One of the main challenges in underwater automatic target recognition is in the data scarcity of underwater sonar imagery. This challenge arises especially in data-driven approaches because of the limited training dataset and unknown environmental conditions before the mission. Transfer learning and synthetic data generation have been suggested as effective methods to overcome this challenge. However, the efficiency and effectiveness of synthetic data generation methods have been limited due to the difficulty from implementing complex acoustic imaging processes and data-driven model’s poor performance under domain shifts. In this paper, we present a novel approach to address this challenge by utilizing cycle-Generative Adversarial Networks (GAN) to generate synthetic sonar images to enhance the effectiveness of the training data set. Our method simplifies the process of synthetic data generation by leveraging cycle-GAN, which is a deep Convolutional Neural Network (CNN) for image-to-image translation using unpaired dataset. The cycle-GAN based generation model transfers camera images of ship and plane into realistic synthetic sonar images. Then, these generated synthetic images are used to augment the training data set for the classification model. In this work, the effectiveness of this approach is demonstrated through a series of experiments, showing improvements in classification accuracy. One advantage of the proposed approach is in the simplification of the synthetic data generation process while improving classification accuracy. Another advantage is that the ship and plane sonar image generation model is trained solely on seabed sonar images, which are relatively easy to obtain. This approach has the potential to greatly benefit the field of underwater sonar image classification by providing a more efficient solution for addressing data scarcity.
{"title":"Cycle-GAN-based synthetic sonar image generation for improved underwater classification","authors":"Sunmo Koo, Sangpil Youm, Jane Shin","doi":"10.1117/12.3016056","DOIUrl":"https://doi.org/10.1117/12.3016056","url":null,"abstract":"One of the main challenges in underwater automatic target recognition is in the data scarcity of underwater sonar imagery. This challenge arises especially in data-driven approaches because of the limited training dataset and unknown environmental conditions before the mission. Transfer learning and synthetic data generation have been suggested as effective methods to overcome this challenge. However, the efficiency and effectiveness of synthetic data generation methods have been limited due to the difficulty from implementing complex acoustic imaging processes and data-driven model’s poor performance under domain shifts. In this paper, we present a novel approach to address this challenge by utilizing cycle-Generative Adversarial Networks (GAN) to generate synthetic sonar images to enhance the effectiveness of the training data set. Our method simplifies the process of synthetic data generation by leveraging cycle-GAN, which is a deep Convolutional Neural Network (CNN) for image-to-image translation using unpaired dataset. The cycle-GAN based generation model transfers camera images of ship and plane into realistic synthetic sonar images. Then, these generated synthetic images are used to augment the training data set for the classification model. In this work, the effectiveness of this approach is demonstrated through a series of experiments, showing improvements in classification accuracy. One advantage of the proposed approach is in the simplification of the synthetic data generation process while improving classification accuracy. Another advantage is that the ship and plane sonar image generation model is trained solely on seabed sonar images, which are relatively easy to obtain. This approach has the potential to greatly benefit the field of underwater sonar image classification by providing a more efficient solution for addressing data scarcity.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"73 1","pages":"130610B - 130610B-15"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141381334","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}
Bryan Gonzalez, Jeremy Niemiec, Dylan Ballback, Aleiya Holyoak, Zachary R. Nadeau, Gabriel M. Alkire, Avery Cuenin, Christopher Hockley, Monica Garcia
The OpenMutt platform is a modular, robotic quadruped for use as a testbed for a variety of research opportunities to increase multidisciplinary research. The OpenMutt quadruped allows for a low-cost testbed for actuator drive design, biomimicry, and instrumentation. The current design is intended to be modular and facilitate different research disciplines with the usage of a robust 13:1 cycloidal actuator, modular feet, and multiple mounting points for the investigation of various sensing modalities and hardware packages.
