Computer Engineering Commons^™

Machine Learning For Internet Of Things Data Analysis: A Survey, Mohammad Saeid Mahdavinejad, Mohammadreza Rezvan, Mohammadamin Barekatain, Peyman Adibi, Payam Barnaghi, Amit Sheth

Publications

Rapid developments in hardware, software, and communication technologies have facilitated the emergence of Internet-connected sensory devices that provide observations and data measurements from the physical world. By 2020, it is estimated that the total number of Internet-connected devices being used will be between 25 and 50 billion. As these numbers grow and technologies become more mature, the volume of data being published will increase. The technology of Internet-connected devices, referred to as Internet of Things (IoT), continues to extend the current Internet by providing connectivity and interactions between the physical and cyber worlds. In addition to an increased volume, the …

Cmos Radioactive Isotope Identification With Multichannel Analyzer And Embedded Neural Network, Samuel Murray

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

A radiation detection and identification system is designed and implemented to perform gamma ray spectroscopy on radioactive sources and identify which isotopes are present in the sources. A multichannel analyzer is implemented on an ASIC to process the signal produced from gamma rays detected by a scintillator and photomultiplier tube and to quantize the gamma ray energies to build a histogram. A fast, low memory embedded neural network is implemented on a microcontroller ASIC to identify the isotopes present in the gamma ray histogram produced by the multichannel analyzer in real time.

Advisors: Sina Balkir and Michael W. Hoffman

Advanced Recurrent Network-Based Hybrid Acoustic Models For Low Resource Speech Recognition, Jian Kang, Wei-Qiang Zhang, Wei-Wei Liu, Jia Liu, Michael T. Johnson

Electrical and Computer Engineering Faculty Publications

Recurrent neural networks (RNNs) have shown an ability to model temporal dependencies. However, the problem of exploding or vanishing gradients has limited their application. In recent years, long short-term memory RNNs (LSTM RNNs) have been proposed to solve this problem and have achieved excellent results. Bidirectional LSTM (BLSTM), which uses both preceding and following context, has shown particularly good performance. However, the computational requirements of BLSTM approaches are quite heavy, even when implemented efficiently with GPU-based high performance computers. In addition, because the output of LSTM units is bounded, there is often still a vanishing gradient issue over multiple layers. …

Tunable Plasmonic Resonances In Highly Porous Nano-Bamboo Si-Au Superlattice-Type Thin Films, Ufuk Kılıç, Alyssa Mock, René Feder, Derek Sekora, Matthew J. Hilfiker, Rafal Korlacki, Eva Schubert, Christos Argyropoulos, Mathias Schubert

Department of Electrical and Computer Engineering: Faculty Publications

We report on fabrication of spatially-coherent columnar plasmonic nanostructure superlattice-type thin films with high porosity and strong optical anisotropy using glancing angle deposition. Subsequent and repeated depositions of silicon and gold lead to nanometer-dimension subcolumns with controlled lengths. The superlattice-type columns resemble bamboo structures where smaller column sections of gold form junctions sandwiched between larger silicon column sections (“nano-bamboo”). We perform generalized spectroscopic ellipsometry measurements and finite element method computations to elucidate the strongly anisotropic optical properties of the highly-porous nano-bamboo structures. The occurrence of a strongly localized plasmonic mode with displacement pattern reminiscent of a dark quadrupole mode is …

Intelligent Computational Transportation, Yuming Zhang

Electrical and Computer Engineering ETDs

Transportation is commonplace around our world. Numerous researchers dedicate great efforts to vast transportation research topics. The purpose of this dissertation is to investigate and address a couple of transportation problems with respect to geographic discretization, pavement surface automatic examination, and traffic ow simulation, using advanced computational technologies. Many applications require a discretized 2D geographic map such that local information can be accessed efficiently. For example, map matching, which aligns a sequence of observed positions to a real-world road network, needs to find all the nearby road segments to the individual positions. To this end, the map is discretized by …

High-Performance Testbed For Vision-Aided Autonomous Navigation For Quadrotor Uavs In Cluttered Environments, Shakeeb Ahmad

