Graph Neural Networks (GNN) were originally developed to infer relationships between objects in complex graph environments such as social networks. However, they have recently been applied to other domains which naturally support graph expression, such as hardware and software analysis. We propose to extend the application of GNNs to datasets which contain a temporal component, thus enabling GNN inference of event-driven situations involving the radio frequency (RF) spectrum. Post-battle analysis can train a GNN to identify individual subgraphs representing sequences of events. Trained GNNs can then be used in war time to infer a larger situation as a series of subgraphs are identified.
{"title":"Situational awareness on a graph: towards graph neural networks for spectrum analysis and battlefield management","authors":"Jeff Anderson","doi":"10.1117/12.3014462","DOIUrl":"https://doi.org/10.1117/12.3014462","url":null,"abstract":"Graph Neural Networks (GNN) were originally developed to infer relationships between objects in complex graph environments such as social networks. However, they have recently been applied to other domains which naturally support graph expression, such as hardware and software analysis. We propose to extend the application of GNNs to datasets which contain a temporal component, thus enabling GNN inference of event-driven situations involving the radio frequency (RF) spectrum. Post-battle analysis can train a GNN to identify individual subgraphs representing sequences of events. Trained GNNs can then be used in war time to infer a larger situation as a series of subgraphs are identified.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"13 1‐2","pages":"130580L - 130580L-8"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141376992","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}
Face recognition technology has been well investigated in past decades and widely deployed in many real-world applications. However, low-resolution face recognition is still a challenging task in resource-constrained edge computing environment like the Internet of Video Things (IoVT) applications. For instance, low-resolution images are common in surveillance video streams, in which the rare information, variable angles, and light conditions create difficulties for recognition tasks. To address these problems, we optimized the correlation feature face recognition (CoFFaR) method and conducted experimental studies in two data preparation modes, symmetric and exhaustive arranging. The experimental results show that the CoFFaR method achieved an accuracy rate of over 82.56%, and the two-dimensional (2D) feature points after dimension reduction are uniformly distributed in a diagonal pattern. The analysis leads to the conclusion that the data augmentation advantage brought by the method of exhaustive arranging data preparation can effectively improve the performance, and the constraints by making the feature vector closer to its clustering center have no apparent improvement in the accuracy of the model identification.
{"title":"A homogeneous low-resolution face recognition method using correlation features at the edge","authors":"Xuan Zhao, Deeraj Nagothu, Yu Chen","doi":"10.1117/12.3008368","DOIUrl":"https://doi.org/10.1117/12.3008368","url":null,"abstract":"Face recognition technology has been well investigated in past decades and widely deployed in many real-world applications. However, low-resolution face recognition is still a challenging task in resource-constrained edge computing environment like the Internet of Video Things (IoVT) applications. For instance, low-resolution images are common in surveillance video streams, in which the rare information, variable angles, and light conditions create difficulties for recognition tasks. To address these problems, we optimized the correlation feature face recognition (CoFFaR) method and conducted experimental studies in two data preparation modes, symmetric and exhaustive arranging. The experimental results show that the CoFFaR method achieved an accuracy rate of over 82.56%, and the two-dimensional (2D) feature points after dimension reduction are uniformly distributed in a diagonal pattern. The analysis leads to the conclusion that the data augmentation advantage brought by the method of exhaustive arranging data preparation can effectively improve the performance, and the constraints by making the feature vector closer to its clustering center have no apparent improvement in the accuracy of the model identification.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"229 1","pages":"130620F - 130620F-17"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141376146","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}
Zahidur Rahman, Leonid Roytman, A. Kadik, D. Rosy, Pradipta Nandi
In light of the profound global health impact of pandemics, the reliance on data-driven insights to understand disease outbreaks has never been more crucial. Malaria is a disease transmitted by mosquitoes that is endemic to specific regions and causes severe illness and death to millions each year. The sensitivity of mosquito vectors to environmental factors like temperature, precipitation, and humidity enables the mapping of areas at high risk of disease outbreaks through satellite remote sensing. This study proposes the development of a practical geospatial system that can provide early warning for malaria. It combines Geographic Information System (GIS) tools, Artificial Neural Networks (ANN) for efficient pattern recognition, robust on-ground environmental data (including epidemiological and vector ecology data), and the capabilities of satellite remote sensing. The study employs Vegetation Health Indices (VHI) derived from satellite-mounted Advanced Very High-Resolution Radiometers (AVHRR) on a weekly basis with a 4-km resolution to predict malaria risk in Bangladesh. While the focus is on Bangladesh due to its significant malaria threat, the technology developed can be adapted for use in other countries and against different disease threats. Implementing an early malaria warning system would be a significant asset to global public health efforts. It would enable targeted resource allocation for pandemic containment and serve as a vital decision-making tool for national security assessments and potential troop deployments in disease-prone regions.
