Article
Engineering, Marine
Jiansen Zhao, Fengchuan Song, Guobao Gong, Shengzheng Wang
Summary: To accurately and in real-time monitor shorelines, an improved shoreline detection method is proposed, combining water surface area segmentation and edge detection. An improved U-Net network is introduced for water segmentation, using ResNet-34 as the backbone and a concise decoder integrated attention mechanism to enhance processing speed and accuracy. Transfer learning is also employed to improve training efficiency and address data insufficiency. Experimental results show that the network achieves 97.05% MIoU and 40 FPS with the fewest parameters and effectively detects shorelines in real time in various environments.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Environmental Sciences
Bin Yan, Pan Fan, Xiaoyan Lei, Zhijie Liu, Fuzeng Yang
Summary: This study proposed an improved YOLOv5s algorithm for apple target recognition in apple picking robots. Experimental results show that the algorithm successfully differentiates between occluded graspable and ungraspable apples, with improved performance and speed.
Article
Computer Science, Artificial Intelligence
Wei Zhan, Chenfan Sun, Maocai Wang, Jinhui She, Yangyang Zhang, Zhiliang Zhang, Yong Sun
Summary: This research identified that small objects are the main reason for the reduced detection performance of object detection algorithms in drone-captured scenes. To address this, four methods were proposed to improve the precision of small object detection based on the yolov5 model. When designing these methods, considerations were made for the model to be small in size, fast in speed, low cost, and easy to deploy in actual applications.
Article
Agriculture, Multidisciplinary
Taiheng Zeng, Siyi Li, Qiming Song, Fenglin Zhong, Xuan Wei
Summary: In this study, a lightweight improved YOLOv5 based algorithm was proposed for real-time localization and ripeness detection of tomato fruits. The algorithm reconstructed the backbone network of YOLOv5 using a down-sampling convolutional layer and the bneck module of MobileNetV3, and further reduced the model size by performing channel pruning for the neck layer. Experimental results showed significant improvements in terms of parameter compression, model size reduction, and detection speed on the CPU platform.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2023)
Article
Multidisciplinary Sciences
Gang Yao, Yujia Sun, Mingpu Wong, Xiaoning Lv
Summary: This study implemented a lightweight neural network based on the YOLOv4 algorithm to detect concrete surface cracks. By adopting the symmetry concept and improving model modules, the detection accuracy and efficiency were enhanced. The improved model achieved a significant increase in mAP while reducing model size and computational complexity.
Article
Automation & Control Systems
Hongjuan Yang, Jiaxin Liu, Guiming Mei, Dongsheng Yang, Xingqiao Deng, Chao Duan
Summary: This paper proposes a real-time detection method for rail corrugation based on machine vision and a convolutional neural network, which improves the accuracy and efficiency of rail corrugation detection. A rail surface segmentation method based on the gray maximum value of the sliding window is also proposed. The experimental results show that the improved model has an average detection time of 4.01ms and a detection accuracy 2.78% higher than the unimproved ShuffleNet V2. These research results will contribute to the development of intelligent real-time detection of rail corrugation.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Multidisciplinary Sciences
Ce Guo, Xiao-ling Lv, Yan Zhang, Ming-lu Zhang
Summary: In the electronics industry, the YOLOv4-tiny method is utilized to improve the detection of electronic components, and different network structures are built to enhance accuracy by adaptively integrating middle- and high-level features. The method is validated successfully on an electronic component dataset, showing improved accuracy and high detection speed compared to other mainstream algorithms.
SCIENTIFIC REPORTS
(2021)
Article
Food Science & Technology
Vincent M. Blaschke, Thao Uyen Tran, Mohammad Naneh, Jutta Zagon, Matthias Winkel
Summary: In this study, a highly specific duplex PCR method was developed for the detection of most commercially relevant crustaceans in food. The limit of detection was 1 pg of crustacean DNA or 10 ppm of crustacean sample. Cross-testing with various plant and animal species ensured practical applicability, and a robustness test confirmed the practical use of the protocol.
