NSTL国家科技图书文献中心

1. Imaging through Scattering Media via Optronic Convolutional Neural Network NSTL国家科技图书文献中心

Luofei Tu | Zicheng Huang ... - 《Fourth International Computational Imaging Conference (CITA 2024),Part Two of Two Parts》 - International Computational Imaging Conference - 2025, - 135423M.1～135423M.9 - 共9页

摘要：-electronic fully convolutional* neural network (OP-FCNN* | With the growing influence of machine learning | , it brings benefits to the inverse problem of | imaging through scattering media in computational | imaging. This study introduces an innovative opto

关键词： Imaging through scattering | Convolutional neural network | Deep learning

2. Wavelet Integrated Convolutional Neural Network for ECG Signal Denoising NSTL国家科技图书文献中心

Takamasa Terada | Masahiro Toyoura - 《MultiMedia Modeling,Part IV》 - International Conference on MultiMedia Modeling - 2025, - 311～324 - 共14页

摘要： neural network (CNN) model with an additional wavelet | intensity and type. This study proposes a convolutional | Wearable electrocardiogram (ECG) measurement | using dry electrodes has a problem with high-intensity | noise distortion. Hence, a robust noise reduction

关键词： Electrocardiogram | Wavelet transform | Denoising autoencoder | Convolutional neural network

3. PCIR: Privacy-Preserving Convolutional Neural Network Inference With Rapid Responsiveness NSTL国家科技图书文献中心

Jinguo Li | Yan Yan ... - 《Computational intelligence》 - 2025,41(2) - e70030.1～e70030.12 - 共12页

摘要： convolutional neural network inference (PCIR). PCIR aims to | convolutional neural networks (CNNs) to offer predictive | triples. Finally, we evaluate PCIR with benchmark neural | Several companies leverage trained | services to users. These companies capitalize on CNNs

关键词： convolutional neural network | data privacy | deep learning | model privacy

4. swCNN: A Small World Convolutional Neural Network for Efficient Training NSTL国家科技图书文献中心

Shubham Dwivedi | Tushar Sandhan ... - 《Pattern Recognition,Part VIII》 - International Conference on Pattern Recognition - 2025, - 359～374 - 共16页

摘要： convolutional neural networks (CNNs). This work introduces a | Neural Network (swCNN), inspired by small-world network | The advent of small-world network* theory has* | significantly revolutionized network* science. Small-world* | novel architecture, the Small World Convolutional

关键词： Small-world phenomenon | Deep learning | Convolutional neural network (CNN) | Efficient training

5. Intention inference for space targets using deep convolutional neural network NSTL国家科技图书文献中心

Li, Jiasheng | Yang, Zhen ... - 《Advances in Space Research》 - 2025,75(2) - 2184～2200 - 共17页

摘要： convolutional neural network (CNN). By employing a relative | enhances recognition accuracy over other neural network | simulations were carried out to fine-tune the network | Intention inference for space targets is | crucial for space situational awareness. This paper

关键词： Intention inference | Image classification | Convolutional neural network | Astrodynamics | Satellite relative motion

6. Combining multi-level feature extraction algorithm with residual graph convolutional neural network for partial discharge detection NSTL国家科技图书文献中心

Zhang, Chungfeng | Fulnecek, Jan ... - 《Measurement》 - 2025,242PD - 116151～ - 共15页

摘要： convolutional neural network (1D-CNN) with a residual graph | convolutional neural network (ResGCN) to recognize PD signals | Partial discharge (PD) identification is | critical for the insulation diagnosis of cable conductors | ; however, there is still scope for enhancement in the

关键词： Partial discharge | Convolutional neural network | Graph data | Graph attention mechanism | Graph convolutional neural network

7. Earthquake magnitude estimation using a two-step convolutional neural network NSTL国家科技图书文献中心

Liu, Xinliang | Ren, Tao ... - 《Journal of seismology》 - 2025,29(1) - 241～256 - 共16页

摘要： convolutional neural network (CNN) procedure is proposed to | In this paper, an efficient two-step | estimate earthquake magnitude using raw waveform data up | to only 4 s after the P wave onset. In the proposed | procedure, magnitude estimation is split into

关键词： Convolutional neural network | Earthquake magnitude estimation | Two-step procedure | Unsure response

8. RV-CVP: A Flexible Variable Precision RISC-V ISA Extension for Convolutional Neural Network NSTL国家科技图书文献中心

Jingyi Zhu | Di Zhao ... - 《Network and Parallel Computing,Part I》 - IFIP WG 10.3 International Conference on Network and Parallel Computing - 2025, - 461～473 - 共13页