{"title":"OpenMutt: a low-cost quadruped for student education in research","authors":"Bryan Gonzalez, Jeremy Niemiec, Dylan Ballback, Aleiya Holyoak, Zachary R. Nadeau, Gabriel M. Alkire, Avery Cuenin, Christopher Hockley, Monica Garcia","doi":"10.1117/12.3014032","DOIUrl":"https://doi.org/10.1117/12.3014032","url":null,"abstract":"The OpenMutt platform is a modular, robotic quadruped for use as a testbed for a variety of research opportunities to increase multidisciplinary research. The OpenMutt quadruped allows for a low-cost testbed for actuator drive design, biomimicry, and instrumentation. The current design is intended to be modular and facilitate different research disciplines with the usage of a robust 13:1 cycloidal actuator, modular feet, and multiple mounting points for the investigation of various sensing modalities and hardware packages.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"3 6","pages":"130580W - 130580W-7"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141381678","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}
Naseem Alsadi, Syed Zaidi, Mankaran Rooprai, S. A. Gadsden, J. Yawney, W. Hilal
The Internet of Things (IoT) and other emerging ubiquitous technologies are supporting the rapid spread of smart systems, which has underlined the need for safe, open, and decentralized data storage solutions. With its inherent decentralization and immutability, blockchain offers itself as a potential solution for these requirements. However, the practicality of incorporating blockchain into real-time sensor data storage systems is a topic that demands in-depth examination. While blockchain promises unmatched data security and auditability, some intrinsic qualities, namely scalability restrictions, transactional delays, and escalating storage demands, impede its seamless deployment in high-frequency, voluminous data contexts typical of real-time sensors. This essay launches a methodical investigation into these difficulties, illuminating their underlying causes, potential effects, and potential countermeasures. In addition, we present a novel pragmatic experimental setup and analysis of blockchain for smart system applications, with an extended discussion of the benefits and disadvantages of deploying blockchain based solutions for smart system ecosystems.
{"title":"Integration of blockchain in smart systems: problems and opportunities for real-time sensor data storage","authors":"Naseem Alsadi, Syed Zaidi, Mankaran Rooprai, S. A. Gadsden, J. Yawney, W. Hilal","doi":"10.1117/12.3013828","DOIUrl":"https://doi.org/10.1117/12.3013828","url":null,"abstract":"The Internet of Things (IoT) and other emerging ubiquitous technologies are supporting the rapid spread of smart systems, which has underlined the need for safe, open, and decentralized data storage solutions. With its inherent decentralization and immutability, blockchain offers itself as a potential solution for these requirements. However, the practicality of incorporating blockchain into real-time sensor data storage systems is a topic that demands in-depth examination. While blockchain promises unmatched data security and auditability, some intrinsic qualities, namely scalability restrictions, transactional delays, and escalating storage demands, impede its seamless deployment in high-frequency, voluminous data contexts typical of real-time sensors. This essay launches a methodical investigation into these difficulties, illuminating their underlying causes, potential effects, and potential countermeasures. In addition, we present a novel pragmatic experimental setup and analysis of blockchain for smart system applications, with an extended discussion of the benefits and disadvantages of deploying blockchain based solutions for smart system ecosystems.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"18 1","pages":"130580R - 130580R-11"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141380034","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}
Owen O'Malley, Svetlana Avramov-Zamurovic, Nathaniel Ferlic, Matthew Kalensky, K. Judd, Carlos Pirela, Thomas J. Kelly
Accurate measurement of laser light phase after propagation through underwater optical turbulence is crucial for defense and commercial applications like underwater communications and sensing. Traditional phase-measuring methods, like Shack-Hartmann wavefront sensors, have limited effectiveness in strong optical turbulence. The Gerchberg-Saxton (GS) method utilizes synchronized intensity images in the image and Fourier planes and retrieves the phase through an iterative algorithm. We evaluate the Gerchberg-Saxton algorithm's accuracy for laser light propagation through simulated Kolmogorov turbulence and experimentally generated Rayleigh-Bénard (RB) natural convection. The results of the phase retrieved from the experimental data recorded in pupil and focal planes are compared with the phase measurements from a Shack-Hartmann sensor. We tested the efficacy of the Gerchberg-Saxton algorithm to estimate the phase of laser light upon propagation through underwater optical turbulence.
