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.

A Temporal–Spatial Atlas of Peripheral Nerve Evoked Cortex Potential in Rat:A Novel Testbed to Explore the Responding Patterns of the Brain to Peripheral Nerves

Observing the dynamic progress of the brain in response to peripheral nerve stimulation as a whole is the basis for a deeper understanding of overall brain function;however,it remains a great challenge.In this work,a novel mini-invasive orthogonal recording method is developed to observe the overall evoked cortex potential(ECP)in rat brain.A typical ECP atlas with recognizable waveforms in the rat cortex corresponding to the median,ulnar,and radial nerve trunks and subdivided branches is acquired.Reproducible exciting temporal–spatial progress in the rat brain is obtained and visualized for the first time.Changes in the ECPs and exciting sequences in the cortex four months after median nerve transection are also observed.The results suggest that the brain’s response to peripheral stimulation has precise and reproducible temporal–spatial properties.This resource can serve as a testbed to explore the overall functional interaction and dynamic remodeling mechanisms between the peripheral and central nervous systems over time.

Spatial and temporal evolution of electromagnetic pulses from solid target irradiated with multi-hundred-terawatt laser pulse inside target chamber

Giant electromagnetic pulses(EMPs) induced by high-power laser irradiating solid targets interfere with various experimental diagnoses and even damage equipment,so unveiling the evolution of EMPs inside the laser chamber is crucial for designing effective EMP shielding.In this work,the transmission characteristics of EMPs as a function of distances from the target chamber center(TCC) are studied using B-dot probes.The mean EMP amplitude generated by picosecond laser-target interaction reaches 561 kV m^(-1),357 kV m^(-1),395 kV m^(-1),and 341 kV m^(-1)at 0.32 m,0.53 m,0.76 m,and 1 m from TCC,which decreases dramatically from 0.32 m to 0.53 m.However,it shows a fluctuation from 0.53 m to 1 m.The temporal features of EMPs indicate that time-domain EMP signals near the target chamber wall have a wider full width at half maximum compared to that close to TCC,mainly due to the echo oscillation of electromagnetic waves inside the target chamber based on simulation and experimentation.The conclusions of this study will provide a new approach to mitigate strong electromagnetic pulses by decreasing the echo oscillation of electromagnetic waves inside the target chamber during laser coupling with targets.

Transformer-Aided Deep Double Dueling Spatial-Temporal Q-Network for Spatial Crowdsourcing Analysis

With the rapid development ofmobile Internet,spatial crowdsourcing has becomemore andmore popular.Spatial crowdsourcing consists of many different types of applications,such as spatial crowd-sensing services.In terms of spatial crowd-sensing,it collects and analyzes traffic sensing data from clients like vehicles and traffic lights to construct intelligent traffic prediction models.Besides collecting sensing data,spatial crowdsourcing also includes spatial delivery services like DiDi and Uber.Appropriate task assignment and worker selection dominate the service quality for spatial crowdsourcing applications.Previous research conducted task assignments via traditional matching approaches or using simple network models.However,advanced mining methods are lacking to explore the relationship between workers,task publishers,and the spatio-temporal attributes in tasks.Therefore,in this paper,we propose a Deep Double Dueling Spatial-temporal Q Network(D3SQN)to adaptively learn the spatialtemporal relationship between task,task publishers,and workers in a dynamic environment to achieve optimal allocation.Specifically,D3SQNis revised through reinforcement learning by adding a spatial-temporal transformer that can estimate the expected state values and action advantages so as to improve the accuracy of task assignments.Extensive experiments are conducted over real data collected fromDiDi and ELM,and the simulation results verify the effectiveness of our proposed models.

