The advancement of open architecture ecosystems is fundamentally dependent on the interoperability, scalability, and adaptability of their constituent elements. As Machine Learning (ML) systems become increasingly integral to these ecosystems, the need for a systematic approach to engineer, deploy, and re-engineer them grows. This paper presents a novel modeling approach based on recently published, formal, systems-theoretic models of learning systems. These models serve dual purposes: first, they give a theoretical grounding to standards that govern the architecture, functionality, and performance criteria for ML systems; second, they allow for requirements to be specified at various levels of abstraction to ensure the systems are intrinsically aligned with the overall objectives of the open architecture ecosystem they belong to. Through the proposed modeling approach, we demonstrate how the adoption of standardized models can significantly enhance interoperability between disparate machine learning systems and other architectural components. Further, we relate our framework to on-going efforts such as Open Neural Network Exchange (ONNX). We identify how our approach can be used to address limitations in government acquisition processes for ML systems. The proposed systems-theoretic framework provides a structured methodology that contributes to the foundational building blocks for open architecture ecosystems for ML systems, thereby advancing the state-of-the-art in complex system integration.
开放式架构生态系统的发展从根本上取决于其组成元素的互操作性、可扩展性和适应性。随着机器学习（ML）系统日益成为这些生态系统的组成部分，人们越来越需要一种系统化的方法来设计、部署和重新设计这些系统。本文介绍了一种新颖的建模方法，该方法基于最近出版的学习系统的正式系统理论模型。这些模型具有双重目的：首先，它们为管理 ML 系统的架构、功能和性能标准的标准提供了理论基础；其次，它们允许在不同的抽象层次上指定需求，以确保系统在本质上与它们所属的开放架构生态系统的总体目标保持一致。通过建议的建模方法，我们展示了采用标准化模型如何显著增强不同机器学习系统和其他架构组件之间的互操作性。此外，我们还将我们的框架与开放神经网络交换（ONNX）等正在进行的工作联系起来。我们确定了如何利用我们的方法来解决政府在获取机器学习系统过程中的局限性。所提出的系统理论框架提供了一种结构化方法，有助于为 ML 系统的开放式架构生态系统提供基础构件，从而推动复杂系统集成领域的最新发展。
{"title":"A systems theoretic perspective on open architectures for learning systems","authors":"Tyler Cody, Peter A. Beling","doi":"10.1117/12.3012391","DOIUrl":"https://doi.org/10.1117/12.3012391","url":null,"abstract":"The advancement of open architecture ecosystems is fundamentally dependent on the interoperability, scalability, and adaptability of their constituent elements. As Machine Learning (ML) systems become increasingly integral to these ecosystems, the need for a systematic approach to engineer, deploy, and re-engineer them grows. This paper presents a novel modeling approach based on recently published, formal, systems-theoretic models of learning systems. These models serve dual purposes: first, they give a theoretical grounding to standards that govern the architecture, functionality, and performance criteria for ML systems; second, they allow for requirements to be specified at various levels of abstraction to ensure the systems are intrinsically aligned with the overall objectives of the open architecture ecosystem they belong to. Through the proposed modeling approach, we demonstrate how the adoption of standardized models can significantly enhance interoperability between disparate machine learning systems and other architectural components. Further, we relate our framework to on-going efforts such as Open Neural Network Exchange (ONNX). We identify how our approach can be used to address limitations in government acquisition processes for ML systems. The proposed systems-theoretic framework provides a structured methodology that contributes to the foundational building blocks for open architecture ecosystems for ML systems, thereby advancing the state-of-the-art in complex system integration.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"62 s284","pages":"1305808 - 1305808-6"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141377378","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}
M. Malinowski, Eder Herrera-Estrella, Robert Foster, Jacopo Agagliate, Alex Gilerson
Uncertainties in radiance above the ocean surface are mostly determined by the skylight reflected from the air-water interface. Their accurate characterization is important for the accurate measurements of the water-leaving radiance as well as for the estimation of the impact of these uncertainties on the atmospheric correction of satellite and airborne ocean observations. Uncertainties are affected by the state of the ocean surface dependent on the wind speed and the corresponding reflection coefficient, which can be calculated based on Cox-Munk relationships. These uncertainties were estimated in the hyperspectral mode from shipborne measurements by the Hyperspectral Imager ULTRIS X20 (Cubert, Germany), with a 400-1000 nm wavelength range and a 410x410 pixel resolution. Measurements were taken during a VIIRS Cal/Val cruise in Hawaii area in a broad range of wind speeds 0-10 m/s and at viewing angles 20-60 degrees. In addition, airborne measurements from a helicopter at four different altitudes of 60, 150, 450, and 750 meters were carried out in different parts of Chesapeake Bay to establish a relationship between uncertainties and altitude. For these, a Teledyne DALSA M2450 polarized camera with a filter wheel containing several filters at different spectral bands was used together with the imager to characterize wave slope statistics and to determine uncertainties in measurements of the Stokes vector components and the degree of linear polarization (DoLP). Measurement uncertainties are further compared with simulations.