{"title":"Harnessing data and satellites for early malaria warning: a global health imperative","authors":"Zahidur Rahman, Leonid Roytman, A. Kadik, D. Rosy, Pradipta Nandi","doi":"10.1117/12.3012771","DOIUrl":"https://doi.org/10.1117/12.3012771","url":null,"abstract":"In light of the profound global health impact of pandemics, the reliance on data-driven insights to understand disease outbreaks has never been more crucial. Malaria is a disease transmitted by mosquitoes that is endemic to specific regions and causes severe illness and death to millions each year. The sensitivity of mosquito vectors to environmental factors like temperature, precipitation, and humidity enables the mapping of areas at high risk of disease outbreaks through satellite remote sensing. This study proposes the development of a practical geospatial system that can provide early warning for malaria. It combines Geographic Information System (GIS) tools, Artificial Neural Networks (ANN) for efficient pattern recognition, robust on-ground environmental data (including epidemiological and vector ecology data), and the capabilities of satellite remote sensing. The study employs Vegetation Health Indices (VHI) derived from satellite-mounted Advanced Very High-Resolution Radiometers (AVHRR) on a weekly basis with a 4-km resolution to predict malaria risk in Bangladesh. While the focus is on Bangladesh due to its significant malaria threat, the technology developed can be adapted for use in other countries and against different disease threats. Implementing an early malaria warning system would be a significant asset to global public health efforts. It would enable targeted resource allocation for pandemic containment and serve as a vital decision-making tool for national security assessments and potential troop deployments in disease-prone regions.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"113 1","pages":"130590D - 130590D-9"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141381431","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}
Pappu K. Yadav, Thomas Burks, Snehit Vaddi, Jianwei Qin, Moon Kim, M. Ritenour, F. Vasefi
The transmission of Escherichia coli (E. coli) bacteria to humans through infected fruits and vegetables, such as citrus, can lead to severe health issues, including bloody diarrhea and kidney disease (Hemolytic Uremic Syndrome). Therefore, the implementation of a suitable sensor and detection approach for inspecting the presence of E. coli colonies on fruits and vegetables would greatly enhance food safety measures. This article presents an evaluation of SafetySpect's Contamination, Sanitization Inspection, and Disinfection (CSI-D+) system, comprising an UV camera, an RGB camera, and illumination at fluorescence excitation wavelengths: ultraviolet C (UVC) at 275 nm. To conduct the study, eight different concentrations ranging from 100 (control) to 108 (maximum) cell counts of bacterial populations were inoculated on extracted citrus peel specimens. Specimen data could represent either irrigation or sprayer-based contamination events or direct contact with wildlife. Our study delves into early detection using the portable CSI-D+ system, capturing 240x240 pixel UV-C fluorescence images of E. Coli-inoculated grapefruit peel plugs. We developed a pipeline to prepare these images for the YOLOv8 deep learning framework, facilitating E. coli classification across varying concentrations and backgrounds. To enhance explainability, we employed Eigen Class Activation Map (Eigen-CAM) with YOLOv8, utilizing 'pytorch-eigen-cam' (https://github.com/rigvedrs/YOLO-V8-CAM) to elucidate the model's decision-making in detecting and classifying different E. coli concentrations. Our study demonstrated that the CSI-D+ system could classify fluorescence images at eight different concentration levels with an overall accuracy of more than 83% in which the control class reached a perfect classification accuracy while the images with E. coli concentration of 106 CFU/drop had the lowest accuracy of 71%. Similarly, the images with maximum concentration i.e., 108 CFU/drop were classified at an accuracy of 94%. These findings demonstrate the application of the CSI-D+ system as a rapid, non-invasive tool for E. coli detection on citrus peel surfaces that may be on the tree thus alerting the potential for similar contamination on fruit still on the tree. By providing timely insights, these results could enable effective intervention strategies to eliminate dangerous E. Coli from the food chain.
