Skip to Main Content. A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
Donate to arXiv
However, due to the nature of stochastic of the short-term dynamic OD matrix, how to accurately predict the distribution of passenger travel spatio-temporally is still an open challenge. In this paper, combined multisource data with deep learning method is proposed to improve prediction of dynamic OD matrix accuracy. Firstly, multisource data such as smart card data, weather data and mobile phone data are introduced.
And after quantitative analysis of the influencing factors, choosing 31 features as model inputs. Finally, using the Beijing subway network which had 54,OD for verification. In addition, the application method of multisource data in OD prediction in this paper can deal with more data from other sources to further improve the information exploit effect on passenger flow law.
Article :. Date of Publication: 13 May DOI: Sponsored by: IEEE. Need Help?Background: 'Place' matters in understanding prevalence variations and inequalities in child maltreatment risk. However, most studies examining ecological variations in child maltreatment risk fail to take into account the implications of the spatial and temporal dimensions of neighborhoods.
In this study, we conduct a high-resolution small-area study to analyze the influence of neighborhood characteristics on the spatio-temporal epidemiology of child maltreatment risk. Methods: We conducted a year small-area Bayesian spatio-temporal epidemiological study with all families with child maltreatment protection measures in the city of Valencia, Spain.
As neighborhood units, we used census block groups. Cases were geocoded using the family address. Neighborhood-level characteristics analyzed included three indicators of neighborhood disadvantage-neighborhood economic status, neighborhood education level, and levels of policing activity- immigrant concentration, and residential instability. Bayesian spatio-temporal modelling and disease mapping methods were used to provide area-specific risk estimations.
Results: Results from a spatio-temporal autoregressive model showed that neighborhoods with low levels of economic and educational status, with high levels of policing activity, and high immigrant concentration had higher levels of substantiated child maltreatment risk. Disease mapping methods were used to analyze areas of excess risk. Results showed chronic spatial patterns of high child maltreatment risk during the years analyzed, as well as stability over time in areas of low risk.
Areas with increased or decreased child maltreatment risk over the years were also observed. Conclusions: A spatio-temporal epidemiological approach to study the geographical patterns, trends over time, and the contextual determinants of child maltreatment risk can provide a useful method to inform policy and action. This method can offer a more accurate description of the problem, and help to inform more localized prevention and intervention strategies.
This new approach can also contribute to an improved epidemiological surveillance system to detect ecological variations in risk, and to assess the effectiveness of the initiatives to reduce this risk. Keywords: Area-specific risk estimation; Bayesian spatio-temporal modeling; Child maltreatment; Disease mapping; Neighborhood influences; Small-area study; Spatial inequality.
Abstract Background: 'Place' matters in understanding prevalence variations and inequalities in child maltreatment risk. Publication types Research Support, Non-U.Prompt diagnosis and treatment is critical to continue progress and avoid epidemics in the increasingly susceptible population. Short-term forecasts could be used to highlight anomalies in incidence and support health service logistics. The model which best fits the data is not necessarily most useful for prediction, yet little empirical work has been done to investigate the balance between fit and predictive performance.
We developed statistical models of monthly VL case counts at block level. By evaluating a set of randomly-generated models, we found that fit and one-month-ahead prediction were strongly correlated and that rolling updates to model parameters as data accrued were not crucial for accurate prediction. The final model incorporated auto-regression over four months, spatial correlation between neighbouring blocks, and seasonality. Comparison of one- three- and four-month-ahead predictions from the final model fit demonstrated that a longer time horizon yielded only a small sacrifice in predictive power for the vast majority of blocks.
The model developed is informed by routinely-collected surveillance data as it accumulates, and predictions are sufficiently accurate and precise to be useful. Such forecasts could, for example, be used to guide stock requirements for rapid diagnostic tests and drugs. More comprehensive data on factors thought to influence geographic variation in VL burden could be incorporated, and might better explain the heterogeneity between blocks and improve uniformity of predictive performance.