Electrical and Computer Engineering ETDs

This thesis presents the development of an aerial robotic testbed based on Robot Operating System (ROS). The purpose of this high-performance testbed is to develop a system capable of performing robust navigation tasks using vision tools such as a stereo camera. While ensuring the computation of robot odometery, the system is also capable of sensing the environment using the same stereo camera. Hence, all the navigation tasks are performed using a stereo camera and an inertial measurement unit (IMU) as the main sensor suite. ROS is used as a framework for software integration due to its capabilities to provide efficient …

Compact Hardware Implementation Of A Sha-3 Core For Wireless Body Sensor Networks, Yi Yang, Debiao He, Neeraj Kumar, Sherali Zeadally

Information Science Faculty Publications

One of the most important Internet of Things applications is the wireless body sensor network (WBSN), which can provide universal health care, disease prevention, and control. Due to large deployments of small scale smart sensors in WBSNs, security, and privacy guarantees (e.g., security and safety-critical data, sensitive private information) are becoming a challenging issue because these sensor nodes communicate using an open channel, i.e., Internet. We implement data integrity (to resist against malicious tampering) using the secure hash algorithm 3 (SHA-3) when smart sensors in WBSNs communicate with each other using the Internet. Due to the limited resources (i.e., storage, …

Survey Results On Adults And Cybersecurity Education, Frank Breitinger, Joseph Ricci, Ibrahim Baggili

Electrical & Computer Engineering and Computer Science Faculty Publications

Cyberattacks and identity theft are common problems nowadays where researchers often say that humans are the weakest link in the security chain. Therefore, this survey focused on analyzing the interest for adults for ‘cyber threat education seminars’, e.g., how to project themselves and their loved ones. Specifically, we asked questions to understand a possible audience, willingness for paying / time commitment, or fields of interest as well as background and previous training experience. The survey was conducted in late 2016 and taken by 233 participants. The results show that many are worried about cyber threats and about their children exploring …

Adaptive Virtual Impedance Droop Control Based On Consensus Control Of Reactive Current, Zhilin Lu, Qing Wei, Yiyi Zhang, Junhui Zhao, Emad Manla

Electrical & Computer Engineering and Computer Science Faculty Publications

It is difficult to achieve accurate distribution of reactive power based on conventional droop control due to the line impedance mismatch in an islanded microgrid. An adaptive virtual impendence method based on consensus control of reactive current is proposed in this paper. A distributed control structure without the central controller has been established. In this structure, each distributed generation unit (DG) is an independent agent, one-way communication is used between the adjacent DGs, and the reactive power sharing is equivalent to a problem of reactive power current consensus. It has been proven that the system is asymptotically stable under the …

A Neuromorphic Quadratic, Integrate, And Fire Silicon Neuron With Adaptive Gain, David Parent, Eric Basham

Faculty Publications

An integrated circuit implementation of a silicon neuron was designed, manufactured, and tested. The circuit was designed using the Quadratic, Integrate, and Fire (QIF) neuron model in 0.5 µm silicon technology. The neuron implementation was optimized for low current consumption, drawing only 1.56 mA per QIF circuit and utilized hysteretic reset, non-inverting integrator, and voltage-squarer circuits. The final area of each circuit in silicon was 268 µm height × 400 µm width. This design is the first IC of its kind for this neuron model and is successfully able to output true spiking that follows the behaviors of bistability, monotonic, …

Grasp Synthesis For Purposeful Fracturing Of Object, Mahyar Abdeetedal, Mehrdad Kermani Ph.D., P.Eng.

Electrical and Computer Engineering Publications

No abstract provided.