The Spatial-Temporal Characteristics of Meteorological Disasters in the Southwest Region of Zhejiang Province during 1953-2022

Meteorological disasters are some of the most serious and costly natural disasters, which have larger effects on economic and social activity. Liuchun Lake is an ecotourism area in the southwest region of Zhejiang province, where also has experienced meteorological disasters including rainstorm and cold wave. Understanding the temporal-spatial characteristics of meteorological disasters is important for the local tourism and economic development. Based on the daily temperature and precipitation from 18 meteorological stations in the southwest of Zhejiang province during 1953-2022 and some statistical approaches, the temporal and spatial characteristics of meteorological disasters (Freezing, Rainstorm, Cold wave) are analyzed. The results indicate that 1) Rainstorm occurred frequently around the Liuchun lake, the frequency was about 8 times/a, it can also reach about 3 times/a in the other region. Freezing and cold wave (including strong cold wave and extremely cold wave) had the same spatial distribution as rainstorm, however, except for Liuchun lake, they occurred less than one time in the other regions;2) The trend of rainstorm had larger spatial difference, it increased in all the study area, but it increased more significantly around the study area than around Liuchun lake. Freezing was on the downtrend in the whole region, with 93.3% of the stations passed the 95% significant level. Cold wave also showed a declined trend, but it was insignificantly at most of the stations, only 33% of the stations passed the 90% significant level. Compared with cold wave, strong cold wave and extremely strong cold wave had weaker decline in all the regions. In general, from 1953 to 2022 rainstorm showed an increasing trend, it was the main meteorological disaster in the study area, cold wave displayed a decreasing trend, but it still occurred about 2 - 3 times/a in most regions.

Spatiotemporal Differentiation of Urban Spatial Form and Carbon Emissions in Poyang Lake City Group

In response to the inherent requirements of low-carbon land spatial planning in Jiangxi Province and the lack of existing research,this paper explored the mechanism of spatial form elements of Poyang Lake urban agglomeration on urban carbon emissions.Based on generalized linear regression and geographically weighted regression models,this paper analyzed the spatiotemporal distribution characteristics of carbon emissions,the spatiotemporal relationship between urban form index and carbon emissions,and the spatial differentiation of the intensity of dominant factors from 63 county-level administrative units in the Poyang Lake city group from 2005 to 2020.The results showed that:①The carbon emissions of urban agglomerations around Poyang Lake are generally increasing,and the spatial distribution of carbon emissions is characterized by high-value concentration in the middle and low-value agglomeration in pieces;②The main driving factor for the spatial heterogeneity of carbon emissions was the expansion of built-up area;③Improving urban compactness and optimizing urban form could effectively reduce urban carbon emissions.The results showcased the correlation between urban spatial landscape pattern and the spatiotemporal distribution of carbon emissions,which could make the low-carbon land spatial planning in the Poyang Lake city group more reasonable and practical.

The Spatiotemporal Distribution Characteristics of Cloud Types and Phases in the Arctic Based on CloudSat and CALIPSO Cloud Classification Products

The cloud type product 2B-CLDCLASS-LIDAR based on CloudSat and CALIPSO from June 2006 to May 2017 is used to examine the temporal and spatial distribution characteristics and interannual variability of eight cloud types(high cloud, altostratus, altocumulus, stratus, stratocumulus, cumulus, nimbostratus, and deep convection) and three phases(ice,mixed, and water) in the Arctic. Possible reasons for the observed interannual variability are also discussed. The main conclusions are as follows:(1) More water clouds occur on the Atlantic side, and more ice clouds occur over continents.(2)The average spatial and seasonal distributions of cloud types show three patterns: high clouds and most cumuliform clouds are concentrated in low-latitude locations and peak in summer;altostratus and nimbostratus are concentrated over and around continents and are less abundant in summer;stratocumulus and stratus are concentrated near the inner Arctic and peak during spring and autumn.(3) Regional averaged interannual frequencies of ice clouds and altostratus clouds significantly decrease, while those of water clouds, altocumulus, and cumulus clouds increase significantly.(4) Significant features of the linear trends of cloud frequencies are mainly located over ocean areas.(5) The monthly water cloud frequency anomalies are positively correlated with air temperature in most of the troposphere, while those for ice clouds are negatively correlated.(6) The decrease in altostratus clouds is associated with the weakening of the Arctic front due to Arctic warming, while increased water vapor transport into the Arctic and higher atmospheric instability lead to more cumulus and altocumulus clouds.

