Other Computer Engineering Commons^™

Performance Comparison Of Binarized Neural Network With Convolutional Neural Network, Lopamudra Baruah

Dissertations, Master's Theses and Master's Reports

Deep learning is a trending topic widely studied by researchers due to increase in the abundance of data and getting meaningful results with them. Convolutional Neural Networks (CNN) is one of the most popular architectures used in deep learning. Binarized Neural Network (BNN) is also a neural network which consists of binary weights and activations. Neural Networks has large number of parameters and overfitting is a common problem to these networks. To overcome the overfitting problem, dropout is a solution. Randomly dropping some neurons along with its connections helps to prevent co-adaptations which finally help in reducing overfitting. Many researchers …

Brief Study Of Classification Algorithms In Machine Learning, Ramesh Sankara Subbu

Dissertations and Theses

The purpose of this study is to briefly learn the theory and implementation of three most commonly used Machine Learning algorithms: k-Nearest Neighbors (kNN), Decision Trees and Naïve Bayes. All these algorithms fall under the Classification algorithm category of Unsupervised Machine Learning. This paper is constructed structurally in explaining the working theory behind each algorithm and an implementation of a Machine Learning problem solved by each algorithm. KNN algorithm is designed using Euclidean distance measurement and Decision Trees make use of ID3 algorithm as a basis. We conclude the study by providing an overall picture of its strengths and weaknesses …

Design Automation For Carbon Nanotube Circuits Considering Performance And Security Optimization, Lin Liu

Dissertations, Master's Theses and Master's Reports

As prevailing copper interconnect technology advances to its fundamental physical limit, interconnect delay due to ever-increasing wire resistivity has greatly limited the circuit miniaturization. Carbon nanotube (CNT) interconnects have emerged as promising replacement materials for copper interconnects due to their superior conductivity. Buffer insertion for CNT interconnects is capable of improving circuit timing of signal nets with limited buffer deployment. However, due to the imperfection of fabricating long straight CNT, there exist significant unidimensional-spatially correlated variations on the critical CNT geometric parameters such as the diameter and density, which will affect the circuit performance.

This dissertation develops a novel timing …

Respiratory Prediction And Image Quality Improvement Of 4d Cone Beam Ct And Mri For Lung Tumor Treatments, Seonyeong Park

Theses and Dissertations

Identification of accurate tumor location and shape is highly important in lung cancer radiotherapy, to improve the treatment quality by reducing dose delivery errors. Because a lung tumor moves with the patient's respiration, breathing motion should be correctly analyzed and predicted during the treatment for prevention of tumor miss or undesirable treatment toxicity. Besides, in Image-Guided Radiation Therapy (IGRT), the tumor motion causes difficulties not only in delivering accurate dose, but also in assuring superior quality of imaging techniques such as four-dimensional (4D) Cone Beam Computed Tomography (CBCT) and 4D Magnetic Resonance Imaging (MRI). Specifically, 4D CBCT used in CBCT …

Electronic Deer Warning System, David Zhuo, Anlang Lu

Computer Engineering

Deer-vehicle collisions (DVCs) are extremely dangerous, often injuring or even killing drivers. Unfortunately, this form of automotive accident is commonplace in the United States. According to the NHTSA, DVCs result in 200 human deaths a year.2

Despite these deadly incidents, there currently are no deployed federal or state systems for preventing DVCs. There are many consumer electronic deer deterrent products, but their long-term effectiveness is questionable.3 In fact, there does not appear to be much research into electronic deer deterrent systems. Aside from constant audio output and electric shock, no other means of electronic deterrent exist. Even if fixed deterrents …

A System For Monitoring And Managing Indoor Air Quality And Environmental Conditions, Ali Ibrahim

Boise State University Theses and Dissertations

The quality of indoor air depends on different types of pollutant sources existing in a semi-enclosed environment. The sources can be biological, chemical, or toxic pollutants. These sources can cause health issues and discomfort for occupants. One of the indicators of poor indoor air quality is Carbon Dioxide (CO₂). CO₂ can be used to indicate the indoor air exchange rate. The lack of air exchange means higher levels of CO₂. High levels of indoor particulates can also be an indication of poor air quality. Due to the lack of fresh air, air circulation, and air …

Pothole Reporting System, Alissa L. Mcgill, Brian G. Simmons, Sean D. Querry, Elizabeth J. Hammell

Williams Honors College, Honors Research Projects

The purpose of this project is to create a pothole detection device that can be attached to the underside of a commercial vehicle. Potholes cost motorists around 6.4 billion dollars annually, thus demonstrating the need for a system to aid with the detection and reporting of potholes. The four systems we needed to consider for the implementation of this project were the power system, the sensing system, the data processing system, and the reporting and logging system. Power pulled from the vehicle will enable the sensors and data processing module. The data processing module will analyze the readings from the …