Multiuser Coding And Signal Processing In A Low Power Sensor Network, Dongqi Lai

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

Backscatter communication system is a wireless communication system that is used by both academic community and industry circles in recent years. This communication system only requires ultra-low power usage and simple design of the sensors. This project is using backscatter communication system to transmit data with backscatter tags. The method we used is semi-passive backscatter communication. This project focuses on transmitting signals with multiple sensors so there is a problem about distinguishing the signal reflected by different nodes. We modulated the transmitting digital signal with Walsh function to solve the problem of separating the signals between different nodes. By using …

Implementation Of Vision Processing Tasks On A Smart Camera Platform Using Neighborhood Processors, Dingyi Hong

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

Two applications of vision processing on a smart camera platform using neighborhood processors are presented. A smart camera application of real-time trajectory calculation for tracking objects and predicting their path of motion by using a single intelligent camera or a dual camera system are designed, simulated and implemented. Another application of object recognition with a key points algorithm for detecting simple shaped objects and locating the camera position within a 3-D coordinate system via imaging by using artificial neural network is applied to provide quick and accurate processing on a neighborhood-level parallel processor or other limited vision chip. For all …

Search Methods For Mobile Manipulator Performance Measurement, Samuel Nana Yaw Amoako-Frimpong

Master's Theses (2009 -)

Mobile manipulators are a potential solution to the increasing need for additional flexibility and mobility in industrial robotics applications. However, they tend to lack the accuracy and precision achieved by fixed manipulators, especially in scenarios where both the manipulator and the autonomous vehicle move simultaneously. This thesis analyzes the problem of dynamically evaluating the positioning error of mobile manipulators. In particular, it investigates the use of Bayesian methods to predict the position of the end-effector in the presence of uncertainty propagated from the mobile platform. Simulations and real-world experiments are carried out to test the proposed method against a deterministic …

Experience Constructing The Artifact Genome Project (Agp): Managing The Domain's Knowledge One Artifact At A Time, Cinthya Grajeda, Laura Sanchez, Ibrahim Baggili, Devon R. Clark, Frank Breitinger

Electrical & Computer Engineering and Computer Science Faculty Publications

While various tools have been created to assist the digital forensics community with acquiring, processing, and organizing evidence and indicating the existence of artifacts, very few attempts have been made to establish a centralized system for archiving artifacts. The Artifact Genome Project (AGP) has aimed to create the largest vetted and freely available digital forensics repository for Curated Forensic Artifacts (CuFAs). This paper details the experience of building, implementing, and maintaining such a system by sharing design decisions, lessons learned, and future work. We also discuss the impact of AGP in both the professional and academic realms of digital forensics. …

Analysis Of Bulk Power System Resilience Using Vulnerability Graph, Md Ariful Haque

Computational Modeling & Simulation Engineering Theses & Dissertations

Critical infrastructure such as a Bulk Power System (BPS) should have some quantifiable measure of resiliency and definite rule-sets to achieve a certain resilience value. Industrial Control System (ICS) and Supervisory Control and Data Acquisition (SCADA) networks are integral parts of BPS. BPS or ICS are themselves not vulnerable because of their proprietary technology, but when the control network and the corporate network need to have communications for performance measurements and reporting, the ICS or BPS become vulnerable to cyber-attacks. Thus, a systematic way of quantifying resiliency and identifying crucial nodes in the network is critical for addressing the cyber …

Network Traffic Time Series Performance Analysisusing Statistical Methods, Purnawansyah Purnawansyah, Haviluddin Haviluddin, Rayner Alfred, Achmad Fanany Onnlita Gaffar

Knowledge Engineering and Data Science

This paper presents an approach for a network traffic characterization by using statistical techniques. These techniques are obtained using the decomposition, winter’s exponential smoothing and autoregressive integrated moving average (ARIMA). In this paper, decomposition and winter’s exponential smoothing techniques were used additive and multiplicative model. Then, ARIMA based-on Box-Jenkins methodology. The results of ARIMA (1,0,2) was shown the best model that can be used to the internet network traffic forecasting

Decision Support System Determination Of Main Work Unitin Wpp-711 Using Fuzzy Topsis, Hozairi Hozairi, Yaser Krisnafi

Knowledge Engineering and Data Science

Decision-making to determine the working units for being prioritized to be developed in order to improve fishery monitoring in WPP-711 is imperative. The Ministry of Maritime Affairs and Fisheries should make no mismatch decision-making through long-term calculation and analysis. The problem of determining the priority of working units is a complex problem, thus it is required to find an appropriate method to avoid a mismatch decision. Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) is a decision-making method capable of solving multi-criteria problems. TOPSIS working principle determines the alternative by considering the shortest distance from the positive …

