NSTL国家科技图书文献中心

1. Embedded-ViT: A Framework for Embedded Deployment of Vision-Transformer in Medical Applications NSTL国家科技图书文献中心

Erik Ostrowski | Muhammad Shafique - 《Advances in Visual Computing,Part II》 - International Symposium on Visual Computing - 2025, - 371～382 - 共12页

摘要： allows the embedded* deployment of transformers in the* | GPUs for deployment, contrary to the Internet of | Things trend, which enables the mobile deployment* of AI* | deployment are even more critical in the medical field, and | medical field. In this paper, we propose our Embedded

关键词： Semantic segmentation | Lightweight | Embedded deployment | CAD | Computer vision | Vision transformer

2. Underwater-MLA: lightweight aggregated underwater object detection network based on multi-branches for embedded deployment NSTL国家科技图书文献中心

Chen, Xiao | Fan, Chenye ... - 《Measurement Science & Technology》 - 2025,36(1) - 1～20 - 共20页

摘要： performance on embedded* terminals. Link to open-source code* | In response to the limited memory and | computing capabilities of underwater devices, as well as | the various target leakage issues caused by complex | underwater environments, we propose a lightweight

关键词： object detection | lightweight | YOLOv5s | multi-branching | embedded deployment

3. J-Net: A Low-Resolution Lightweight Neural Network for Semantic Segmentation in the Medical Field for Embedded Deployment NSTL国家科技图书文献中心

Erik Ostrowski | Muhammad Shafique - 《Advances in Visual Computing,Part I》 - International Symposium on Visual Computing - 2025, - 480～492 - 共13页

摘要： in embedded* medical devices, where budgets are* | in MRI images. We also tested the deployment* speed* | on Nvidia's Jetson Nano to emulate deployment* in* | resource-constrained embedded* scenarios. The framework is* | When deploying neural networks in real-life

关键词： Semantic segmentation | Lightweight | Embedded deployment | CAD | Computer vision

4. Lightweight design and deployment of object detection model for low-light scenes NSTL国家科技图书文献中心

Kangjian Sun | Ju Huo ... - 《Fourth International Conference on Computer Vision,Application,and Algorithm (CVAA 2024)》 - International Conference on Computer Vision,Application,and Algorithm - 2025, - 1348620.1～1348620.9 - 共9页

摘要： limited computing power of embedded* devices, the YOLOv8n* | migrated to the embedded* platform NVIDIA Jetson Xavier NX* | . The deployment* process is optimized by multi-process* | Low-light scenes are common in fields such as | autonomous driving, which tests the robustness of

关键词： YOLOv8n | Model lightweight | Embedded deployment | Low-light scene

5. Dynamic FPGA reconfiguration for scalable embedded artificial intelligence (AI): A co-design methodology for convolutional neural networks (CNN) acceleration NSTL国家科技图书文献中心

Jalil Boudjadar | Saif Ul Islam ... - 《Future generations computer systems》 - 2025,169(Aug.) - 107777.1～107777.11 - 共11页

摘要： intelligence (AI) applications, particularly in Embedded* AI* | deployment on FPGAs, there remains a gap in methodologies | In recent years, FPGA platforms have shown | significant potential for accelerating artificial | . While various studies have explored adaptive AI

关键词： Adaptive CNNs | FPGA dynamic reconfiguration | Hardware acceleration | Co-design framework | Embedded AI | Computation performance | Scalable AI deployment

6. A comprehensive equivalent circuit model of Li-ion batteries for SOC estimation in electric vehicles based on parametric sensitivity analysis NSTL国家科技图书文献中心

Prashant,Aher | Raviraj,Deshmukh ... - 《Ionics》 - 2025,31(1) - 287～303 - 共17页 - 被引量：1

摘要： for embedded* deployment due to reduced computations* | are unsuitable for deployment* due to constraints* | from the embedded* point of view. This article* | accuracy and embedded* computations. The extended Kalman* | Abstract On-board estimation of battery state

关键词： Battery state estimation | Equivalent circuit model | Model parameter sensitivity | Online parameter identification | Sate of health | State of charge

7. Mobile recognition system for multinational currencies based on CA‑DSC‑RepVGG algorithm NSTL国家科技图书文献中心

Xiaonan Yang | Zuoxi Zhao ... - 《The Journal of Supercomputing》 - 2025,81(2) - 433.1～433.27 - 共27页

摘要： difficulties in deployment on an expanding array of embedded | -time and embedded* device deployment of multi-country* | rk3568 embedded* device. A series of comparative* | pre-improvement period. Following deployment* on* | Convolutional neural networks (CNNs) continue

关键词： Multinational currency recognition | CA-DSC-RepVGG | Lightweight | rk3568

8. Efficient Post-training Augmentation for Adaptive Inference in Heterogeneous and Distributed IoT Environments NSTL国家科技图书文献中心

Max Sponner | Lorenzo Servadei ... - 《Embedded Computer Systems: Architectures,Modeling,and Simulation,Part II》 - International Conference on Embedded Computer Systems - 2025, - 99～108 - 共10页

