Temporal Flows Research Articles

Learning Heterogeneous Spatial-Temporal Context for Skeleton-Based Action Recognition.

Graph convolution networks (GCNs) have been widely used and achieved fruitful progress in the skeleton-based action recognition task. In GCNs, node interaction modeling dominates the context aggregation and, therefore, is crucial for a graph-based convolution kernel to extract representative features. In this article, we introduce a closer look at a powerful graph convolution formulation to capture rich movement patterns from these skeleton-based graphs. Specifically, we propose a novel heterogeneous graph convolution (HetGCN) that can be considered as the middle ground between the extremes of (2 + 1)-D and 3-D graph convolution. The core observation of HetGCN is that multiple information flows are jointly intertwined in a 3-D convolution kernel, including spatial, temporal, and spatial-temporal cues. Since spatial and temporal information flows characterize different cues for action recognition, HetGCN first dynamically analyzes pairwise interactions between each node and its cross-space-time neighbors and then encourages heterogeneous context aggregation among them. Considering the HetGCN as a generic convolution formulation, we further develop it into two specific instantiations (i.e., intra-scale and inter-scale HetGCN) that significantly facilitate cross-space-time and cross-scale learning on skeleton graphs. By integrating these modules, we propose a strong human action recognition system that outperforms state-of-the-art methods with the accuracy of 93.1% on NTU-60 cross-subject (X-Sub) benchmark, 88.9% on NTU-120 X-Sub benchmark, and 38.4% on kinetics skeleton.

Oceanic feeling in Mati Diop’s Atlantique

ABSTRACT The ocean is a constant presence in Mati Diop’s award-winning film Atlantique/Atlantics (2019), a ghostly love story about the ongoing migration crisis set in Dakar, Senegal. A critical issue Diop explores in this film is the contradiction between the geopolitical stasis of a high-rise tower and the expansive continuity of the sea, making the physical reality captured by the lens overlap with the unrestricted flow of presences carried by waves of sea and sound through the film frame. This article analyses oceanic aesthetics and the unrestricted flows of bodies of water and work in both Diop’s recent feature film and her first experimental documentary of almost the same title, Atlantiques/Atlantics (2009). These corporeal drifts disrupt narrative and temporal flows and position the cinema as a space for poetic and political change. What the ocean embodies is not only a tragic archive of colonial violence, as Rosalind Galt has recently argued, but also a space for a feminist and decolonial refusal of such loss.

Learning to Generate Temporal Origin-destination Flow Based-on Urban Regional Features and Traffic Information

Origin-destination (OD) flow contains population mobility information between every two regions in the city, which is of great value in urban planning and transportation management. Nevertheless, the collection of OD flow data is extremely difficult due to the hindrance of privacy issues and collection costs. Significant efforts have been made to generate OD flow based on urban regional features, e.g., demographics, land use, and so on, since spatial heterogeneity of urban function is the primary cause that drives people to move from one place to another. On the other hand, people travel through various routes between OD, which will have effects on urban traffic, e.g., road travel speed and time. These effects of OD flows reveal the fine-grained spatiotemporal patterns of population mobility. Few works have explored the effectiveness of incorporating urban traffic information into OD generation. To bridge this gap, we propose to generate real-world daily temporal OD flows enhanced by urban traffic information in this paper. Our model consists of two modules: Urban2OD and OD2Traffic . In the Urban2OD module, we devise a spatiotemporal graph neural network to model the complex dependencies between daily temporal OD flows and regional features. In the OD2Traffic module, we introduce an attention-based neural network to predict urban traffic based on OD flow from the Urban2OD module. Then, by utilizing gradient backpropagation, these two modules are able to enhance each other to generate high-quality OD flow data. Extensive experiments conducted on real-world datasets demonstrate the superiority of our proposed model over the state of the art.

