NSTL国家科技图书文献中心

1. A time-aware developer recommendation approach based on multi-feature fusion NSTL国家科技图书文献中心

Zhang, Lu | Chen, Shizhan ... - 《Applied Soft Computing》 - 2025,169 - 共12页

摘要： approach based on multi-feature* fusion, called TFRec. We* | Recommending developers suitable for Pull | Requests (PRs) review holds paramount importance in | facilitating evolution and knowledge sharing on GitHub | . Current researches primarily focus on modeling developer

关键词： Developer recommendation | Pull request review | Time-aware attention | Multi-feature fusion | High-order propagation

2. PM_(2.5) Concentration Prediction Using CNN-LSTM Model Based on Multi-Feature Fusion NSTL国家科技图书文献中心

ZhiwenWang | Jiexia Huang ... - 《Concurrency and computation: practice and experience》 - 2025,37(4/5) - e8391.1～e8391.18 - 共18页

摘要： combined prediction model based on multi-feature fusion | accuracy of CNN-LSTM model based on multi-feature fusion | has good feature* extraction ability and strong* | In order to solve the problem that the | existing PM_(2.5) concentration prediction methods ignore

关键词： CNN-LSTM combined forecasting model | maximum information coefficient | multi-feature fusion | PM_(2.5) concentration | spatial characteristic factor of PM_(2.5) concentration

3. Multi-feature fusion target recognition method based on forward-looking dual linear array scanning laser fuze NSTL国家科技图书文献中心

Guo, Jiachong | Liu, Xing ... - 《Optics & Laser Technology》 - 2025,181(Pt.B) - 共14页

摘要： features of the target. Additionally, a multi-feature | field, a multi-line laser scanning target size | information fusion* method is proposed, enabling the* | multi-line laser target echo signal. In addition, the | impact of different combinations of fusion* features*

关键词： Forward looking two-line array scanning | Laser fuze | Size calculation | Contour feature | Multi-feature fusion

4. MFR-Net: A multi-feature fusion phase unwrapping method for different speckle noises NSTL国家科技图书文献中心

Liu, Yun | Kang, Qi ... - 《Optics and Lasers in Engineering》 - 2025,184(Jan. Pt.1) - 1.1～1.11 - 共11页

摘要： subsequent measurement accuracy, a multi-feature fusion | is composed of a front-end multi-module filter | Phase unwrapping is a crucial step in laser | interferometry for obtaining accurate physical measurement of | object. To reduce the impact of speckle noise on

关键词： Phase unwrapping | Speckle noise | Neural network | Multi-feature fusion | QUALITY | SEGMENTATION

5. AM-MFF: A multi-feature fusion framework based on attention mechanism for robust and interpretable lithium-ion battery state of health estimation NSTL国家科技图书文献中心

Chen S.-Z. | Liu J.... - 《Applied energy》 - 2025,381(Mar.1) - 1.1～1.21 - 共21页

摘要： proposes a multi-feature* fusion framework based on* | . Subsequently, an AM-based feature* fusion (AMFF) module is* | between features, facilitating efficient multi-feature | multidimensional feature-based methods fail to fully utilise the | fusion. The attention scores from the AMFF module

关键词： Attention mechanism | Interpretability | Lithium-ion battery | Multi-feature fusion | Robustness | State of health

6. Electricity behaviors anomaly detection based on multi-feature fusion and contrastive learning NSTL国家科技图书文献中心

Guan Y. | Shi Y.... - 《Information systems》 - 2025,127(Jan.) - 1.1～1.10 - 共10页

摘要： based on multi-feature* fusion and contrastive learning* | detection. In terms of temporal feature* representation* | of spatial feature* representation learning, GCN and* | , this paper also designs a gated fusion* module and* | © 2024 Elsevier LtdAbnormal electricity usage

关键词： Anomaly detection | Contrastive learning | Electricity data | Gated fusion | Missing value completion

7. Embedded feature fusion for multi-view multi-label feature selection NSTL国家科技图书文献中心

Hao, Pingting | Gao, Wanfu ... - 《Pattern Recognition》 - 2025,157 - 共11页

摘要： aspects, which are the feature* fusion between views and* | , multi-view multi-label learning (MVML) has garnered | embedded feature* selection model that combines with two* | feature enhancement. Firstly, we calculate the adaptive | relations, and integrate it into one unified feature

关键词： Multi-view learning | Multi-label learning | Feature selection | Feature fusion

8. One-step multi-view spectral clustering based on multi-feature similarity fusion NSTL国家科技图书文献中心

Kong, Dezheng | Zhou, Shuisheng ... - 《Signal Processing》 - 2025,227 - 共13页

摘要： or multi-feature* fusion, and then uses the k-means* | of graph fusion* and multi-feature fusion have not* | conducts graph learning, multi-feature similarity fusion | -feature* similarity fusion. This model simultaneously* | Multi-view clustering has attracted increasing

