scholarly journals Audio-Based Aircraft Detection System for Safe RPAS BVLOS Operations

Electronics ◽  
2020 ◽  
Vol 9 (12) ◽  
pp. 2076
Author(s):  
Jorge Mariscal-Harana ◽  
Víctor Alarcón ◽  
Fidel González ◽  
Juan José Calvente ◽  
Francisco Javier Pérez-Grau ◽  
...  
Keyword(s):  
Real Time ◽  
Data Augmentation ◽  
Detection System ◽  
Cost Effective ◽  
True Positive Rate ◽  
Training Dataset ◽  
Computational Performance ◽  
Combining Data ◽  
Wide Range ◽  
Aircraft Detection

For the Remotely Piloted Aircraft Systems (RPAS) market to continue its current growth rate, cost-effective ‘Detect and Avoid’ systems that enable safe beyond visual line of sight (BVLOS) operations are critical. We propose an audio-based ‘Detect and Avoid’ system, composed of microphones and an embedded computer, which performs real-time inferences using a sound event detection (SED) deep learning model. Two state-of-the-art SED models, YAMNet and VGGish, are fine-tuned using our dataset of aircraft sounds and their performances are compared for a wide range of configurations. YAMNet, whose MobileNet architecture is designed for embedded applications, outperformed VGGish both in terms of aircraft detection and computational performance. YAMNet’s optimal configuration, with >70% true positive rate and precision, results from combining data augmentation and undersampling with the highest available inference frequency (i.e., 10 Hz). While our proposed ‘Detect and Avoid’ system already allows the detection of small aircraft from sound in real time, additional testing using multiple aircraft types is required. Finally, a larger training dataset, sensor fusion, or remote computations on cloud-based services could further improve system performance.

scholarly journals Audio-Based Aircraft Detection System for Safe RPAS BVLOS Operations

2020 ◽  
Author(s):  
Jorge Mariscal-Harana ◽  
Víctor Alarcón ◽  
Fidel González ◽  
Juan José Calvente ◽  
Francisco Javier Pérez-Grau ◽  
...  
Keyword(s):  
Real Time ◽  
Data Augmentation ◽  
Detection System ◽  
Cost Effective ◽  
True Positive Rate ◽  
Training Dataset ◽  
Computational Performance ◽  
Combining Data ◽  
Wide Range ◽  
Aircraft Detection

For the Remotely Piloted Aircraft Systems (RPAS) market to continue its current growth rate, cost-effective "Detect and Avoid" systems that enable safe beyond visual line of sight (BVLOS) operations are critical. We propose an audio-based "Detect and Avoid" system, composed of microphones and an embedded computer, which performs real-time inferences using a sound event detection (SED) deep learning model. Two state-of-the-art SED models, YAMNet and VGGish, are fine-tuned using our dataset of aircraft sounds and their performances are compared for a wide range of configurations. YAMNet, whose MobileNet architecture is designed for embedded applications, outperformed VGGish both in terms of aircraft detection and computational performance. YAMNet's optimal configuration, with > 70% true positive rate and precision, results from combining data augmentation and undersampling with the highest available inference frequency (i.e. 10 Hz). While our proposed "Detect and Avoid" system already allows the detection of small aircraft from sound in real time, additional testing using multiple aircraft types is required. Finally, a larger training dataset, sensor fusion, or remote computations on cloud-based services could further improve system performance.

scholarly journals Audio-Based Aircraft Detection System for Safe RPAS BVLOS Operations

2020 ◽  
Author(s):  
Jorge Mariscal-Harana ◽  
Víctor Alarcón ◽  
Fidel González ◽  
Juan José Calvente ◽  
Francisco Javier Pérez-Grau ◽  
...  
Keyword(s):  
Real Time ◽  
Data Augmentation ◽  
Detection System ◽  
Cost Effective ◽  
True Positive Rate ◽  
Computational Performance ◽  
Combining Data ◽  
Wide Range ◽  
Positive Rate ◽  
Aircraft Detection

