Other Electrical and Computer Engineering Commons^™

An End-To-End Face Recognition System Evaluation Framework, James Andrew Duncan

Graduate Theses, Dissertations, and Problem Reports (ETD)

The performance of face recognition system components is traditionally reported using metrics such as the Receiver Operating Characteristic (ROC), Cumulative Match Characteristic (CMC), and Identification Error Tradeoff (IET). Recently, new metrics have been published to take advantage of annotation-dense datasets such as IARPA Janus Benchmark-Surveillance and IARPA Janus Benchmark-Multi Domain Face to describe end-to-end face recognition system performance. Unlike traditional (component-level) analysis, end-to-end analysis of a system produces a metric proportional to the experience of a user of a face recognition system. The End-to-End Cumulative Match Characteristic (E2ECMC) summarizes detection, identity consolidation, and identity retrieval performance. The End-to-End Subject Cumulative …

Interoperability Of Contact And Contactless Fingerprints Across Multiple Fingerprint Sensors, Brady M. Williams

Graduate Theses, Dissertations, and Problem Reports (ETD)

Contactless fingerprinting devices have grown in popularity in recent years due to speed and convenience of capture. Also, due to the global COID-19 pandemic, the need for safe and hygienic options for fingerprint capture are more pressing than ever. However, contactless systems face challenges in the areas of interoperability and matching performance as shown in other works. In this paper, we present a contactless vs. contact interoperability assessment of several contactless devices, including cellphone fingerphoto capture. During the interoperability assessment, the quality of the fingerprints was considered using the NBIS NFIQ software with the contact-based fingerprint performing the best overall …

Weed Recognition In Agriculture: A Mask R-Cnn Approach, Sruthi Keerthi Valicharla

Graduate Theses, Dissertations, and Problem Reports (ETD)

Recent interdisciplinary collaboration on deep learning has led to a growing interest in its application in the agriculture domain. Weed control and management are some of the crucial tasks in agriculture to maintain high crop productivity. The inception phase of weed control and management is to successfully recognize the weed plants, followed by providing a suitable management plan. Due to the complexities in agriculture images, such as similar colour and texture, we need to incorporate a deep neural network that uses pixel-wise grouping for identifying the plant species. In this thesis, we analysed the performance of one of the most …

Integration Of Deep Hashing And Channel Coding For Biometric Security And Biometric Retrieval, Veeru Talreja

Graduate Theses, Dissertations, and Problem Reports (ETD)

In the last few years, the research growth in many research and commercial fields are due to the adoption of state of the art deep learning techniques. The same applies to even biometrics and biometric security. Additionally, there has been a rise in the development of deep learning techniques used for approximate nearest neighbor (ANN) search for retrieval on multi-modal datasets. These deep learning techniques knows as deep hashing (DH) integrate feature learning and hash coding into an end-to-end trainable framework. Motivated by these factors, this dissertation considers the integration of deep hashing and channel coding for biometric security and …

Identical Twins As A Facial Similarity Benchmark For Human Facial Recognition, John Andrew Mccauley

Graduate Theses, Dissertations, and Problem Reports (ETD)

The problem of distinguishing identical twins and non-twin look-alikes in automated facial recognition (FR) applications has become increasingly important with the widespread adoption of facial biometrics. Due to the high facial similarity of both identical twins and look-alikes, these face pairs represent the hardest cases presented to facial recognition tools. This work presents an application of one of the largest twin datasets compiled to date to address two FR challenges: 1) determining a baseline measure of facial similarity between identical twins and 2) applying this similarity measure to determine the impact of doppelgangers, or look-alikes, on FR performance for large …

Electronic Profiling Of Synthetic Dna Using Schottky Junctions, Souhad M.A Daraghma

Student Works (2020-2029)

Deoxyribonucleic acid (DNA) has attracted a lot of attention lately owing to the discovery of its semiconducting property and is considered as an interesting material that could find applications in nanotechnology and electronic devices. In-depth understanding of its charge transfer mechanism is however required for effective development of DNA-based technology. This unfortunately remains still a non-trivial task despite the numerous theoretical and experimental studies that have been conducted to date. The complexity of the previously employed methods, and their lack of accuracy has made it difficult to grasp the clear understanding of the electronic behaviors of the DNA molecules under …

Technique Design Of Filter On Surface-Acoustic Waves, Dilmurod Abdujalilovich Davronbekov, Zafar Tulyaganovich Khakimov

Acta of Turin Polytechnic University in Tashkent

The article describes the design of filters on surface acoustic waves (SAWs), which are selective elements and are widely used in blocks, devices and signal processing systems in telecommunications, including wireless communication systems such as cellular, trunking and others. Designs of filters for surfactants are considered, which are divided into two large groups - by functional purpose and by a systematic approach to the synthesis of performance characteristics of filters for surfactants. Optimization algorithms and methods for synthesizing surfactant filters have been developed and improved. An improved technique for the synthesis of a filter based on surface acoustic waves is …

