In response to the scarcity of infrared aircraft samples and the tendency of traditional deep learning to overfit,a few-shot infrared aircraft classification method based on cross-correlation networks is proposed.This...In response to the scarcity of infrared aircraft samples and the tendency of traditional deep learning to overfit,a few-shot infrared aircraft classification method based on cross-correlation networks is proposed.This method combines two core modules:a simple parameter-free self-attention and cross-attention.By analyzing the self-correlation and cross-correlation between support images and query images,it achieves effective classification of infrared aircraft under few-shot conditions.The proposed cross-correlation network integrates these two modules and is trained in an end-to-end manner.The simple parameter-free self-attention is responsible for extracting the internal structure of the image while the cross-attention can calculate the cross-correlation between images further extracting and fusing the features between images.Compared with existing few-shot infrared target classification models,this model focuses on the geometric structure and thermal texture information of infrared images by modeling the semantic relevance between the features of the support set and query set,thus better attending to the target objects.Experimental results show that this method outperforms existing infrared aircraft classification methods in various classification tasks,with the highest classification accuracy improvement exceeding 3%.In addition,ablation experiments and comparative experiments also prove the effectiveness of the method.展开更多
Load forecasting is of great significance to the development of new power systems.With the advancement of smart grids,the integration and distribution of distributed renewable energy sources and power electronics devi...Load forecasting is of great significance to the development of new power systems.With the advancement of smart grids,the integration and distribution of distributed renewable energy sources and power electronics devices have made power load data increasingly complex and volatile.This places higher demands on the prediction and analysis of power loads.In order to improve the prediction accuracy of short-term power load,a CNN-BiLSTMTPA short-term power prediction model based on the Improved Whale Optimization Algorithm(IWOA)with mixed strategies was proposed.Firstly,the model combined the Convolutional Neural Network(CNN)with the Bidirectional Long Short-Term Memory Network(BiLSTM)to fully extract the spatio-temporal characteristics of the load data itself.Then,the Temporal Pattern Attention(TPA)mechanism was introduced into the CNN-BiLSTM model to automatically assign corresponding weights to the hidden states of the BiLSTM.This allowed the model to differentiate the importance of load sequences at different time intervals.At the same time,in order to solve the problem of the difficulties of selecting the parameters of the temporal model,and the poor global search ability of the whale algorithm,which is easy to fall into the local optimization,the whale algorithm(IWOA)was optimized by using the hybrid strategy of Tent chaos mapping and Levy flight strategy,so as to better search the parameters of the model.In this experiment,the real load data of a region in Zhejiang was taken as an example to analyze,and the prediction accuracy(R2)of the proposed method reached 98.83%.Compared with the prediction models such as BP,WOA-CNN-BiLSTM,SSA-CNN-BiLSTM,CNN-BiGRU-Attention,etc.,the experimental results showed that the model proposed in this study has a higher prediction accuracy.展开更多
Satellite communication systems are facing serious electromagnetic interference,and interference signal recognition is a crucial foundation for targeted anti-interference.In this paper,we propose a novel interference ...Satellite communication systems are facing serious electromagnetic interference,and interference signal recognition is a crucial foundation for targeted anti-interference.In this paper,we propose a novel interference recognition algorithm called HDCGD-CBAM,which adopts the time-frequency images(TFIs)of signals to effectively extract the temporal and spectral characteristics.In the proposed method,we improve the Convolutional Long Short-Term Memory Deep Neural Network(CLDNN)in two ways.First,the simpler Gate Recurrent Unit(GRU)is used instead of the Long Short-Term Memory(LSTM),reducing model parameters while maintaining the recognition accuracy.Second,we replace convolutional layers with hybrid dilated convolution(HDC)to expand the receptive field of feature maps,which captures the correlation of time-frequency data on a larger spatial scale.Additionally,Convolutional Block Attention Module(CBAM)is introduced before and after the HDC layers to strengthen the extraction of critical features and improve the recognition performance.The experiment results show that the HDCGD-CBAM model significantly outper-forms existing methods in terms of recognition accuracy and complexity.When Jamming-to-Signal Ratio(JSR)varies from-30dB to 10dB,it achieves an average accuracy of 78.7%and outperforms the CLDNN by 7.29%while reducing the Floating Point Operations(FLOPs)by 79.8%to 114.75M.Moreover,the proposed model has fewer parameters with 301k compared to several state-of-the-art methods.展开更多
针对现有交通监控场景下车辆目标检测算法参数多、计算量大,难以在资源有限的设备中部署的问题,提出一种基于YOLOv8改进的轻量型车辆目标检测算法GSE-YOLO。结合Ghost卷积技术,设计出一种轻量型特征提取模块C2fGhostv2,在减少计算负担...针对现有交通监控场景下车辆目标检测算法参数多、计算量大,难以在资源有限的设备中部署的问题,提出一种基于YOLOv8改进的轻量型车辆目标检测算法GSE-YOLO。结合Ghost卷积技术,设计出一种轻量型特征提取模块C2fGhostv2,在减少计算负担的同时保证良好的特征提取能力。在颈部网络,引入SA(shu ffl e attention)注意力机制,主动选择合适的特征图权重凸显重要特征信息,减少背景对车辆检测的干扰。引入新的损失函数EIOU,解决边界框的纵横比模糊问题,提高预测框精度。实验结果表明,在交通数据集UA-DETRAC上,GSE-YOLO在检测精度没有损失的情况下,相较于原始YOLOv8参数量降低36.11%,计算量降低29.21%,更适合在计算量有限的边缘设备上部署,具有实用价值。展开更多
