{"title":"Guest Editorial Network Intelligence for Uncrewed Aerial Vehicles","authors":"Zan Li;Katsuya Suto;Ling Lyu;Conghao Zhou;Nan Cheng;Wei Zhang","doi":"10.1109/JMASS.2025.3567191","DOIUrl":"https://doi.org/10.1109/JMASS.2025.3567191","url":null,"abstract":"","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"6 2","pages":"54-58"},"PeriodicalIF":0.0,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11018828","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144196705","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-04-30DOI: 10.1109/JMASS.2025.3565996
Ananya Hazarika;Mehdi Rahmati
In the rapidly evolving field of uncrewed aerial vehicles (UAVs), these miniaturized platforms are increasingly being designed for intelligent aerial data acquisition, enabling dynamic target detection and tracking to facilitate the deployment of new use cases. This article presents a novel integrated sensing and communications framework for UAV networks to enhance latency, reliability, and resource allocation efficiency. A novel multidimensional freshness metric, the age of valid sensing (AVS), is introduced as a measure of actionable intelligence to quantify and prioritize the sensing data, accurately capturing the quality and relevance of information in dynamic environments, leading to improved UAV coordination and efficient resource allocation. The effectiveness of AVS is strengthened by the presence of Frechet distance, which performs the behavioral analysis of moving targets to enable spatiotemporal clustering based on their trajectory similarity for efficient sensing. Intelligence is being added to each UAV through a robust multiagent reinforcement learning (MARL) framework to regularly update their target sensing and communications information, dynamically balancing data freshness and the likelihood of successful information gathering. This approach allows for the efficient integration and processing of sensing data from multiple geographically dispersed targets, significantly improving real-time tracking and decision-making capabilities in complex environments. Our simulation results demonstrate the superior performance of the proposed framework in achieving lower latency, higher detection accuracy, and improved resource efficiency compared to existing methods.
{"title":"Intelligent Spatiotemporal Freshness Framework for Multi-UAV Target Detection and Tracking","authors":"Ananya Hazarika;Mehdi Rahmati","doi":"10.1109/JMASS.2025.3565996","DOIUrl":"https://doi.org/10.1109/JMASS.2025.3565996","url":null,"abstract":"In the rapidly evolving field of uncrewed aerial vehicles (UAVs), these miniaturized platforms are increasingly being designed for intelligent aerial data acquisition, enabling dynamic target detection and tracking to facilitate the deployment of new use cases. This article presents a novel integrated sensing and communications framework for UAV networks to enhance latency, reliability, and resource allocation efficiency. A novel multidimensional freshness metric, the age of valid sensing (AVS), is introduced as a measure of actionable intelligence to quantify and prioritize the sensing data, accurately capturing the quality and relevance of information in dynamic environments, leading to improved UAV coordination and efficient resource allocation. The effectiveness of AVS is strengthened by the presence of Frechet distance, which performs the behavioral analysis of moving targets to enable spatiotemporal clustering based on their trajectory similarity for efficient sensing. Intelligence is being added to each UAV through a robust multiagent reinforcement learning (MARL) framework to regularly update their target sensing and communications information, dynamically balancing data freshness and the likelihood of successful information gathering. This approach allows for the efficient integration and processing of sensing data from multiple geographically dispersed targets, significantly improving real-time tracking and decision-making capabilities in complex environments. Our simulation results demonstrate the superior performance of the proposed framework in achieving lower latency, higher detection accuracy, and improved resource efficiency compared to existing methods.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"6 3","pages":"294-304"},"PeriodicalIF":2.1,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891273","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}
Synthetic aperture radar interferometry (InSAR) is an essential tool for observing the Earth’s surface, widely employed in geohazard and ground subsidence monitoring. Enhancing interferogram quality through phase filtering is particularly significant. Traditional filtering methods are often ineffective, while emerging deep learning approaches still face challenges in noise removal and stripe edge preservation. This article proposes a novel InSAR phase filtering method, the dilated phase network (DP-Net), based on a U-shaped multidimensional and multiscale fusion neural network. The proposed method employs a U-shaped network architecture to achieve effective fusion and fine processing of interferogram features across multiple dimensions. By incorporating a Dilated module with embedded cavity convolution, the network enhances its capability to capture features at various scales. Furthermore, the method integrates features at different levels during the encoding-decoding process, enabling effective noise reduction while preserving interferogram details and improving filtering quality. Additionally, a simulated dataset is generated and trained using digital elevation model (DEM) inversion with hierarchical noise addition. The efficacy of the method is validated through filtering experiments on both simulated and real data.