{"title":"Detection of E. coli concentration levels using CSI-D+ handheld with UV-C fluorescence imaging and deep learning on leaf surfaces","authors":"Pappu K. Yadav, Thomas Burks, Snehit Vaddi, Jianwei Qin, Moon Kim, M. Ritenour, F. Vasefi","doi":"10.1117/12.3014017","DOIUrl":"https://doi.org/10.1117/12.3014017","url":null,"abstract":"The transmission of Escherichia coli (E. coli) bacteria to humans through infected fruits and vegetables, such as citrus, can lead to severe health issues, including bloody diarrhea and kidney disease (Hemolytic Uremic Syndrome). Therefore, the implementation of a suitable sensor and detection approach for inspecting the presence of E. coli colonies on fruits and vegetables would greatly enhance food safety measures. This article presents an evaluation of SafetySpect's Contamination, Sanitization Inspection, and Disinfection (CSI-D+) system, comprising an UV camera, an RGB camera, and illumination at fluorescence excitation wavelengths: ultraviolet C (UVC) at 275 nm. To conduct the study, eight different concentrations ranging from 100 (control) to 108 (maximum) cell counts of bacterial populations were inoculated on extracted citrus peel specimens. Specimen data could represent either irrigation or sprayer-based contamination events or direct contact with wildlife. Our study delves into early detection using the portable CSI-D+ system, capturing 240x240 pixel UV-C fluorescence images of E. Coli-inoculated grapefruit peel plugs. We developed a pipeline to prepare these images for the YOLOv8 deep learning framework, facilitating E. coli classification across varying concentrations and backgrounds. To enhance explainability, we employed Eigen Class Activation Map (Eigen-CAM) with YOLOv8, utilizing 'pytorch-eigen-cam' (https://github.com/rigvedrs/YOLO-V8-CAM) to elucidate the model's decision-making in detecting and classifying different E. coli concentrations. Our study demonstrated that the CSI-D+ system could classify fluorescence images at eight different concentration levels with an overall accuracy of more than 83% in which the control class reached a perfect classification accuracy while the images with E. coli concentration of 106 CFU/drop had the lowest accuracy of 71%. Similarly, the images with maximum concentration i.e., 108 CFU/drop were classified at an accuracy of 94%. These findings demonstrate the application of the CSI-D+ system as a rapid, non-invasive tool for E. coli detection on citrus peel surfaces that may be on the tree thus alerting the potential for similar contamination on fruit still on the tree. By providing timely insights, these results could enable effective intervention strategies to eliminate dangerous E. Coli from the food chain.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"362 14","pages":"1306006 - 1306006-11"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141380811","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}
Noah Boursier, Kal Holder, Bruce M. Applegate, Bartek Rajwa, J. P. Robinson, E. Bae
In the realm of food safety, the standard practice involves collecting food product samples and sending them to a central laboratory for microbiological testing. However, this process introduces delays in obtaining the microbiological testing results and subsequently affects the timely delivery of food products to consumers. To further reduce the time-to-detection issue, we propose the development of a self-contained, battery-operated, high-sensitivity optical sensor that can be affixed to the cap of the typical food sample collection container. This device, called MPACT, offers real-time and in-transit monitoring of the contamination status of the food sample, specifically targeting E. coli O157:H7, through a bioluminescence assay. The assay exclusively targets the target pathogen and, when detected, produces minimal luminescence. As the sample is transported in the container, the number of bacterial cells multiplies, and once the luminescent signal reaches a predefined threshold, the sensor reports the results via Bluetooth. This study focuses on the design of the bottle cap sensor and examines its sensitivity by subjecting it to bioluminescence samples.