In recent years,many unknown protocols are constantly emerging,and they bring severe challenges to network security and network management.Existing unknown protocol recognition methods suffer from weak feature extract...In recent years,many unknown protocols are constantly emerging,and they bring severe challenges to network security and network management.Existing unknown protocol recognition methods suffer from weak feature extraction ability,and they cannot mine the discriminating features of the protocol data thoroughly.To address the issue,we propose an unknown application layer protocol recognition method based on deep clustering.Deep clustering which consists of the deep neural network and the clustering algorithm can automatically extract the features of the input and cluster the data based on the extracted features.Compared with the traditional clustering methods,deep clustering boasts of higher clustering accuracy.The proposed method utilizes network-in-network(NIN),channel attention,spatial attention and Bidirectional Long Short-term memory(BLSTM)to construct an autoencoder to extract the spatial-temporal features of the protocol data,and utilizes the unsupervised clustering algorithm to recognize the unknown protocols based on the features.The method firstly extracts the application layer protocol data from the network traffic and transforms the data into one-dimensional matrix.Secondly,the autoencoder is pretrained,and the protocol data is compressed into low dimensional latent space by the autoencoder and the initial clustering is performed with K-Means.Finally,the clustering loss is calculated and the classification model is optimized according to the clustering loss.The classification results can be obtained when the classification model is optimal.Compared with the existing unknown protocol recognition methods,the proposed method utilizes deep clustering to cluster the unknown protocols,and it can mine the key features of the protocol data and recognize the unknown protocols accurately.Experimental results show that the proposed method can effectively recognize the unknown protocols,and its performance is better than other methods.展开更多
基金Supported by the National Pre-research Program during the 14th Five-Year Plan(514010405)。
文摘In response to the scarcity of infrared aircraft samples and the tendency of traditional deep learning to overfit,a few-shot infrared aircraft classification method based on cross-correlation networks is proposed.This method combines two core modules:a simple parameter-free self-attention and cross-attention.By analyzing the self-correlation and cross-correlation between support images and query images,it achieves effective classification of infrared aircraft under few-shot conditions.The proposed cross-correlation network integrates these two modules and is trained in an end-to-end manner.The simple parameter-free self-attention is responsible for extracting the internal structure of the image while the cross-attention can calculate the cross-correlation between images further extracting and fusing the features between images.Compared with existing few-shot infrared target classification models,this model focuses on the geometric structure and thermal texture information of infrared images by modeling the semantic relevance between the features of the support set and query set,thus better attending to the target objects.Experimental results show that this method outperforms existing infrared aircraft classification methods in various classification tasks,with the highest classification accuracy improvement exceeding 3%.In addition,ablation experiments and comparative experiments also prove the effectiveness of the method.
文摘Load forecasting is of great significance to the development of new power systems.With the advancement of smart grids,the integration and distribution of distributed renewable energy sources and power electronics devices have made power load data increasingly complex and volatile.This places higher demands on the prediction and analysis of power loads.In order to improve the prediction accuracy of short-term power load,a CNN-BiLSTMTPA short-term power prediction model based on the Improved Whale Optimization Algorithm(IWOA)with mixed strategies was proposed.Firstly,the model combined the Convolutional Neural Network(CNN)with the Bidirectional Long Short-Term Memory Network(BiLSTM)to fully extract the spatio-temporal characteristics of the load data itself.Then,the Temporal Pattern Attention(TPA)mechanism was introduced into the CNN-BiLSTM model to automatically assign corresponding weights to the hidden states of the BiLSTM.This allowed the model to differentiate the importance of load sequences at different time intervals.At the same time,in order to solve the problem of the difficulties of selecting the parameters of the temporal model,and the poor global search ability of the whale algorithm,which is easy to fall into the local optimization,the whale algorithm(IWOA)was optimized by using the hybrid strategy of Tent chaos mapping and Levy flight strategy,so as to better search the parameters of the model.In this experiment,the real load data of a region in Zhejiang was taken as an example to analyze,and the prediction accuracy(R2)of the proposed method reached 98.83%.Compared with the prediction models such as BP,WOA-CNN-BiLSTM,SSA-CNN-BiLSTM,CNN-BiGRU-Attention,etc.,the experimental results showed that the model proposed in this study has a higher prediction accuracy.