{"title":"Comparison between phase retrieval methods for laser light propagated through Rayleigh-Benard underwater convection","authors":"Owen O'Malley, Svetlana Avramov-Zamurovic, Nathaniel Ferlic, Matthew Kalensky, K. Judd, Carlos Pirela, Thomas J. Kelly","doi":"10.1117/12.3013458","DOIUrl":"https://doi.org/10.1117/12.3013458","url":null,"abstract":"Accurate measurement of laser light phase after propagation through underwater optical turbulence is crucial for defense and commercial applications like underwater communications and sensing. Traditional phase-measuring methods, like Shack-Hartmann wavefront sensors, have limited effectiveness in strong optical turbulence. The Gerchberg-Saxton (GS) method utilizes synchronized intensity images in the image and Fourier planes and retrieves the phase through an iterative algorithm. We evaluate the Gerchberg-Saxton algorithm's accuracy for laser light propagation through simulated Kolmogorov turbulence and experimentally generated Rayleigh-Bénard (RB) natural convection. The results of the phase retrieved from the experimental data recorded in pupil and focal planes are compared with the phase measurements from a Shack-Hartmann sensor. We tested the efficacy of the Gerchberg-Saxton algorithm to estimate the phase of laser light upon propagation through underwater optical turbulence.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"20 20","pages":"130610H - 130610H-11"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141379183","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}
Abhay M. Joshi, S. Datta, Abigale R. Joshi, Michael Sivertz, David Inzalaco, Joel Hatch
Space-based optical communication links incorporating high speed photoreceivers, i.e. photodiodes integrated with Transimpedance Amplifiers (TIA), are required for multiple platforms, from low earth orbit satellite communication constellations to inter-planetary links and deep space missions. Our prior studies have demonstrated that InP/InGaAs photodiodes are resilient to radiation induced displacement and ionization damage when irradiated with a wide variety of ions. It is also necessary to qualify TIAs that may exhibit latch ups due to Single Event Effect (SEE) when irradiated with heavy ions having high Linear Energy Transfer (LET). We present a balanced InGaAs photoreceiver, i.e. a matched pair of photodiodes followed by a Silicon CMOS TIA, with automatic gain control mode that supports coherent and direct detection optical communication links with a symbol rate up to 25 Gbaud and aggregate data rate up to 100 Gbps and beyond. These devices were subjected to 76 MeV/n, 96 MeV/n, and 154 MeV/n Bismuth Ions up to a fluence of 1E7 ions/cm2 for each ion energy. The ion energies were chosen with the objective of achieving LET-Si of ⪆70 MeV-cm2 /mg. During the radiation runs, the TIAs were biased and their drive currents and RF output noise spectra were continuously recorded. The in-situ data was complemented by detailed analog and digital characterization of these devices before and after irradiation, including photodiode dark current, TIA drive current, RF response, RF return loss, noise spectrum, 25 Gbps Amplitude Shift Keyed (ASK) eye diagrams and bit error ratio, and 10.709 Gbps Return to Zero Differential Phase Shift Keyed (RZ-DPSK) eye diagrams and bit error ratio. We did not observe any significant impact on these devices due to radiation.