{"title":"Design of real-time pathogen monitoring device for sampled food products during shipment","authors":"Noah Boursier, Kal Holder, Bruce M. Applegate, Bartek Rajwa, J. P. Robinson, E. Bae","doi":"10.1117/12.3016191","DOIUrl":"https://doi.org/10.1117/12.3016191","url":null,"abstract":"In the realm of food safety, the standard practice involves collecting food product samples and sending them to a central laboratory for microbiological testing. However, this process introduces delays in obtaining the microbiological testing results and subsequently affects the timely delivery of food products to consumers. To further reduce the time-to-detection issue, we propose the development of a self-contained, battery-operated, high-sensitivity optical sensor that can be affixed to the cap of the typical food sample collection container. This device, called MPACT, offers real-time and in-transit monitoring of the contamination status of the food sample, specifically targeting E. coli O157:H7, through a bioluminescence assay. The assay exclusively targets the target pathogen and, when detected, produces minimal luminescence. As the sample is transported in the container, the number of bacterial cells multiplies, and once the luminescent signal reaches a predefined threshold, the sensor reports the results via Bluetooth. This study focuses on the design of the bottle cap sensor and examines its sensitivity by subjecting it to bioluminescence samples.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"122 3","pages":"1306008 - 1306008-7"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141376694","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}
Noah Boursier, Junwoo Jang, Awadhoot M. Ghatge, Kevin Lim, Thomas R. McClure, J. P. Robinson, E. Bae
With the development and expansion of the internet of things, many scientific and engineering instruments are leaving the benchtop restriction and moving on to provide on-site detection. On-site detection requires a complete miniaturization of a benchtop system while maintaining a similar performance with respect to the analyte detection sensitivity. In addition, due to the mobile nature, utilizing a battery source is required. Here we present a portable loop-medicated isothermal amplification detection system for on-site detection and amplification of target analyte via fluorescence detection. The digital twin design incorporates three major components: an isothermal heating chamber, light-tight enclosure for sample insert, and fluorescence imaging system via micro-controllers. The isothermal heating chamber was designed with Peltier heater to provide small form factor accurate temperature control. For light-tight enclosure is a 3D printed device that allows DNA samples to be inserted and fluorescent images to be taken within the chamber. Lastly, fluorescent imaging system operates with a stand-alone camera connected to an Arduino micro-controller. Excitation is provided by blue colored LED and emission is detected via long-pass filter that matches the emission spectrum.
随着物联网的发展和扩大，许多科学和工程仪器正在摆脱台式机的限制，转而提供现场检测。现场检测要求台式系统完全微型化，同时在分析物检测灵敏度方面保持类似的性能。此外，由于其移动性，还需要使用电池源。在此，我们介绍一种便携式环形医疗等温扩增检测系统，用于通过荧光检测对目标分析物进行现场检测和扩增。数字孪生设计包含三个主要部分：等温加热室、用于插入样品的光密外壳以及通过微控制器实现的荧光成像系统。等温加热室采用珀尔帖加热器设计，体积小，温度控制精确。光密外壳是一个 3D 打印装置，可在腔体内插入 DNA 样品并拍摄荧光图像。最后，荧光成像系统通过一个与 Arduino 微控制器相连的独立相机运行。激发由蓝色 LED 提供，发射则通过与发射光谱相匹配的长通滤波器检测。
{"title":"Design of a portable fluorescence imaging platform for on-site detection target analyte by loop-medicated isothermal amplification","authors":"Noah Boursier, Junwoo Jang, Awadhoot M. Ghatge, Kevin Lim, Thomas R. McClure, J. P. Robinson, E. Bae","doi":"10.1117/12.3016161","DOIUrl":"https://doi.org/10.1117/12.3016161","url":null,"abstract":"With the development and expansion of the internet of things, many scientific and engineering instruments are leaving the benchtop restriction and moving on to provide on-site detection. On-site detection requires a complete miniaturization of a benchtop system while maintaining a similar performance with respect to the analyte detection sensitivity. In addition, due to the mobile nature, utilizing a battery source is required. Here we present a portable loop-medicated isothermal amplification detection system for on-site detection and amplification of target analyte via fluorescence detection. The digital twin design incorporates three major components: an isothermal heating chamber, light-tight enclosure for sample insert, and fluorescence imaging system via micro-controllers. The isothermal heating chamber was designed with Peltier heater to provide small form factor accurate temperature control. For light-tight enclosure is a 3D printed device that allows DNA samples to be inserted and fluorescent images to be taken within the chamber. Lastly, fluorescent imaging system operates with a stand-alone camera connected to an Arduino micro-controller. Excitation is provided by blue colored LED and emission is detected via long-pass filter that matches the emission spectrum.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"10 14","pages":"130600A - 130600A-10"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141380367","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}
Naval Air Warfare Center Aircraft Division (NAWCAD) engineers and scientists recently completed initial laboratory and field testing of the Modulated Underwater Laser Imaging System (MULIS) prototype. This represents the culmination of years of collaboration between NAWCAD, industry, and academia partners to transition NAWCAD’s radar-encoded laser imaging technology out of the lab and into the field. This paper presents results from both initial laboratory and field tests of the MULIS prototype. Laboratory tests evaluated imaging performance in a variety of simulated water clarity conditions. MULIS was then integrated into a REMUS 600 Autonomous Underwater Vehicle (AUV) for a field test event in the Chesapeake Bay in the summer of 2023. Multiple successful missions were run over the course of the field test, obtaining 3D imagery of the submerged objects despite the challenging water clarity conditions in the Chesapeake Bay.