Integration of the approach in the management of the VL programme would be an important step to ensuring continued successful control. This paper demonstrates a statistical modelling approach for forecasting of monthly visceral leishmaniasis VL incidence at block level in India, which could be used to tailor control efforts according to local estimates and monitor deviations from the currently decreasing trend. By fitting a variety of models to four years of historical data and assessing predictions within a further month test period, we found that the model which best fit the observed data also showed the best predictive performance, and predictive accuracy was maintained when making rolling predictions up to four months ahead of the observed data.
Since there is a two-month delay between reporting and processing of the data, predictive power more than three months ahead of current data is crucial to make forecasts which can feasibly be acted upon. Some heterogeneity remains in predictive power across the study region which could potentially be improved using unit-specific data on factors believed to be associated with reported VL incidence e.
This is an open access article distributed under the terms of the Creative Commons Attribution Licensewhich permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
The views, opinions, assumptions or any other information set out in this article are solely those of the authors and should not be attributed to the funders or any person connected with the funders.
The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Competing interests: The authors have declared that no competing interests exist. The short-term forecasting of diseases targeted for elimination can be a important management tool. Visceral leishmaniasis VL is the acute disease caused by Leishmania donovaniwhich is transmitted through infected female Phlebotomus argentipes sandflies.Webinar \
In India, the burden of disease is largely contained within the four northeastern states of Bihar, Jharkhand, Uttar Pradesh and West Bengal, with the rural state of Bihar most broadly affected [ 1 — 3 ]. Incidence of VL in India has decreased substantially since the initiation of the regional Kala-Azar Elimination Programme KEPwhich aims to tackle the disease across the Indian subcontinent through enhanced case detection and treatment and reduction of vector density [ 4 ].
As a result, reported cases have fallen from 29, in to less than 5, in [ 34 ].Often, in environmental data collection, data arise from two sources: numerical models and monitoring networks. The first source provides predictions at the level of grid cells, while the second source gives measurements at points. The first is characterized by full spatial coverage of the region of interest, high temporal resolution, no missing data but consequential calibration concerns.
The second tends to be sparsely collected in space with coarser temporal resolution, often with missing data but, where recorded, provides, essentially, the true value. Accommodating the spatial misalignment between the two types of data is of fundamental importance for both improved predictions of exposure as well as for evaluation and calibration of the numerical model.
In this article we propose a simple, fully model-based strategy to downscale the output from numerical models to point level. The static spatial model, specified within a Bayesian framework, regresses the observed data on the numerical model output using spatially-varying coefficients which are specified through a correlated spatial Gaussian process. As an example, we apply our method to ozone concentration data for the eastern U.
Our results show that our method outperforms Bayesian melding in terms of computing speed and it is superior to both Bayesian melding and ordinary kriging in terms of predictive performance; predictions obtained with our method are better calibrated and predictive intervals have empirical coverage closer to the nominal values. Moreover, our model can be easily extended to accommodate for the temporal dimension.
In this regard, we consider several spatio-temporal versions of the static model. We compare them using out-of-sample predictions of ozone concentration for the eastern U. For the best choice, we present a summary of the analysis.
Supplemental materialincluding color versions of Figures 4567and 8and MCMC diagnostic plots, are available online. Numerical models are widely used by scientists to understand and predict spatio-temporal processes. Meteorological centers derive weather forecasts using numerical weather prediction models; oceanographers predict storm surges and ocean wave fields using computer models that simulate hurricane intensity and trajectory; atmospheric scientists predict concentration for various pollutants using air quality models, etc.
While the specific aspects of each of these models are different, they all share a similar feature. They are deterministic models that mathematically approximate the underlying physical and chemical processes via nonlinear partial differential equations. As explicit solutions to the these equations are usually not available, solutions are obtained by discretizing both space and time. As a result, predictions are usually given in terms of averages over grid cells. Using a large number of grid cells, these predictions can cover large spatial domains and can also have very high temporal resolution.