{"title":"Estimation of uncertainties in above-water radiometric measurements from hyperspectral and polarimetric imaging","authors":"M. Malinowski, Eder Herrera-Estrella, Robert Foster, Jacopo Agagliate, Alex Gilerson","doi":"10.1117/12.3014923","DOIUrl":"https://doi.org/10.1117/12.3014923","url":null,"abstract":"Uncertainties in radiance above the ocean surface are mostly determined by the skylight reflected from the air-water interface. Their accurate characterization is important for the accurate measurements of the water-leaving radiance as well as for the estimation of the impact of these uncertainties on the atmospheric correction of satellite and airborne ocean observations. Uncertainties are affected by the state of the ocean surface dependent on the wind speed and the corresponding reflection coefficient, which can be calculated based on Cox-Munk relationships. These uncertainties were estimated in the hyperspectral mode from shipborne measurements by the Hyperspectral Imager ULTRIS X20 (Cubert, Germany), with a 400-1000 nm wavelength range and a 410x410 pixel resolution. Measurements were taken during a VIIRS Cal/Val cruise in Hawaii area in a broad range of wind speeds 0-10 m/s and at viewing angles 20-60 degrees. In addition, airborne measurements from a helicopter at four different altitudes of 60, 150, 450, and 750 meters were carried out in different parts of Chesapeake Bay to establish a relationship between uncertainties and altitude. For these, a Teledyne DALSA M2450 polarized camera with a filter wheel containing several filters at different spectral bands was used together with the imager to characterize wave slope statistics and to determine uncertainties in measurements of the Stokes vector components and the degree of linear polarization (DoLP). Measurement uncertainties are further compared with simulations.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"37 1","pages":"1306103 - 1306103-13"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141381947","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}
Amid the SARS-CoV-2 pandemic, traditional virus detection methods like RT-qPCR face limitations in terms of infrastructure and processing time. This has spurred the development of agile diagnostic technologies, emphasizing non-invasive and rapid testing. Surface-Enhanced Raman Scattering (SERS) and Localized Surface Plasmon Resonance (LSPR) have emerged as promising alternatives. SERS, amplifying Raman signals through metal nanostructures, offers high sensitivity, high specificity, rapid response, qualitative and quantitative analysis enhanced by recent innovations like multiwell-array substrates. Integration with machine learning refines SERS's diagnostic capabilities, enabling rapid and accurate identification of SARS-CoV-2. LSPR, leveraging light-metal nanoparticle interactions, revolutionizes rapid viral detection, especially with the development of portable handheld devices. These devices enable real-time, on-site testing, proving crucial in managing infectious disease outbreaks. Their applications extend beyond SARS-CoV-2, holding potential for various pathogens.
