Pub Date : 2019-07-01DOI: 10.1109/NAECON46414.2019.9058086
B. Narayanan, R. Hardie
Lung segmentation plays a crucial role in computer-aided diagnosis using Chest Radiographs (CRs). We implement a U-Net architecture for lung segmentation in CRs across multiple publicly available datasets. We utilize a private dataset with 160 CRs provided by the Riverain Medical Group for training purposes. A publicly available dataset provided by the Japanese Radiological Scientific Technology (JRST) is used for testing. The active shape model-based results would serve as the ground truth for both these datasets. In addition, we also study the performance of our algorithm on a publicly available Shenzhen dataset which contains 566 CRs with manually segmented lungs (ground truth). Our overall performance in terms of pixel-based classification is about 98.3% and 95.6% for a set of 100 CRs in Shenzhen dataset and 140 CRs in JRST dataset. We also achieve an intersection over union value of 0.95 at a computation time of 8 seconds for the entire suite of Shenzhen testing cases.
{"title":"A Computationally Efficient U-Net Architecture for Lung Segmentation in Chest Radiographs","authors":"B. Narayanan, R. Hardie","doi":"10.1109/NAECON46414.2019.9058086","DOIUrl":"https://doi.org/10.1109/NAECON46414.2019.9058086","url":null,"abstract":"Lung segmentation plays a crucial role in computer-aided diagnosis using Chest Radiographs (CRs). We implement a U-Net architecture for lung segmentation in CRs across multiple publicly available datasets. We utilize a private dataset with 160 CRs provided by the Riverain Medical Group for training purposes. A publicly available dataset provided by the Japanese Radiological Scientific Technology (JRST) is used for testing. The active shape model-based results would serve as the ground truth for both these datasets. In addition, we also study the performance of our algorithm on a publicly available Shenzhen dataset which contains 566 CRs with manually segmented lungs (ground truth). Our overall performance in terms of pixel-based classification is about 98.3% and 95.6% for a set of 100 CRs in Shenzhen dataset and 140 CRs in JRST dataset. We also achieve an intersection over union value of 0.95 at a computation time of 8 seconds for the entire suite of Shenzhen testing cases.","PeriodicalId":193529,"journal":{"name":"2019 IEEE National Aerospace and Electronics Conference (NAECON)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134555450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/NAECON46414.2019.9058262
Jun Ren, Yu Shi, Yijing Deng, J. Hesler, P. Fay, Lei Liu
We report our recent progress toward the development of optically controlled tunable/reconfigurable THz circuits/components in waveguide configurations for advanced sensing and adaptive wireless communications. The development and demonstration of a modified WR-4.3 variable waveguide attenuator based on photo-excited Si with 60-dB range and 0.7-dB insertion loss will first be reviewed. Then the investigation of a WR-5.1 reconfigurable band-stop filter (BSF) prototype based on photo-induced electromagnetic band gap (PI-EBG) structures using semiconductor mesa arrays will be presented. The center frequency of the BSF can be reconfigured from 166–200 GHz with adjustable stop-band rejection and bandwidth. Finally, the development of high-performance THz integrated switches using the same optical control methodology enabling the implementation of more advanced tunable/reconfigurable THz waveguide circuits will be envisioned, investigated and discussed. Preliminary results reveal that the optically controlled RF switches show a potentially record-high figure-of-merit (evaluated by RonCoff constant) of 153 THz, allowing them to outperform both conventional solid-state-device-based (e.g., HEMTs) and emerging phase-changing-material-based (e.g., VO2) counterparts, and therefore promising to compete with MEMS switches in the mmW-THz region for a novel class of tunable/reconfigurable circuits/components.