Tapestry of Time and Actions: Modeling Human Activity Sequences Using Temporal Point Process Flows

Human beings always engage in a vast range of activities and tasks that demonstrate their ability to adapt to different scenarios. These activities can range from the simplest daily routines, like walking and sitting, to multi-level complex endeavors such as cooking a four-course meal. Any human activity can be represented as a temporal sequence of actions performed to achieve a certain goal. Unlike the time series datasets extracted from electronics or machines, these action sequences are highly disparate in their nature—the time to finish a sequence of actions can vary between different persons. Therefore, understanding the dynamics of these sequences is essential for many downstream tasks such as activity length prediction, goal prediction, and next action recommendation. Existing neural network based approaches that learn a continuous-time activity sequence are limited to the presence of only visual data or are designed specifically for a particular task (i.e., limited to next action or goal prediction). In this article, we present ProActive , a neural marked temporal point process framework for modeling the continuous-time distribution of actions in an activity sequence while simultaneously addressing three high-impact problems: next action prediction, sequence goal prediction, and end-to-end sequence generation. Specifically, we utilize a self-attention module with temporal normalizing flows to model the influence and the inter-arrival times between actions in a sequence. Moreover, for time-sensitive prediction, we perform an early detection of sequence goal via a constrained margin-based optimization procedure. This in turn allows ProActive to predict the sequence goal using a limited number of actions. In addition, we propose a novel addition over the ProActive model, called ProActive++ , that can handle variations in the order of actions (i.e., different methods of achieving a given goal). We demonstrate that this variant can learn the order in which the person or actor prefers to do their actions. Extensive experiments on sequences derived from three activity recognition datasets show the significant accuracy boost of our ProActive and ProActive++ over the state of the art in terms of action and goal prediction, and the first-ever application of end-to-end action sequence generation.

Bounded aspirations and youth capacity: interrogating public higher education in North India

ABSTRACT This paper engages with youth and the everyday culture of public higher education in selected urban sites of the Banaras Hindu University (BHU). As a public university, the BHU inspires massive youth mobility from rural areas and small towns in North India, specially of youth from socially disadvantaged castes and women. I find that these youth are not lacking in a capacity to aspire. Rather, their desires are formed in complex social conditions, and involve overlapping temporal flows. Their migration for education is about escaping the routine and habits of a rural past. It is simultaneously a dream for a future with secure government jobs and urban living. Further, their aspirations are not merely utilitarian – they include a normative idea of the university, with good-quality education and an egalitarian culture, replete with freedoms. However, the everyday culture of the public university is replete with boundaries. Persisting patriarchal constraints, bureaucratic academic cultures, and rampant casteism place boundaries on youth aspirations. Finally, I argue that the relational resources among youth on campus form a collective resource that provides them with a navigational capacity to overcome bounded aspirations.

Research on optimization of table tennis hitting action based on image recognition technology

Abstract In the process of table tennis batting action analysis, the analysis system that relies on modern digital image processing technology plays an increasingly important role. The new GoogleNet model, as a kind of auxiliary means, because of its intuitive, rapid, and other characteristics, can be very good to find out and optimize the drawbacks of batting action in the process of the game and help learners to master the batting essentials quickly. In this paper, the batch regression algorithm is used to transform the images of players’ batting actions during table tennis games, and the AM-Softmax algorithm in the Softmax classifier is used to construct the New GoogleNet model to build the batting action recognition and analysis model that contains both temporal and spatial flows. The main conclusions are as follows: the accuracy of the test results for forehand and left-handed ball attacks based on the New GoogleNet model is as high as 92% and 90%. Forehand and left-handed ball rolling accuracy was 87.5% and 85%, respectively. The optical flow optimization method resulted in a 0.4% and 1.4% increase in the accuracy of the experiments. In the two-stream fusion method with thresholds s=99% and s=1, the accuracy of optimization of the hitting action reached 89.8% and 91.4%, respectively. The accuracy in the averaging method was 95.9% when the optical flow threshold s=1. When the optical flow threshold s = 99% is used in the downscaling method, the accuracy is 93.5%. The results of this paper are of great significance for the recognition of batting movements during table tennis matches and the optimization and improvement of batting movements.