{"title":"DP-Net: A U-Shaped Multidimensional Multiscale Fusion Neural Network for InSAR Phase Filtering","authors":"Jinfeng Lin;Xiaomao Chen;Xiaofeng Qin;Shanshan Zhang","doi":"10.1109/JMASS.2025.3561785","DOIUrl":"https://doi.org/10.1109/JMASS.2025.3561785","url":null,"abstract":"Synthetic aperture radar interferometry (InSAR) is an essential tool for observing the Earth’s surface, widely employed in geohazard and ground subsidence monitoring. Enhancing interferogram quality through phase filtering is particularly significant. Traditional filtering methods are often ineffective, while emerging deep learning approaches still face challenges in noise removal and stripe edge preservation. This article proposes a novel InSAR phase filtering method, the dilated phase network (DP-Net), based on a U-shaped multidimensional and multiscale fusion neural network. The proposed method employs a U-shaped network architecture to achieve effective fusion and fine processing of interferogram features across multiple dimensions. By incorporating a Dilated module with embedded cavity convolution, the network enhances its capability to capture features at various scales. Furthermore, the method integrates features at different levels during the encoding-decoding process, enabling effective noise reduction while preserving interferogram details and improving filtering quality. Additionally, a simulated dataset is generated and trained using digital elevation model (DEM) inversion with hierarchical noise addition. The efficacy of the method is validated through filtering experiments on both simulated and real data.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"6 3","pages":"286-293"},"PeriodicalIF":2.1,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891024","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}
Pub Date : 2025-03-30DOI: 10.1109/JMASS.2025.3571345
{"title":"The Journal of Miniaturized Air and Space Systems","authors":"","doi":"10.1109/JMASS.2025.3571345","DOIUrl":"https://doi.org/10.1109/JMASS.2025.3571345","url":null,"abstract":"","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"6 2","pages":"C2-C2"},"PeriodicalIF":0.0,"publicationDate":"2025-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11018829","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144179129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Coprime pairs of integer matrices have applications in various fields, including multirate systems and multidimensional signal processing. This article addresses problems related to coprime matrices when given two integer matrices of the same size. These problems include determining whether the matrices are coprime, computing their greatest common divisor (gcd), and finding two unknown integer matrices that satisfy Bezout’s equation. First, we present a division theorem for two matrices, which guarantees that the remainder matrix is either the zero matrix or a nonsingular matrix with a smaller absolute determinant than that of the divisor. The gcd of two integer matrices can be computed by repeatedly applying the division theorem until the remainder matrix becomes zero. We then propose an algorithm for finding the gcd and another for determining Bezout’s coefficient matrices from a given pair of integer matrices. Finally, we provide the general solution to Bezout’s equation for nonsingular and commuting integer matrices. This article offers a theoretical derivation of a method for solving Bezout’s equation for integer matrices, generalizing the Euclidean algorithm for integers to integer matrices. Simulations demonstrate that these approaches significantly improve computational efficiency.
