertations

The state of the art in design and development flows for FPGAs are not sufficiently mature to allow programmers to implement their applications through traditional software development flows. The stipulation of synthesis as well as the requirement of background knowledge on the FPGAs' low-level physical hardware structure are major challenges that prevent programmers from using FPGAs. The reconfigurable computing community is seeking solutions to raise the level of design abstraction at which programmers must operate, and move the synthesis process out of the programmers' path through the use of overlays. A recent approach, Just-In-Time Assembly (JITA), was proposed that enables …

Investigation Into The Application Of Personality Insights And Language Tone Analysis In Spam Classification, Colm Mcgetrick

Dissertations

Due to its persistence spam remains as one of the biggest problems facing users and suppliers of email communication services. Machine learning techniques have been very successful at preventing many spam mails from arriving in user mailboxes, however they still account for over 50% of all emails sent. Despite this relative success the economic cost of spam has been estimated as high as $50 billion in 2005 and more recently at $20 billion so spam can still be considered a considerable problem. In essence a spam email is a commercial communication trying to entice the receiver to take some positive …

Detection Of Plant Emergence Based On Spatio Temporal Image Sequence Analysis, Bhushit Agarwal

School of Computing: Dissertations, Theses, and Student Research

The phenome of a plant is the sum of all observable phenotypes for that plant. Phenotypes are observable characteristics or traits of a plant. These traits generally reflect a combination of influences from the genotype of the plant and the environment in which the plant has grown and developed. Collecting phenotypic data has traditionally been a slow and costly manual process, albeit one highly necessary for plant breeding and the development of improved agronomic practices. As a result automated methods for plant phenotyping analysis have become an active research field in recent years. Image-based plant phenotyping analysis facilitates extraction of …

Vehicle Make And Model Recognition For Intelligent Transportation Monitoring And Surveillance., Faezeh Tafazzoli

Electronic Theses and Dissertations

Vehicle Make and Model Recognition (VMMR) has evolved into a significant subject of study due to its importance in numerous Intelligent Transportation Systems (ITS), such as autonomous navigation, traffic analysis, traffic surveillance and security systems. A highly accurate and real-time VMMR system significantly reduces the overhead cost of resources otherwise required. The VMMR problem is a multi-class classification task with a peculiar set of issues and challenges like multiplicity, inter- and intra-make ambiguity among various vehicles makes and models, which need to be solved in an efficient and reliable manner to achieve a highly robust VMMR system. In this dissertation, …

Uncovering Exceptional Predictions Using Exploratory Analysis Of Second Stage Machine Learning., Aneseh Alvanpour

Electronic Theses and Dissertations

Nowadays, algorithmic systems for making decisions are widely used to facilitate decisions in a variety of fields such as medicine, banking, applying for universities or network security. However, many machine learning algorithms are well-known for their complex mathematical internal workings which turn them into black boxes and makes their decision-making process usually difficult to understand even for experts. In this thesis, we try to develop a methodology to explain why a certain exceptional machine learned decision was made incorrectly by using the interpretability of the decision tree classifier. Our approach can provide insights about potential flaws in feature definition or …

Using A Multi Variate Pattern Analysis (Mvpa) Approach To Decode Fmri Responses To Fear And Anxiety., Sajjad Torabian Esfahani

Electronic Theses and Dissertations

This study analyzed fMRI responses to fear and anxiety using a Multi Variate Pattern Analysis (MVPA) approach. Compared to conventional univariate methods which only represent regions of activation, MVPA provides us with more detailed patterns of voxels. We successfully found different patterns for fear and anxiety through separate classification attempts in each subject’s representational space. Further, we transformed all the individual models into a standard space to do group analysis. Results showed that subjects share a more common fear response. Also, the amygdala and hippocampus areas are more important for differentiating fear than anxiety.

Peeking Into The Other Half Of The Glass : Handling Polarization In Recommender Systems., Mahsa Badami

Electronic Theses and Dissertations

This dissertation is about filtering and discovering information online while using recommender systems. In the first part of our research, we study the phenomenon of polarization and its impact on filtering and discovering information. Polarization is a social phenomenon, with serious consequences, in real-life, particularly on social media. Thus it is important to understand how machine learning algorithms, especially recommender systems, behave in polarized environments. We study polarization within the context of the users' interactions with a space of items and how this affects recommender systems. We first formalize the concept of polarization based on item ratings and then relate …

Data Driven Discovery Of Materials Properties., Fadoua Khmaissia

Electronic Theses and Dissertations

The high pace of nowadays industrial evolution is creating an urgent need to design new cost efficient materials that can satisfy both current and future demands. However, with the increase of structural and functional complexity of materials, the ability to rationally design new materials with a precise set of properties has become increasingly challenging. This basic observation has triggered the idea of applying machine learning techniques in the field, which was further encouraged by the launch of the Materials Genome Initiative (MGI) by the US government since 2011. In this work, we present a novel approach to apply machine learning …

Repeatability Of Reference Signal Received Power Measurements In Lte Networks, Hayder A Abdulrasool Khzaali

Theses and Dissertations

No abstract provided.