Flight parameter calculation method of multi-projectiles using temporal and spatial information constraint

The dynamic parameters of multiple projectiles that are fired using multi-barrel weapons in highfrequency continuous firing modes are important indicators to measure the performance of these weapons.The characteristics of multiple projectiles are high randomness and large numbers launched in a short period of time,making it very difficult to obtain the real dispersion parameters of the projectiles due to the occlusion or coincidence of multiple projectiles.Using six intersecting-screen testing system,in this paper,we propose an association recognition and matching algorithm of multiple projectiles using a temporal and spatial information constraint mechanism.We extract the output signal from each detection screen and then use the wavelet transform to process the output signal.We present a method to identify and extract the time values on which the projectiles pass through the detection screens using the wavelet transform modulus maximum theory.We then use the correlation of the output signals of three parallel detection screens to establish a correlation coefficient recognition constraint function for the multiple projectiles.Based on the premise of linear projectile motion,we establish a temporal and spatial constraint matching model using the projectile’s position coordinates in each detection screen and the projectile’s time constraints within the multiple intersecting-screen geometry.We then determine the time values of the multiple projectiles in each detection screen using an iterative search cycle registration,and finally obtain the flight parameters for the multiple projectiles in the presence of uncertainty.The proposed method and algorithm were verified experimentally and can solve the problem of uncertainty in projectiles flight parameter under different multiple projectile firing states.

Spatiotemporal Prediction of Urban Traffics Based on Deep GNN

Traffic prediction already plays a significant role in applications like traffic planning and urban management,but it is still difficult to capture the highly non-linear and complicated spatiotemporal correlations of traffic data.As well as to fulfil both long-termand short-termprediction objectives,a better representation of the temporal dependency and global spatial correlation of traffic data is needed.In order to do this,the Spatiotemporal Graph Neural Network(S-GNN)is proposed in this research as amethod for traffic prediction.The S-GNN simultaneously accepts various traffic data as inputs and investigates the non-linear correlations between the variables.In terms of modelling,the road network is initially represented as a spatiotemporal directed graph,with the features of the samples at the time step being captured by a convolution module.In order to assign varying attention weights to various adjacent area nodes of the target node,the adjacent areas information of nodes in the road network is then aggregated using a graph network.The data is output using a fully connected layer at the end.The findings show that S-GNN can improve short-and long-term traffic prediction accuracy to a greater extent;in comparison to the control model,the RMSE of S-GNN is reduced by about 0.571 to 9.288 and the MAE(Mean Absolute Error)by about 0.314 to 7.678.The experimental results on two real datasets,Pe MSD7(M)and PEMS-BAY,also support this claim.

Enhancing quantum temporal steering via frequency modulation

Various strategies have been proposed to harness and protect space-like quantum correlations in different models under decoherence.However,little attention has been given to temporal-like correlations,such as quantum temporal steering(TS),in this context.In this work,we investigate TS in a frequency-modulated two-level system coupled to a zero-temperature reservoir in both the weak and strong coupling regimes.We analyze the impact of various frequency-modulated parameters on the behavior of TS and non-Markovian.The results demonstrate that appropriate frequency-modulated parameters can enhance the TS of the two-level system,regardless of whether the system is experiencing Markovian or non-Markovian dynamics.Furthermore,a suitable ratio between modulation strength and frequency(i.e.,all zeroes of the 0th Bessel function J_(0)(δ/?))can significantly enhance TS in the strong coupling regime.These findings indicate that efficient and effective manipulation of quantum TS can be achieved through a frequency-modulated approach.

Cognitive Disorders, Depression and Anxiety in Temporal Lobe Epilepsy: An Overview

Partial epilepsies, originating in a specific brain region, affect about 60% of adults with epilepsy. Temporal lobe epilepsy (TLE) is the most prevalent subtype within this category, often necessitating surgical intervention due to its refractoriness to antiepileptic drugs (AEDs). Hippocampal sclerosis, a common underlying pathology, often exacerbates the severity by introducing cognitive and emotional challenges. This review delves deeper into the cognitive profile of TLE, along with the risk factors for cognitive disorders, depression, and anxiety in this population.