{"title":"Advancements in pathogen detection: the integration of SERS and LSPR technologies in handheld clinical diagnostics","authors":"Sebastian Huelck","doi":"10.1117/12.3022222","DOIUrl":"https://doi.org/10.1117/12.3022222","url":null,"abstract":"Amid the SARS-CoV-2 pandemic, traditional virus detection methods like RT-qPCR face limitations in terms of infrastructure and processing time. This has spurred the development of agile diagnostic technologies, emphasizing non-invasive and rapid testing. Surface-Enhanced Raman Scattering (SERS) and Localized Surface Plasmon Resonance (LSPR) have emerged as promising alternatives. SERS, amplifying Raman signals through metal nanostructures, offers high sensitivity, high specificity, rapid response, qualitative and quantitative analysis enhanced by recent innovations like multiwell-array substrates. Integration with machine learning refines SERS's diagnostic capabilities, enabling rapid and accurate identification of SARS-CoV-2. LSPR, leveraging light-metal nanoparticle interactions, revolutionizes rapid viral detection, especially with the development of portable handheld devices. These devices enable real-time, on-site testing, proving crucial in managing infectious disease outbreaks. Their applications extend beyond SARS-CoV-2, holding potential for various pathogens.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"22 13","pages":"130590E - 130590E-6"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141378972","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}
We report favorable preliminary findings of work in progress bridging the Artificial Intelligence (AI) gap between bottom-up data-driven Machine Learning (ML) and top-down conceptually driven symbolic reasoning. Our overall goal is automatic generation, maintenance and utilization of explainable, parsimonious, plausibly causal, probably approximately correct, hybrid symbolic/numeric models of the world, the self and other agents, for prediction, what-if (counter-factual) analysis and control. Our old Evolutionary Learning with Information Theoretic Evaluation of Ensembles (ELITE2) techniques quantify strengths of arbitrary multivariate nonlinear statistical dependencies, prior to discovering forms by which observed variables may drive others. We extend these to apply Granger causality, in terms of conditional Mutual Information (MI), to distinguish causal relationships and find their directions. As MI can reflect one observable driving a second directly or via a mediator, two being driven by a common cause, etc., to untangle the causal graph we will apply Pearl causality with its back- and front-door adjustments and criteria. Initial efforts verified that our information theoretic indices detect causality in noise corrupted data despite complex relationships among hidden variables with chaotic dynamics disturbed by process noise, The next step is to apply these information theoretic filters in Genetic Programming (GP) to reduce the population of discovered statistical dependencies to plausibly causal relationships, represented symbolically for use by a reasoning engine in a cognitive architecture. Success could bring broader generalization, using not just learned patterns but learned general principles, enabling AI/ML based systems to autonomously navigate complex unknown environments and handle “black swans”.
我们报告了在自下而上的数据驱动型机器学习（ML）和自上而下的概念驱动型符号推理之间搭建桥梁的人工智能（AI）工作的初步成果。我们的总体目标是自动生成、维护和利用可解释的、解析的、似因似果的、可能近似正确的世界、自我和其他代理的混合符号/数字模型，用于预测、假设（反事实）分析和控制。在发现观察到的变量可能驱动其他变量的形式之前，我们原有的集合信息论评估进化学习（ELITE2）技术可以量化任意多变量非线性统计依赖关系的强度。我们将其扩展到格兰杰因果关系中，以条件互信息（MI）来区分因果关系并找到其方向。由于 MI 可以反映一个观测变量直接或通过中介驱动另一个观测变量，也可以反映两个观测变量被一个共同原因驱动等，因此，为了理清因果关系图，我们将应用珀尔因果关系及其前后门调整和标准。下一步是在遗传编程（GP）中应用这些信息理论过滤器，将已发现的统计依赖关系减少为可信的因果关系，并用符号表示出来，供认知架构中的推理引擎使用。成功可以带来更广泛的通用性，不仅可以使用学习到的模式，还可以使用学习到的一般原则，从而使基于人工智能/人工智能的系统能够自主导航复杂的未知环境，并处理 "黑天鹅"。