Decomposition of skin-friction and wall heat flux of temporal transition in compressible channel flows with direct numerical and constrained large-eddy simulations

The twofold integral-based decompositions of skin-friction and wall heat flux coefficients are implemented in compressible temporal transitional channel flows with direct numerical simulation and constrained large eddy simulation (CLES) to explore (i) the generations of the skin-friction and wall heat flux coefficients and their overshoot during the transition and (ii) why CLES under-predicts the overshoot phenomenon. The Reynolds shear stress, the mean velocity gradient with respect to time, and the mean velocity convection are dominating terms during the transition process of skin friction coefficient Cf, and the effect of the mean velocity convection becomes stronger as the Mach number (Ma) increases. For the wall heat flux coefficient Bq, the turbulent heat transfer, the mean energy gradients in time, and the viscous stress are significant contributors. The effects of molecular heat transfer and the mean convection on transition are increasingly important to Bq as Ma increases. The overshoot of Cf and Bq at Ma = 1.5 is mainly caused by the significant changes of mean velocity profiles and mean energy profiles with respect to time respectively. At Ma = 3.0, the overshoot of Cf is due to the significant change of mean velocity profiles in time and the mean velocity convection, while the overshoot of Bq is due to the mean energy changes in time and mean energy convection. It is found that the underestimation of the overshoots of Cf and Bq in CLES is primarily caused by the variances of the mean velocity gradient and mean energy gradient, respectively.

Measuring visitor flows using mobile positioning data in three Hungarian second-tier cities

PurposeThe research analyses the spatial-temporal behaviour of international visitors using mobile positioning data (MPD) in three second-tier cities in Hungary: Szeged, Debrecen and Pécs. The purpose of this study is to identify the origins of visitors, length of stay, seasonal concentrations and mobility between cities.Design/methodology/approachA large volume of data generated by foreign mobile phone users was processed and analysed for six consecutive months in 2018. The movements of around 3.5 million foreigners visiting Hungary were captured.FindingsThe data showed significant differences in tourist turnover, mobility patterns and flows indicating different levels of tourism activity and potential in the three cities. This included day trips, cross-border tourism, seasonal fluctuations and activity-driven demand (e.g. special events and cultural tourism).Research limitations/implicationsMPD cannot fully explain or predict drivers of visitor behaviour, such as purpose of visit, the precise activities that they undertake there and the experiences that they gain. It can, however, provide information on spatial and temporal flows, patterns and concentrations of visitors.Practical implicationsThe investigated cities should follow distinct tourism development policies to attract more tourists and strengthen the links with their neighbouring destinations at the same time as differentiating themselves through marketing as competitive alternative destinations.Social implicationsAugmenting tourism has socio-economic implications for residents and communities. The development of cultural tourism and local event-based tourism must incorporate community needs.Originality/valueThe paper analyses the extent to which MPD can provide insights into visitors’ spatio-temporal mobility and flows in relatively under-visited second-tier cities and it highlights opportunities and gaps for big data research in an urban context.

Tracking the temporal flows of mobile communication in daily life

Prior theoretical perspectives assert that mobile media and communication accelerate time perception. To test this hypothesis, we coupled mobile app logs and experience sampling to capture social app use and time perception in daily life. Participants ( N = 132) provided self-reports of time perception ( n = 9,081) and recordings of social app use ( n = 2,193,655). Although people perceived time as relatively fast on average, results did not support an overall link between social app use and accelerated time perception. Conversely, social media use—but not messaging use—was associated with decelerated time perception. In addition, observed relationships between social app use and time perception were consistent across individuals. We conclude by considering how future mobile communication research will be challenged to measure and model how temporal flows are interwoven with mobile connection in the background of daily life.

Making a market in environmental credits II: Watershed moments

This pair of papers examines and describes the state action necessary to make markets function as environmental policy instruments and as strategies of governance. We do this through a detailed look at the mechanics of environmental credit compliance markets in the US states of Oregon, Ohio, and North Carolina in which stream credits are privately created and sold to developers who have impacted protected stream systems. In this paper, we observe that the governance of streams as water resources requires the state to create a scalar hierarchy that fixes certain characteristics of streams at certain scales of state action. These fixes attempt to resolve, bracket, or ignore the temporal and spatial variability of streams that can confound governance; however, these variabilities are essential to the scientific study of streams. At each of the four distinct scales, four different operations crucial to market function were observed; at each scale, elements of natural variability were fixed or confined to be expressed only within the given scale. These observations reveal principles of how scale functions within environmental governance, as well as failures where gaps and resistances appear that create unforeseen outcomes in market-led policy. In three different state settings, the establishment of a fixed scale of governance is made in different ways that depend on the local institutional and social context. However, they all act to render an unruly set of temporal and spatial flows as instead occurring within certain fixed scalar boundaries, and thus amenable to governance with markets.