For the Remotely Piloted Aircraft Systems (RPAS) market to continue its current growth rate, cost-effective "Detect and Avoid" systems which enable safe beyond visual line of sight (BVLOS) operations are critical. We propose an audio-based "Detect and Avoid" system, composed of microphones and an embedded computer, which performs real-time inferences using a sound event detection (SED) deep learning model. Two state-of-the-art SED models, YAMNet and VGGish, are fine-tuned using our aircraft sounds dataset and their performances are compared for a wide range of configurations. YAMNet, whose MobileNet architecture is designed for embedded applications, outperformed VGGish both in terms of aircraft detection and computational performance. YAMNet's optimal configuration, with > 70% true positive rate and precision, results from combining data augmentation and undersampling with the highest available inference frequency (i.e. 10 Hz). While our proposed "Detect and Avoid" system already allows the detection of small aircraft from sound in real time, a larger dataset, sensor fusion, or the use of cloud-based services for remote computations could further improve its performance.

scholarly journals A Latency-Insensitive Design Approach to Programmable FPGA-Based Real-Time Simulators

Electronics ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1838
Author(s):  
Federico Montaño ◽  
Tarek Ould-Bachir ◽  
Jean Pierre David
Keyword(s):  
Real Time ◽  
Cost Effective ◽  
Power Converter ◽  
Peak Performance ◽  
Time Step ◽  
Computational Performance ◽  
Wide Range ◽  
Power Electronic Circuits ◽  
Field Programmable ◽  
Latency Insensitive

This paper presents a methodology for the design of field-programmable gate array (FPGA)-based real-time simulators (RTSs) for power electronic circuits (PECs). The programmability of the simulator results from the use of an efficient and scalable overlay architecture (OA). The proposed OA relies on a latency-insensitive design (LID) paradigm. LID consists of connecting small processing units that automatically synchronize and exchange data when appropriate. The use of such data-driven architecture aims to ease the design process while achieving a higher computational efficiency. The benefits of the proposed approach is evaluated by assessing the performance of the proposed solver in the simulation of a two-stage AC–AC power converter. The minimum achievable time-step and FPGA resource consumption for a wide range of power converter sizes is also evaluated. The proposed overlays are parametrizable in size, they are cost-effective, they provide sub-microsecond time-steps, and they offer a high computational performance with a reported peak performance of 300 GFLOPS.

Development of a real-time machine vision system for functional textile fabric defect detection using a deep YOLOv4 model

2021 ◽  
pp. 004051752110342
Author(s):  
Sifundvolesihle Dlamini ◽  
Chih-Yuan Kao ◽  
Shun-Lian Su ◽  
Chung-Feng Jeffrey Kuo
Keyword(s):  
Machine Vision ◽  
Real Time ◽  
Defect Detection ◽  
Data Augmentation ◽  
Detection System ◽  
Vision System ◽  
Good Precision ◽  
Machine Vision System ◽  
Time Machine ◽  
Textile Fabric

We introduce a real-time machine vision system we developed with the aim of detecting defects in functional textile fabrics with good precision at relatively fast detection speeds to assist in textile industry quality control. The system consists of image acquisition hardware and image processing software. The software we developed uses data preprocessing techniques to break down raw images to smaller suitable sizes. Filtering is employed to denoise and enhance some features. To generalize and multiply the data to create robustness, we use data augmentation, which is followed by labeling where the defects in the images are labeled and tagged. Lastly, we utilize YOLOv4 for localization where the system is trained with weights of a pretrained model. Our software is deployed with the hardware that we designed to implement the detection system. The designed system shows strong performance in defect detection with precision of [Formula: see text], and recall and [Formula: see text] scores of [Formula: see text] and [Formula: see text], respectively. The detection speed is relatively fast at [Formula: see text] fps with a prediction speed of [Formula: see text] ms. Our system can automatically locate functional textile fabric defects with high confidence in real time.

scholarly journals Spectroscopy Transmittance by LED Calibration

Sensors ◽  
2019 ◽  
Vol 19 (13) ◽  
pp. 2951 ◽  
Author(s):  
Daniel Carreres-Prieto ◽  
Juan T. García ◽  
Fernando Cerdán-Cartagena ◽  
Juan Suardiaz-Muro
Keyword(s):  
Real Time ◽  
Light Emitting Diode ◽  
Research Work ◽  
Cost Effective ◽  
Spectral Width ◽  
Calibration Procedure ◽  
Pollution Monitoring ◽  
Light Emitting ◽  
Wide Range ◽  
Incandescent Lamps