关键词： Spectral clustering | Multi-feature similarity fusion | One-step | Graph theory

9. Reconstruction method of 128 x 256 array single photon Lidar based on multi-domain stability feature fusion NSTL国家科技图书文献中心

Ma, Le | Sun, Jianfeng ... - 《Optics & Laser Technology》 - 2025,181(Pt.B) - 共9页

摘要： method based on multi-domain stability feature fusion | suppressing background noise through the fusion* of stable* | features. Additionally, the Multi-scale Algorithm (MSA | Under low-light conditions, random light | distribution and non-uniform pixel sensitivity reduce both

关键词： 128x256 array single photon Lidar | Noise suppression | Multi-feature fusion

10. Enhancing Motor Imagery Classification with Residual Graph Convolutional Networks and Multi-Feature Fusion NSTL国家科技图书文献中心

Xu, Fangzhou | Shi, Weiyou ... - 《International Journal of Neural Systems》 - 2025,35(1) - 共21页

摘要： analysis and feature* encoding, it was established that* | Stroke, an abrupt cerebrovascular ailment | resulting in brain tissue damage, has prompted the | adoption of motor imagery (MI)-based brain-computer | interface (BCI) systems in stroke rehabilitation. However

摘要： approach based on multi-feature* fusion, called TFRec. We* | Recommending developers suitable for Pull | Requests (PRs) review holds paramount importance in | facilitating evolution and knowledge sharing on GitHub | . Current researches primarily focus on modeling developer

关键词： Developer recommendation | Pull request review | Time-aware attention | Multi-feature fusion | High-order propagation

摘要： combined prediction model based on multi-feature fusion | accuracy of CNN-LSTM model based on multi-feature fusion | has good feature* extraction ability and strong* | In order to solve the problem that the | existing PM_(2.5) concentration prediction methods ignore

关键词： CNN-LSTM combined forecasting model | maximum information coefficient | multi-feature fusion | PM_(2.5) concentration | spatial characteristic factor of PM_(2.5) concentration

摘要： features of the target. Additionally, a multi-feature | field, a multi-line laser scanning target size | information fusion* method is proposed, enabling the* | multi-line laser target echo signal. In addition, the | impact of different combinations of fusion* features*

关键词： Forward looking two-line array scanning | Laser fuze | Size calculation | Contour feature | Multi-feature fusion

摘要： subsequent measurement accuracy, a multi-feature fusion | is composed of a front-end multi-module filter | Phase unwrapping is a crucial step in laser | interferometry for obtaining accurate physical measurement of | object. To reduce the impact of speckle noise on

关键词： Phase unwrapping | Speckle noise | Neural network | Multi-feature fusion | QUALITY | SEGMENTATION

关键词： Attention mechanism | Interpretability | Lithium-ion battery | Multi-feature fusion | Robustness | State of health

摘要： based on multi-feature* fusion and contrastive learning* | detection. In terms of temporal feature* representation* | of spatial feature* representation learning, GCN and* | , this paper also designs a gated fusion* module and* | © 2024 Elsevier LtdAbnormal electricity usage

关键词： Anomaly detection | Contrastive learning | Electricity data | Gated fusion | Missing value completion

摘要： aspects, which are the feature* fusion between views and* | , multi-view multi-label learning (MVML) has garnered | embedded feature* selection model that combines with two* | feature enhancement. Firstly, we calculate the adaptive | relations, and integrate it into one unified feature

关键词： Multi-view learning | Multi-label learning | Feature selection | Feature fusion

摘要： or multi-feature* fusion, and then uses the k-means* | of graph fusion* and multi-feature fusion have not* | conducts graph learning, multi-feature similarity fusion | -feature* similarity fusion. This model simultaneously* | Multi-view clustering has attracted increasing

关键词： Spectral clustering | Multi-feature similarity fusion | One-step | Graph theory

摘要： method based on multi-domain stability feature fusion | suppressing background noise through the fusion* of stable* | features. Additionally, the Multi-scale Algorithm (MSA | Under low-light conditions, random light | distribution and non-uniform pixel sensitivity reduce both

关键词： 128x256 array single photon Lidar | Noise suppression | Multi-feature fusion

摘要： analysis and feature* encoding, it was established that* | Stroke, an abrupt cerebrovascular ailment | resulting in brain tissue damage, has prompted the | adoption of motor imagery (MI)-based brain-computer | interface (BCI) systems in stroke rehabilitation. However

关键词： Brain network | modified residual graph convolutional network | modified S -transform | self-attention mechanism | stroke

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： approach based on multi-feature fusion, called TFRec. We | Recommending developers suitable for Pull | Requests (PRs) review holds paramount importance in | facilitating evolution and knowledge sharing on GitHub | . Current researches primarily focus on modeling developer

关键词： Developer recommendation | Pull request review | Time-aware attention | Multi-feature fusion | High-order propagation

摘要： combined prediction model based on multi-feature fusion | accuracy of CNN-LSTM model based on multi-feature fusion | has good feature extraction ability and strong | In order to solve the problem that the | existing PM_(2.5) concentration prediction methods ignore