摘要：Convolutional neural network (CNN) performs | well in several research fields and achieves high | accuracy. With the development of CNNs, various hardware | acceleration methods have been proposed. Instruction Set | Architecture (ISA) based acceleration methods are gaining

关键词： RISC-V | Variable precision | Convolutional neural network

9. Indoor visible light positioning system based on memristive convolutional neural network NSTL国家科技图书文献中心

Chen, Qi | Wang, Fengying ... - 《Optics Communications》 - 2025,577 - 131340.1～131340.11 - 共11页

摘要： highefficiency memristive convolutional neural network | convolutional neural networks. By integrating ResNeXt, ESCA | mechanism, and pruning algorithm, the convolutional neural | network is enhanced, significantly boosting the | issues such as excessive network* parameters, gradient*

关键词： Visible light positioning(VLP) | ResNeXt | ESCA | Memristor | Memristor convolutional neural network

10. Modulation Recognition Based on Convolutional Neural Network and Image Coding Techniques NSTL国家科技图书文献中心

Hengyi Hong | Qian Wang ... - 《The International Conference Optoelectronic Information and Optical Engineering (OIOE2024),Part Two of Two Parts》 - International Conference Optoelectronic Information and Optical Engineering - 2025, - 135132X.1～135132X.7 - 共7页

摘要： Field (GAF) coding technique and convolutional neural | network (CNN) is proposed. The homogeneous and | In order to improve the accuracy and | generalization ability of modulated pattern recognition, a | modulation recognition method based on Gramian Angular

摘要：-electronic fully convolutional* neural network (OP-FCNN* | With the growing influence of machine learning | , it brings benefits to the inverse problem of | imaging through scattering media in computational | imaging. This study introduces an innovative opto

关键词： Imaging through scattering | Convolutional neural network | Deep learning

摘要： neural network (CNN) model with an additional wavelet | intensity and type. This study proposes a convolutional | Wearable electrocardiogram (ECG) measurement | using dry electrodes has a problem with high-intensity | noise distortion. Hence, a robust noise reduction

关键词： Electrocardiogram | Wavelet transform | Denoising autoencoder | Convolutional neural network

摘要： convolutional neural network inference (PCIR). PCIR aims to | convolutional neural networks (CNNs) to offer predictive | triples. Finally, we evaluate PCIR with benchmark neural | Several companies leverage trained | services to users. These companies capitalize on CNNs

关键词： convolutional neural network | data privacy | deep learning | model privacy

摘要： convolutional neural networks (CNNs). This work introduces a | Neural Network (swCNN), inspired by small-world network | The advent of small-world network* theory has* | significantly revolutionized network* science. Small-world* | novel architecture, the Small World Convolutional

关键词： Small-world phenomenon | Deep learning | Convolutional neural network (CNN) | Efficient training

摘要： convolutional neural network (CNN). By employing a relative | enhances recognition accuracy over other neural network | simulations were carried out to fine-tune the network | Intention inference for space targets is | crucial for space situational awareness. This paper

关键词： Intention inference | Image classification | Convolutional neural network | Astrodynamics | Satellite relative motion

摘要： convolutional neural network (1D-CNN) with a residual graph | convolutional neural network (ResGCN) to recognize PD signals | Partial discharge (PD) identification is | critical for the insulation diagnosis of cable conductors | ; however, there is still scope for enhancement in the

关键词： Partial discharge | Convolutional neural network | Graph data | Graph attention mechanism | Graph convolutional neural network

摘要： convolutional neural network (CNN) procedure is proposed to | In this paper, an efficient two-step | estimate earthquake magnitude using raw waveform data up | to only 4 s after the P wave onset. In the proposed | procedure, magnitude estimation is split into

关键词： Convolutional neural network | Earthquake magnitude estimation | Two-step procedure | Unsure response

摘要：Convolutional neural network (CNN) performs | well in several research fields and achieves high | accuracy. With the development of CNNs, various hardware | acceleration methods have been proposed. Instruction Set | Architecture (ISA) based acceleration methods are gaining

关键词： RISC-V | Variable precision | Convolutional neural network

摘要： highefficiency memristive convolutional neural network | convolutional neural networks. By integrating ResNeXt, ESCA | mechanism, and pruning algorithm, the convolutional neural | network is enhanced, significantly boosting the | issues such as excessive network* parameters, gradient*