{"title":"Bridging the AI/ML gap with explainable symbolic causal models using information theory","authors":"Stuart W. Card","doi":"10.1117/12.3014447","DOIUrl":"https://doi.org/10.1117/12.3014447","url":null,"abstract":"We report favorable preliminary findings of work in progress bridging the Artificial Intelligence (AI) gap between bottom-up data-driven Machine Learning (ML) and top-down conceptually driven symbolic reasoning. Our overall goal is automatic generation, maintenance and utilization of explainable, parsimonious, plausibly causal, probably approximately correct, hybrid symbolic/numeric models of the world, the self and other agents, for prediction, what-if (counter-factual) analysis and control. Our old Evolutionary Learning with Information Theoretic Evaluation of Ensembles (ELITE2) techniques quantify strengths of arbitrary multivariate nonlinear statistical dependencies, prior to discovering forms by which observed variables may drive others. We extend these to apply Granger causality, in terms of conditional Mutual Information (MI), to distinguish causal relationships and find their directions. As MI can reflect one observable driving a second directly or via a mediator, two being driven by a common cause, etc., to untangle the causal graph we will apply Pearl causality with its back- and front-door adjustments and criteria. Initial efforts verified that our information theoretic indices detect causality in noise corrupted data despite complex relationships among hidden variables with chaotic dynamics disturbed by process noise, The next step is to apply these information theoretic filters in Genetic Programming (GP) to reduce the population of discovered statistical dependencies to plausibly causal relationships, represented symbolically for use by a reasoning engine in a cognitive architecture. Success could bring broader generalization, using not just learned patterns but learned general principles, enabling AI/ML based systems to autonomously navigate complex unknown environments and handle “black swans”.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"23 25","pages":"1305802 - 1305802-4"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141379071","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}
Cheng-Yu Cheng, Qi Zhao, Cheng-Ying Wu, Yuchen Yang, Muhammad Qureshi, Hang Liu, Genshe Chen
Cooperative Augmented Reality (AR) can provide real-time, immersive, and context-aware situational awareness while enhancing mobile sensing capabilities and benefiting various applications. Distributed edge computing has emerged as an essential paradigm to facilitate cooperative AR. We designed and implemented a distributed system to enable fast, reliable, and scalable cooperative AR. In this paper, we present a novel approach and architecture that integrates advanced sensing, communications, and processing techniques to create such a cooperative AR system and demonstrate its capability with HoloLens and edge servers connected over a wireless network. Our research addresses the challenges of implementing a distributed cooperative AR system capable of capturing data from a multitude of sensors on HoloLens, performing fusion and accurate object recognition, and seamlessly projecting the reconstructed 3D model into the wearer’s field of view. The paper delves into the intricate architecture of the proposed cooperative AR system, detailing its distributed sensing and edge computing components, and the Apache Storm-integrated platform. The implementation encompasses data collection, aggregation, analysis, object recognition, and rendering of 3D models on the HoloLens, all in real-time. The proposed system enhances the AR experience while showcasing the vast potential of distributed edge computing. Our findings illustrate the feasibility and advantages of merging distributed cooperative sensing and edge computing to offer dynamic, immersive AR experiences, paving the way for new applications.
