Automatic segmentation of landslides from remote sensing imagery is challenging because traditional machine learning and early CNN-based models often fail to generalize across heterogeneous landscapes,where segmentati...Automatic segmentation of landslides from remote sensing imagery is challenging because traditional machine learning and early CNN-based models often fail to generalize across heterogeneous landscapes,where segmentation maps contain sparse and fragmented landslide regions under diverse geographical conditions.To address these issues,we propose a lightweight dual-stream siamese deep learning framework that integrates optical and topographical data fusion with an adaptive decoder,guided multimodal fusion,and deep supervision.The framework is built upon the synergistic combination of cross-attention,gated fusion,and sub-pixel upsampling within a unified dual-stream architecture specifically optimized for landslide segmentation,enabling efficient context modeling and robust feature exchange between modalities.The decoder captures long-range context at deeper levels using lightweight cross-attention and refines spatial details at shallower levels through attention-gated skip fusion,enabling precise boundary delineation and fewer false positives.The gated fusion further enhances multimodal integration of optical and topographical cues,and the deep supervision stabilizes training and improves generalization.Moreover,to mitigate checkerboard artifacts,a learnable sub-pixel upsampling is devised to replace the traditional transposed convolution.Despite its compact design with fewer parameters,the model consistently outperforms state-of-the-art baselines.Experiments on two benchmark datasets,Landslide4Sense and Bijie,confirm the effectiveness of the framework.On the Bijie dataset,it achieves an F1-score of 0.9110 and an intersection over union(IoU)of 0.8839.These results highlight its potential for accurate large-scale landslide inventory mapping and real-time disaster response.The implementation is publicly available at https://github.com/mishaown/DiGATe-UNet-LandSlide-Segmentation(accessed on 3 November 2025).展开更多
As the penetration ratio of wind power in active distribution networks continues to increase,the system exhibits some characteristics such as randomness and volatility.Fast and accurate short-term wind power predictio...As the penetration ratio of wind power in active distribution networks continues to increase,the system exhibits some characteristics such as randomness and volatility.Fast and accurate short-term wind power prediction is essential for algorithms like scheduling and optimization control.Based on the spatio-temporal features of Numerical Weather Prediction(NWP)data,it proposes the WVMD_DSN(Whale Optimization Algorithm,Variational Mode Decomposition,Dual Stream Network)model.The model first applies Pearson correlation coefficient(PCC)to choose some NWP features with strong correlation to wind power to form the feature set.Then,it decomposes the feature set using Variational Mode Decomposition(VMD)to eliminate the nonstationarity and obtains Intrinsic Mode Functions(IMFs).Here Whale Optimization Algorithm(WOA)is applied to optimise the key parameters of VMD,namely the number of mode components K and penalty factor a.Finally,incorporating attention mechanism(AM),Squeeze-Excitation Network(SENet),and Bidirectional Gated Recurrent Unit(BiGRU),it constructs the dual-stream network(DSN)for short-term wind power prediction.Comparative experiments demonstrate that the WVMD_DSN model outperforms existing baseline algorithms and exhibits good generalization performance.The relevant code is available at https://github.com/ruanyuyuan/Wind-power-forecast.git(accessed on 20 August 2024).展开更多