{"title":"Euclidean-Based Approaches for Solving Coprime Integer Matrices","authors":"Xiaoping Li;Xuefang Li;Qunying Liao;Jiancun Fan;Tongxing Zheng","doi":"10.1109/JMASS.2025.3574470","DOIUrl":"https://doi.org/10.1109/JMASS.2025.3574470","url":null,"abstract":"Coprime pairs of integer matrices have applications in various fields, including multirate systems and multidimensional signal processing. This article addresses problems related to coprime matrices when given two integer matrices of the same size. These problems include determining whether the matrices are coprime, computing their greatest common divisor (gcd), and finding two unknown integer matrices that satisfy Bezout’s equation. First, we present a division theorem for two matrices, which guarantees that the remainder matrix is either the zero matrix or a nonsingular matrix with a smaller absolute determinant than that of the divisor. The gcd of two integer matrices can be computed by repeatedly applying the division theorem until the remainder matrix becomes zero. We then propose an algorithm for finding the gcd and another for determining Bezout’s coefficient matrices from a given pair of integer matrices. Finally, we provide the general solution to Bezout’s equation for nonsingular and commuting integer matrices. This article offers a theoretical derivation of a method for solving Bezout’s equation for integer matrices, generalizing the Euclidean algorithm for integers to integer matrices. Simulations demonstrate that these approaches significantly improve computational efficiency.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"6 4","pages":"348-355"},"PeriodicalIF":2.1,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145555455","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}
Pub Date : 2025-03-25DOI: 10.1109/JMASS.2025.3554688
Jingjian Long;Xuemin Xing;Guanfeng Zheng;Liang Wang;Xiangjun Yao;Xiongwei Yang
Objectives: Long-term deformation monitoring for highway network constructed in soft soil areas is essential. The plastic creep characteristic plays an important role in soft soil deformation. However, it has been neglected in most traditional InSAR time-series deformation models. To address this limitation, a joint modeling and deformation estimation method is proposed for highway networks in soft soil areas. Technology or Method: The processing of deformation modeling and parameter estimation are performed separately for subgrades and bridges. For the roadbed objects constructed in soft soil areas, a nonlinear visco-plastic body periodical precipitation (NVPBPP) model, which combines the Nonlinear Visco-plastic Body model with periodical and precipitation models to consider the plastic creep effects on temporal deformation for soft soil clay areas; for the bridge region, a thermal expansion linear (TEL) model and the traditional linear velocity model are incorporated, which characterizes the thermal expansion properties for bridge material. Results: The experiment is conducted on a highway network including roads and three bridges in a soft soil area in Beijing. The time series settlement from 22 January 2012 to 6 February 2015 is generated, with the maximum cumulative settlement estimated as 135 mm. The modeling accuracy of the NVPBPP model is estimated as ±6.5 mm, with 61.3% improvement compared to the traditional InSAR linear rate model; The external deformation cross-validation shows that our work has a high correlation coefficient of 0.97 with existed published results. Clinical or Biological Impact: Our method can provide data support and a reference for monitoring long-term health and ensuring transportation safety especially in poor soil regions.
{"title":"InSAR Joint Modeling and Deformation Estimation for Highway Network in Soft Soil Areas","authors":"Jingjian Long;Xuemin Xing;Guanfeng Zheng;Liang Wang;Xiangjun Yao;Xiongwei Yang","doi":"10.1109/JMASS.2025.3554688","DOIUrl":"https://doi.org/10.1109/JMASS.2025.3554688","url":null,"abstract":"Objectives: Long-term deformation monitoring for highway network constructed in soft soil areas is essential. The plastic creep characteristic plays an important role in soft soil deformation. However, it has been neglected in most traditional InSAR time-series deformation models. To address this limitation, a joint modeling and deformation estimation method is proposed for highway networks in soft soil areas. Technology or Method: The processing of deformation modeling and parameter estimation are performed separately for subgrades and bridges. For the roadbed objects constructed in soft soil areas, a nonlinear visco-plastic body periodical precipitation (NVPBPP) model, which combines the Nonlinear Visco-plastic Body model with periodical and precipitation models to consider the plastic creep effects on temporal deformation for soft soil clay areas; for the bridge region, a thermal expansion linear (TEL) model and the traditional linear velocity model are incorporated, which characterizes the thermal expansion properties for bridge material. Results: The experiment is conducted on a highway network including roads and three bridges in a soft soil area in Beijing. The time series settlement from 22 January 2012 to 6 February 2015 is generated, with the maximum cumulative settlement estimated as 135 mm. The modeling accuracy of the NVPBPP model is estimated as ±6.5 mm, with 61.3% improvement compared to the traditional InSAR linear rate model; The external deformation cross-validation shows that our work has a high correlation coefficient of 0.97 with existed published results. Clinical or Biological Impact: Our method can provide data support and a reference for monitoring long-term health and ensuring transportation safety especially in poor soil regions.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"6 3","pages":"274-285"},"PeriodicalIF":2.1,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891276","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}