合作式增强现实（AR）可提供实时、身临其境和情境感知的态势感知，同时增强移动传感能力并使各种应用受益。分布式边缘计算已成为促进合作式增强现实的重要模式。我们设计并实施了一个分布式系统，以实现快速、可靠和可扩展的协同 AR。在本文中，我们介绍了一种新颖的方法和架构，该方法和架构集成了先进的传感、通信和处理技术，从而创建了这样一个合作式 AR 系统，并利用通过无线网络连接的 HoloLens 和边缘服务器演示了该系统的能力。我们的研究解决了实施分布式合作 AR 系统的挑战，该系统能够从 HoloLens 上的多个传感器捕获数据，执行融合和准确的物体识别，并将重建的 3D 模型无缝投射到佩戴者的视野中。本文深入探讨了拟议的合作式 AR 系统的复杂架构，详细介绍了其分布式传感和边缘计算组件以及集成 Apache Storm 的平台。实施过程包括数据收集、汇总、分析、对象识别以及在 HoloLens 上实时渲染 3D 模型。拟议的系统增强了 AR 体验，同时展示了分布式边缘计算的巨大潜力。我们的研究结果表明，将分布式协同传感与边缘计算结合起来，提供动态、身临其境的 AR 体验是可行的，并具有优势，从而为新的应用铺平了道路。
{"title":"Distributed edge computing for cooperative augmented reality: enhancing mobile sensing capabilities","authors":"Cheng-Yu Cheng, Qi Zhao, Cheng-Ying Wu, Yuchen Yang, Muhammad Qureshi, Hang Liu, Genshe Chen","doi":"10.1117/12.3021841","DOIUrl":"https://doi.org/10.1117/12.3021841","url":null,"abstract":"Cooperative Augmented Reality (AR) can provide real-time, immersive, and context-aware situational awareness while enhancing mobile sensing capabilities and benefiting various applications. Distributed edge computing has emerged as an essential paradigm to facilitate cooperative AR. We designed and implemented a distributed system to enable fast, reliable, and scalable cooperative AR. In this paper, we present a novel approach and architecture that integrates advanced sensing, communications, and processing techniques to create such a cooperative AR system and demonstrate its capability with HoloLens and edge servers connected over a wireless network. Our research addresses the challenges of implementing a distributed cooperative AR system capable of capturing data from a multitude of sensors on HoloLens, performing fusion and accurate object recognition, and seamlessly projecting the reconstructed 3D model into the wearer’s field of view. The paper delves into the intricate architecture of the proposed cooperative AR system, detailing its distributed sensing and edge computing components, and the Apache Storm-integrated platform. The implementation encompasses data collection, aggregation, analysis, object recognition, and rendering of 3D models on the HoloLens, all in real-time. The proposed system enhances the AR experience while showcasing the vast potential of distributed edge computing. Our findings illustrate the feasibility and advantages of merging distributed cooperative sensing and edge computing to offer dynamic, immersive AR experiences, paving the way for new applications.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"55 1","pages":"130620O - 130620O-11"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141381309","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}
Billy E. Geerhart, Venkateswara Dasari, Brian Rapp, Peng Wang, Ju Wang, Christopher X. Payne
The Label-Diffusion-LIDAR-Segmentation (LDLS) algorithm uses multi-modal data for enhanced inference of environmental categories. The algorithm segments the Red-Green-Blue (RGB) channels and maps the results to the LIDAR point cloud using matrix calculations to reduce noise. Recent research has developed custom optimization techniques using quantization to accelerate the 3D object detection using LDLS in robotic systems. These optimizations achieve a 3x speedup over the original algorithm, making it possible to deploy the algorithm in real-world applications. The optimizations include quantization for the segmentation inference as well as matrix optimizations for the label diffusion. We will present our results, compare them with the baseline, and discuss their significance in achieving real-time object detection in resource-constrained environments.