Exploiting Hardware Abstraction For Parallel Programming Framework: Platform And Multitasking, Hongyuan Ding

Graduate Theses and Dissertations

With the help of the parallelism provided by the fine-grained architecture, hardware accelerators on Field Programmable Gate Arrays (FPGAs) can significantly improve the performance of many applications. However, designers are required to have excellent hardware programming skills and unique optimization techniques to explore the potential of FPGA resources fully. Intermediate frameworks above hardware circuits are proposed to improve either performance or productivity by leveraging parallel programming models beyond the multi-core era.

In this work, we propose the PolyPC (Polymorphic Parallel Computing) framework, which targets enhancing productivity without losing performance. It helps designers develop parallelized applications and implement them on FPGAs. …

In Situ Electron Microscopy Of Plasmon-Mediated Nanocrystal Synthesis, Peter Sutter, Ying Li, Christos Argyropoulos, Eli A. Sutter

Department of Electrical and Computer Engineering: Faculty Publications

Chemical processes driven by nonthermal energy (e.g., visible light) are attractive for future approaches to energy conversion, synthesis, photocatalysis, and so forth. The growth of anisotropic metal nanostructures mediated by excitation of a localized surface plasmon resonance (LSPR) is a prototype example of such a reaction. Important aspects, notably the growth mechanism and a possible role of plasmonic “hot spots” within the metal nanostructures, remain poorly understood. Here, we use in situ electron microscopy to stimulate and image the plasmon-mediated growth of triangular Ag nanoprisms in solution. The quantification of the time-dependent evolution of the lateral size and thickness of …

Rules Based Analysis Engine For Application Layer Ids, David Scrobonia

Master's Theses

Web application attack volume, complexity, and costs have risen as people, companies, and entire industries move online. Solutions implemented to defend web applications against malicious activity have traditionally been implemented at the network or host layer. While this is helpful for detecting some attacks, it does not provide the gran- ularity to see malicious behavior occurring at the application layer. The AppSensor project, an application level intrusion detection system (IDS), is an example of a tool that operates in this layer. AppSensor monitors users within the application by observing activity in suspicious areas not able to be seen by traditional …

Hexarray: A Novel Self-Reconfigurable Hardware System, Fady Hussein

Boise State University Theses and Dissertations

Evolvable hardware (EHW) is a powerful autonomous system for adapting and finding solutions within a changing environment. EHW consists of two main components: a reconfigurable hardware core and an evolutionary algorithm. The majority of prior research focuses on improving either the reconfigurable hardware or the evolutionary algorithm in place, but not both. Thus, current implementations suffer from being application oriented and having slow reconfiguration times, low efficiencies, and less routing flexibility. In this work, a novel evolvable hardware platform is proposed that combines a novel reconfigurable hardware core and a novel evolutionary algorithm.

The proposed reconfigurable hardware core is a …

Analog And Mixed Signal Verification Using Satisfiability Solver On Discretized Models, Nikita Ramesh Wanjale

UNLV Theses, Dissertations, Professional Papers, and Capstones

With increasing demand of performance constraints and the ever reducing size of the IC chips, analog and mixed-signal designs have become indispensable and increasingly complex in modern CMOS technologies. This has resulted in the rise of stochastic behavior in circuits, making it important to detect all the corner cases and verify the correct functionality of the design under all circumstances during the earlier stages of the design process. It can be achieved by functional or formal verification methods, which are still widely unexplored for Analog and Mixed-Signal (AMS) designs.