TSCND:Temporal Subsequence-Based Convolutional Network with Difference for Time Series Forecasting

Time series forecasting plays an important role in various fields, such as energy, finance, transport, and weather. Temporal convolutional networks (TCNs) based on dilated causal convolution have been widely used in time series forecasting. However, two problems weaken the performance of TCNs. One is that in dilated casual convolution, causal convolution leads to the receptive fields of outputs being concentrated in the earlier part of the input sequence, whereas the recent input information will be severely lost. The other is that the distribution shift problem in time series has not been adequately solved. To address the first problem, we propose a subsequence-based dilated convolution method (SDC). By using multiple convolutional filters to convolve elements of neighboring subsequences, the method extracts temporal features from a growing receptive field via a growing subsequence rather than a single element. Ultimately, the receptive field of each output element can cover the whole input sequence. To address the second problem, we propose a difference and compensation method (DCM). The method reduces the discrepancies between and within the input sequences by difference operations and then compensates the outputs for the information lost due to difference operations. Based on SDC and DCM, we further construct a temporal subsequence-based convolutional network with difference (TSCND) for time series forecasting. The experimental results show that TSCND can reduce prediction mean squared error by 7.3% and save runtime, compared with state-of-the-art models and vanilla TCN.

Geographically and Temporally Weighted Regression in Assessing Dengue Fever Spread Factors in Yunnan Border Regions

Objective This study employs the Geographically and Temporally Weighted Regression(GTWR)model to assess the impact of meteorological elements and imported cases on dengue fever outbreaks,emphasizing the spatial-temporal variability of these factors in border regions.Methods We conducted a descriptive analysis of dengue fever’s temporal-spatial distribution in Yunnan border areas.Utilizing annual data from 2013 to 2019,with each county in the Yunnan border serving as a spatial unit,we constructed a GTWR model to investigate the determinants of dengue fever and their spatio-temporal heterogeneity in this region.Results The GTWR model,proving more effective than Ordinary Least Squares(OLS)analysis,identified significant spatial and temporal heterogeneity in factors influencing dengue fever’s spread along the Yunnan border.Notably,the GTWR model revealed a substantial variation in the relationship between indigenous dengue fever incidence,meteorological variables,and imported cases across different counties.Conclusion In the Yunnan border areas,local dengue incidence is affected by temperature,humidity,precipitation,wind speed,and imported cases,with these factors’influence exhibiting notable spatial and temporal variation.

TCAS-PINN:Physics-informed neural networks with a novel temporal causality-based adaptive sampling method

Physics-informed neural networks(PINNs)have become an attractive machine learning framework for obtaining solutions to partial differential equations(PDEs).PINNs embed initial,boundary,and PDE constraints into the loss function.The performance of PINNs is generally affected by both training and sampling.Specifically,training methods focus on how to overcome the training difficulties caused by the special PDE residual loss of PINNs,and sampling methods are concerned with the location and distribution of the sampling points upon which evaluations of PDE residual loss are accomplished.However,a common problem among these original PINNs is that they omit special temporal information utilization during the training or sampling stages when dealing with an important PDE category,namely,time-dependent PDEs,where temporal information plays a key role in the algorithms used.There is one method,called Causal PINN,that considers temporal causality at the training level but not special temporal utilization at the sampling level.Incorporating temporal knowledge into sampling remains to be studied.To fill this gap,we propose a novel temporal causality-based adaptive sampling method that dynamically determines the sampling ratio according to both PDE residual and temporal causality.By designing a sampling ratio determined by both residual loss and temporal causality to control the number and location of sampled points in each temporal sub-domain,we provide a practical solution by incorporating temporal information into sampling.Numerical experiments of several nonlinear time-dependent PDEs,including the Cahn–Hilliard,Korteweg–de Vries,Allen–Cahn and wave equations,show that our proposed sampling method can improve the performance.We demonstrate that using such a relatively simple sampling method can improve prediction performance by up to two orders of magnitude compared with the results from other methods,especially when points are limited.