Solar Photovoltaic Performance Monitoring: A Bibliometric Review, Research Gaps And Opportunities, Javed Sayyad, Paresh Nasikkar

Library Philosophy and Practice (e-journal)

Electrical power generation has been revolutionized by growing demand and use of Renewable Energy (RE) sources such as Solar Photovoltaic (SPV) as the main electricity source in modern times. The main objective of this bibliometric analysis is to understand the scope of the literature available for SPV performance characterization. This detailed reviewed was performed on the documents related to SPV research considering all the subject categories from Scopus and Web of Science (WoS) databases. The patterns for the particular set of keywords were broke down with the recuperated outcomes from Scopus database in the language, publication type, year of publication, …

Conditional Generative Adversarial Network Demosaicing Strategy For Division Of Focal Plane Polarimeters, Garrett Sargent, Bradley M. Ratliff, Vijayan K. Asari

Electrical and Computer Engineering Faculty Publications

Division of focal plane (DoFP), or integrated microgrid polarimeters, typically consist of a 2 × 2 mosaic of linear polarization filters overlaid upon a focal plane array sensor and obtain temporally synchronized polarized intensity measurements across a scene, similar in concept to a Bayer color filter array camera. However, the resulting estimated polarimetric images suffer a loss in resolution and can be plagued by aliasing due to the spatially-modulated microgrid measurement strategy. Demosaicing strategies have been proposed that attempt to minimize these effects, but result in some level of residual artifacts. In this work we propose a conditional generative adversarial …

Transfer-To-Transfer Learning Approach For Computer Aided Detection Of Covid-19 In Chest Radiographs, Barath Narayanan Narayanan, Russell C. Hardie, Vignesh Krishnaraja, Christina Karam, Venkata Salini Priyamvada Davuluru

Electrical and Computer Engineering Faculty Publications

The coronavirus disease 2019 (COVID-19) global pandemic has severely impacted lives across the globe. Respiratory disorders in COVID-19 patients are caused by lung opacities similar to viral pneumonia. A Computer-Aided Detection (CAD) system for the detection of COVID-19 using chest radiographs would provide a second opinion for radiologists. For this research, we utilize publicly available datasets that have been marked by radiologists into two-classes (COVID-19 and non-COVID-19). We address the class imbalance problem associated with the training dataset by proposing a novel transfer-to-transfer learning approach, where we break a highly imbalanced training dataset into a group of balanced mini-sets and …

Novel Memristor Based True Random Number Generator, Scott Stoller

Boise State University Theses and Dissertations

Random numbers are an important, but often overlooked part of the modern computing environment. They are used everywhere around us for a variety of purposes, from simple decision making in video games such as a coin toss, to securing financial transactions and encrypting confidential communications. They are even useful for gambling and the lottery.

Random numbers are generated in many ways. Pseudo random number generators (PRNGs) generate numbers based on a formula. True random number generators (TRNGs) capture entropy from the environment to generate randomness. As our society and our devices become more connected in the digital world, it is …

Design Of A Single-Carrier Pulse Width Modulation With Submodule Fault-Tolerant Capability For Modular Multilevel Converter, Tuanku Badzlin Hashfi

Student Works (2020-2029)

Multilevel converters are attracting a lot of attention and becoming one of the energy conversion choices for new topologies and control in industry applications and research fields. Modular multilevel converters (MMCs) are considered very promising among converter topologies for future medium-voltage and high-power applications compared to NPC, FC and CHB topologies. The improved phase disposition pulse width modulation (PDPWM) technique control for MMCs, which has a fault-tolerant capability, is presented. This study presents two methods to distribute pulses into submodules (SMs) by using PDPWM which has drawback to distribute the power equally among the submodules (SMs). First method, this study …

Optimal Distribution System Reconfiguration Incorporating Dg And Variable Load Profile Using Artificial Neural Network, Hesham Hanie Youssef

Student Works (2020-2029)

Optimal network reconfiguration is a common method used in distribution systems to ensure minimum power losses are always attained. This is very important task for achieving cost effective operation. Due to varying load demands, conventional network reconfiguration techniques have to be repeated whenever system loading changes to find a new configuration that has minimum power losses. This task is time consuming and ineffective approach for a real time application. Therefore, this research proposes an Artificial Neural Network (ANN) technique for optimal distribution network reconfiguration to overcome long processing time, mainly in load variation case. The proposed method involves; (1) Implement …

Challenges To Adopting Hybrid Methodology: Addressing Organizational Culture And Change Control Problems In Enterprise It Infrastructure Projects, Harishankar Krishnakumar