Article
Environmental Sciences
Sheng-Po Chen, Cheng-Hsuan (Sarah) Lu, James E. Davies, Chang-Feng Ou-Yang, Neng-Huei Lin, Amy K. Huff, Bradley R. Pierce, Shobha Kondragunta, Jia-Lin Wang
Summary: This article introduces a near-real-time aerosol forecast and diagnostic approach based on satellite data, focusing on its application in East Asia. The method combines satellite retrievals and modeling techniques to provide cost-effective alternatives for air quality management. The capabilities of the system are demonstrated through case studies on biomass burning and haze events in Southeast Asia and China.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Engineering, Biomedical
Yoke Rung Wong, Chi Wei Ong, Alyssa LiYu Toh, Einly Lim, Pei Ho, Hwa Liang Leo
Summary: A novel method for measuring the real-time input flow impedance of thoracic aorta aneurysm (TAA) was developed in this study. The unique features of real-time input flow impedance were extracted to correlate with TAA formation. The proposed fluid mechanics model has the potential to analyze aneurysmal diseases in real-time.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Engineering, Civil
Chunbao Xiong, Sida Lian, Wen Chen
Summary: This study proposes an ensemble method based on a 3D real-time sonar system for automatic monitoring, evaluation, and positioning of exposed subsea pipelines. The method uses the YOLO V5 algorithm for automatic pipeline identification and the region grow algorithm for initial exposure evaluation. The pipeline positioning is achieved through the spatial position mapping relationship.
JOURNAL OF CIVIL STRUCTURAL HEALTH MONITORING
(2023)
Article
Engineering, Aerospace
Chuanfeng Song, Weiping Jiang, Hua Chen, Qusen Chen, Xuexi Liu, Yan Chen, Jian Wang
Summary: An improved polynomial fitting method is proposed to enhance the orbit extrapolation ability by considering satellite velocities and accelerations. Experimental results demonstrate that the method can accurately extrapolate satellite orbits within a few centimeters.
ADVANCES IN SPACE RESEARCH
(2022)
Article
Agronomy
Sheng Jiang, Ziyi Liu, Jiajun Hua, Zhenyu Zhang, Shuai Zhao, Fangnan Xie, Jiangbo Ao, Yechen Wei, Jingye Lu, Zhen Li, Shilei Lyu
Summary: This study introduces a real-time detection and maturity classification method for loofah, which includes a one-stage instance segmentation model called LuffaInst and a machine learning-based maturity classification model. Experimental results show that LuffaInst has lower parameter weights and higher accuracy than other prevalent instance segmentation models. A random forest model relying on color and texture features is also developed for three maturity classifications of loofah fruit instances. The research results have important implications for loofah fruit maturity detection.
Article
Astronomy & Astrophysics
M. Kerr, W. Duvall, W. N. Johnson, R. S. Woolf, J. E. Grove, H. Kim
Summary: We propose a fast maximum-likelihood (ML) algorithm for real-time detection of gamma-ray transients on low-performance processors. The ML method is nearly twice as sensitive as algorithms based on excess counts, allowing detection of significantly more short gamma-ray bursts. We validate the algorithm through simulations and experimental data, demonstrating its improved sensitivity and accurate on-board localizations, while also suggesting improvements for off-line localization resolution.
ASTROPHYSICAL JOURNAL
(2023)
Article
Plant Sciences
Maoyong Cao, Fangfang Tang, Peng Ji, Fengying Ma
Summary: Field crops are usually planted in rows for better efficiency and management. Automatic detection of crop planting rows is of great significance for autonomous navigation and precise spraying in intelligent agricultural machinery. In this study, an improved ENet semantic segmentation network model is proposed to perform row segmentation of farmland images. The network structure is designed to efficiently extract low-dimensional information and significantly improve the accuracy of boundary locations and row-to-row segmentation. An improved random sampling consensus algorithm is used to extract the navigation line based on the characteristics of the segmented image. The experimental results demonstrate the accurate and efficient extraction of farmland navigation lines, with strong robustness and high applicability. This algorithm provides important technical support for agricultural UAVs in farmland operations.