Autonomous Navigation With Obstacle Avoidance For Unmanned Aircraft Systems Using Milp, James A. Devens

Theses and Dissertations

Autonomous coordination among multiple aerial vehicles to ensure a collision free airspace is a critical aspect of today’s airspace. With the rise of Unmanned Aerial Vehicles (UAVs) in the military and commercial sectors, obstacle avoidance in a densely populated airspace is necessary. This thesis investigates finding optimal or near-optimal trajectories in real-time for aircraft in complex airspaces containing a large number of obstacles. The solution for the trajectories is described as a linear program subject to mixed integer constraints, known as a Mixed Integer Linear Program (MILP). The resulting MILP problem is solved in real time using a well-known, public …

In-Shoe Plantar Pressure System To Investigate Ground Reaction Force Using Android Platform, Ahmed A. Mostfa

Theses and Dissertations

Human footwear is not yet designed to optimally relieve pressure on the heel of the foot. Proper foot pressure assessment requires personal training and measurements by specialized machinery. This research aims to investigate and hypothesize about Preferred Transition Speed (PTS) and to classify the gait phase of explicit variances in walking patterns between different subjects. An in-shoe wearable pressure system using Android application was developed to investigate walking patterns and collect data on Activities of Daily Living (ADL). In-shoe circuitry used Flexi-Force A201 sensors placed at three major areas: heel contact, 1st metatarsal, and 5th metatarsal with a PIC16F688 microcontroller …

Real-Time Digital Effects Processing Using Ios, Jonah W. Clinard

Computer Engineering

In today’s society, we are seeing incredible improvements in terms of creating smaller technological devices that behave more and more like the personal computers of yesterday. Mobile “Smart” devices, in particular, are becoming incredibly powerful not just in terms of processing power, but in the fact that they are able to provide assistance to users in their everyday lives. Application developers are now able utilize the power and size of these devices, to create and realize ideas that would have been previously viewed as impossible. This project applies the fields of digital signal processing, music, and mobile application development, to …

Estimation On Gibbs Entropy For An Ensemble, Lekhya Sai Sake

Electronic Theses, Projects, and Dissertations

In this world of growing technology, any small improvement in the present scenario would create a revolution. One of the popular revolutions in the computer science field is parallel computing. A single parallel execution is not sufficient to see its non-deterministic features, as same execution with the same data at different time would end up with a different path. In order to see how non deterministic a parallel execution can extend up to, creates the need of the ensemble of executions. This project implements a program to estimate the Gibbs Entropy for an ensemble of parallel executions. The goal is …

Rfid Microscope Lab, Patricia Carranza

Computer Engineering

The RFID Microscope Lab is a new exhibit created for the San Luis Obispo Children's Museum. The goal of the project is to create a modern, interactive exhibit that will teach children about different natural specimens through the use of technology. A computer, custom software, and RFID technology, will be used to display facts, microscopic images, and short videos of ten different specimens.

Robust And Real-Time Stereo Matching On Parallel Graphics Hardware Using Gradient-Based Disparity Refinement, Jedrzej Kowalczuk

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

Computer vision attempts to provide camera-equipped machines with visual perception, i.e., the capability to comprehend their surroundings through the analysis and understanding of images. The ability to perceive depth is a vital component of visual perception that enables machines to interpret the three-dimensional structure of their surroundings and allows them to navigate through the environment. In computer vision, depth perception is achieved via stereo matching, a process that identifies correspondences between pixels in images acquired using a pair of horizontally offset cameras. It is possible to calculate depths from correspondences or, more specifically, the positional offsets (disparities) between pixels in …

Disc Golf Locator, Christian Wallenfelsz, Shane Gamble, Noah Sanor, Brandon Linhart

Electrical and Computer Engineering Faculty Research

Disc golf is a game similar to traditional golf where players throw small plastic discs into chain-link nets. Disc golf courses cover several acres containing lakes, small wooded areas, large bushes, and grassy fields. It is not uncommon to accidentally throw a golf disc into the woods or bushes, so it is the goal of this project to create a device to locate the disc and make suggestions for the player to improve performance. A small device will be attached the disc which will track its location and flight characteristics. The device will contain a GPS receiver, an inertial measurement …

Impact Of Detector-Element Active-Area Shape And Fill Factor On Image Sampling, Restoration, And Super-Resolution, Russell C. Hardie, Douglas R. Droege, Alexander J. Dapore, Mark E. Greiner

Electrical and Computer Engineering Faculty Publications

In many undersampled imaging systems, spatial integration from the individual detector elements is the dominant component of the system point spread function (PSF). Conventional focal plane arrays (FPAs) utilize square detector elements with a nearly 100% fill factor, where fill factor is defined as the fraction of the detector element area that is active in light detection. A large fill factor is generally considered to be desirable because more photons are collected for a given pitch, and this leads to a higher signal-to-noise-ratio (SNR). However, the large active area works against super-resolution (SR) image restoration by acting as an additional …

Comparing The Efficiency Of Heterogeneous And Homogeneous Data Center Workloads, Brandon Kimmons

College of Graduate Studies: Theses & Dissertations

Abstract

Information Technology, as an industry, is growing very quickly to keep pace with increased data storage and computing needs. Data growth, if not planned or managed correctly, can have larger efficiency implications on your data center as a whole. The long term reduction in efficiency will increase costs over time and increase operational overhead. Similarly, increases in processor efficiency have led to increased system density in data centers. This can increase cost and operational overhead in your data center infrastructure.