{"title":"Development of Optically Controlled Tunable/Reconfigurable Terahertz Waveguide Circuits/Components For Advanced Sensing and Adaptive Wireless Communications","authors":"Jun Ren, Yu Shi, Yijing Deng, J. Hesler, P. Fay, Lei Liu","doi":"10.1109/NAECON46414.2019.9058262","DOIUrl":"https://doi.org/10.1109/NAECON46414.2019.9058262","url":null,"abstract":"We report our recent progress toward the development of optically controlled tunable/reconfigurable THz circuits/components in waveguide configurations for advanced sensing and adaptive wireless communications. The development and demonstration of a modified WR-4.3 variable waveguide attenuator based on photo-excited Si with 60-dB range and 0.7-dB insertion loss will first be reviewed. Then the investigation of a WR-5.1 reconfigurable band-stop filter (BSF) prototype based on photo-induced electromagnetic band gap (PI-EBG) structures using semiconductor mesa arrays will be presented. The center frequency of the BSF can be reconfigured from 166–200 GHz with adjustable stop-band rejection and bandwidth. Finally, the development of high-performance THz integrated switches using the same optical control methodology enabling the implementation of more advanced tunable/reconfigurable THz waveguide circuits will be envisioned, investigated and discussed. Preliminary results reveal that the optically controlled RF switches show a potentially record-high figure-of-merit (evaluated by RonCoff constant) of 153 THz, allowing them to outperform both conventional solid-state-device-based (e.g., HEMTs) and emerging phase-changing-material-based (e.g., VO2) counterparts, and therefore promising to compete with MEMS switches in the mmW-THz region for a novel class of tunable/reconfigurable circuits/components.","PeriodicalId":193529,"journal":{"name":"2019 IEEE National Aerospace and Electronics Conference (NAECON)","volume":"356 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122447307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/NAECON46414.2019.9058320
Reem Alshanbari, S. Khan, Nazek El‐atab, Muhammad Mustafa Hussain
Recently unmanned aerial vehicles (UAV) have received a growing attention due to their wide range of applications. Here, we demonstrate UAVs with artificial intelligence (AI) capabilities for application in autonomous payload transport. An algorithm is developed for target detection with multiple phases on the ground, which once the target is detected, would trigger the release of the payload that is attached on the drone. The experimental results show that the average frame rate over x seconds achieved a 19.4010717352 fps (frame per second) detection speed. Releasing the payload is achieved using a 3D printed system based on rack and pinion gears. In addition, auto flight program is developed to enable the autonomous movement of the drone. As a proof-of-concept, a small drone known as "Phantom DJI" is used for .6 kg autonomous payload transport along a predefined route to a target location.
{"title":"AI Powered Unmanned Aerial Vehicle for Payload Transport Application","authors":"Reem Alshanbari, S. Khan, Nazek El‐atab, Muhammad Mustafa Hussain","doi":"10.1109/NAECON46414.2019.9058320","DOIUrl":"https://doi.org/10.1109/NAECON46414.2019.9058320","url":null,"abstract":"Recently unmanned aerial vehicles (UAV) have received a growing attention due to their wide range of applications. Here, we demonstrate UAVs with artificial intelligence (AI) capabilities for application in autonomous payload transport. An algorithm is developed for target detection with multiple phases on the ground, which once the target is detected, would trigger the release of the payload that is attached on the drone. The experimental results show that the average frame rate over x seconds achieved a 19.4010717352 fps (frame per second) detection speed. Releasing the payload is achieved using a 3D printed system based on rack and pinion gears. In addition, auto flight program is developed to enable the autonomous movement of the drone. As a proof-of-concept, a small drone known as \"Phantom DJI\" is used for .6 kg autonomous payload transport along a predefined route to a target location.","PeriodicalId":193529,"journal":{"name":"2019 IEEE National Aerospace and Electronics Conference (NAECON)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124200757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/NAECON46414.2019.9058018
Ahmed Mekky, T. Alberts, O. González
This paper presents the experimental results of the trajectory control of a Qball-X4 quadrotor in confined environments and with the presence of model uncertainties. The presented controller utilizes Artificial-Neural-Networks to adjust for aerodynamic and model uncertainties on-line. The provided experimental results show the robustness and effectiveness of the developed ANN controller when applied to the Qball X4 quadrotor.