Temporal discrepancies in “rapid” HIV testing: explaining misdiagnoses at the point-of-care in Zimbabwe

BackgroundRapid diagnostic tests have revolutionized the HIV response in low resource and high HIV prevalence settings. However, disconcerting levels of misdiagnosis at the point-of-care call for research into their root causes. As rapid HIV tests are technologies that cross borders and have inscribed within them assumptions about the context of implementation, we set out to explore the (mis)match between intended and actual HIV testing practices in Zimbabwe.MethodsWe examined actual HIV testing practices through participant observations in four health facilities and interviews with 28 rapid HIV testers. As time was identified as a key sphere of influence in thematic analyses of the qualitative data, a further layer of analysis juxtaposed intended (as scripted in operating procedures) and actual HIV testing practices from a temporal perspective.ResultsWe uncover substantial discrepancies between the temporal flows assumed and inscribed into rapid HIV test kits (their intended use) and those presented by the high frequency testing and low resource and staffing realities of healthcare settings in Zimbabwe. Aside from pointing to temporal root causes of misdiagnosis, such as the premature reading of test results, our findings indicate that the rapidity of rapid diagnostic technologies is contingent on a slow, steady, and controlled environment. This not only adds a different dimension to the meaning of “rapid” HIV testing, but suggests that errors are embedded in the design of the diagnostic tests and testing strategies from the outset, by inscribing unrealistic assumptions about the context within which they used.ConclusionTemporal analyses can usefully uncover difficulties in attuning rapid diagnostic test technologies to local contexts. Such insight can help explain potential misdiagnosis ‘crisis points’ in point-of-care testing, and the need for public health initiatives to identify and challenge the underlying temporal root causes of misdiagnosis.

On the way to maturity...

As we close another year of existence with the publication of this third issue of volume 16, we take the opportunity to share with everyone the joy of having complied with the requirements of the indexing platforms, reaching the milestones outlined for the first three years of the JFA. Thanks to the joint effort of authors, reviewers, editors, and management team, who prepare, organize, and produce the journal, we achieved the appropriate temporal, quantitative, and qualitative flows whose results are expressed by the publication of 180 articles in three years. We must celebrate the participation of countries worldwide, which surprised us with their interest in our vehicle of scientific dissemination. The chart and table below demonstrate that important countries such as the USA, Spain, Portugal, South Africa, and Australia have already become familiar with our system and honored us with their submissions. But we still have a lot to do!!! In addition to encouraging Latin American countries to collaborate more effectively by sending their studies, we would like to have young professionals on our side. It would be extremely useful for everyone if the training services for Foot and Ankle specialists throughout Latin America considered performing scientific studies and publishing them in the JFA as one of the technical training requirements. The research growth and published studies in our continent would soon be rewarded by the improvement in care and outcomes for our patients, the greatest objective of all. The renewal and expansion of the Board of Reviewers started this year will continue, and soon, we hope to reduce even more the evaluation and decision time of each submission, in addition to improving, every day, the standard of revisions. In this moment of reflection in which we see the end of another difficult year where we feel all the serious consequences of the pandemic that has hit humanity, we can celebrate a small victory achieved by every one of us who participated in constructing our journal to whom we are most grateful. Happy Holidays to all!

Balancing the GHG emissions and operational costs for a mixed fleet of electric buses and diesel buses

Making the urban buses electric is regarded as a major strategy to reduce greenhouse gas (GHG) emissions and environmental impacts of fossil fuels. In practice, not all diesel buses (DBs) are replaced by electric buses (EBs) because of budget constraint. This paper investigates the balance of the deployment problem for a mixed fleet with DBs and EBs in the sense of total GHG emissions and operational costs by incorporating the effect of the spatial–temporal passenger flows. The balance strategy of fleet deployment is defined the Pareto optimal allocation of EBs among bus lines to minimize simultaneously the total operational cost and GHG emissions. A real-world urban bus system of Liuzhou City in China is conducted. We find that the bus lines located in the downtown with higher passenger loading would prefer to adopt EBs at the peak hours, and most DBs are allocated to the bus lines with long travel distance at off-peak hours in the suburb. Therefore, the reduced emission by adopting EBs mainly concentrates on the center of the city, and more produced emissions of DBs are distributed far away from the downtown. When all DBs replaced by EBs, the upper bound of the carbon emission reduction ratio is 77.04%, which reduces from 207.15 tons to 47.56 tons per day.