This paper proposes the idea that balanced data center workloads are more efficient in comparison to similar levels of …

Hybrid Single And Dual Pattern Structured Light Illumination, Minghao Wang

Theses and Dissertations--Electrical and Computer Engineering

Structured Light Illumination is a widely used 3D shape measurement technique in non-contact surface scanning. Multi-pattern based Structured Light Illumination methods reconstruct 3-D surface with high accuracy, but are sensitive to object motion during the pattern projection and the speed of scanning process is relatively long. To reduce this sensitivity, single pattern techniques are developed to achieve a high speed scanning process, such as Composite Pattern (CP) and Modified Composite Pattern (MCP) technique. However, most of single patter techniques have a significant banding artifact and sacrifice the accuracy. We focus on developing SLI techniques can achieve both high speed, high …

Detection Of Variable Retention Time In Dram, Neraj Kumar

Dissertations and Theses

This thesis investigates a test method to detect the presence of Variable Retention Time (VRT) bits in manufactured DRAM. The VRT bits retention time is modeled as a 2-state random telegraph process that includes miscorrelation between test and use. The VRT defect is particularly sensitive to test and use conditions. A new test method is proposed to screen the VRT bits by simulating the use conditions during manufacturing test. Evaluation of the proposed test method required a bit-level VRT model to be parameterized as a function of temperature and voltage conditions. The complete 2-state VRT bit model combines models for …

Model-Free Method Of Reinforcement Learning For Visual Tasks, Jeff S. Soldate, Jonghoon Jin, Eugenio Culurciello

The Summer Undergraduate Research Fellowship (SURF) Symposium

There has been success in recent years for neural networks in applications requiring high level intelligence such as categorization and assessment. In this work, we present a neural network model to learn control policies using reinforcement learning. It takes a raw pixel representation of the current state and outputs an approximation of a Q value function made with a neural network that represents the expected reward for each possible state-action pair. The action is chosen an \epsilon-greedy policy, choosing the highest expected reward with a small chance of random action. We used gradient descent to update the weights and biases …

Foss Big Data Storage Solution, Nurdeen Salami

STAR Program Research Presentations

NASA projects require a reliable approach to store large volumes of data. Accordingly, it is crucial to adopt a lightweight, reliable, and scalable database. Current NASA databases bear costly license fees with undesirable speed and flexibility. The purpose of utilizing the AERO Institute as an IT test bed, or “Sandbox,” is to design, build, test, and implement software solutions prior to transfer to NASA projects. Cassandra coupled with the Astyanax API is a viable solution for storing big data. Store a minimum of 2GB of C-FOSS data in multiple file formats (.csv, .log, .xml, and .jpg). Use benchmark tests to …

Ultraviolet Led Biofouling Mitigation, Andrew Lam

Computer Engineering

The goal is to determine if low-cost UV LEDs can mitigate marine biofouling on small glass or acrylic camera lenses. A microprocessor-controlled experimental setup to control the illumination of low-cost UV LEDs of various wavelength and packaging was fashioned. The system consists of a programmed microcontroller, a manufactured LED breakout interface, and a submergible UV LED array enclosed in a borosilicate glass tube. A preliminary qualitative assessment of four different UV LEDs was conducted during a three-week deployment of the experimental setup in the raw seawater system at the Cal Poly Center for Costal and Marine Sciences in Avila Beach, …

Team Omnimouse, Derek J. Halman, Josh B. Porter, Steven A. Silver, Ian S. Stemper

Computer Engineering

INFORMATION, DATA, FIGURES AND DRAWINGS EMBODIED IN THIS DOCUMENT ARE STRICTLY CONFIDENTIAL AND ARE SUPPLIED ON THE UNDERSTANDING THAT THEY WILL NOT BE DISCLOSED TO THIRD PARTIES WITHOUT THE PRIOR WRITTEN CONSENT OF QUALITY OF LIFE PLUS.