{"title":"Radiation testing of 25 Gbaud balanced photoreceivers with bismuth ions for linear energy transfer up to 70 MeV cm2/mg","authors":"Abhay M. Joshi, S. Datta, Abigale R. Joshi, Michael Sivertz, David Inzalaco, Joel Hatch","doi":"10.1117/12.3013868","DOIUrl":"https://doi.org/10.1117/12.3013868","url":null,"abstract":"Space-based optical communication links incorporating high speed photoreceivers, i.e. photodiodes integrated with Transimpedance Amplifiers (TIA), are required for multiple platforms, from low earth orbit satellite communication constellations to inter-planetary links and deep space missions. Our prior studies have demonstrated that InP/InGaAs photodiodes are resilient to radiation induced displacement and ionization damage when irradiated with a wide variety of ions. It is also necessary to qualify TIAs that may exhibit latch ups due to Single Event Effect (SEE) when irradiated with heavy ions having high Linear Energy Transfer (LET). We present a balanced InGaAs photoreceiver, i.e. a matched pair of photodiodes followed by a Silicon CMOS TIA, with automatic gain control mode that supports coherent and direct detection optical communication links with a symbol rate up to 25 Gbaud and aggregate data rate up to 100 Gbps and beyond. These devices were subjected to 76 MeV/n, 96 MeV/n, and 154 MeV/n Bismuth Ions up to a fluence of 1E7 ions/cm2 for each ion energy. The ion energies were chosen with the objective of achieving LET-Si of ⪆70 MeV-cm2 /mg. During the radiation runs, the TIAs were biased and their drive currents and RF output noise spectra were continuously recorded. The in-situ data was complemented by detailed analog and digital characterization of these devices before and after irradiation, including photodiode dark current, TIA drive current, RF response, RF return loss, noise spectrum, 25 Gbps Amplitude Shift Keyed (ASK) eye diagrams and bit error ratio, and 10.709 Gbps Return to Zero Differential Phase Shift Keyed (RZ-DPSK) eye diagrams and bit error ratio. We did not observe any significant impact on these devices due to radiation.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"86 4","pages":"1306207 - 1306207-11"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141376458","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}
Sravani Varanasi, Tianye Zhai, Hong Gu, Yihong Yang, Fow-Sen Choa
Substance Use Disorder (SUD) represents a pervasive global health crisis characterized by the compulsive and detrimental use of psychoactive substances. In this study, we explore the functional connectivity disparities between two age- and sex-matched groups comprising 53 individuals with Cocaine Use Disorder (CUD) and 52 Healthy Control (HC) subjects. We employed resting-state fMRI data, which were preprocessed using the CONN toolbox, ensuring high-quality data for subsequent analysis. The CONN toolbox has a default atlas of 164 ROIs based on the FSL-Harvard Oxford atlas and the automated Anatomical Labeling Atlas (AAL). The investigation extended into first level and second level-analysis features within the CONN toolbox to discern functional connectivity patterns between these two groups. At the group level analysis centered on contrasting CUD patients and HCs, we particularly focused on the Region-of-Interest (ROI)-ROI connectivity maps in this study. This study revealed some key findings: Firstly, we observed that HC subjects exhibited significantly stronger connectivity between the Superior Temporal Gyrus (STG) and regions of interest within the basal ganglia network (BSL), compared to individuals with CUD. Secondly, the HC group demonstrated heightened connectivity between regions of interest belonging to the visual network and the cerebellum, contrasting with the weaker connectivity observed in the CUD group. Lastly, there was a notable increase in connectivity between the Inferior Temporal Gyrus, temporooccipital part (toITG), and the cerebellum in individuals with CUD, further emphasizing the disruption in functional connectivity within this population. Understanding these functional connectivity differences may inform future interventions and diagnostic approaches in the context of cocaine use disorder.