Dissertations and Theses

IT infrastructure projects have long been an overlooked field superseded by the more popular software development silos and cross-functional project teams when it comes to enterprise Agile transformations. This paper presents a systematic literature review by leveraging a qualitative research methodology based on empirical evidence provided in contemporary scholarly research articles to explore how certain variables such as organizational culture- including team structure, leadership hierarchy, geolocation, etc. along with an organization’s change management processes affect the adoption of a Hybrid/Agile project management methodology, focusing on reported challenges and critical success factors that define such large-scale enterprise transformations. The salient features …

Forecasting Vegetation Health In The Mena Region By Predicting Vegetation Indicators With Machine Learning Models, Sachi Perera, Wenzhao Li, Erik Linstead, Hesham El-Askary

Mathematics, Physics, and Computer Science Faculty Articles and Research

Machine learning (ML) techniques can be applied to predict and monitor drought conditions due to climate change. Predicting future vegetation health indicators (such as EVI, NDVI, and LAI) is one approach to forecast drought events for hotspots (e.g. Middle East and North Africa (MENA) regions). Recently, ML models were implemented to predict EVI values using parameters such as land types, time series, historical vegetation indices, land surface temperature, soil moisture, evapotranspiration etc. In this work, we collected the MODIS atmospherically corrected surface spectral reflectance imagery with multiple vegetation related indices for modeling and evaluation of drought conditions in the MENA …

Optimized Transconductance Designs To Enhance The Linearity Performance Of Rf Front-End Receiver Circuits In 130 Nm Cmos Technology, Nandini Vitee

Student Works (2020-2029)

Highly linear front-end circuits are greatly desired for wireless receivers to improve the dynamic range. However, intermodulation distortions caused by the non-linear transconductor current limits the linearity of the front-end receiver circuit in CMOS technologies. In addition to the inherent nonlinear effect, the downscaling of CMOS further exacerbates the linearity of the circuit due to lower voltage headroom and high-field mobility. Thus, it is essential to develop effective circuit techniques that can aid linearity enhancement without jeopardizing other preferred performances such as low noise, high conversion gain, and low-power consumption. In this thesis, two different high linear transconductors are presented …

High Wind Alerts: A System Created With Observations From The X-Band Teaching And Research Radar, Lauren Warner

The Journal of Purdue Undergraduate Research

Following the August 13, 2011, Indiana State Fair stage collapse tragedy, caused by a wind gust from an approaching thunderstorm, Purdue University enforced a wind speed restriction of 30 mph (13 m s-1) for tents at outdoor events. During these events, volunteers stand outside with handheld anemometers, measuring and reporting when the wind speeds exceed this limit. In this study, we report testing of a new system to automate high-wind alerts based on observations from a Doppler radar, the X-band Teaching and Research Radar (XTRRA), near Purdue’s campus. XTRRA scans over campus at low elevations approximately every 5 minutes. Using …

Fault-Tolerant Capability Of Star Connected Symmetrical Six-Phase Induction Machine With Single And Two Isolated Neutrals, Wan Noraishah Wan Abdul Munim

Student Works (2020-2029)

Traditionally, electrical machines have been designed to operate with single- or three phase power supplies. In the early stage of power electronics development, three-phase machine suffers problems such as high torque ripple due to low order harmonics during six-step switching and limited current handling capacity of the power switches. This has motivated the use of multiphase machines which is capable of mitigating the aforementioned issues. The revival of multiphase machine research is mainly motivated by the need for more reliable drive systems. The vector space decomposition (VSD) model is used for a healthy multiphase machine as the basis for control …

Circus In Motion: A Multimodal Exergame Supporting Vestibular Therapy For Children With Autism, Oscar Peña, Franceli L. Cibrian, Monica Tentori

Engineering Faculty Articles and Research

Exergames are serious games that involve physical exertion and are thought of as a form of exercise by using novel input models. Exergames are promising in improving the vestibular differences of children with autism but often lack of adaptation mechanisms that adjust the difficulty level of the exergame. In this paper, we present the design and development of Circus in Motion, a multimodal exergame supporting children with autism with the practice of non-locomotor movements. We describe how the data from a 3D depth camera enables the tracking of non-locomotor movements allowing children to naturally interact with the exergame . A …

Admittance Method For Estimating Local Field Potentials Generated In A Multi-Scale Neuron Model Of The Hippocampus, Clayton S. Bingham, Javad Paknahad, Christopher Bc Girard, Kyle Loizos, Jean-Marie C. Bouteiller, Dong Song, Gianluca Lazzi, Theodore W. Berger

Engineering Faculty Articles and Research

Significant progress has been made toward model-based prediction of neral tissue activation in response to extracellular electrical stimulation, but challenges remain in the accurate and efficient estimation of distributed local field potentials (LFP). Analytical methods of estimating electric fields are a first-order approximation that may be suitable for model validation, but they are computationally expensive and cannot accurately capture boundary conditions in heterogeneous tissue. While there are many appropriate numerical methods of solving electric fields in neural tissue models, there isn't an established standard for mesh geometry nor a well-known rule for handling any mismatch in spatial resolution. Moreover, the …