Mos Current Mode Logic (Mcml) Analysis For Quiet Digital Circuitry And Creation Of A Standard Cell Library For Reducing The Development Time Of Mixed Signal Chips, David Marusiak

Master's Theses

Many modern digital systems use forms of CMOS logical implementation due to the straight forward design nature of CMOS logic and minimal device area since CMOS uses fewer transistors than other logic families. To achieve high-performance requirements in mixed-signal chip development and quiet, noiseless circuitry, this thesis provides an alternative toCMOSin the form of MOS Current Mode Logic (MCML). MCML dissipates constant current and does not produce noise during value changing in a circuit CMOS circuits do. CMOS logical networks switch during clock ticks and with every device switching, noise is created on the supply and ground to deal with …

A Comparison Of Image Processing Techniques For Bird Detection, Elsa Reyes

Master's Theses

Orchard fruits and vegetable crops are vulnerable to wild birds and animals. These wild birds and animals can cause critical damage to the produce. Traditional methods of scaring away birds such as scarecrows are not long-term solutions but short-term solutions. This is a huge problem especially near areas like San Luis Obispo where there are vineyards. Bird damage can be as high as 50% for grapes being grown in vineyards. The total estimated revenue lost annually in the 10 counties in California due to bird and rodent damage to 22 selected crops ranged from $168 million to $504 million (in …

Detection And Control Of Small Civilian Uavs, Matthew Peacock

Theses : Honours

With the increasing proliferation of small civilian Unmanned Aerial Vehicles (UAVs), the threat to critical infrastructure (CI) security and privacy is now widely recognised and must be addressed. These devices are easily available at a low cost, with their usage largely unrestricted allowing users to have no accountability. Further, current implementations of UAVs have little to no security measures applied to their control interfaces. To combat the threat raised by small UAVs, being aware of their presence is required, a task that can be challenging and often requires customised hardware.

This thesis aimed to address the threats posed by the …

Vehicular Motion Sensor: Developing A Wide-Range Motion Sensing Alarm System, Joshua Isaacson

Senior Honors Theses

Vehicular safety has become a serious concern in recent years. Many drivers have difficulty backing out of parking spaces, especially when large trucks and sport utility vehicles block the peripheral view from smaller vehicles. This can lead to accidents and pedestrian injuries when drivers are unable to see or do not pay careful attention to their surroundings.

Vehicular motion sensor systems can alert drivers of approaching obstacles when attempting to back out of parking spaces with limited visibility. This thesis aims to explain the limitations of current systems and the research conducted by the author to develop a prototype for …

Enhancing Electromagnetic Side-Channel Analysis In An Operational Environment, David P. Montminy

Theses and Dissertations

Side-channel attacks exploit the unintentional emissions from cryptographic devices to determine the secret encryption key. This research identifies methods to make attacks demonstrated in an academic environment more operationally relevant. Algebraic cryptanalysis is used to reconcile redundant information extracted from side-channel attacks on the AES key schedule. A novel thresholding technique is used to select key byte guesses for a satisfiability solver resulting in a 97.5% success rate despite failing for 100% of attacks using standard methods. Two techniques are developed to compensate for differences in emissions from training and test devices dramatically improving the effectiveness of cross device template …

Adaptive Ofdm For Wireless Interconnect In Confined Enclosures, Vit Sipal, Javier Gelabert, Christopher J. Stevens, Ben Allen, David Edwards

Articles

This letter considers and recommends OFDM with adaptive subcarrier modulation as a suitable candidate for wireless UWB communication in computer chassis. A rigorous measurement campaign studies the guaranteed spectral efficiency. It concludes that enhancement of the existing WiMedia OFDM systems with a bandwidth of 528 MHz in order to support adaptive OFDM would enable data-rates above 1 Gbps over short ranges, i.e. the spectral efficiency would be doubled. Moreover, the guaranteed spectral efficiency is shown to increase with bandwidth, i.e. the guaranteed data-rate increases better than linearly with bandwidth.

Obd2 Pid Reader, Andrew Fong

Computer Engineering

The most current standard on automobiles for monitoring data is OBD-II. Using On board diagnostic Parameter ID (OBD PID) codes hobbyists and mechanics have the ability to monitor, chart, and obtain data on cars by communicating to the ECU. The OBD-II connector is often located under the driver’s side inside of the car. The hardware will consist of a generic Bluetooth OBD2 connector and a laptop running windows. The software will be an program exe created by visual basic. The software created in visual basic will allow the user to examine PID codes in order to record and discover new …

Practical Irrigation Scheduling Program, Dominic Sween

BioResource and Agricultural Engineering

This senior project discusses the design, construction, and evaluation of an irrigation scheduling program that aids users in alfalfa irrigation management, with the potential for application with other crops. The program uses a very accurate irrigation prediction model that forecasts what the estimated irrigation need of each week will be, as well as the number of irrigations needed to satisfy the requirement. The model was found to predict the sum of the actual required weekly irrigation amount within less than 1% of the true value. The program was based off the single crop coefficient approach that was outlined previously by …