标签扩散-激光雷达分割（LDLS）算法利用多模态数据加强对环境类别的推断。该算法对红绿蓝（RGB）通道进行分割，并利用矩阵计算将结果映射到激光雷达点云，以减少噪声。最近的研究开发了使用量化的定制优化技术，以加速机器人系统中使用 LDLS 的 3D 物体检测。这些优化技术将原始算法的速度提高了 3 倍，使该算法在实际应用中的部署成为可能。优化包括分割推理的量化以及标签扩散的矩阵优化。我们将介绍我们的成果，将其与基线进行比较，并讨论它们在资源受限环境中实现实时物体检测的意义。
{"title":"Quantization to accelerate inference in multimodal 3D object detection","authors":"Billy E. Geerhart, Venkateswara Dasari, Brian Rapp, Peng Wang, Ju Wang, Christopher X. Payne","doi":"10.1117/12.3013702","DOIUrl":"https://doi.org/10.1117/12.3013702","url":null,"abstract":"The Label-Diffusion-LIDAR-Segmentation (LDLS) algorithm uses multi-modal data for enhanced inference of environmental categories. The algorithm segments the Red-Green-Blue (RGB) channels and maps the results to the LIDAR point cloud using matrix calculations to reduce noise. Recent research has developed custom optimization techniques using quantization to accelerate the 3D object detection using LDLS in robotic systems. These optimizations achieve a 3x speedup over the original algorithm, making it possible to deploy the algorithm in real-world applications. The optimizations include quantization for the segmentation inference as well as matrix optimizations for the label diffusion. We will present our results, compare them with the baseline, and discuss their significance in achieving real-time object detection in resource-constrained environments.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"25 32","pages":"1305807 - 1305807-10"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141378876","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}
The rapid advancement of multimedia content editing software tools has made it increasingly easy for malicious actors to manipulate real-time multimedia data streams, encompassing audio and video. Among the notorious cybercrimes, replay attacks have gained widespread prevalence, necessitating the development of more efficient authentication methods for detection. A cutting-edge authentication technique leverages Electrical Network Frequency (ENF) signals embedded within multimedia content. ENF signals offer a range of advantageous attributes, including uniqueness, unpredictability, and total randomness, rendering them highly effective for detecting replay attacks. To counter potential attackers who may seek to deceive detection systems by embedding fake ENF signals, this study harnesses the growing accessibility of deep Convolutional Neural Networks (CNNs). These CNNs are not only deployable on platforms with limited computational resources, such as Single-Board Computers (SBCs), but they also exhibit the capacity to swiftly identify interference within a signal by learning distinctive spatio-temporal patterns. In this paper, we explore applying a Computationally Efficient Deep Learning Model (CEDM) as a powerful tool for rapidly detecting potential fabrications within ENF signals originating from diverse audio sources. Our experimental study validates the effectiveness of the proposed method.
{"title":"A lightweight deep learning model for rapid detection of fabricated ENF signals from audio sources","authors":"Adilet Pazylkarim, Deeraj Nagothu, Yu Chen","doi":"10.1117/12.3013456","DOIUrl":"https://doi.org/10.1117/12.3013456","url":null,"abstract":"The rapid advancement of multimedia content editing software tools has made it increasingly easy for malicious actors to manipulate real-time multimedia data streams, encompassing audio and video. Among the notorious cybercrimes, replay attacks have gained widespread prevalence, necessitating the development of more efficient authentication methods for detection. A cutting-edge authentication technique leverages Electrical Network Frequency (ENF) signals embedded within multimedia content. ENF signals offer a range of advantageous attributes, including uniqueness, unpredictability, and total randomness, rendering them highly effective for detecting replay attacks. To counter potential attackers who may seek to deceive detection systems by embedding fake ENF signals, this study harnesses the growing accessibility of deep Convolutional Neural Networks (CNNs). These CNNs are not only deployable on platforms with limited computational resources, such as Single-Board Computers (SBCs), but they also exhibit the capacity to swiftly identify interference within a signal by learning distinctive spatio-temporal patterns. In this paper, we explore applying a Computationally Efficient Deep Learning Model (CEDM) as a powerful tool for rapidly detecting potential fabrications within ENF signals originating from diverse audio sources. Our experimental study validates the effectiveness of the proposed method.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"18 23","pages":"1305811 - 1305811-13"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141378890","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}
Darrell L. Young, Perry Boyette, James Moreland, Jason Teske
Large Language Models (LLMs) provide new capabilities to rapidly reform, regroup; and reskill for new missions, opportunities, and respond to an ever-changing operational landscape. Agile contracts can enable larger flow of value in new development contexts. These methods of engagement and partnership enable the establishment of high performing teams through the forming, storming, norming, and performing stages that then inform the best liberating structures that exceed traditional rigid hierarchical models or even established mission engineering methods. Use of Generative AI based on LLMs coupled with modern agile model-based engineering in design allows for automated requirements decomposition trained in the lingua franca of the development team and translation to the dialects of other domain disciplines with the business acumen afforded by proven approaches in industry. Cutting-edge AI automations to track and adapt knowledge, skills, and abilities across ever changing jobs and roles will be illustrated using prevailing architecture frameworks, model-based system engineering, simulation, and decision-making assisted approaches to emergent objectives.