FRONTIERS IN PLANT SCIENCE
(2022)
Review
Engineering, Chemical
Joshua L. Santarpia, Shanna Ratnesar-Shumate, Allen Haddrell
AEROSOL SCIENCE AND TECHNOLOGY
(2020)
Article
Nuclear Science & Technology
Joshua A. Hubbard, Timothy J. Boyle, Ethan T. Zepper, Alexander Brown, Taylor Settecerri, Joshua L. Santarpia, Paul Kotula, Bonnie McKenzie, Gabriel A. Lucero, Laura J. Lemieux, Joseph A. Zigmond, Nicole D. Zayas, Rose Preston, Brenda Maes, Andres L. Sanchez, Dora K. Wiemann, Fernando Guerrero, Xavier J. Robinson, Dianna Perales
Summary: This study reproduced experiments from 1973 using current aerosol measurement methods to enhance understanding of particulate formation and transport from fires containing nuclear waste, aiming to update standards and practices in nuclear facilities. Experimental data revealed consistent measurements with current standards for uranium air release fractions (ARFs), while values for lutetium and ytterbium were lower. Variations in metal nitrate solubility due to elemental composition and temperature may impact ARF values for uranium surrogates.
NUCLEAR TECHNOLOGY
(2021)
Article
Engineering, Chemical
Paul Dabisch, Michael Schuit, Artemas Herzog, Katie Beck, Stewart Wood, Melissa Krause, David Miller, Wade Weaver, Denise Freeburger, Idris Hooper, Brian Green, Gregory Williams, Brian Holland, Jordan Bohannon, Victoria Wahl, Jason Yolitz, Michael Hevey, Shanna Ratnesar-Shumate
Summary: This study found that temperature, simulated sunlight, and humidity are significant factors influencing the persistence of infectious SARS-CoV-2 in aerosols, with sunlight and temperature having a greater impact than humidity. The time needed for a 90% decrease in infectious virus varied from minutes to hours depending on environmental conditions, suggesting that the virus could remain infectious for extended periods under certain conditions.
AEROSOL SCIENCE AND TECHNOLOGY
(2021)
Article
Chemistry, Multidisciplinary
Alec McCarthy, Lorenzo Saldana, Daniel N. Ackerman, Yajuan Su, Johnson John, Shixuan Chen, Shelbie Weihs, St Patrick Reid, Joshua L. Santarpia, Mark A. Carlson, Jingwei Xie
Summary: The study on nanofiber swabs has shown that they can significantly improve the efficiency of absorption and release of various biological substances, and improve the sensitivity of tests in SARS-CoV-2 detection, reducing false negative rates.
Article
Engineering, Chemical
Shanna Ratnesar-Shumate, Kyle Bohannon, Gregory Williams, Brian Holland, Melissa Krause, Brian Green, Denise Freeburger, Paul Dabisch
Summary: This study compared the performance of eight common low-flow aerosol sampling devices for the collection and preservation of infectious SARS-CoV-2 in small particle aerosols. Most samplers measured similar concentrations of infectious SARS-CoV-2, except for the midget impingers which measured significantly lower concentrations. Furthermore, additional clean airflow through three of the four impingers following collection of infectious virus led to a decrease in the concentration of virus over time, indicating potential inactivation of the virus and unsuitability for long duration sampling.
AEROSOL SCIENCE AND TECHNOLOGY
(2021)
Article
Nuclear Science & Technology
Joshua A. Hubbard, Timothy J. Boyle, Ethan T. Zepper, Alexander Brown, Taylor Settecerri, Joshua L. Santarpia, Nelson Bell, Joseph A. Zigmond, Steven S. Storch, Brenda J. Maes, Nicole D. Zayas, Dora K. Wiemann, Marissa Ringgold, Fernando Guerrero, Xavier J. Robinson, Gabriel A. Lucero, Laura J. Lemieux
Summary: This study used solid waste samples to mimic nuclear waste, burning them to quantify the release of metal cations. Results showed higher airborne release fractions for lutetium and depleted uranium, with differences in uncertainties. These data provide a baseline for future experimental and computational works.
NUCLEAR TECHNOLOGY
(2022)
Review
Engineering, Chemical
Yong-Le Pan, Aimable Kalume, Chuji Wang, Joshua Santarpia
Summary: The study provides a comprehensive update on the aging processes of airborne bioaerosols under various environmental conditions, showing that multiple factors such as solar radiation, heat, ozone, and free radicals can impact the physical, chemical, and biological properties of aerosolized biological organisms. It highlights the challenges in quantitatively describing these changes and calls for more comprehensive studies to address these challenges.