Local administrations demand real-time and continuous pollution monitoring in sewer networks. Spectroscopy is a non-destructive technique that can be used to continuously monitor quality in sewers. Covering a wide range of wavelengths can be useful for improving pollution characterization in wastewater. Cost-effective and in-sewer spectrophotometers would contribute to accomplishing discharge requirements. Nevertheless, most available spectrometers are based on incandescent lamps, which makes it unfeasible to place them in a sewerage network for real-time monitoring. This research work shows an innovative calibration procedure that allows (Light-Emitting Diode) LED technology to be used as a replacement for traditional incandescent lamps in the development of spectrophotometry equipment. This involves firstly obtaining transmittance values similar to those provided by incandescent lamps, without using any optical components. Secondly, this calibration process enables an increase in the range of wavelengths available (working range) through a better use of the LED’s spectral width, resulting in a significant reduction in the number of LEDs required. Thirdly, this method allows important reductions in costs, dimensions and consumptions to be achieved, making its implementation in a wide variety of environments possible.

LZER0: GNSS cost-effective real-time positioning applied to landslide monitoring

2020 ◽  
Author(s):  
Lavinia Tunini ◽  
David Zuliani ◽  
Paolo Fabris ◽  
Marco Severin
Keyword(s):  
Real Time ◽  
Monitoring System ◽  
Low Cost ◽  
Cost Effective ◽  
Single Frequency ◽  
Landslide Monitoring ◽  
Natural Risk ◽  
Near Surface ◽  
Landslide Event ◽  
Wide Range

<p>The Global Navigation Satellite Systems (GNSS) provide a globally extended dataset of primordial importance for a wide range of applications, such as crustal deformation, topographic measurements, or near surface processes studies. However, the high costs of GNSS receivers and the supporting software can represent a strong limitation for the applicability to landslide monitoring. Low-cost tools and techniques are strongly required to face the plausible risk of losing the equipment during a landslide event.</p><p>Centro di Ricerche Sismologiche (CRS) of Istituto Nazionale di Oceanografia e di Geofisica Sperimentale OGS in collaboration with SoluTOP, in the last years, has developed a cost-effective GNSS device, called LZER0, both for post-processing and real-time applications. The aim is to satisfy the needs of both scientific and professional communities which require low-cost equipment to increase and improve the measurements on structures at risk, such as landslides or buildings, without losing precision.</p><p>The landslide monitoring system implements single-frequency GNSS devices and open source software packages for GNSS positioning, dialoguing through Linux shell scripts. Furthermore a front-end web page has been developed to show real-time tracks. The system allows measuring real-time surface displacements with a centimetre precision and with a cost ten times minor than a standard RTK GPS operational system.</p><p>This monitoring system has been tested and now applied to two landslides in NE- Italy: one near Tolmezzo municipality and one near Brugnera village. Part of the device development has been included inside the project CLARA 'CLoud plAtform and smart underground imaging for natural Risk Assessment' funded by the Italian Ministry of Education, University and Research (MIUR).</p>

scholarly journals Portable and label-free quantitative Loop-mediated Isothermal Amplification (qLAMP) for reliable COVID-19 diagnostics in 3 minutes: An Arduino-based detection system assisted by a pH microelectrode

2021 ◽  
Author(s):  
Mario Moisés Alvarez ◽  
Sergio Bravo-González ◽  
Everardo González-González ◽  
Grissel Trujillo-de Santiago
Keyword(s):  
Real Time ◽  
Detection System ◽  
Genetic Material ◽  
Cost Effective ◽  
Isothermal Amplification ◽  
Diagnostic Methods ◽  
Label Free ◽  
Viral Pathogens ◽  
Loop Mediated Isothermal Amplification ◽  
Amplification System

Loop-mediated isothermal amplification (LAMP) has been recently studied as an alternative method for cost-effective diagnostics in the context of the current COVID-19 pandemic. Recent reports document that LAMP-based diagnostic methods have a comparable sensitivity and specificity to that of RT-qPCR. We report the use of a portable Arduino-based LAMP-based amplification system assisted by pH microelectrodes for the accurate and reliable diagnosis of SARS-CoV-2 during the first 3 minutes of the amplification reaction. We show that this simple system enables a straightforward discrimination between samples containing or not containing artificial SARS-CoV-2 genetic material in the range of 10 to 10,000 copies per 50 μL of reaction mix. We also spiked saliva samples with SARS-CoV-2 synthetic material and corroborated that the LAMP reaction can be successfully monitored in real time using microelectrodes in saliva samples as well. These results may have profound implications for the design of real-time and portable quantitative systems for the reliable detection of viral pathogens including SARS-CoV-2.