{"title":"Generative AI agile assistant","authors":"Darrell L. Young, Perry Boyette, James Moreland, Jason Teske","doi":"10.1117/12.3011173","DOIUrl":"https://doi.org/10.1117/12.3011173","url":null,"abstract":"Large Language Models (LLMs) provide new capabilities to rapidly reform, regroup; and reskill for new missions, opportunities, and respond to an ever-changing operational landscape. Agile contracts can enable larger flow of value in new development contexts. These methods of engagement and partnership enable the establishment of high performing teams through the forming, storming, norming, and performing stages that then inform the best liberating structures that exceed traditional rigid hierarchical models or even established mission engineering methods. Use of Generative AI based on LLMs coupled with modern agile model-based engineering in design allows for automated requirements decomposition trained in the lingua franca of the development team and translation to the dialects of other domain disciplines with the business acumen afforded by proven approaches in industry. Cutting-edge AI automations to track and adapt knowledge, skills, and abilities across ever changing jobs and roles will be illustrated using prevailing architecture frameworks, model-based system engineering, simulation, and decision-making assisted approaches to emergent objectives.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"11 1","pages":"1305809 - 1305809-12"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141378795","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}
Chiranjibi Shah, M. M. Nabi, S. Y. Alaba, Ryan Caillouet, Jack H. Prior, Matthew Campbell, Matthew D. Grossi, Farron Wallace, John E. Ball, Robert J. Moorhead
Fish species must be identified for stock assessments, ecosystem monitoring, production management, and the conservation of endangered species. Implementing algorithms for fish species detection in underwater settings like the Gulf of Mexico poses a formidable challenge. Active learning, a method that efficiently identifies informative samples for annotation while staying within a budget, has demonstrated its effectiveness in the context of object detection in recent times. In this study, we present an active detection model designed for fish species recognition in underwater environments. This model can be employed as an object detection system to effectively lower the expense associated with manual annotation. It uses epistemic uncertainty with Evidential Deep Learning (EDL) and proposes a novel module denoted as Model Evidence Head (MEH) for fish species detection in underwater environments. It employs Hierarchical Uncertainty Aggregation (HUA) to obtain the informativeness of an image. We conducted experiments using a fine-grained and extensive dataset of reef fish collected from the Gulf of Mexico, specifically the Southeast Area Monitoring and Assessment Program Dataset 2021 (SEAMAPD21). The experimental results demonstrate that an active detection framework achieves better detection performance on the SEAMAPD21 dataset demonstrating a favorable balance between performance and data efficiency for underwater fish species recognition.