JOURNAL OF AEROSOL SCIENCE
(2021)
Article
Environmental Sciences
Joshua L. Santarpia, Vicki L. Herrera, Danielle N. Rivera, Shanna Ratnesar-Shumate, St. Patrick Reid, Daniel N. Ackerman, Paul W. Denton, Jacob W. S. Martens, Ying Fang, Nicholas Conoan, Michael V. Callahan, James V. Lawler, David M. Brett-Major, John J. Lowe
Summary: The study found evidence of viral replication in submicron aerosol samples from COVID-19 patients, further confirming the potential for airborne transmission of COVID-19. Therefore, it emphasizes the importance of using efficient respiratory protection in healthcare and public settings to limit transmission.
JOURNAL OF EXPOSURE SCIENCE AND ENVIRONMENTAL EPIDEMIOLOGY
(2022)
Article
Virology
Joshua L. Santarpia, Nicholas W. Markin, Vicki L. Herrera, Daniel N. Ackerman, Danielle N. Rivera, Gabriel A. Lucero, Steven J. Lisco
Summary: This study evaluated the effectiveness of an Infectious Aerosol Capture Mask (IACM) in capturing exhaled breath aerosols from COVID-19 patients. The results showed that the mask captured at least 99% of particles and could effectively capture particles between 0.1 and 20 μm during breathing and speaking. During coughing, only a small percentage of the smallest particles escaped the mask. Additionally, no SARS-CoV-2 aerosol was detected in samples collected adjacent to the patient when wearing the mask.
Article
Environmental Sciences
Joshua L. Santarpia, Don R. Collins, Shanna A. Ratnesar-Shumate, Crystal C. Glen, Andres L. Sanchez, Carlos G. Antonietti, Jilliane Taylor, Nathan F. Taylor, Christopher A. Bare, Sean M. Kinahan, Danielle N. Rivera, Elizabeth Corson, Steven C. Hill, Chatt C. Williamson, Mark Coleman, Yong-Le Pan
Summary: The study examined the impact of environmental conditions on the fluorescence spectra of atmospheric bioaerosols, revealing significant alterations due to atmospheric aging processes that could affect spectroscopic measurements.
Article
Environmental Sciences
Sarah J. Stein, Ashley R. Ravnholdt, Vicki L. Herrera, Danielle N. Rivera, Paul T. Williams, Joshua L. Santarpia
Summary: To determine the potential of SARS-CoV-2 aerosol transmission during COVID-19 testing, researchers examined aerosol and surface samples from Nebraska Medicine testing and vaccine clinics. They found aerosols containing SARS-CoV-2 RNA within the clinics, indicating viral shedding from infected individuals. SARS-CoV-2 RNA was also detected in surface samples, highlighting the importance of respiratory protection and sanitization practices for healthcare workers and public-facing occupations.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
(2023)
Article
Multidisciplinary Sciences
Yadong Xu, Yajuan Su, Xianchen Xu, Brian Arends, Ganggang Zhao, Daniel N. Ackerman, Henry Huang, St. Patrick Reid, Joshua L. Santarpia, Chansong Kim, Zehua Chen, Sana Mahmoud, Yun Ling, Alexander Brown, Qian Chen, Guoliang Huang, Jingwei Xie, Zheng Yan
Summary: We report a phase separation-based synthesis of porous liquid metal-elastomer composites with high leakage resistance and antimicrobial property, along with large stretchability, tissue-like compliance, high and stable electrical conductivity over deformation, high breathability, and magnetic resonance imaging compatibility. The enabled skin-interfaced bioe-lectronics can monitor cardiac electrical and mechanical activities and offer electrical stimulations in a mechanically imperceptible and electrically stable manner even during motions.
Article
Engineering, Chemical
Sean M. Kinahan, Gabriel A. Lucero, Matthew S. Tezak, Kevin Hommema, Paul Gemmer, Eric Scribben, Thomas Hawkyard, Don R. Collins, Kevin K. Crown, Joshua L. Santarpia
Summary: This study compared the results of microfiber and Goldberg rotating drum methods in an outdoor experimental environment and found that the two methods yielded similar results. There was no statistically significant difference in aging rates for carbon-filtered air compared to ambient air, as well as for protection from sunlight compared to exposure to sunlight.
AEROSOL SCIENCE AND TECHNOLOGY
(2023)
Article
Multidisciplinary Sciences
Cathryn M. Siegrist, Sean M. Kinahan, Taylor Settecerri, Adrienne C. Greene, Joshua L. Santarpia
SCIENTIFIC REPORTS
(2020)