Short-Term Holiday Travel Demand Prediction for Urban Tour Transportation: A Combined Model Based on STC-LSTM Deep Learning Approach

Short-term prediction of holiday travel demand is a complex but key issue to the planning and management of tour transportation system in big cities. This paper develops an improved spatial and temporal correlation long short-term memory model (STC-LSTM) to forecast short-term holiday travel demand based on deep learning approach. Analysis results show six kinds of tourist flow correlations appears in different sets of tourist attractions, and 27.94 percent of the tourist attractions have mid- or high- positive tourist flow correlation with others, meaning that a positive synchronization mechanism exists between suburban tourist attractions in Beijing. The proposed model predicts the holiday travel demand on the basis of the historical data of the spatial and temporal related tourist flows, and the auxiliary data including meteorological data, temporal data, and Internet search index. Based on actual case study with tourist flow data of the suburban tourist attraction in Beijing, the proposed STC-LSTM is carried out to compared with other conventional prediction approaches. Results show that the proposed approach can improve the prediction accuracy and well capture the different spatial and temporal correlations of tourist flows.

Efficient k-means clustering and greedy selection-based reduction of nodal search space for optimization of sensor placement in the water distribution networks

Monitoring of water distribution network (WDN) requires placement of sensors at strategic locations to detect maximum contamination events at the earliest. The multi-objective optimization (MOO) of sensor placement is a complicated problem owing to its combinatorial nature, interconnected and large WDN sizes, and temporal flows producing complex outcomes for a given set of contamination events. In this study, a new method is proposed to reduce the complexity of the problem by condensing the nodal search space. This method first segregates the nodes based on intrusion events detected, using k-means clustering, followed by selecting nodes from each group based on the improvement observed in the objectives, namely, contamination event detection, expected detection time, and affected population. The selected nodes formed the decision variable space for the MOO study. The developed strategy was tested on two benchmark networks: BWSN Network1 and C-town network, and its performance is compared with the traditional method in terms of hypervolume contribution rate (CR) indicator and the number of Pareto points. The optimal subset of nodes generated twice the number of Pareto points than the complete set of nodes set for placing 20 sensors and had 10% more than CR indicator than the traditional method. For the placement of 5 sensors, the proposed solutions were better at the higher detection likelihood values, which is required to achieve maximum detection. The proposed sensor placement algorithm can be easily scaled to large WDNs. It is expected to provide a better optimal sensor placement solution irrespective of network size as compared to the traditional approach.

The spatial and temporal distribution of nitrogen flow in the agricultural system and green development assessment of the Yellow River Basin

The Yellow River Basin (YRB) is an important agricultural production area with diverse of Agri-ecological functional units in northwest China. Through data collection and Nutrient Flows in Food chain, Environment and Resources Use (NUFER） and NUFER-AGD model, present study aimed to explore the spatial and temporal flows of nitrogen (N) in the cropping and animal farming systems of the YRB from 1999 to 2019; and to evaluate the developing status and restrictive factors for the green development in this area. The total N input of the area increased from 2.10 × 107 t in 1999–3.66 × 107 t in 2019, mainly originated from fertilizer (53%, 2019) and fodder (39%, 2019) input. The total N output increased from 8.27 × 106 t in 1999–13.77 × 106 t in 2019, and the main pathway of N loss was ammonia volatilization, accounting for 53.5% in 1999 and 53.1% in 2019 of the total losses. Based on the N input and loss per unit area in 2019, the upper reaches of the YRB were low-input and high-emission; the middle reaches were high-input and high-emission; the lower reaches were high-input and low-emission. Fifty variables of five dimensions, society development, economy growth, agricultural production, resources input and ecological environment were selected to assess whole YRB for the green development index, the results show that 36% variables reached the green level, and the parameters of the agricultural production and ecological environment among all variables were the key factors of limiting green development of the YRB area. These founding are of great importance to provide scientific support for sustainable agricultural development and ecological protection at regional scale.