{"title":"Experimental Implementation of an ANN Controller for Quadrotor Trajectory Control in Confined Environment","authors":"Ahmed Mekky, T. Alberts, O. González","doi":"10.1109/NAECON46414.2019.9058018","DOIUrl":"https://doi.org/10.1109/NAECON46414.2019.9058018","url":null,"abstract":"This paper presents the experimental results of the trajectory control of a Qball-X4 quadrotor in confined environments and with the presence of model uncertainties. The presented controller utilizes Artificial-Neural-Networks to adjust for aerodynamic and model uncertainties on-line. The provided experimental results show the robustness and effectiveness of the developed ANN controller when applied to the Qball X4 quadrotor.","PeriodicalId":193529,"journal":{"name":"2019 IEEE National Aerospace and Electronics Conference (NAECON)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116805172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/NAECON46414.2019.9058065
Dan Pritsker, Colman Cheung, Hong Shan Neoh, G. Nash
Gaussian Noise Generators are common in various applications of Electronic Countermeasures and Low Probability of Intercept radar. It can be applied to military applications, law enforcement and commercial segments. The key requirement for such a generator is the ability to operate in wide spectral band. The main driver for this requirement is the ever increasing radars bandwidth to achieve high radar resolution.In addition to wideband capabilities, it is important to have a fine control over the suppressed and unsuppressed spectral frequencies. The countermeasures must allow friendly system to continue to operate, while suppressing the adversary systems. Moreover, due to limited transmit power envelope on analog RF power amplifier chain, it is advantageous to limit a transmission only to specific band-limited regions. The countermeasures should be able to reconfigure its settings in terms of active spectral frequencies agilely, when operational conditions or power considerations change. This paper presents proposed implementation on FPGA that achieves such key metrics.
{"title":"Wideband Programmable Gaussian Noise Generator on FPGA","authors":"Dan Pritsker, Colman Cheung, Hong Shan Neoh, G. Nash","doi":"10.1109/NAECON46414.2019.9058065","DOIUrl":"https://doi.org/10.1109/NAECON46414.2019.9058065","url":null,"abstract":"Gaussian Noise Generators are common in various applications of Electronic Countermeasures and Low Probability of Intercept radar. It can be applied to military applications, law enforcement and commercial segments. The key requirement for such a generator is the ability to operate in wide spectral band. The main driver for this requirement is the ever increasing radars bandwidth to achieve high radar resolution.In addition to wideband capabilities, it is important to have a fine control over the suppressed and unsuppressed spectral frequencies. The countermeasures must allow friendly system to continue to operate, while suppressing the adversary systems. Moreover, due to limited transmit power envelope on analog RF power amplifier chain, it is advantageous to limit a transmission only to specific band-limited regions. The countermeasures should be able to reconfigure its settings in terms of active spectral frequencies agilely, when operational conditions or power considerations change. This paper presents proposed implementation on FPGA that achieves such key metrics.","PeriodicalId":193529,"journal":{"name":"2019 IEEE National Aerospace and Electronics Conference (NAECON)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125568617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/NAECON46414.2019.9057890
Kellen O’Shea, B. Tsao, L. Herrera, Chad Miller
The advancement of modern aircraft seeks to place a higher priority on the electrical power systems to execute flight operations. Transitioning to aircraft with a larger dependence on these systems is advantageous because they increase reliability, maintainability, and cost efficiency. This requires an intelligent power system that is capable of not only powering the aircraft at ideal conditions, but also detecting faults and autonomously redistributing power to flight-critical electrical loads. This paper investigates how to detect parallel faults using recursive least squares estimation. Results indicate how estimation is affected by system variables.
{"title":"Recursive Least Squares Parameter Estimation for DC Fault Detection and Localization","authors":"Kellen O’Shea, B. Tsao, L. Herrera, Chad Miller","doi":"10.1109/NAECON46414.2019.9057890","DOIUrl":"https://doi.org/10.1109/NAECON46414.2019.9057890","url":null,"abstract":"The advancement of modern aircraft seeks to place a higher priority on the electrical power systems to execute flight operations. Transitioning to aircraft with a larger dependence on these systems is advantageous because they increase reliability, maintainability, and cost efficiency. This requires an intelligent power system that is capable of not only powering the aircraft at ideal conditions, but also detecting faults and autonomously redistributing power to flight-critical electrical loads. This paper investigates how to detect parallel faults using recursive least squares estimation. Results indicate how estimation is affected by system variables.","PeriodicalId":193529,"journal":{"name":"2019 IEEE National Aerospace and Electronics Conference (NAECON)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125830448","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/NAECON46414.2019.9058267
Josh Gaston, Eric Grigorian, Zach Smithson, William L. Trautman
The Rotorcraft Obstacle Avoidance Simulation Environment (ROSE) research aims toward the implementation and testing of machine learning algorithms to provide autonavigation and obstacle avoidance capabilities to rotorcraft. The ROSE system includes autonomous navigation algorithms, sensor models, flight models, and a cockpit simulator to support analysis, training, and risk-reduction efforts.