多特征模态融合时存在噪声的叠加,而为减小模态间的差异采用的级联方式的结构也未充分利用模态间的特征信息,因此设计一种跨模态双流交替交互网络(DAINet)方法。首先,构建双流交替增强(DAE)模块,以交互双分支形式融合模态特征,并通过学...多特征模态融合时存在噪声的叠加,而为减小模态间的差异采用的级联方式的结构也未充分利用模态间的特征信息,因此设计一种跨模态双流交替交互网络(DAINet)方法。首先,构建双流交替增强(DAE)模块,以交互双分支形式融合模态特征,并通过学习模态数据的映射关系,以红外-可见光-红外(IR-VIS-IR)和可见光-红外-可见光(VIS-IR-VIS)的双向反馈调节实现模态间噪声的交叉抑制;然后,构建跨模态特征交互(CMFI)模块,并引入残差结构将红外-可见光模态内以及模态间的低层特征和高层特征进行有效融合,从而减小模态间的差异并充分利用模态间的特征信息;最后,在自建红外-可见光多模态台风数据集及RGB-NIR多模态公开场景数据集上进行实验,以验证DAE模块和CMFI模块的有效性。实验结果表明,与简单级联融合方法相比,所提的基于DAINet的特征融合方法在自建台风数据集上的红外模态和可见光模态上的总体分类精度分别提高了6.61和3.93个百分点,G-mean值分别提高了6.24和2.48个百分点,表明所提方法在类别不均衡分类任务上的通用性;所提方法在RGB-NIR数据集上的2种测试模态下的总体分类精度分别提高了13.47和13.90个百分点。同时,所提方法在2个数据集上分别与IFCNN(general Image Fusion framework based on Convolutional Neural Network)和DenseFuse方法进行对比的实验结果表明,所提方法在自建台风数据集上的2种测试模态下的总体分类精度分别提高了9.82、6.02和17.38、1.68个百分点。展开更多
针对校园网络安全入侵检测中存在的复杂网络流量模式识别困难和实时响应能力不足的问题,提出一种基于双流金字塔增强策略的深度可分离卷积网络(DSCN)模型,以优化校园网络安全入侵检测与响应系统。该模型通过双流结构融合低分辨率与高分...针对校园网络安全入侵检测中存在的复杂网络流量模式识别困难和实时响应能力不足的问题,提出一种基于双流金字塔增强策略的深度可分离卷积网络(DSCN)模型,以优化校园网络安全入侵检测与响应系统。该模型通过双流结构融合低分辨率与高分辨率路径的多尺度信息,显著提升其对复杂网络流量模式的识别能力,同时深度可分离卷积(DSC)通过分解卷积操作,有效降低模型的计算复杂度,进而提升系统的实时响应能力。将该模型在KDD Cup 1999、CICIDS 2017、CICIDS 2021和UNSW-NB15数据集上进行验证,结果表明,该模型在入侵检测率、误报率、响应时间等多项指标上表现优异,为校园网络安全防护提供了一种高效的技术解决方案。展开更多
基金funded by the National Natural Science Foundation of China,grant number 62262045the Fundamental Research Funds for the Central Universities,grant number 2023CDJYGRH-YB11the Open Funding of SUGON Industrial Control and Security Center,grant number CUIT-SICSC-2025-03.
文摘Automatic segmentation of landslides from remote sensing imagery is challenging because traditional machine learning and early CNN-based models often fail to generalize across heterogeneous landscapes,where segmentation maps contain sparse and fragmented landslide regions under diverse geographical conditions.To address these issues,we propose a lightweight dual-stream siamese deep learning framework that integrates optical and topographical data fusion with an adaptive decoder,guided multimodal fusion,and deep supervision.The framework is built upon the synergistic combination of cross-attention,gated fusion,and sub-pixel upsampling within a unified dual-stream architecture specifically optimized for landslide segmentation,enabling efficient context modeling and robust feature exchange between modalities.The decoder captures long-range context at deeper levels using lightweight cross-attention and refines spatial details at shallower levels through attention-gated skip fusion,enabling precise boundary delineation and fewer false positives.The gated fusion further enhances multimodal integration of optical and topographical cues,and the deep supervision stabilizes training and improves generalization.Moreover,to mitigate checkerboard artifacts,a learnable sub-pixel upsampling is devised to replace the traditional transposed convolution.Despite its compact design with fewer parameters,the model consistently outperforms state-of-the-art baselines.Experiments on two benchmark datasets,Landslide4Sense and Bijie,confirm the effectiveness of the framework.On the Bijie dataset,it achieves an F1-score of 0.9110 and an intersection over union(IoU)of 0.8839.These results highlight its potential for accurate large-scale landslide inventory mapping and real-time disaster response.The implementation is publicly available at https://github.com/mishaown/DiGATe-UNet-LandSlide-Segmentation(accessed on 3 November 2025).
