Encrypted traffic classification based on fusion of vision transformer and temporal features

Aiming at the problem that the current encrypted traffic classification methods only use the single network framework such as convolutional neural network(CNN),recurrent neural network(RNN),and stacked autoencoder(SAE),and only construct a shallow network to extract features,which leads to the low accuracy of encrypted traffic classification,an encrypted traffic classification framework based on the fusion of vision transformer and temporal features was proposed.Bottleneck transformer network(BoTNet)was used to extract spatial features and bi-directional long short-term memory(BiLSTM)was used to extract temporal features.After the two sub-networks are parallelized,the feature fusion method of early fusion was used in the framework to perform feature fusion.Finally,the encrypted traffic was identified through the fused features.The experimental results show that the BiLSTM and BoTNet fusion transformer(BTFT)model can enhance the performance of encrypted traffic classification by fusing multi-dimensional features.The accuracy rate of a virtual private network(VPN)and non-VPN binary classification is 99.9%,and the accuracy rate of fine-grained encrypted traffic twelve-classification can also reach 97%.

Deepfake Video Detection Based on Improved CapsNet and Temporal–Spatial Features

Rapid development of deepfake technology led to the spread of forged audios and videos across network platforms,presenting risks for numerous countries,societies,and individuals,and posing a serious threat to cyberspace security.To address the problem of insufficient extraction of spatial features and the fact that temporal features are not considered in the deepfake video detection,we propose a detection method based on improved CapsNet and temporal–spatial features(iCapsNet–TSF).First,the dynamic routing algorithm of CapsNet is improved using weight initialization and updating.Then,the optical flow algorithm is used to extract interframe temporal features of the videos to form a dataset of temporal–spatial features.Finally,the iCapsNet model is employed to fully learn the temporal–spatial features of facial videos,and the results are fused.Experimental results show that the detection accuracy of iCapsNet–TSF reaches 94.07%,98.83%,and 98.50%on the Celeb-DF,FaceSwap,and Deepfakes datasets,respectively,displaying a better performance than most existing mainstream algorithms.The iCapsNet–TSF method combines the capsule network and the optical flow algorithm,providing a novel strategy for the deepfake detection,which is of great significance to the prevention of deepfake attacks and the preservation of cyberspace security.

How do temporal and spectral features .matter in crop classification in Heilongjiang Province, China？

How to fully use spectral and temporal information for efficient identification of crops becomes a crucial issue since each crop has its specific seasonal dynamics. A thorough understanding on the relative usefulness of spectral and temporal features is thus essential for better organization of crop classification information. This study, taking Heilongjiang Province as the study area, aims to use time-series moderate resolution imaging spectroradiometer （MODIS） surface reflectance product （MOD09A1） data to evaluate the importance of spectral and temporal features for crop classification. In doing so, a feature selection strategy based on separability index （SI） was first used to rank the most important spectro-temporal features for crop classification. Ten feature scenarios with different spectral and temporal variable combinations were then devised, which were used for crop classification using the support vector machine and their accuracies were finally assessed with the same crop samples. The results show that the normalized difference tillage index （NDTI）, land surface water index （LSWl） and enhanced vegetation index （EVI） are the most informative spectral features and late August to early September is the most informative temporal window for identifying crops in Heilongjiang for the observed year 2011. Spectral diversity and time variety are both vital for crop classification, and their combined use can improve the accuracy by about 30% in comparison with single image. The feature selection technique based on SI analysis is superior for achieving high crop classification accuracy （producers＇ accuracy of 94.03% and users＇ accuracy of 93.77%） with a small number of features. Increasing temporal resolution is not necessarily important for improving the classification accuracies for crops, and a relatively high classification accuracy can be achieved as long as the images associated with key phenological phrases are retained.