关键词： CNN-LSTM combined forecasting model | maximum information coefficient | multi-feature fusion | PM_(2.5) concentration | spatial characteristic factor of PM_(2.5) concentration

摘要： features of the target. Additionally, a multi-feature | field, a multi-line laser scanning target size | information fusion method is proposed, enabling the | multi-line laser target echo signal. In addition, the | impact of different combinations of fusion features

关键词： Forward looking two-line array scanning | Laser fuze | Size calculation | Contour feature | Multi-feature fusion

摘要： subsequent measurement accuracy, a multi-feature fusion | is composed of a front-end multi-module filter | Phase unwrapping is a crucial step in laser | interferometry for obtaining accurate physical measurement of | object. To reduce the impact of speckle noise on

关键词： Phase unwrapping | Speckle noise | Neural network | Multi-feature fusion | QUALITY | SEGMENTATION

摘要： proposes a multi-feature fusion framework based on | . Subsequently, an AM-based feature fusion (AMFF) module is | between features, facilitating efficient multi-feature | multidimensional feature-based methods fail to fully utilise the | fusion. The attention scores from the AMFF module

关键词： Attention mechanism | Interpretability | Lithium-ion battery | Multi-feature fusion | Robustness | State of health

摘要： based on multi-feature fusion and contrastive learning | detection. In terms of temporal feature representation | of spatial feature representation learning, GCN and | , this paper also designs a gated fusion module and | © 2024 Elsevier LtdAbnormal electricity usage

关键词： Anomaly detection | Contrastive learning | Electricity data | Gated fusion | Missing value completion

摘要： aspects, which are the feature fusion between views and | , multi-view multi-label learning (MVML) has garnered | embedded feature selection model that combines with two | feature enhancement. Firstly, we calculate the adaptive | relations, and integrate it into one unified feature

关键词： Multi-view learning | Multi-label learning | Feature selection | Feature fusion

摘要： or multi-feature fusion, and then uses the k-means | of graph fusion and multi-feature fusion have not | conducts graph learning, multi-feature similarity fusion | -feature similarity fusion. This model simultaneously | Multi-view clustering has attracted increasing

关键词： Spectral clustering | Multi-feature similarity fusion | One-step | Graph theory

摘要： method based on multi-domain stability feature fusion | suppressing background noise through the fusion of stable | features. Additionally, the Multi-scale Algorithm (MSA | Under low-light conditions, random light | distribution and non-uniform pixel sensitivity reduce both

关键词： 128x256 array single photon Lidar | Noise suppression | Multi-feature fusion

摘要： analysis and feature encoding, it was established that | Stroke, an abrupt cerebrovascular ailment | resulting in brain tissue damage, has prompted the | adoption of motor imagery (MI)-based brain-computer | interface (BCI) systems in stroke rehabilitation. However

关键词： Brain network | modified residual graph convolutional network | modified S -transform | self-attention mechanism | stroke

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： approach based on multi-feature* fusion, called TFRec. We* | Recommending developers suitable for Pull | Requests (PRs) review holds paramount importance in | facilitating evolution and knowledge sharing on GitHub | . Current researches primarily focus on modeling developer

摘要： combined prediction model based on multi-feature fusion | accuracy of CNN-LSTM model based on multi-feature fusion | has good feature* extraction ability and strong* | In order to solve the problem that the | existing PM_(2.5) concentration prediction methods ignore

摘要： features of the target. Additionally, a multi-feature | field, a multi-line laser scanning target size | information fusion* method is proposed, enabling the* | multi-line laser target echo signal. In addition, the | impact of different combinations of fusion* features*

摘要： based on multi-feature* fusion and contrastive learning* | detection. In terms of temporal feature* representation* | of spatial feature* representation learning, GCN and* | , this paper also designs a gated fusion* module and* | © 2024 Elsevier LtdAbnormal electricity usage

摘要： aspects, which are the feature* fusion between views and* | , multi-view multi-label learning (MVML) has garnered | embedded feature* selection model that combines with two* | feature enhancement. Firstly, we calculate the adaptive | relations, and integrate it into one unified feature

摘要： or multi-feature* fusion, and then uses the k-means* | of graph fusion* and multi-feature fusion have not* | conducts graph learning, multi-feature similarity fusion | -feature* similarity fusion. This model simultaneously* | Multi-view clustering has attracted increasing

摘要： method based on multi-domain stability feature fusion | suppressing background noise through the fusion* of stable* | features. Additionally, the Multi-scale Algorithm (MSA | Under low-light conditions, random light | distribution and non-uniform pixel sensitivity reduce both

摘要： analysis and feature* encoding, it was established that* | Stroke, an abrupt cerebrovascular ailment | resulting in brain tissue damage, has prompted the | adoption of motor imagery (MI)-based brain-computer | interface (BCI) systems in stroke rehabilitation. However