Enhanced Temporal Correlation for Universal Lesion Detection

Universal lesion detection(ULD)methods for computed tomography(CT)images play a vital role in the modern clinical medicine and intelligent automation.It is well known that single 2D CT slices lack spatial-temporal characteristics and contextual information compared to 3D CT blocks.However,3D CT blocks necessitate significantly higher hardware resources during the learning phase.Therefore,efficiently exploiting temporal correlation and spatial-temporal features of 2D CT slices is crucial for ULD tasks.In this paper,we propose a ULD network with the enhanced temporal correlation for this purpose,named TCE-Net.The designed TCE module is applied to enrich the discriminate feature representation of multiple sequential CT slices.Besides,we employ multi-scale feature maps to facilitate the localization and detection of lesions in various sizes.Extensive experiments are conducted on the DeepLesion benchmark demonstrate that thismethod achieves 66.84%and 78.18%for FS@0.5 and FS@1.0,respectively,outperforming compared state-of-the-art methods.

Multi-Stream Temporally Enhanced Network for Video Salient Object Detection

Video salient object detection(VSOD)aims at locating the most attractive objects in a video by exploring the spatial and temporal features.VSOD poses a challenging task in computer vision,as it involves processing complex spatial data that is also influenced by temporal dynamics.Despite the progress made in existing VSOD models,they still struggle in scenes of great background diversity within and between frames.Additionally,they encounter difficulties related to accumulated noise and high time consumption during the extraction of temporal features over a long-term duration.We propose a multi-stream temporal enhanced network(MSTENet)to address these problems.It investigates saliency cues collaboration in the spatial domain with a multi-stream structure to deal with the great background diversity challenge.A straightforward,yet efficient approach for temporal feature extraction is developed to avoid the accumulative noises and reduce time consumption.The distinction between MSTENet and other VSOD methods stems from its incorporation of both foreground supervision and background supervision,facilitating enhanced extraction of collaborative saliency cues.Another notable differentiation is the innovative integration of spatial and temporal features,wherein the temporal module is integrated into the multi-stream structure,enabling comprehensive spatial-temporal interactions within an end-to-end framework.Extensive experimental results demonstrate that the proposed method achieves state-of-the-art performance on five benchmark datasets while maintaining a real-time speed of 27 fps(Titan XP).Our code and models are available at https://github.com/RuJiaLe/MSTENet.

Examining the Spatiotemporal Dynamics and Determinants of Land Urbanization in Prefecture-level Cities,China

Examining the spatiotemporal dynamics and determinants of land urbanization is critical for promoting healthy urban development and the rational use of land resources.Based on the dataset consisting of land use change data and selected factors in 2010 and2020,this study used visual analysis to reveal the spatiotemporal dynamics of land urbanization across prefecture-level cities in China.Meanwhile,the driving forces underlying land urbanization were examined by using geographical detector technique.Following are the findings:1)we find that there exist notable spatial variances in land urbanization across prefecture-level cities.Currently,the differentiation in land urbanization between the northern and southern cities is more pronounced than that between the coastal and inland cities,or between the eastern and western cities.Prefecture-level cities located in central and western China have experienced the most rapid growth in land urbanization.Conversely,the growth rate in northeastern China is the lowest,while the velocity in eastern China remains relatively stable.By using spatial autocorrelation analysis,this study reveals that the land urbanization level in prefecture-level cities has significant spatial agglomeration.2)We further find that land urbanization in China is influenced by factors related to urban land supply and demand,and urban population growth,economic growth,land financial and political incentive have greater impact on land urbanization than other factors.3)We also find that the impacts of determinants on China’s land urbanization vary over time,the explanatory power of economic development increased,while the explanatory power of state forces declined.We argue that integrating the supply and demand factors of land urbanization can provide a more comprehensive understanding of the driving mechanisms underlying land urbanization in China and other transitional countries,and help decision-makers in these countries formulate more detailed and specific land urbanization policies.