Pub Date : 2025-03-14DOI: 10.1109/JMASS.2025.3551430
Yun He;LinJuan Li;Gang Xie;Haoxue Zhang;Feng Chen;Sida Liu
Semantic segmentation plays a pivotal role in the interpretation of remote sensing entities. However, the complexity of the environments, diversity of objects, and richness of details make semantic segmentation even more challenging. Existing methods have limitations in interclass edge continuity and intraclass completeness within segmentation results. To address these issues, a feature decoupling guided Network is developed for learning the discriminative representation. In which the feature decoupling module separates encoded features into homogeneous information for primary object features and distinct information for object boundaries. Another, the semantic-aware integration unit is employed to strengthen semantic consistency during decomposition. To facilitate practical application, we created the Taiyuan Land Cover (TYLC) dataset for semantic segmentation to analyze land resource utilization. Extensive experiments on the TYLC dataset achieved a mean intersection over the union of 54.2%, the mean $F_{1}$ score of 67.7%, and the mean recall of 66.6%. Quantitative results demonstrate the algorithm’s superiority, and visualizations indicate that the segmentation output has excellent completeness and edge continuity.
{"title":"Decoupling Representation Learning for Remote Sensing Semantic Segmentation","authors":"Yun He;LinJuan Li;Gang Xie;Haoxue Zhang;Feng Chen;Sida Liu","doi":"10.1109/JMASS.2025.3551430","DOIUrl":"https://doi.org/10.1109/JMASS.2025.3551430","url":null,"abstract":"Semantic segmentation plays a pivotal role in the interpretation of remote sensing entities. However, the complexity of the environments, diversity of objects, and richness of details make semantic segmentation even more challenging. Existing methods have limitations in interclass edge continuity and intraclass completeness within segmentation results. To address these issues, a feature decoupling guided Network is developed for learning the discriminative representation. In which the feature decoupling module separates encoded features into homogeneous information for primary object features and distinct information for object boundaries. Another, the semantic-aware integration unit is employed to strengthen semantic consistency during decomposition. To facilitate practical application, we created the Taiyuan Land Cover (TYLC) dataset for semantic segmentation to analyze land resource utilization. Extensive experiments on the TYLC dataset achieved a mean intersection over the union of 54.2%, the mean <inline-formula> <tex-math>$F_{1}$ </tex-math></inline-formula> score of 67.7%, and the mean recall of 66.6%. Quantitative results demonstrate the algorithm’s superiority, and visualizations indicate that the segmentation output has excellent completeness and edge continuity.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"6 3","pages":"262-273"},"PeriodicalIF":2.1,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891275","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}
Pub Date : 2025-03-10DOI: 10.1109/JMASS.2025.3549731
Davi L. Figueiredo;Leonardo K. Slongo;Eduardo A. Bezerra
The low reliability of the electrical power systems (EPSs) is one of the major factors responsible for the high number of nanosatellite mission failures. Although several reliability-enhancing techniques have been proposed in the past, most studies do not take into account their applicability, overlooking the cost, power, and board area required for them to be implemented. In light of this, the present work proposes an EPS architecture that incorporates four reliability-enhancing techniques into a low-cost, small-footprint design. Namely, methodical COTS selection, processor-less design, partial standby redundancy, and load monitoring and control. Each technique was thoughtfully chosen to enhance reliability without compromising other design areas. The entire proposal was backed up by block diagrams, theoretical analysis, and SPICE circuit simulations. Furthermore, this work also proposes a three-metric system for evaluating and comparing the reliability of different EPS architectures. Based on this evaluation method, it was possible to compare the EPS architecture presented herein with its previous version and with the NanoPower P31U, which is designed by GomSpace. Comparison results confirmed the effectiveness of the techniques that were incorporated into this EPS, indicating that it exhibits the highest architecture reliability among the three candidates that were considered for this analysis.