Statistical study on the spatial - temporal distribution features of the arctic sea ice extent

On the basis of the arctic monthly mean sea ice extent data set during 1953-1984, the arctic region is divided into eight subregions,and the analyses of empirical orthogonal functions, power spectrum and maximum entropy spectrum are made to indentify the major spatial and temporal features of the sea ice fluctuations within 32-year period. And then, a brief appropriate physical explanation is tentatively suggested. The results show that both seasonal and non-seasonal variations of the sea ice extent are remarkable, and iis mean annual peripheral positions as well as their interannu-al shifting amplitudes are quite different among all subregions. These features are primarily affected by solar radiation, o-cean circulation, sea surface temperature and maritime-continental contrast, while the non-seasonal variations are most possibly affected by the cosmic-geophysical factors such as earth pole shife, earth rotation oscillation and solar activity.

西藏1971～2008年最高最低气温时空变化及分布特征(英文)

Based on temperature data of meteorological stations from 1971 to 2008 in Tibet,the temporal and spatial variation of maximum andminimum temperature in Tibet was analyzed.The results showed that both maximum temperature andminimum temperature increased distinctly,the warming amplitude of winter was the highest among the four seasons,and next came spring.The increment ofminimum temperature was visibly over that of maximum temperature,particularlyminimum temperature in winter with significant increment.For spatial variation,maximum temperature in most stations increased except particular stations,while theminimum temperature in all stations rose.In addition,the space variation law ofminimum temperature,being more obvious thanminimum temperature,increased from southeast to northwest with different spatial changes in various seasons.From decadal variation,both maximum andminimum temperature appeared increase from 1970s to the first eight years in the 21st century,and the rise ofminimum temperature was significant greater than maximum temperature.The increase of maximum andminimum temperature was the highest from 2001 to 2008,whereas the lowest in 1970s.

ANTARCTIC SEA ICE AND THE POLAR VORTEX INDEX:TEMPORAL AND SPATIAL CHARACTERISTICS AND THEIR RELATIONSHIP

The cluster analysis method has been used to divide the Antarctic sea ice variation field into 5 sectors.Then,for each of these sectors,the corresponding indexes of vortex area and vortex intensity on the 500 hPa level have been calcu- lated.These data were used to analyse the temporal and spatial characteristics of both Antarctic sea ice and the vortex index variations and their relationship.Our results show that substantial differences are presented in the climatic pattern and interannual variations of the sea ice data and vortex index in different sectors.The maximum sea ice extent varia- tions appear in sector 1 and sector 4.Oscillation periods of 2—2.5 and 5—7 years exist in the variations of sea ice extent and vortex index in most sectors.A positive trend is only found in sector 1 sea ice extent while the other sectors show negative trends.The average extent of the Antarctic sea ice as a whole has retreated at a rate of 1.6 latitudes per 100 years.The vortex areas for all sectors have decreased.Nevertheless,the vortex intensities in 3 sectors have increased.The relationship between sea ice and vortex characters in each sector is obvious,but a little complex.Sectors 1 and 5,which are located in the Southeast Pacific and South Atlantic,are the most sensitive areas in terms of sea ice/atmosphere interaction.

Discovering Cohesive Temporal Subgraphs with Temporal Density Aware Exploration

Real-world networks,such as social networks,cryptocurrency networks,and e-commerce networks,always have occurrence time of interactions between nodes.Such networks are typically modeled as temporal graphs.Mining cohesive subgraphs from temporal graphs is practical and essential in numerous data mining applications,since mining cohesive subgraphs gets insights into the time-varying nature of temporal graphs.However,existing studies on mining cohesive subgraphs,such as Densest-Exact and k-truss,are mainly tailored for static graphs(whose edges have no temporal information).Therefore,those cohesive subgraph models cannot indicate both the temporal and the structural characteristics of subgraphs.To this end,we explore the model of cohesive temporal subgraphs by incorporating both the evolving and the structural characteristics of temporal subgraphs.Unfortunately,the volume of time intervals in a temporal network is quadratic.As a result,the time complexity of mining temporal cohesive subgraphs is high.To efficiently address the problem,we first mine the temporal density distribution of temporal graphs.Guided by the distribution,we can safely prune many unqualified time intervals with the linear time cost.Then,the remaining time intervals where cohesive temporal subgraphs fall in are examined using the greedy search.The results of the experiments on nine real-world temporal graphs indicate that our model outperforms state-of-the-art solutions in efficiency and quality.Specifically,our model only takes less than two minutes on a million-vertex DBLP and has the highest overall average ranking in EDB and TC metrics.