{"title":"Rotorcraft Obstacle Avoidance Simulation Environment (ROSE)","authors":"Josh Gaston, Eric Grigorian, Zach Smithson, William L. Trautman","doi":"10.1109/NAECON46414.2019.9058267","DOIUrl":"https://doi.org/10.1109/NAECON46414.2019.9058267","url":null,"abstract":"The Rotorcraft Obstacle Avoidance Simulation Environment (ROSE) research aims toward the implementation and testing of machine learning algorithms to provide autonavigation and obstacle avoidance capabilities to rotorcraft. The ROSE system includes autonomous navigation algorithms, sensor models, flight models, and a cockpit simulator to support analysis, training, and risk-reduction efforts.","PeriodicalId":193529,"journal":{"name":"2019 IEEE National Aerospace and Electronics Conference (NAECON)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121952844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/naecon46414.2019.9057999
{"title":"NAECON 2019 Table of Contents","authors":"","doi":"10.1109/naecon46414.2019.9057999","DOIUrl":"https://doi.org/10.1109/naecon46414.2019.9057999","url":null,"abstract":"","PeriodicalId":193529,"journal":{"name":"2019 IEEE National Aerospace and Electronics Conference (NAECON)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123541891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-07-01DOI: 10.1109/NAECON46414.2019.9058099
J. H. Ramos, P. Ganesh, W. Warke, Kyle Volle, K. Brink
Researchers working on projects that involve multirotor platforms often spend a disproportionate amount of time and effort on the vehicle infrastructure rather than the intended research. This is especially true for graduate students or research laboratories attempting to establish flight capabilities for the first time and this paper aims to expedite that process. The paper provides a complete commercial-off-the-shelf (COTS) hardware and Robot Operating System (ROS) node-based software solution to support reliable and repeatable flight capability for multirotor systems without the need for Global Positioning System (GPS) or motion capture systems. We detail a simplified filtering approach that breaks the typical multirotor estimator into more accessible pieces; an attitude filter, a velocity filter, and an altitude filter and their associated controllers that take velocity, altitude, and yaw-rate control requests. This solution enables the user to have a stable flight from manual or higher-level guidance inputs while providing a solid baseline implementation of GPS-denied multirotor systems. Links are provided for the open-source algorithms, multirotor simulator, hardware list and assembly instructions.
{"title":"REEF Estimator: A Simplified Open Source Estimator and Controller for Multirotors","authors":"J. H. Ramos, P. Ganesh, W. Warke, Kyle Volle, K. Brink","doi":"10.1109/NAECON46414.2019.9058099","DOIUrl":"https://doi.org/10.1109/NAECON46414.2019.9058099","url":null,"abstract":"Researchers working on projects that involve multirotor platforms often spend a disproportionate amount of time and effort on the vehicle infrastructure rather than the intended research. This is especially true for graduate students or research laboratories attempting to establish flight capabilities for the first time and this paper aims to expedite that process. The paper provides a complete commercial-off-the-shelf (COTS) hardware and Robot Operating System (ROS) node-based software solution to support reliable and repeatable flight capability for multirotor systems without the need for Global Positioning System (GPS) or motion capture systems. We detail a simplified filtering approach that breaks the typical multirotor estimator into more accessible pieces; an attitude filter, a velocity filter, and an altitude filter and their associated controllers that take velocity, altitude, and yaw-rate control requests. This solution enables the user to have a stable flight from manual or higher-level guidance inputs while providing a solid baseline implementation of GPS-denied multirotor systems. Links are provided for the open-source algorithms, multirotor simulator, hardware list and assembly instructions.","PeriodicalId":193529,"journal":{"name":"2019 IEEE National Aerospace and Electronics Conference (NAECON)","volume":"4 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131549535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：