Solving Time Dependent Fokker-Planck Equations Via Temporal Normalizing Flow

In this work, we propose an adaptive learning approach based on temporal normalizing flows for solving time-dependent Fokker-Planck (TFP) equations. It is well known that solutions of such equations are probability density functions, and thus our approach relies on modelling the target solutions with the temporal normalizing flows. The temporal normalizing flow is then trained based on the TFP loss function, without requiring any labeled data. Being a machine learning scheme, the proposed approach is mesh-free and can be easily applied to high dimensional problems. We present a variety of test problems to show the effectiveness of the learning approach.

Solving Time Dependent Fokker-Planck Equations via Temporal Normalizing Flow

In this work, we propose an adaptive learning approach based on temporal normalizing flows for solving time-dependent Fokker-Planck (TFP) equations. It is well known that solutions of such equations are probability density functions, and thus our approach relies on modelling the target solutions with the temporal normalizing flows. The temporal normalizing flow is then trained based on the TFP loss function, without requiring any labeled data. Being a machine learning scheme, the proposed approach is mesh-free and can be easily applied to high dimensional problems. We present a variety of test problems to show the effectiveness of the learning approach.

ANCIENT CHINESE AND ANCIENT GREEK PERCEPTION OF TEMPORALITY: COMPARATIVE ASPECT AND CONNECTION WITH MODERNITY

The article is devoted to the problem of interpreting the essence of temporal flows in Ancient Chinese and Ancient Greek philosophical traditions. It is emphasized that the sense of the passage of time is the cornerstone of the formation of any civilizational system, because it introduces the production of retrospective and prospective images, on which any prolonged activity is based. The state of human consciousness is seen as a key to the interpretation of temporal transit between modes of the past, present, and future, and the Ancient Chinese and Ancient Greek traditions offer two diametrically different approaches to define this state. The purpose of our research is to compare temporal interpretations in the civilizational systems of Ancient China and Ancient Greece and to determine which elements of them are present in modern temporal orientations in the global world and can serve as a guidelines for their improvement. In this aspect we also proclaim the relevance of our research, its resonance with today’s challenges. In the course of our research, we came to the conclusion that the Ancient Chinese tradition emphasizes the intuitive perception of time flows, and this intuition is based on the cyclic patterns of transformations of natural processes, which are based on the circulation of yang and yin energies. The task of a person is to maximally purify consciousness from egocentrism, from trying to occupy a central place in the world system. The Ancient Greek tradition in the opposite way brings the phenomenon of human consciousness on the forefront of temporal interpretations.Temporal interpretation becomes possible and prognostic precisely because human consciousness chooses a certain temporal narrative, plot, logos of the unfolding of events and interprets time on a previously given position. Two methods of orientation in temporal flows, invented in Ancient China and Ancient Greece, can become important guidelines for a modern person who faces new temporal challenges. In particular, these two approaches make it possible to carry out information storage in a different manner, which, in turn, directly affects the orderliness of the temporal flow in human consciousness in the era of groundbreaking technological changes.

Traffic Flow Online Prediction Based on a Generative Adversarial Network with Multi-Source Data

Traffic prediction is essential for advanced traffic planning, design, management, and network sustainability. Current prediction methods are mostly offline, which fail to capture the real-time variation of traffic flows. This paper establishes a sustainable online generative adversarial network (GAN) by combining bidirectional long short-term memory (BiLSTM) and a convolutional neural network (CNN) as the generative model and discriminative model, respectively, to keep learning with continuous feedback. BiLSTM constantly generates temporal candidate flows based on valuable memory units, and CNN screens out the best spatial prediction by returning the feedback gradient to BiLSTM. Multi-dimensional indicators are selected to map the multi-view fusion local trend for accurate prediction. To balance computing efficiency and accuracy, different batch sizes are pre-tested and allocated to different lanes. The models are trained with rectified adaptive moment estimation (RAdam) by dividing the dataset into the training and testing sets with a rolling time-domain scheme. In comparison with the autoregressive integrated moving average (ARIMA), BiLSTM, generating adversarial network for traffic flow (GAN-TF), and generating adversarial network for non-signal traffic (GAN-NST), the proposed improved generating adversarial network for traffic flow (IGAN-TF) successfully generates more accurate and stable flows and performs better.