scholarly journals Development of a high-throughput real-time PCR system for detection of enzootic pathogens in pigs

2019 ◽  
Vol 32 (1) ◽  
pp. 51-64 ◽  
Author(s):  
Nicole B. Goecke ◽  
Charlotte K. Hjulsager ◽  
Jesper S. Krog ◽  
Kerstin Skovgaard ◽  
Lars E. Larsen
Keyword(s):  
Real Time ◽  
High Throughput ◽  
Real Time Pcr ◽  
Pathogen Detection ◽  
Detection System ◽  
Working Hours ◽  
Negative Influence ◽  
Optimal Choice ◽  
National Veterinary Institute ◽  
Wide Range

Respiratory and intestinal diseases in pigs can have significant negative influence on productivity and animal welfare. A wide range of real-time PCR (rtPCR) assays are used in our laboratory (National Veterinary Institute, Technical University of Denmark) for pathogen detection, and PCR analyses are performed on traditional rtPCR platforms in which a limited number of samples can be analyzed per day given limitations in equipment and personnel. To mitigate these restrictions, rtPCR assays have been optimized for the high-throughput rtPCR BioMark platform (Fluidigm). Using this platform, we developed a high-throughput detection system that can be used for simultaneous examination of 48 samples with detection specificity for 18 selected respiratory and enteric viral and bacterial pathogens of high importance to Danish pig production. The rtPCR assays were validated and optimized to run under the same reaction conditions using a BioMark 48.48 dynamic array (DA) integrated fluidic circuit chip, and the sensitivity and specificity were assessed by testing known positive samples. Performance of the 48.48DA was similar to traditional rtPCR analysis, and the specificity of the 48.48DA was high. Application of the high-throughput platform has resulted in a significant reduction in cost and working hours and has provided production herds with a new innovative service with the potential to facilitate the optimal choice of disease control strategies such as vaccination and treatment.

scholarly journals Development of cost-effective real-time PCR test: to detect a wide range of HBV DNA concentrations in the western amazon region of Brazil

2014 ◽  
Vol 11 (1) ◽  
Author(s):  
Alcione de Oliveira dos Santos ◽  
Luan Felipo Botelho Souza ◽  
Lourdes Maria Borzacov ◽  
Juan Miguel Villalobos-Salcedo ◽  
Deusilene Souza Vieira
Keyword(s):  
Real Time ◽  
Real Time Pcr ◽  
Cost Effective ◽  
Hbv Dna ◽  
Amazon Region ◽  
Wide Range ◽  
Pcr Test

scholarly journals Development of an Automatic Image Cropping and Feature Extraction System for Real-Time Warping Monitoring in 3D Printing

2021 ◽  
Author(s):  
Jiarui Xie
Keyword(s):  
Real Time ◽  
Detection System ◽  
Region Of Interest ◽  
Cost Effective ◽  
Time Warping ◽  
Time Data ◽  
Fused Filament Fabrication ◽  
System A ◽  
Effective Manner

Fused Filament Fabrication (FFF) is an additive manufacturing technology that can produce complicated structures in a simple-to-use and cost-effective manner. Although promising, the technology is prone to defects, e.g. warping, compromising the quality of the manufactured component. To avoid the adverse effects caused by warping, this thesis utilizes deep-learning algorithms to develop a warping detection system using Convolutional Neural Networks (CNN). To create such a system, a real-time data acquisition and analysis pipeline is laid out. The system is responsible for capturing a snapshot of the print layer-bylayer and simultaneously extracting the corners of the component. The extracted region-of-interest is then passed through a CNN outputting the probability of a corner being warped. If a warp is detected, a signal is sent to pause the print, thereby creating a closed-loop monitoring system. The underlying model is tested on a real-time manufacturing environment yielding a mean accuracy of 99.21%.

Sign in / Sign up

Export Citation Format

Share Document