{"title":"Functional connectivity differences between cocaine users and healthy controls: an fMRI study","authors":"Sravani Varanasi, Tianye Zhai, Hong Gu, Yihong Yang, Fow-Sen Choa","doi":"10.1117/12.3013689","DOIUrl":"https://doi.org/10.1117/12.3013689","url":null,"abstract":"Substance Use Disorder (SUD) represents a pervasive global health crisis characterized by the compulsive and detrimental use of psychoactive substances. In this study, we explore the functional connectivity disparities between two age- and sex-matched groups comprising 53 individuals with Cocaine Use Disorder (CUD) and 52 Healthy Control (HC) subjects. We employed resting-state fMRI data, which were preprocessed using the CONN toolbox, ensuring high-quality data for subsequent analysis. The CONN toolbox has a default atlas of 164 ROIs based on the FSL-Harvard Oxford atlas and the automated Anatomical Labeling Atlas (AAL). The investigation extended into first level and second level-analysis features within the CONN toolbox to discern functional connectivity patterns between these two groups. At the group level analysis centered on contrasting CUD patients and HCs, we particularly focused on the Region-of-Interest (ROI)-ROI connectivity maps in this study. This study revealed some key findings: Firstly, we observed that HC subjects exhibited significantly stronger connectivity between the Superior Temporal Gyrus (STG) and regions of interest within the basal ganglia network (BSL), compared to individuals with CUD. Secondly, the HC group demonstrated heightened connectivity between regions of interest belonging to the visual network and the cerebellum, contrasting with the weaker connectivity observed in the CUD group. Lastly, there was a notable increase in connectivity between the Inferior Temporal Gyrus, temporooccipital part (toITG), and the cerebellum in individuals with CUD, further emphasizing the disruption in functional connectivity within this population. Understanding these functional connectivity differences may inform future interventions and diagnostic approaches in the context of cocaine use disorder.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"47 S221","pages":"1305908 - 1305908-7"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141377266","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, Yahui Chen, Jiewen Zuo
Excessive consumption of β-adrenergic agonists from livestock, poultry, or viscera can present serious health risks, potentially endangering lives. Surface-enhanced Raman scattering (SERS) provides a precise method for measuring levels of β-adrenergic agonists. This study involved collecting spectra of ractopamine aqueous solutions by synthesizing Au@Ag NPS alloy substrates. A linear relationship between the concentration of ractopamine (ranged from 1 to 10 mg/L) and SERS intensity. Automatic Whittaker Filter (AWF) algorithm was used to preprocess the Raman spectra to remove the fluorescence background. A linear regression model was established between the SERS intensity of different Raman characteristic peaks of ractopamine and the content of ractopamine solution. The established model had linear relationship with a correlation coefficient R2 of 0.98 and RMSE of 0.332 mg/L. This method provides a new idea for the determination of ractopamine. This study is helpful to develop a simple, low-cost and easy-to-store SERS method for the detection of ractopamine based on Au@Ag NPS.
{"title":"Rapid determination of Ractopamine by SERS coupled with size-tunable Au-Ag alloy","authors":"Tianzhen Yin, Yankun Peng, K. Chao, J. Qin, Feifei Tao, Yahui Chen, Jiewen Zuo","doi":"10.1117/12.3013243","DOIUrl":"https://doi.org/10.1117/12.3013243","url":null,"abstract":"Excessive consumption of β-adrenergic agonists from livestock, poultry, or viscera can present serious health risks, potentially endangering lives. Surface-enhanced Raman scattering (SERS) provides a precise method for measuring levels of β-adrenergic agonists. This study involved collecting spectra of ractopamine aqueous solutions by synthesizing Au@Ag NPS alloy substrates. A linear relationship between the concentration of ractopamine (ranged from 1 to 10 mg/L) and SERS intensity. Automatic Whittaker Filter (AWF) algorithm was used to preprocess the Raman spectra to remove the fluorescence background. A linear regression model was established between the SERS intensity of different Raman characteristic peaks of ractopamine and the content of ractopamine solution. The established model had linear relationship with a correlation coefficient R2 of 0.98 and RMSE of 0.332 mg/L. This method provides a new idea for the determination of ractopamine. This study is helpful to develop a simple, low-cost and easy-to-store SERS method for the detection of ractopamine based on Au@Ag NPS.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"353 6","pages":"130600C - 130600C-6"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141380654","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}
Yajie Bao, Dan Shen, Genshe Chen, K. Pham, Erik Blasch
The mobility and versatility of Unmanned Aerial Systems (UASs) make them valuable platforms in Distributed Cooperative Beamforming (DCB) applications, where high-precision time synchronization and Positioning, Navigation, and Timing (PNT) are required. UAS with PNT can quickly respond to changing situations and provide temporary coverage in remote or disaster-affected areas. While the onboard PNT equipment allows UASs to obtain reliable PNT solutions, human presence with supervisory roles (aka human-on-the-loop (HotL)) is almost inevitable in such equipment with automation and multi-level resilience of prevention, response, and recovery functions. This paper employs a meta-model to describe interactions among the human operators and multiple UAS platforms for resilience aware HotL PNT in the DCB scenario. The roles of UASs and humans in the decision-making process of resilient PNT are clarified. Interaction points where humans should collaborate with UASs are identified to augment the autonomy of the UASs. Moreover, requirements are specified for the interaction points. Simulations of a HotL multi-UAS positioning system demonstrate that the requirements modeling facilitates the design of human-machine teaming, and the human presence enhances the resilience of the positioning system.