{"title":"Initial laboratory and field testing of the modulated underwater laser imaging system","authors":"Nicholas Makrakis, D. Illig, Linda Mullen","doi":"10.1117/12.3014336","DOIUrl":"https://doi.org/10.1117/12.3014336","url":null,"abstract":"Naval Air Warfare Center Aircraft Division (NAWCAD) engineers and scientists recently completed initial laboratory and field testing of the Modulated Underwater Laser Imaging System (MULIS) prototype. This represents the culmination of years of collaboration between NAWCAD, industry, and academia partners to transition NAWCAD’s radar-encoded laser imaging technology out of the lab and into the field. This paper presents results from both initial laboratory and field tests of the MULIS prototype. Laboratory tests evaluated imaging performance in a variety of simulated water clarity conditions. MULIS was then integrated into a REMUS 600 Autonomous Underwater Vehicle (AUV) for a field test event in the Chesapeake Bay in the summer of 2023. Multiple successful missions were run over the course of the field test, obtaining 3D imagery of the submerged objects despite the challenging water clarity conditions in the Chesapeake Bay.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"2 1","pages":"1306106 - 1306106-6"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141378722","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}
Parker Huggins, Win Janvrin, Jake Martin, Ashley Womer, Austin R. J. Downey, John Ferry, Mohammed Baalousha, Jin Yan
The characterization of algae biomass is essential for ensuring the health of an aquatic ecosystem. Algae overgrowth can be detrimental to the chemical composition of a habitat and affect the availability of safe drinking water. In-situ sensors are commonplace in ocean and water quality monitoring scenarios where the collection of field data using readily deployable, cost-effective sensors is required. For this purpose, the use of compact time domain nuclear magnetic resonance (TD-NMR) is proposed for the assessment of Magnetic Particle (MP) content in algae. A custom NMR system capable of rapidly acquiring relaxometric data is introduced, and the T2 relaxation curves of algae samples sourced from Lake Wateree in South Carolina are analyzed. A clear correlation between the relaxation rate and MP concentration of the samples is observed, and the viability of the proposed scheme for MP-based estimations concerning algae is discussed.