基金This work was supported by the Beijing Natural Science Foundation(L202003).
文摘Satellite communication systems are facing serious electromagnetic interference,and interference signal recognition is a crucial foundation for targeted anti-interference.In this paper,we propose a novel interference recognition algorithm called HDCGD-CBAM,which adopts the time-frequency images(TFIs)of signals to effectively extract the temporal and spectral characteristics.In the proposed method,we improve the Convolutional Long Short-Term Memory Deep Neural Network(CLDNN)in two ways.First,the simpler Gate Recurrent Unit(GRU)is used instead of the Long Short-Term Memory(LSTM),reducing model parameters while maintaining the recognition accuracy.Second,we replace convolutional layers with hybrid dilated convolution(HDC)to expand the receptive field of feature maps,which captures the correlation of time-frequency data on a larger spatial scale.Additionally,Convolutional Block Attention Module(CBAM)is introduced before and after the HDC layers to strengthen the extraction of critical features and improve the recognition performance.The experiment results show that the HDCGD-CBAM model significantly outper-forms existing methods in terms of recognition accuracy and complexity.When Jamming-to-Signal Ratio(JSR)varies from-30dB to 10dB,it achieves an average accuracy of 78.7%and outperforms the CLDNN by 7.29%while reducing the Floating Point Operations(FLOPs)by 79.8%to 114.75M.Moreover,the proposed model has fewer parameters with 301k compared to several state-of-the-art methods.
文摘针对现有交通监控场景下车辆目标检测算法参数多、计算量大,难以在资源有限的设备中部署的问题,提出一种基于YOLOv8改进的轻量型车辆目标检测算法GSE-YOLO。结合Ghost卷积技术,设计出一种轻量型特征提取模块C2fGhostv2,在减少计算负担的同时保证良好的特征提取能力。在颈部网络,引入SA(shu ffl e attention)注意力机制,主动选择合适的特征图权重凸显重要特征信息,减少背景对车辆检测的干扰。引入新的损失函数EIOU,解决边界框的纵横比模糊问题,提高预测框精度。实验结果表明,在交通数据集UA-DETRAC上,GSE-YOLO在检测精度没有损失的情况下,相较于原始YOLOv8参数量降低36.11%,计算量降低29.21%,更适合在计算量有限的边缘设备上部署,具有实用价值。
基金This work is supported by the National Key R&D Program of China(2017YFB0802900).
文摘In recent years,many unknown protocols are constantly emerging,and they bring severe challenges to network security and network management.Existing unknown protocol recognition methods suffer from weak feature extraction ability,and they cannot mine the discriminating features of the protocol data thoroughly.To address the issue,we propose an unknown application layer protocol recognition method based on deep clustering.Deep clustering which consists of the deep neural network and the clustering algorithm can automatically extract the features of the input and cluster the data based on the extracted features.Compared with the traditional clustering methods,deep clustering boasts of higher clustering accuracy.The proposed method utilizes network-in-network(NIN),channel attention,spatial attention and Bidirectional Long Short-term memory(BLSTM)to construct an autoencoder to extract the spatial-temporal features of the protocol data,and utilizes the unsupervised clustering algorithm to recognize the unknown protocols based on the features.The method firstly extracts the application layer protocol data from the network traffic and transforms the data into one-dimensional matrix.Secondly,the autoencoder is pretrained,and the protocol data is compressed into low dimensional latent space by the autoencoder and the initial clustering is performed with K-Means.Finally,the clustering loss is calculated and the classification model is optimized according to the clustering loss.The classification results can be obtained when the classification model is optimal.Compared with the existing unknown protocol recognition methods,the proposed method utilizes deep clustering to cluster the unknown protocols,and it can mine the key features of the protocol data and recognize the unknown protocols accurately.Experimental results show that the proposed method can effectively recognize the unknown protocols,and its performance is better than other methods.