{"title":"Reliability-Enhanced Electrical Power System for Nanosatellites","authors":"Davi L. Figueiredo;Leonardo K. Slongo;Eduardo A. Bezerra","doi":"10.1109/JMASS.2025.3549731","DOIUrl":"https://doi.org/10.1109/JMASS.2025.3549731","url":null,"abstract":"The low reliability of the electrical power systems (EPSs) is one of the major factors responsible for the high number of nanosatellite mission failures. Although several reliability-enhancing techniques have been proposed in the past, most studies do not take into account their applicability, overlooking the cost, power, and board area required for them to be implemented. In light of this, the present work proposes an EPS architecture that incorporates four reliability-enhancing techniques into a low-cost, small-footprint design. Namely, methodical COTS selection, processor-less design, partial standby redundancy, and load monitoring and control. Each technique was thoughtfully chosen to enhance reliability without compromising other design areas. The entire proposal was backed up by block diagrams, theoretical analysis, and SPICE circuit simulations. Furthermore, this work also proposes a three-metric system for evaluating and comparing the reliability of different EPS architectures. Based on this evaluation method, it was possible to compare the EPS architecture presented herein with its previous version and with the NanoPower P31U, which is designed by GomSpace. Comparison results confirmed the effectiveness of the techniques that were incorporated into this EPS, indicating that it exhibits the highest architecture reliability among the three candidates that were considered for this analysis.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"6 3","pages":"248-261"},"PeriodicalIF":2.1,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891330","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}
Uncrewed aerial vehicles (UAVs) have emerged as a state-of-the-art solution for establishing communication in remote and obstructed areas. However, before UAVs can be integrated into existing communication infrastructure, it is essential to address the energy constraints and security concerns arising from their line-of-sight links. This article focuses on a UAV-enabled communication system in which a UAV relay facilitates information transfer from the source to the destination nodes when the direct link is heavily shadowed or obstructed. A nearby terrestrial passive eavesdropper can intercept information transmitted through the source-to-UAV and UAV-to-destination links. To address this, we utilize destination-aided cooperative jamming. Additionally, we consider simultaneous wireless information and power transfer (SWIPT) at the UAV to provide the energy required for data transmission. In particular, the UAV utilizes a hybrid-SWIPT technique to harvest energy from the radio-frequency signals. For this setup, we derive accurate expressions of secrecy outage probability and system secrecy throughput (SST) over Beaulieu-Xie distributed channels. Using the SST expression, we formulate an SST maximization problem to jointly optimize the transmit powers, power allocation, SWIPT coefficients, and UAV’s 3-D position. The formulated problem is solved using the hybrid heuristic framework, combining continuous genetic and particle swarm optimization algorithms. Numerical results demonstrate the significant enhancement in information secrecy of the system with the proposed hybrid scheme and also provide valuable insights into the system’s behavior.