Market Basket Analysis To Identify Customer Behaviorsby Way Of Transaction Data, Fachrul Kurniawan, Binti Umayah, Jihad Hammad, Supeno Mardi Susiki Nugroho, Mochammad Hariadi

Knowledge Engineering and Data Science

Transaction data is a set of recording data result in connections with sales-purchase activities at a particular company. In these recent years, transaction data have been prevalently used as research objects in means of discovering new information. One of the possible attempts is to design an application that can be used to analyze the existing transaction data. That application has the quality of market basket analysis. In addition, the application is designed to be desktop-based whose components are able to process as well as re-log the existing transaction data. The used method in designing this application is by way of …

Capital Letter Pattern Recognition In Text To Speechby Way Of Perceptron Algorithm, Novan Wijaya

Knowledge Engineering and Data Science

Computer vision is a data transformation retrieved or generated from webcam into another form in means of determining decision. All kinds of transformations are carried through to attain specific aims. One of the supporting techniques in implementing computer vision on a system is digital image processing as the objective of digital image processing is to transform digital-formatted picture so that it can be processed in computer. Computer vision and digital image processing can be implemented in a system of capital letter introduction and real-time handwriting reading on a whiteboard supported by artificial neural network mode “perceptron algorithm” used as a …

Sql Logic Error Detection Using Start End Mid Algorithm, Jevri Tri Ardiansyah, Aji Prasetya Wibawa, Triyanna Widiyaningtyas, Okazaki Yasuhisa

Knowledge Engineering and Data Science

Database is an important part of a system and it stores data to be manipulated. SQL (Structured Query Language) is used for manipulating those data to extract information and make decision. There are two types of error which make SQL is challenging to learn, namely syntax error and logic error. Compiler can detect syntax error, but it does not show error warning while logical error occurred. It makes logic error more difficult to understand than syntax error. A web based SQL compiler with errors detection ability by using Start End Mid algorithm is then developed, To help database's user to …

Multiple-Change-Point Modeling And Exact Bayesian Inference Of Degradation Signal For Prognostic Improvement, Yuxin Wen, Jianguo Wu, Qiang Matthew Zhou, Tzu-Liang Bill Tseng

Engineering Faculty Articles and Research

Prognostics play an increasingly important role in modern engineering systems for smart maintenance decision-making. In parametric regression-based approaches, the parametric models are often too rigid to model degradation signals in many applications. In this paper, we propose a Bayesian multiple-change-point (CP) modeling framework to better capture the degradation path and improve the prognostics. At the offline modeling stage, a novel stochastic process is proposed to model the joint prior of CPs and positions. All hyperparameters are estimated through an empirical two-stage process. At the online monitoring and remaining useful life (RUL) prediction stage, a recursive updating algorithm is developed to …

A Study Of Scalability And Cost-Effectiveness Of Large-Scale Scientific Applications Over Heterogeneous Computing Environment, Arghya K. Das

LSU Doctoral Dissertations

Recent advances in large-scale experimental facilities ushered in an era of data-driven science. These large-scale data increase the opportunity to answer many fundamental questions in basic science. However, these data pose new challenges to the scientific community in terms of their optimal processing and transfer. Consequently, scientists are in dire need of robust high performance computing (HPC) solutions that can scale with terabytes of data.

In this thesis, I address the challenges in three major aspects of scientific big data processing as follows: 1) Developing scalable software and algorithms for data- and compute-intensive scientific applications. 2) Proposing new cluster architectures …

Cryptki: Mobile Hardware Wallet, Derrick Chan, Rowan Decker, William Nguyen, Yuya Oguchi

Interdisciplinary Design Senior Theses

Cryptocurrencies are rapidly receiving mainstream attention and adoption. As a result, new technologies are developing to store and transact cryptocurrencies to keep up with a rapidly developing market. We have developed a way to utilize a mobile phone to communicate with the Ethereum blockchain in order to monitor and initiate cryptocurrency transactions. The project allows users to create new Ethereum addresses and to send arbitrary amounts of Ether to existing Ethereum addresses, while maintaining security for the end user. We conclude that this method of communication with the Ethereum blockchain is viable and is an avenue for exploration in the …