{"title":"Assessing magnetic particle content in algae using compact time domain nuclear magnetic resonance","authors":"Parker Huggins, Win Janvrin, Jake Martin, Ashley Womer, Austin R. J. Downey, John Ferry, Mohammed Baalousha, Jin Yan","doi":"10.1117/12.3013987","DOIUrl":"https://doi.org/10.1117/12.3013987","url":null,"abstract":"The characterization of algae biomass is essential for ensuring the health of an aquatic ecosystem. Algae overgrowth can be detrimental to the chemical composition of a habitat and affect the availability of safe drinking water. In-situ sensors are commonplace in ocean and water quality monitoring scenarios where the collection of field data using readily deployable, cost-effective sensors is required. For this purpose, the use of compact time domain nuclear magnetic resonance (TD-NMR) is proposed for the assessment of Magnetic Particle (MP) content in algae. A custom NMR system capable of rapidly acquiring relaxometric data is introduced, and the T2 relaxation curves of algae samples sourced from Lake Wateree in South Carolina are analyzed. A clear correlation between the relaxation rate and MP concentration of the samples is observed, and the viability of the proposed scheme for MP-based estimations concerning algae is discussed.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"105 4","pages":"1306102 - 1306102-7"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141376936","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}
Tianzhen Yin, Yankun Peng, K. Chao, J. Qin, Feifei Tao, Yang Li, Zhenhao Ma
Establishing a universal and efficient method for determining ractopamine residues in pork is of paramount importance for ensuring food safety. However, the main challenge lies in achieving accurate quantitative detection of complex samples using Surface-Enhanced Raman Scattering (SERS), as it requires overcoming interference from substrate-sample mixing and variations in hotspot distribution. This study introduces an innovative approach to address this challenge by proposing a breakthrough interference factor removal network based on deep learning, termed SERSNet. By enhancing the depth of SERS spectroscopy, SERSNet establishes a correlation between the spectra of pork samples with varying concentrations of ractopamine. A multilayer convolution module is developed to effectively extract the spectral features of ractopamine. The Mean Absolute Error (MAE), root mean square error (RMSE), and Mean Absolute Percentage Error (MAPE) of the proposed model in this paper are 0.90, 0.48, and 80.48, respectively. The performance of the SERSNet model surpasses that of the Multiple Linear Regression (MLR) model. The SERSNet algorithm proposed in this paper demonstrates competitiveness and yields superior results.
{"title":"Rapid quantitative detection of Ractopamine using Raman scattering features combining with deep learning","authors":"Tianzhen Yin, Yankun Peng, K. Chao, J. Qin, Feifei Tao, Yang Li, Zhenhao Ma","doi":"10.1117/12.3013271","DOIUrl":"https://doi.org/10.1117/12.3013271","url":null,"abstract":"Establishing a universal and efficient method for determining ractopamine residues in pork is of paramount importance for ensuring food safety. However, the main challenge lies in achieving accurate quantitative detection of complex samples using Surface-Enhanced Raman Scattering (SERS), as it requires overcoming interference from substrate-sample mixing and variations in hotspot distribution. This study introduces an innovative approach to address this challenge by proposing a breakthrough interference factor removal network based on deep learning, termed SERSNet. By enhancing the depth of SERS spectroscopy, SERSNet establishes a correlation between the spectra of pork samples with varying concentrations of ractopamine. A multilayer convolution module is developed to effectively extract the spectral features of ractopamine. The Mean Absolute Error (MAE), root mean square error (RMSE), and Mean Absolute Percentage Error (MAPE) of the proposed model in this paper are 0.90, 0.48, and 80.48, respectively. The performance of the SERSNet model surpasses that of the Multiple Linear Regression (MLR) model. The SERSNet algorithm proposed in this paper demonstrates competitiveness and yields superior results.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"17 8","pages":"130600D - 130600D-6"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141379908","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}
Justin R. Folden, Derek Alley, D. Illig, Linda Mullen, Sanjeev Koppal
Scattering effects in underwater environments significantly challenge optical perception. This paper introduces a foveating confocal bistatic LiDAR system, uniquely capable of adaptive targeting with its MEMS-modulated transmitter and receiver in turbid underwater conditions. By dynamically adjusting its receiver instantaneous field of view to areas of interest, it effectively increases depth sampling in complex and challenging underwater environments. Applying bistatic principles, separating transmitter and receiver, we allow robustness to scattering media effects. We demonstrate LIDAR results in an underwater laboratory tank setting.
{"title":"Confocal Bistatic LIDAR in scattering media","authors":"Justin R. Folden, Derek Alley, D. Illig, Linda Mullen, Sanjeev Koppal","doi":"10.1117/12.3014721","DOIUrl":"https://doi.org/10.1117/12.3014721","url":null,"abstract":"Scattering effects in underwater environments significantly challenge optical perception. This paper introduces a foveating confocal bistatic LiDAR system, uniquely capable of adaptive targeting with its MEMS-modulated transmitter and receiver in turbid underwater conditions. By dynamically adjusting its receiver instantaneous field of view to areas of interest, it effectively increases depth sampling in complex and challenging underwater environments. Applying bistatic principles, separating transmitter and receiver, we allow robustness to scattering media effects. We demonstrate LIDAR results in an underwater laboratory tank setting.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"147 6‐9","pages":"1306108 - 1306108-5"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141381275","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：