{"title":"Secrecy Analysis and Optimization of UAV-Assisted Communications With Hybrid SWIPT and Cooperative Jamming","authors":"Gaurav Kumar Pandey;Devendra Singh Gurjar;Suneel Yadav;Sourabh Solanki;Juraj Gazda;Symeon Chatzinotas","doi":"10.1109/JMASS.2025.3568592","DOIUrl":"https://doi.org/10.1109/JMASS.2025.3568592","url":null,"abstract":"Uncrewed aerial vehicles (UAVs) have emerged as a state-of-the-art solution for establishing communication in remote and obstructed areas. However, before UAVs can be integrated into existing communication infrastructure, it is essential to address the energy constraints and security concerns arising from their line-of-sight links. This article focuses on a UAV-enabled communication system in which a UAV relay facilitates information transfer from the source to the destination nodes when the direct link is heavily shadowed or obstructed. A nearby terrestrial passive eavesdropper can intercept information transmitted through the source-to-UAV and UAV-to-destination links. To address this, we utilize destination-aided cooperative jamming. Additionally, we consider simultaneous wireless information and power transfer (SWIPT) at the UAV to provide the energy required for data transmission. In particular, the UAV utilizes a hybrid-SWIPT technique to harvest energy from the radio-frequency signals. For this setup, we derive accurate expressions of secrecy outage probability and system secrecy throughput (SST) over Beaulieu-Xie distributed channels. Using the SST expression, we formulate an SST maximization problem to jointly optimize the transmit powers, power allocation, SWIPT coefficients, and UAV’s 3-D position. The formulated problem is solved using the hybrid heuristic framework, combining continuous genetic and particle swarm optimization algorithms. Numerical results demonstrate the significant enhancement in information secrecy of the system with the proposed hybrid scheme and also provide valuable insights into the system’s behavior.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"6 3","pages":"305-320"},"PeriodicalIF":2.1,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891272","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}
Pub Date : 2025-03-06DOI: 10.1109/JMASS.2025.3567087
Nan Cheng;Haoran Chen;Ruijin Sun;Longfei Ma;Conghao Zhou;Yuan Zhang;Yilong Hui
In the wake of disasters, rapid and efficient search and rescue operations are essential. Uncrewed aerial vehicles (UAVs) have become instrumental in such scenarios, providing real-time video streaming that can be used for object detection to locate survivors. This technology, however, faces significant challenges due to the limited communication and onboard computational resources, which are critical for processing and transmitting high-quality video data. To address these issues, this article proposes a novel approach that leverages the concept of the value of information (VoI) to optimize the tradeoff between the accuracy of object detection and the associated communication costs. By dynamically adjusting the video stream’s quality, the proposed system aims to ensure that the most valuable information is transmitted within the constraints of bandwidth and computational power. To operationalize this concept, we introduce a deep reinforcement learning (DRL) algorithm that employs the soft actor-critic (SAC) method. The algorithm benefits from the integration of object features and contextual information extracted by ResNet50, which is then processed through a cross-attention structure within the critic network. Our simulation results indicate that our approach significantly enhances the VoI, achieving higher accuracy in object detection with better resource management compared to traditional strategies.
{"title":"Value-of-Information Optimization for Object Detection-Driven Joint Video Transmission and Processing in UAV-Enabled Wireless Networks","authors":"Nan Cheng;Haoran Chen;Ruijin Sun;Longfei Ma;Conghao Zhou;Yuan Zhang;Yilong Hui","doi":"10.1109/JMASS.2025.3567087","DOIUrl":"https://doi.org/10.1109/JMASS.2025.3567087","url":null,"abstract":"In the wake of disasters, rapid and efficient search and rescue operations are essential. Uncrewed aerial vehicles (UAVs) have become instrumental in such scenarios, providing real-time video streaming that can be used for object detection to locate survivors. This technology, however, faces significant challenges due to the limited communication and onboard computational resources, which are critical for processing and transmitting high-quality video data. To address these issues, this article proposes a novel approach that leverages the concept of the value of information (VoI) to optimize the tradeoff between the accuracy of object detection and the associated communication costs. By dynamically adjusting the video stream’s quality, the proposed system aims to ensure that the most valuable information is transmitted within the constraints of bandwidth and computational power. To operationalize this concept, we introduce a deep reinforcement learning (DRL) algorithm that employs the soft actor-critic (SAC) method. The algorithm benefits from the integration of object features and contextual information extracted by ResNet50, which is then processed through a cross-attention structure within the critic network. Our simulation results indicate that our approach significantly enhances the VoI, achieving higher accuracy in object detection with better resource management compared to traditional strategies.","PeriodicalId":100624,"journal":{"name":"IEEE Journal on Miniaturization for Air and Space Systems","volume":"6 2","pages":"59-69"},"PeriodicalIF":0.0,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144179104","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：