B.O.G.G.L.E.S.: Boundary Optical Geographic Lidar Environment System, Miguel Chapa, Evan Hoerl, Isaac Jorgensen, Carl Maggio

Interdisciplinary Design Senior Theses

The purpose of this paper is to describe a pseudo X-ray vision system that pairs a Lidar scanner with a visualization device. The system as a whole is referred to as B.O.G.G.L.E.S. There are several key factors that went into the development of this system and the background information and design approach are thoroughly described. B.O.G.G.L.E.S functionality is depicted through the use of design constraints and the analysis of test results. Additionally, many possible developments for B.O.G.G.L.E.S are proposed in the paper. This indicates that there are various avenues of improvement for this project that could be implemented in the …

Camera-Based Distance Sensor, Kai Schmidt, Evan Holmes

Interdisciplinary Design Senior Theses

While working on a robotics project at the electrical contracting company for which we work, we discovered a gap in the electronic distance sensor market in terms of range, accuracy, precision, and cost. We designed and constructed a prototype for an electronic distance sensing component which utilizes a camera, laser, and image processor to measure distances. The laser is pointed at a surface and an image of the laser dot is captured. An image processing algorithm determines the pixel position of the dot in the image, and this position is compared to a lookup table of known values to determine …

Halo - A Personal Iot Air Monitor Powered By Harvested Energy, Benjamin Lampe, Taylor Mau, Samantha Morehead, Naeem Turner-Bandele

Interdisciplinary Design Senior Theses

Urban air pollution leads to widespread respiratory illness and millions of deaths annually. PM2.5, particulate matter with a diameter less than 2.5 micrometers, is the product of many common combustion reactions and poses a particularly serious health risk. Its small size allows it to penetrate deep into the lungs and enter the bloodstream. Existing air quality monitors are aimed at scientific research, di↵erentiating between pollutants and providing high accuracy in measurement. These devices are prohibitively expensive and cannot easily be carried around. Due to the highly localized nature of air pollution, and in order to allow individuals and institutions to …

Rf Roaming System Locator: A Modular Omnidirectional Antenna System, George Stathakis, Josh Sullivan, Christian Ayscue

Interdisciplinary Design Senior Theses

Drones are increasingly common in everything from entertainment to delivery services. Currently, GPS and wireless triangulation are the two main methods of tracking drones and collision avoidance. The main problem with these two methods are accuracy and mobility. This thesis goes into building a system that is able to solve the two main drawbacks, by using a completely contained antenna system. The system is robust and can work in a variety of environments and situations. While the thesis focuses on drone tracking, the system is built with modularity in mind and can be adapted to track other RF signals with …

Foreword Special Section On Electrical Contacts, Ronald A. Coutu Jr., Ravi Mahajan

Electrical and Computer Engineering Faculty Research and Publications

Welcome to the Special Topics Section dedicated to the 2016 Holm Conference on Electrical Contacts. This special section contains eight high-quality papers that comprehensively describe the state of the art and potential future directions for topics of great interest to our readers. The Editor-in-Chief (EIC), in consultation with the other EICs, Associate Editors (AEs), and domain experts, selects the topics for the special sections, and a Guest Editor or AE (GE/AE), who is a leading expert in the technical area, then directs the solicitation and peer review of the papers. In cases where the GE/AE is also an author, the …

Rotation Of Two-Petal Laser Beams In The Near Field Of A Spiral Microaxicon, S. S. Stafeev, Liam O'Faolain, M. V. Kotlyar

Cappa Publications

Using a spiral microaxicon with the topological charge 2 and NA = 0.6 operating at a 532-nm wavelength and fabricated by electron-beam lithography, we experimentally demonstrate the rotation of a two-petal laser beam in the near field (several micrometers away from the axicon surface). The estimated rotation rate is 55 °/mm and linearly dependent on the on-axis distance, with the theoretical rotation rate being 53 °/mm. The experimentally measured rotation rate is found to be linear and coincident with the simulation results only on the on-axis segment from 1.5 to 3 mm. The experimentally measured rotation rate is 66 °/mm …