摘要： deployment on heterogeneous or distributed embedded targets | . We evaluated our approach on embedded* Deep Learning* | showcases the potential for EENNs in embedded* applications.* | Early Exit Neural Networks (EENNs) achieve | enhanced efficiency compared to traditional models, but

关键词： Deep learning | Early exit neural networks | Network architecture search

9. Research on Distributed Service Governance Framework Based on Embedded System NSTL国家科技图书文献中心

Ge Qi | Yukun Liu ... - 《Proceedings of the 7th China Aeronautical Science and Technology Conference,v.II》 - China Aeronautical Science and Technology Conference - 2025, - 535～542 - 共8页

摘要： scalability of embedded* software applications and reduce the* | embedded environment. Based on the characteristics of | embedded software development, the software is redefined | to realize the function of remote deployment* and* | In order to improve the portability and

关键词： Embedded software | Distributed service governance | Service lifecycle management

10. Design and Modeling of a Self‑Sensing Micro‑Vibration Isolation System Utilizing a Lightweight Electret‑Based Transducer for Space Applications NSTL国家科技图书文献中心

Chao Dong | Zhaoshu Yang ... - 《Microgravity science and technology》 - 2025,37(1) - 8.1～8.21 - 共21页

摘要： expected to be embedded* with the traditional micro* | transducer is an excellent candidate for the embedded | size and appropriate deployment* pattern, the electret* | A compact and lightweight sensor is always | -vibration isolator in spacecraft. It helps to detect the

摘要： allows the embedded* deployment of transformers in the* | GPUs for deployment, contrary to the Internet of | Things trend, which enables the mobile deployment* of AI* | deployment are even more critical in the medical field, and | medical field. In this paper, we propose our Embedded

关键词： Semantic segmentation | Lightweight | Embedded deployment | CAD | Computer vision | Vision transformer

摘要： performance on embedded* terminals. Link to open-source code* | In response to the limited memory and | computing capabilities of underwater devices, as well as | the various target leakage issues caused by complex | underwater environments, we propose a lightweight

关键词： object detection | lightweight | YOLOv5s | multi-branching | embedded deployment

摘要： in embedded* medical devices, where budgets are* | in MRI images. We also tested the deployment* speed* | on Nvidia's Jetson Nano to emulate deployment* in* | resource-constrained embedded* scenarios. The framework is* | When deploying neural networks in real-life

关键词： Semantic segmentation | Lightweight | Embedded deployment | CAD | Computer vision

摘要： limited computing power of embedded* devices, the YOLOv8n* | migrated to the embedded* platform NVIDIA Jetson Xavier NX* | . The deployment* process is optimized by multi-process* | Low-light scenes are common in fields such as | autonomous driving, which tests the robustness of

关键词： YOLOv8n | Model lightweight | Embedded deployment | Low-light scene

摘要： intelligence (AI) applications, particularly in Embedded* AI* | deployment on FPGAs, there remains a gap in methodologies | In recent years, FPGA platforms have shown | significant potential for accelerating artificial | . While various studies have explored adaptive AI

关键词： Adaptive CNNs | FPGA dynamic reconfiguration | Hardware acceleration | Co-design framework | Embedded AI | Computation performance | Scalable AI deployment

摘要： for embedded* deployment due to reduced computations* | are unsuitable for deployment* due to constraints* | from the embedded* point of view. This article* | accuracy and embedded* computations. The extended Kalman* | Abstract On-board estimation of battery state

关键词： Battery state estimation | Equivalent circuit model | Model parameter sensitivity | Online parameter identification | Sate of health | State of charge

摘要： difficulties in deployment on an expanding array of embedded | -time and embedded* device deployment of multi-country* | rk3568 embedded* device. A series of comparative* | pre-improvement period. Following deployment* on* | Convolutional neural networks (CNNs) continue

关键词： Multinational currency recognition | CA-DSC-RepVGG | Lightweight | rk3568

摘要： deployment on heterogeneous or distributed embedded targets | . We evaluated our approach on embedded* Deep Learning* | showcases the potential for EENNs in embedded* applications.* | Early Exit Neural Networks (EENNs) achieve | enhanced efficiency compared to traditional models, but

关键词： Deep learning | Early exit neural networks | Network architecture search

摘要： scalability of embedded* software applications and reduce the* | embedded environment. Based on the characteristics of | embedded software development, the software is redefined | to realize the function of remote deployment* and* | In order to improve the portability and

关键词： Embedded software | Distributed service governance | Service lifecycle management

摘要： expected to be embedded* with the traditional micro* | transducer is an excellent candidate for the embedded | size and appropriate deployment* pattern, the electret* | A compact and lightweight sensor is always | -vibration isolator in spacecraft. It helps to detect the

关键词： Electret | Micro-vibration | Self-sensing | Isolator | Space application

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： allows the embedded deployment of transformers in the | GPUs for deployment, contrary to the Internet of | Things trend, which enables the mobile deployment of AI | deployment are even more critical in the medical field, and | medical field. In this paper, we propose our Embedded

关键词： Semantic segmentation | Lightweight | Embedded deployment | CAD | Computer vision | Vision transformer