{"title":"Active detection for fish species recognition in underwater environments","authors":"Chiranjibi Shah, M. M. Nabi, S. Y. Alaba, Ryan Caillouet, Jack H. Prior, Matthew Campbell, Matthew D. Grossi, Farron Wallace, John E. Ball, Robert J. Moorhead","doi":"10.1117/12.3013344","DOIUrl":"https://doi.org/10.1117/12.3013344","url":null,"abstract":"Fish species must be identified for stock assessments, ecosystem monitoring, production management, and the conservation of endangered species. Implementing algorithms for fish species detection in underwater settings like the Gulf of Mexico poses a formidable challenge. Active learning, a method that efficiently identifies informative samples for annotation while staying within a budget, has demonstrated its effectiveness in the context of object detection in recent times. In this study, we present an active detection model designed for fish species recognition in underwater environments. This model can be employed as an object detection system to effectively lower the expense associated with manual annotation. It uses epistemic uncertainty with Evidential Deep Learning (EDL) and proposes a novel module denoted as Model Evidence Head (MEH) for fish species detection in underwater environments. It employs Hierarchical Uncertainty Aggregation (HUA) to obtain the informativeness of an image. We conducted experiments using a fine-grained and extensive dataset of reef fish collected from the Gulf of Mexico, specifically the Southeast Area Monitoring and Assessment Program Dataset 2021 (SEAMAPD21). The experimental results demonstrate that an active detection framework achieves better detection performance on the SEAMAPD21 dataset demonstrating a favorable balance between performance and data efficiency for underwater fish species recognition.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"5 15","pages":"130610D - 130610D-10"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141379707","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}
Gabriel Peters, Scott Couwenhoven, Derek Walvoord, Carl Salvaggio
In an era of immense data generation, unlocking the full potential of Machine Learning (ML) hinges on overcoming the limitations posed by the scarcity of labeled data. In Computer Vision (CV) research, algorithm design must consider this shift and focus instead on the abundance of unlabeled imagery. In recent years, there has been a notable trend within the community toward Self-Supervised Learning (SSL) methods that can leverage this untapped data pool. ML practice promotes self-supervised pre-training for generalized feature extraction on a diverse unlabeled dataset followed by supervised transfer learning on a smaller set of labeled, application-specific images. This shift in learning methods elicits conversation about the importance of pre-training data composition for optimizing downstream performance. We evaluate models with varying measures of similarity between pre-training and transfer learning data compositions. Our findings indicate that front-end embeddings sufficiently generalize learned image features independent of data composition, leaving transfer learning to inject the majority of application-specific understanding into the model. Composition may be irrelevant in self-supervised pre-training, suggesting target data is a primary driver of application specificity. Thus, pre-training deep learning models with application-specific data, which is often difficult to acquire, is not necessary for reaching competitive downstream performance. The capability to pre-train on more accessible datasets invites more flexibility in practical deep learning.
{"title":"Application specificity of data for pre-training in computer vision","authors":"Gabriel Peters, Scott Couwenhoven, Derek Walvoord, Carl Salvaggio","doi":"10.1117/12.3013088","DOIUrl":"https://doi.org/10.1117/12.3013088","url":null,"abstract":"In an era of immense data generation, unlocking the full potential of Machine Learning (ML) hinges on overcoming the limitations posed by the scarcity of labeled data. In Computer Vision (CV) research, algorithm design must consider this shift and focus instead on the abundance of unlabeled imagery. In recent years, there has been a notable trend within the community toward Self-Supervised Learning (SSL) methods that can leverage this untapped data pool. ML practice promotes self-supervised pre-training for generalized feature extraction on a diverse unlabeled dataset followed by supervised transfer learning on a smaller set of labeled, application-specific images. This shift in learning methods elicits conversation about the importance of pre-training data composition for optimizing downstream performance. We evaluate models with varying measures of similarity between pre-training and transfer learning data compositions. Our findings indicate that front-end embeddings sufficiently generalize learned image features independent of data composition, leaving transfer learning to inject the majority of application-specific understanding into the model. Composition may be irrelevant in self-supervised pre-training, suggesting target data is a primary driver of application specificity. Thus, pre-training deep learning models with application-specific data, which is often difficult to acquire, is not necessary for reaching competitive downstream performance. The capability to pre-train on more accessible datasets invites more flexibility in practical deep learning.","PeriodicalId":178341,"journal":{"name":"Defense + Commercial Sensing","volume":"3 13","pages":"1305803 - 1305803-14"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141380302","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：