Discrete Choice Analysis of Temporal Factors on Social Network Growth

Social networks like Facebook, X (Twitter), and LinkedIn provide an interaction and communication environment for users to generate and share content, allowing for the observation of social behaviours in the digital world. These networks can be viewed as a collection of nodes and edges, where users and their interactions are represented as nodes and the connections between them as edges. Understanding the factors that contribute to the formation of these edges is important for studying network structure and processes. This knowledge can be applied to various areas such as identifying communities, recommending friends, and targeting online advertisements. Several factors, including node popularity and friends-of-friends relationships, influence edge formation and network growth. This research focuses on the temporal activity of nodes and its impact on edge formation. Specifically, the study examines how the minimum age of friends-of-friends edges and the average age of all edges connected to potential target nodes influence the formation of network edges. Discrete choice analysis is used to analyse the combined effect of these temporal factors and other well-known attributes like node degree (i.e., the number of connections a node has) and network distance between nodes. The findings reveal that temporal properties have a similar impact as network proximity in predicting the creation of links. By incorporating temporal features into the models, the accuracy of link prediction can be further improved.

IndRT-GCNets: Knowledge Reasoning with Independent Recurrent Temporal Graph Convolutional Representations

Due to the structural dependencies among concurrent events in the knowledge graph and the substantial amount of sequential correlation information carried by temporally adjacent events,we propose an Independent Recurrent Temporal Graph Convolution Networks(IndRT-GCNets)framework to efficiently and accurately capture event attribute information.The framework models the knowledge graph sequences to learn the evolutionary represen-tations of entities and relations within each period.Firstly,by utilizing the temporal graph convolution module in the evolutionary representation unit,the framework captures the structural dependency relationships within the knowledge graph in each period.Meanwhile,to achieve better event representation and establish effective correlations,an independent recurrent neural network is employed to implement auto-regressive modeling.Furthermore,static attributes of entities in the entity-relation events are constrained andmerged using a static graph constraint to obtain optimal entity representations.Finally,the evolution of entity and relation representations is utilized to predict events in the next subsequent step.On multiple real-world datasets such as Freebase13(FB13),Freebase 15k(FB15K),WordNet11(WN11),WordNet18(WN18),FB15K-237,WN18RR,YAGO3-10,and Nell-995,the results of multiple evaluation indicators show that our proposed IndRT-GCNets framework outperforms most existing models on knowledge reasoning tasks,which validates the effectiveness and robustness.

Hemichorea in patients with temporal lobe infarcts: Two case reports

BACKGROUND Hemichorea and other hyperkinetic movement disorders are uncommon present-ations of stroke and are usually secondary to deep infarctions affecting the basal ganglia and thalamus.Therefore,temporal ischemic lesions causing hemichorea are rare.We report the cases of two patients with acute ischemic temporal lobe infarct strokes that presented as hemichorea.CASE SUMMARY Patient 1:An 82-year-old woman presented with a 1-mo history of involuntary movement of the left extremity,which was consistent with hemichorea.Her diffusion-weighted imaging(DWI)revealed an acute ischemic stroke that predominantly affected the right temporal cortex,and magnetic resonance angiography of the head showed significant stenosis of the right middle cerebral artery(MCA).Treatment with 2.5 mg of olanzapine per day was initiated.When she was discharged from the hospital,her symptoms appeared to have improved compared with those previously observed.Twenty-seven days after the first admission,she was readmitted due to acute ischemic stroke.Computed tomogra-phy perfusion showed marked hypoperfusion in the right MCA territory.An emergency transfemoral cerebral angiogram was performed and showed severe stenosis in the M1 segment of the right MCA.After percutaneous transluminal angioplasty was successfully performed,abnormal movements or other neuro-logic problems did not occur.Patient 2:A 76-year-old man was admitted to our hospital for a 7-d history of right-upper-sided involuntary movements.DWI showed an acute patchy ischemic stroke in the left temporal lobe without basal ganglia involvement.Subsequent diffusion tensor imaging confirmed fewer white matter fiber tracts on the left side than on the opposite side.Treatment with 2.5 mg of olanzapine per day improved his condition,and he was discharged.CONCLUSION When acute hemichorea suddenly appears,temporal cortical ischemic stroke should be considered a possible diagnosis.In addition,hemichorea may be a sign of impending cerebral infarction with MCA stenosis.