基金the Science and Technology Project of State Grid Corporation of China under Grant 5400-202117142A-0-0-00the National Natural Science Foundation of China under Grant 62372242.
文摘As the penetration ratio of wind power in active distribution networks continues to increase,the system exhibits some characteristics such as randomness and volatility.Fast and accurate short-term wind power prediction is essential for algorithms like scheduling and optimization control.Based on the spatio-temporal features of Numerical Weather Prediction(NWP)data,it proposes the WVMD_DSN(Whale Optimization Algorithm,Variational Mode Decomposition,Dual Stream Network)model.The model first applies Pearson correlation coefficient(PCC)to choose some NWP features with strong correlation to wind power to form the feature set.Then,it decomposes the feature set using Variational Mode Decomposition(VMD)to eliminate the nonstationarity and obtains Intrinsic Mode Functions(IMFs).Here Whale Optimization Algorithm(WOA)is applied to optimise the key parameters of VMD,namely the number of mode components K and penalty factor a.Finally,incorporating attention mechanism(AM),Squeeze-Excitation Network(SENet),and Bidirectional Gated Recurrent Unit(BiGRU),it constructs the dual-stream network(DSN)for short-term wind power prediction.Comparative experiments demonstrate that the WVMD_DSN model outperforms existing baseline algorithms and exhibits good generalization performance.The relevant code is available at https://github.com/ruanyuyuan/Wind-power-forecast.git(accessed on 20 August 2024).
文摘多特征模态融合时存在噪声的叠加,而为减小模态间的差异采用的级联方式的结构也未充分利用模态间的特征信息,因此设计一种跨模态双流交替交互网络(DAINet)方法。首先,构建双流交替增强(DAE)模块,以交互双分支形式融合模态特征,并通过学习模态数据的映射关系,以红外-可见光-红外(IR-VIS-IR)和可见光-红外-可见光(VIS-IR-VIS)的双向反馈调节实现模态间噪声的交叉抑制;然后,构建跨模态特征交互(CMFI)模块,并引入残差结构将红外-可见光模态内以及模态间的低层特征和高层特征进行有效融合,从而减小模态间的差异并充分利用模态间的特征信息;最后,在自建红外-可见光多模态台风数据集及RGB-NIR多模态公开场景数据集上进行实验,以验证DAE模块和CMFI模块的有效性。实验结果表明,与简单级联融合方法相比,所提的基于DAINet的特征融合方法在自建台风数据集上的红外模态和可见光模态上的总体分类精度分别提高了6.61和3.93个百分点,G-mean值分别提高了6.24和2.48个百分点,表明所提方法在类别不均衡分类任务上的通用性;所提方法在RGB-NIR数据集上的2种测试模态下的总体分类精度分别提高了13.47和13.90个百分点。同时,所提方法在2个数据集上分别与IFCNN(general Image Fusion framework based on Convolutional Neural Network)和DenseFuse方法进行对比的实验结果表明,所提方法在自建台风数据集上的2种测试模态下的总体分类精度分别提高了9.82、6.02和17.38、1.68个百分点。
文摘针对校园网络安全入侵检测中存在的复杂网络流量模式识别困难和实时响应能力不足的问题,提出一种基于双流金字塔增强策略的深度可分离卷积网络(DSCN)模型,以优化校园网络安全入侵检测与响应系统。该模型通过双流结构融合低分辨率与高分辨率路径的多尺度信息,显著提升其对复杂网络流量模式的识别能力,同时深度可分离卷积(DSC)通过分解卷积操作,有效降低模型的计算复杂度,进而提升系统的实时响应能力。将该模型在KDD Cup 1999、CICIDS 2017、CICIDS 2021和UNSW-NB15数据集上进行验证,结果表明,该模型在入侵检测率、误报率、响应时间等多项指标上表现优异,为校园网络安全防护提供了一种高效的技术解决方案。