Design Verification is a process to validate the performance of the …

Optimization Framework For Deployment Of Wireless Sensor Networks, Tajudeen Olawale Olasupo

Theses and Dissertations

In order to tackle the problem of network connectivity and sensing coverage in random placement of sensor nodes over an area of interest, this research presents an optimization and visualization framework for characterization and prediction of optimal deployments of large-scale wireless sensor networks (WSNs). This study presents efficient image processing algorithms for classification of deployment terrain in order to optimize deployment and connectivity coverage with required minimum number of nodes and transmission power. It reports formation of efficient models for WSN signal propagation under different terrain conditions. The study describes the developmental approach of the WSN optimization framework and visualization …

The Impact Of Different Propagation Environments On The Performance Of Wireless Sensor Networks, Abdallah Mubark Aldosary

Theses and Dissertations

This dissertation presents a methodology for evaluating the performance of wireless sensor network (WSN) protocols in different propagation environments. To create this methodology, practical RF propagation models that include many of the substantial features of different propagation environments are utilized, and radio energy models for different propagation environments are developed. Accurate environment-specific radio frequency (RF) propagation models should be utilized in order to improve the overall process of decision-making during pre-deployment of WSNs, to facilitate the deployment of the WSN, and to enhance the battery efficiency of sensing nodes so that the network lifetime can be prolonged. The investigating of …

Power Efficient High Temperature Asynchronous Microcontroller Design, Nathan William Kuhns

Graduate Theses and Dissertations

There is an increasing demand for dependable and efficient digital circuitry capable of operating in high temperature environments. Extreme temperatures have adverse effects on traditional silicon synchronous systems because of the changes in delay and setup and hold times caused by the variances in each device’s threshold voltage. This dissertation focuses on the design of the major functionality of an asynchronous 8051 microcontroller in Raytheon’s high temperature Silicon Carbide process, rated for operation over 300ºC. The microcontroller is designed in NULL Convention Logic, for which the traditional bus architecture used for data transfer would consume a large amount of power. …

A Data-Driven Approach For Benchmarking Energy Efficiency Of Warehouse Buildings, Wee Leong Lee, Kar Way Tan, Zui Young Lim

Research Collection School Of Computing and Information Systems

This study proposes adata-driven approach for benchmarking energy efficiency of warehouse buildings.Our proposed approach provides an alternative to the limitation of existingbenchmarking approaches where a theoretical energy-efficient warehouse was usedas a reference. Our approach starts by defining the questions needed to capturethe characteristics of warehouses relating to energy consumption. Using an existingdata set of warehouse building containing various attributes, we first cluster theminto groups by their characteristics. The warehouses characteristics derivedfrom the cluster assignments along with their past annual energy consumptionare subsequently used to train a decision tree model. The decision tree providesa classification of what factors contribute to different …

Cryptography And Data Security In Cloud Computing, Zheng Yan, Robert H. Deng, Vijay Varadharajan

Research Collection School Of Computing and Information Systems

Cloud computing offers a new way of services by re-arranging various resources and providing them to users based on their demands. It also plays an important role in the next generation mobile networks and services (5G) and Cyber-Physical and Social Computing (CPSC). Storing data in the cloud greatly reduces storage burden of users and brings them access convenience, thus it has become one of the most important cloud services. However, cloud data security, privacy and trust become a crucial issue that impacts the success of cloud computing and may impede the development of 5G and CPSC. First, storing data at …

Discovering Your Selling Points: Personalized Social Influential Tags Exploration, Yuchen Li, Kian-Lee Tan, Ju Fan, Dongxiang Zhang

Research Collection School Of Computing and Information Systems

Social influence has attracted significant attention owing to the prevalence of social networks (SNs). In this paper, we study a new social influence problem, called personalized social influential tags exploration (PITEX), to help any user in the SN explore how she influences the network. Given a target user, it finds a size-k tag set that maximizes this user’s social influence. We prove the problem is NP-hard to be approximated within any constant ratio. To solve it, we introduce a sampling-based framework, which has an approximation ratio of 1−ǫ 1+ǫ with high probabilistic guarantee. To speedup the computation, we devise more …

Performance Testing And Analysis Of Synchronous Reluctance Motor Utilizing Dual-Phase Magnetic Material, Patel B. Reddy, Ayman M. El-Refaie, Min Zou, Di Pan, James P. Alexander, Nidhishri Tapadia, Kevin Grace, Kum-Kang Huh, Frank Johnson

Electrical and Computer Engineering Faculty Research and Publications

While interior permanent magnet (1PM) machines have been considered the state-of-the art for traction motors, synchronous reluctance (SynRel) motors with advanced materials can provide a competitive alternative. 1PM machines typically utilize Neodymium 1ron Boron (NdFeB) permanent magnets, which pose an issue in terms of price, sustainability, demagnetization at higher operating temperatures, and uncontrolled generation. On the other hand, SynRel machines do not contain any magnets and are free from these issues. However, the absence of magnets as well the presence of bridges and centerposts limit the flux-weakening capability of a SynRel machine and limit the achievable constant power speed ratio …