{"title":"Requirements modeling of resilience-aware human-on-the-loop PNT of multiple UASs","authors":"Yajie Bao, Dan Shen, Genshe Chen, K. Pham, Erik Blasch","doi":"10.1117/12.3023840","DOIUrl":"https://doi.org/10.1117/12.3023840","url":null,"abstract":"The mobility and versatility of Unmanned Aerial Systems (UASs) make them valuable platforms in Distributed Cooperative Beamforming (DCB) applications, where high-precision time synchronization and Positioning, Navigation, and Timing (PNT) are required. UAS with PNT can quickly respond to changing situations and provide temporary coverage in remote or disaster-affected areas. While the onboard PNT equipment allows UASs to obtain reliable PNT solutions, human presence with supervisory roles (aka human-on-the-loop (HotL)) is almost inevitable in such equipment with automation and multi-level resilience of prevention, response, and recovery functions. This paper employs a meta-model to describe interactions among the human operators and multiple UAS platforms for resilience aware HotL PNT in the DCB scenario. The roles of UASs and humans in the decision-making process of resilient PNT are clarified. Interaction points where humans should collaborate with UASs are identified to augment the autonomy of the UASs. Moreover, requirements are specified for the interaction points. Simulations of a HotL multi-UAS positioning system demonstrate that the requirements modeling facilitates the design of human-machine teaming, and the human presence enhances the resilience of the positioning system.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"33 5","pages":"130620E - 130620E-14"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141379397","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}
This study delves into the Extended Kalman Filter's (EKF) use in ocean science through a detailed bibliometric and text mining examination. Tracing its roots back to the original Kalman Filter from the 1960s, the EKF has become crucial for managing nonlinear dynamics, especially in oceanography. Our analysis, drawing from Scopus data covering 1980-2023, delivers an extensive overview of the EKF's growth, applications, and cross-disciplinary influence in this area. We employed sophisticated bibliometric methods, including Biblioshiny, and text mining approaches via VOSviewer to dissect trends, and thematic groupings in EKF-related ocean science research. The results demonstrate a steady increase in EKF applications, particularly in autonomous underwater vehicle navigation, forecasting ocean currents, and modeling marine ecosystems. The bibliometric findings show its broad interdisciplinary appeal, while the text analysis underscores the EKF's integration with cutting-edge computational techniques and its significance in burgeoning oceanographic technologies. The paper highlights the EKF's indispensable role in ocean science, reflecting its historical importance and versatility in addressing contemporary challenges in marine technology. The study not only sheds light on the EKF's historical and current uses but also suggests potential future directions for research and innovation. It aims to offer crucial insights to researchers, academicians, and policy makers, underlining the EKF's significance in the dynamic, ever-changing realm of ocean science.