摘要： performance on embedded terminals. Link to open-source code | In response to the limited memory and | computing capabilities of underwater devices, as well as | the various target leakage issues caused by complex | underwater environments, we propose a lightweight

关键词： object detection | lightweight | YOLOv5s | multi-branching | embedded deployment

摘要： in embedded medical devices, where budgets are | in MRI images. We also tested the deployment speed | on Nvidia's Jetson Nano to emulate deployment in | resource-constrained embedded scenarios. The framework is | When deploying neural networks in real-life

关键词： Semantic segmentation | Lightweight | Embedded deployment | CAD | Computer vision

摘要： limited computing power of embedded devices, the YOLOv8n | migrated to the embedded platform NVIDIA Jetson Xavier NX | . The deployment process is optimized by multi-process | Low-light scenes are common in fields such as | autonomous driving, which tests the robustness of

关键词： YOLOv8n | Model lightweight | Embedded deployment | Low-light scene

摘要： intelligence (AI) applications, particularly in Embedded AI | deployment on FPGAs, there remains a gap in methodologies | In recent years, FPGA platforms have shown | significant potential for accelerating artificial | . While various studies have explored adaptive AI

关键词： Adaptive CNNs | FPGA dynamic reconfiguration | Hardware acceleration | Co-design framework | Embedded AI | Computation performance | Scalable AI deployment

摘要： for embedded deployment due to reduced computations | are unsuitable for deployment due to constraints | from the embedded point of view. This article | accuracy and embedded computations. The extended Kalman | Abstract On-board estimation of battery state

关键词： Battery state estimation | Equivalent circuit model | Model parameter sensitivity | Online parameter identification | Sate of health | State of charge

摘要： difficulties in deployment on an expanding array of embedded | -time and embedded device deployment of multi-country | rk3568 embedded device. A series of comparative | pre-improvement period. Following deployment on | Convolutional neural networks (CNNs) continue

关键词： Multinational currency recognition | CA-DSC-RepVGG | Lightweight | rk3568

摘要： deployment on heterogeneous or distributed embedded targets | . We evaluated our approach on embedded Deep Learning | showcases the potential for EENNs in embedded applications. | Early Exit Neural Networks (EENNs) achieve | enhanced efficiency compared to traditional models, but

关键词： Deep learning | Early exit neural networks | Network architecture search

摘要： scalability of embedded software applications and reduce the | embedded environment. Based on the characteristics of | embedded software development, the software is redefined | to realize the function of remote deployment and | In order to improve the portability and

关键词： Embedded software | Distributed service governance | Service lifecycle management

摘要： expected to be embedded with the traditional micro | transducer is an excellent candidate for the embedded | size and appropriate deployment pattern, the electret | A compact and lightweight sensor is always | -vibration isolator in spacecraft. It helps to detect the

关键词： Electret | Micro-vibration | Self-sensing | Isolator | Space application

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： allows the embedded* deployment of transformers in the* | GPUs for deployment, contrary to the Internet of | Things trend, which enables the mobile deployment* of AI* | deployment are even more critical in the medical field, and | medical field. In this paper, we propose our Embedded

摘要： performance on embedded* terminals. Link to open-source code* | In response to the limited memory and | computing capabilities of underwater devices, as well as | the various target leakage issues caused by complex | underwater environments, we propose a lightweight

摘要： in embedded* medical devices, where budgets are* | in MRI images. We also tested the deployment* speed* | on Nvidia's Jetson Nano to emulate deployment* in* | resource-constrained embedded* scenarios. The framework is* | When deploying neural networks in real-life

摘要： limited computing power of embedded* devices, the YOLOv8n* | migrated to the embedded* platform NVIDIA Jetson Xavier NX* | . The deployment* process is optimized by multi-process* | Low-light scenes are common in fields such as | autonomous driving, which tests the robustness of

摘要： intelligence (AI) applications, particularly in Embedded* AI* | deployment on FPGAs, there remains a gap in methodologies | In recent years, FPGA platforms have shown | significant potential for accelerating artificial | . While various studies have explored adaptive AI

摘要： for embedded* deployment due to reduced computations* | are unsuitable for deployment* due to constraints* | from the embedded* point of view. This article* | accuracy and embedded* computations. The extended Kalman* | Abstract On-board estimation of battery state

摘要： difficulties in deployment on an expanding array of embedded | -time and embedded* device deployment of multi-country* | rk3568 embedded* device. A series of comparative* | pre-improvement period. Following deployment* on* | Convolutional neural networks (CNNs) continue

摘要： deployment on heterogeneous or distributed embedded targets | . We evaluated our approach on embedded* Deep Learning* | showcases the potential for EENNs in embedded* applications.* | Early Exit Neural Networks (EENNs) achieve | enhanced efficiency compared to traditional models, but

摘要： scalability of embedded* software applications and reduce the* | embedded environment. Based on the characteristics of | embedded software development, the software is redefined | to realize the function of remote deployment* and* | In order to improve the portability and

摘要： expected to be embedded* with the traditional micro* | transducer is an excellent candidate for the embedded | size and appropriate deployment* pattern, the electret* | A compact and lightweight sensor is always | -vibration isolator in spacecraft. It helps to detect the