Electrocardiogram(ECG) pattern modeling and recognition via deterministic learning

A method for electrocardiogram （ECG） pattern modeling and recognition via deterministic learning theory is presented in this paper. Instead of recognizing ECG signals beat-to-beat, each ECG signal which contains a number of heartbeats is recognized. The method is based entirely on the temporal features （i.e., the dynamics） of ECG patterns, which contains complete information of ECG patterns. A dynamical model is employed to demonstrate the method, which is capable of generating synthetic ECG signals. Based on the dynamical model, the method is shown in the following two phases： the identification （training） phase and the recognition （test） phase. In the identification phase, the dynamics of ECG patterns is accurately modeled and expressed as constant RBF neural weights through the deterministic learning. In the recognition phase, the modeling results are used for ECG pattern recognition. The main feature of the proposed method is that the dynamics of ECG patterns is accurately modeled and is used for ECG pattern recognition. Experimental studies using the Physikalisch-Technische Bundesanstalt （PTB） database are included to demonstrate the effectiveness of the approach.

Space-time video super-resolution using long-term temporal feature aggregation

Space-time video super-resolution(STVSR)serves the purpose to reconstruct high-resolution high-frame-rate videos from their low-resolution low-frame-rate counterparts.Recent approaches utilize end-to-end deep learning models to achieve STVSR.They first interpolate intermediate frame features between given frames,then perform local and global refinement among the feature sequence,and finally increase the spatial resolutions of these features.However,in the most important feature interpolation phase,they only capture spatial-temporal information from the most adjacent frame features,ignoring modelling long-term spatial-temporal correlations between multiple neighbouring frames to restore variable-speed object movements and maintain long-term motion continuity.In this paper,we propose a novel long-term temporal feature aggregation network(LTFA-Net)for STVSR.Specifically,we design a long-term mixture of experts(LTMoE)module for feature interpolation.LTMoE contains multiple experts to extract mutual and complementary spatial-temporal information from multiple consecutive adjacent frame features,which are then combined with different weights to obtain interpolation results using several gating nets.Next,we perform local and global feature refinement using the Locally-temporal Feature Comparison(LFC)module and bidirectional deformable ConvLSTM layer,respectively.Experimental results on two standard benchmarks,Adobe240 and GoPro,indicate the effectiveness and superiority of our approach over state of the art.

Facial expression recognition based on bidirectional gated recurrent units within deep residual network

Purpose-recent years,facial expression recognition has been widely used in human machine interaction,clinical medicine and safe driving.However,there is a limitation that conventional recurrent neural networks can only learn the time-series characteristics of expressions based on one-way propagation information.Design/methodology/approach-To solve such limitation,this paper proposes a novel model based on bidirectional gated recurrent unit networks(Bi-GRUs)with two-way propagations,and the theory of identity mapping residuals is adopted to effectively prevent the problem of gradient disappearance caused by the depth of the introduced network.Since the Inception-V3 network model for spatial feature extraction has too many parameters,it is prone to overfitting during training.This paper proposes a novel facial expression recognition model to add two reduction modules to reduce parameters,so as to obtain an Inception-W network with better generalization.Findings-Finally,the proposed model is pretrained to determine the best settings and selections.Then,the pretrained model is experimented on two facial expression data sets of CKþand Oulu-CASIA,and the recognition performance and efficiency are compared with the existing methods.The highest recognition rate is 99.6%,which shows that the method has good recognition accuracy in a certain range.Originality/value-By using the proposed model for the applications of facial expression,the high recognition accuracy and robust recognition results with lower time consumption will help to build more sophisticated applications in real world.