{"title":"Analysis of the extended Kalman filter's role in oceanic science","authors":"Khaled Obaideen, Mohammad A. AlShabi, Talal Bonny","doi":"10.1117/12.3013854","DOIUrl":"https://doi.org/10.1117/12.3013854","url":null,"abstract":"This study delves into the Extended Kalman Filter's (EKF) use in ocean science through a detailed bibliometric and text mining examination. Tracing its roots back to the original Kalman Filter from the 1960s, the EKF has become crucial for managing nonlinear dynamics, especially in oceanography. Our analysis, drawing from Scopus data covering 1980-2023, delivers an extensive overview of the EKF's growth, applications, and cross-disciplinary influence in this area. We employed sophisticated bibliometric methods, including Biblioshiny, and text mining approaches via VOSviewer to dissect trends, and thematic groupings in EKF-related ocean science research. The results demonstrate a steady increase in EKF applications, particularly in autonomous underwater vehicle navigation, forecasting ocean currents, and modeling marine ecosystems. The bibliometric findings show its broad interdisciplinary appeal, while the text analysis underscores the EKF's integration with cutting-edge computational techniques and its significance in burgeoning oceanographic technologies. The paper highlights the EKF's indispensable role in ocean science, reflecting its historical importance and versatility in addressing contemporary challenges in marine technology. The study not only sheds light on the EKF's historical and current uses but also suggests potential future directions for research and innovation. It aims to offer crucial insights to researchers, academicians, and policy makers, underlining the EKF's significance in the dynamic, ever-changing realm of ocean science.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"25 17","pages":"130610K - 130610K-9"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141379834","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}
In the rapidly evolving landscape of artificial intelligence, Large Language Models (LLMs) and Generative AI (GenAI) have emerged as front-runners in shaping the next generation of intelligent applications, where human-like data generation is necessary. While their capabilities have shown transformative potential in centralized computing environments, there is a growing shift towards decentralized edge AI models, where computations are orchestrated closer to data sources to provide immediate insights, faster response times, and localized intelligence without the overhead of cloud communication. For latency-critical applications like autonomous vehicle driving, GenAI at the edge is vital, allowing vehicles to instantly generate and adapt driving strategies based on ever-changing road conditions and traffic patterns. In this paper, we propose a latency-aware service placement approach, designed for the seamless deployment of GenAI services on these cloudlets. We represent GenAI as a Direct Acyclic Graph, where GenAI operations represent the nodes and the dependencies between these operations represent the edges. We propose an Ant Colony Optimization approach that guides the placement of GenAI services at the edge based on capabilities of cloudlets and network conditions. Through experimental validation, we achieve notable GenAI performance at the edge with lower latency and efficient resource utilization. This advancement is expected to revolutionize and innovate in the field of GenAI, paving the way for more efficient and transformative applications at the edge.
{"title":"Latency-aware service placement for GenAI at the edge","authors":"Bipul Thapa, Lena Mashayekhy","doi":"10.1117/12.3013437","DOIUrl":"https://doi.org/10.1117/12.3013437","url":null,"abstract":"In the rapidly evolving landscape of artificial intelligence, Large Language Models (LLMs) and Generative AI (GenAI) have emerged as front-runners in shaping the next generation of intelligent applications, where human-like data generation is necessary. While their capabilities have shown transformative potential in centralized computing environments, there is a growing shift towards decentralized edge AI models, where computations are orchestrated closer to data sources to provide immediate insights, faster response times, and localized intelligence without the overhead of cloud communication. For latency-critical applications like autonomous vehicle driving, GenAI at the edge is vital, allowing vehicles to instantly generate and adapt driving strategies based on ever-changing road conditions and traffic patterns. In this paper, we propose a latency-aware service placement approach, designed for the seamless deployment of GenAI services on these cloudlets. We represent GenAI as a Direct Acyclic Graph, where GenAI operations represent the nodes and the dependencies between these operations represent the edges. We propose an Ant Colony Optimization approach that guides the placement of GenAI services at the edge based on capabilities of cloudlets and network conditions. Through experimental validation, we achieve notable GenAI performance at the edge with lower latency and efficient resource utilization. This advancement is expected to revolutionize and innovate in the field of GenAI, paving the way for more efficient and transformative applications at the edge.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"60 2","pages":"130580G - 130580G-14"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141377234","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：