关键词： Visible light positioning(VLP) | ResNeXt | ESCA | Memristor | Memristor convolutional neural network

摘要： Field (GAF) coding technique and convolutional neural | network (CNN) is proposed. The homogeneous and | In order to improve the accuracy and | generalization ability of modulated pattern recognition, a | modulation recognition method based on Gramian Angular

关键词： Modulation recognition | Convolutional neural network | IQ component | GAF coding

4008-161-200 800-990-8900

国家科技图书文献中心

摘要：-electronic fully convolutional neural network (OP-FCNN | With the growing influence of machine learning | , it brings benefits to the inverse problem of | imaging through scattering media in computational | imaging. This study introduces an innovative opto

关键词： Imaging through scattering | Convolutional neural network | Deep learning

摘要： neural network (CNN) model with an additional wavelet | intensity and type. This study proposes a convolutional | Wearable electrocardiogram (ECG) measurement | using dry electrodes has a problem with high-intensity | noise distortion. Hence, a robust noise reduction

关键词： Electrocardiogram | Wavelet transform | Denoising autoencoder | Convolutional neural network

摘要： convolutional neural network inference (PCIR). PCIR aims to | convolutional neural networks (CNNs) to offer predictive | triples. Finally, we evaluate PCIR with benchmark neural | Several companies leverage trained | services to users. These companies capitalize on CNNs

关键词： convolutional neural network | data privacy | deep learning | model privacy

摘要： convolutional neural networks (CNNs). This work introduces a | Neural Network (swCNN), inspired by small-world network | The advent of small-world network theory has | significantly revolutionized network science. Small-world | novel architecture, the Small World Convolutional

关键词： Small-world phenomenon | Deep learning | Convolutional neural network (CNN) | Efficient training

摘要： convolutional neural network (CNN). By employing a relative | enhances recognition accuracy over other neural network | simulations were carried out to fine-tune the network | Intention inference for space targets is | crucial for space situational awareness. This paper

关键词： Intention inference | Image classification | Convolutional neural network | Astrodynamics | Satellite relative motion

摘要： convolutional neural network (1D-CNN) with a residual graph | convolutional neural network (ResGCN) to recognize PD signals | Partial discharge (PD) identification is | critical for the insulation diagnosis of cable conductors | ; however, there is still scope for enhancement in the

关键词： Partial discharge | Convolutional neural network | Graph data | Graph attention mechanism | Graph convolutional neural network

摘要： convolutional neural network (CNN) procedure is proposed to | In this paper, an efficient two-step | estimate earthquake magnitude using raw waveform data up | to only 4 s after the P wave onset. In the proposed | procedure, magnitude estimation is split into

关键词： Convolutional neural network | Earthquake magnitude estimation | Two-step procedure | Unsure response

摘要：Convolutional neural network (CNN) performs | well in several research fields and achieves high | accuracy. With the development of CNNs, various hardware | acceleration methods have been proposed. Instruction Set | Architecture (ISA) based acceleration methods are gaining

关键词： RISC-V | Variable precision | Convolutional neural network

摘要： highefficiency memristive convolutional neural network | convolutional neural networks. By integrating ResNeXt, ESCA | mechanism, and pruning algorithm, the convolutional neural | network is enhanced, significantly boosting the | issues such as excessive network parameters, gradient

关键词： Visible light positioning(VLP) | ResNeXt | ESCA | Memristor | Memristor convolutional neural network

摘要： Field (GAF) coding technique and convolutional neural | network (CNN) is proposed. The homogeneous and | In order to improve the accuracy and | generalization ability of modulated pattern recognition, a | modulation recognition method based on Gramian Angular

关键词： Modulation recognition | Convolutional neural network | IQ component | GAF coding

4008-161-200 800-990-8900

国家科技图书文献中心

摘要：-electronic fully convolutional* neural network (OP-FCNN* | With the growing influence of machine learning | , it brings benefits to the inverse problem of | imaging through scattering media in computational | imaging. This study introduces an innovative opto

摘要： convolutional neural networks (CNNs). This work introduces a | Neural Network (swCNN), inspired by small-world network | The advent of small-world network* theory has* | significantly revolutionized network* science. Small-world* | novel architecture, the Small World Convolutional

摘要： highefficiency memristive convolutional neural network | convolutional neural networks. By integrating ResNeXt, ESCA | mechanism, and pruning algorithm, the convolutional neural | network is enhanced, significantly boosting the | issues such as excessive network* parameters, gradient*