However, since they have been derived under a deterministic paradigm, they do not convey any information about the inherent uncertainty in their prediction. Additionally, they are often biased with unknown calibration. Predictions from numerical models are also used for environmental regulatory purposes and improved decision making strategies.
Due to the social and economic consequences, it becomes important that outputs of numerical models are evaluated and also calibrated. To accomplish that, outputs of a numerical model must be compared with observations. But while model predictions are given in terms of averages over square grid cells, observations are collected at points in the spatial domain. Model calibration is not the only instance in which the spatial resolution of the numerical model poses an issue.
In recent years, there has been an increasing effort to understand the relationship between environmental factors and human health. Most of this research focused on the effect of air quality on health Dominici et al. Here there is often spatial misalignment between the different sources of data.
Health data are usually available as aggregated counts over spatial units, e. Air quality data, when provided by computer models, are recorded as averages for grid cells.
Finally, we note that the scale at which a numerical model is resolved is not dictated by practical needs, but by the computing resources available. Indeed, with faster computing, finer grid cells can be utilized. Still, it is likely that prediction at point level spatial resolution is needed, as, for example, in the development of emission regulations and in the linkage of ambient exposure to individual exposure. Several approaches have been proposed to address the change of support problem for numerical model outputs or, more generally, for block averages again, viewing the numerical model output as an average of a process over a block or grid cell.
One obvious example you've given already is spatio-temporal. Here are some more:. This doesn't only happen with -al ending words, anarcho-syndicalism is the only one that comes to my mind right now.
In your case of spatiotemporal, I think your Google search result frequencies are a good start. Google NGram Viewer might have been handy for this, but it doesn't recognize hyphens or punctuation generally. It seems to be a widely accepted word. I don't know what your Word spell checker is doing, whether it's checking each individual part of the compound construction and finds that "spatio" is not a word, or whether it checks against "spatio-temporal" and does not recognize it.
This wouldn't surprise me as most dictionaries that have that word list it unhyphenated. Also, the word spatiotemporal is likely to be used within specific scientific or academic contexts, so I'd search for this term and see whether it's popularity is strong enough to satisfy you of whether you want to use it or not. I personally would not hesitate to use it.
As to whether there is an American preference to use spatial-temporal instead, I'm not sure. All I know is both American and non-American dictionaries recognize "spatiotemporal". Sign up to join this community. The best answers are voted up and rise to the top.
Home Questions Tags Users Unanswered. Asked 1 year, 6 months ago. Active 1 year, 6 months ago. Viewed times. Searching the Google scholar, "spatio-temporal" returnnhits, "spatial-temporal" returnshits, "spatial-temporal scales" returns 3, hits, "spatio-temporal scales" returns 13, hits. Interestingly, one journal named " spatial and spatio-temporal epidemiology " The office word spell checking US-EN prefer "spatial-temporal", so I think "spatial-" is used in American English and "spatio-" is used in non-American English.
If you look at this: books. The problem is with NGram Viewer, and in other cases with Google searches you can't search for exactly what you want when there are other symbols or punctuation. If you search for spatio-temporal it gives the message "Replaced spatio-temporal with spatio - temporal to match how we processed the books. Active Oldest Votes. Other than that, you can check dictionaries: American Heritage Dictionary, Collins, Random House Unabridged, Merriam-Webster, Oxford Living Dictionaries and Wiktionary all recognize spatiotemporal, with only one of them having a hyphen.
Zebrafish Zebrafish Sign up or log in Sign up using Google. Sign up using Facebook.
Where to Go Next: A Spatio-Temporal Gated Network for Next POI Recommendation
Sign up using Email and Password. Post as a guest Name. Email Required, but never shown. Featured on Meta. Responding to the Lavender Letter and commitments moving forward. Related 7.Next Point-of-Interest POI recommendation is of great value for both location-based service providers and users. However, the state-of-the-art Recurrent Neural Networks RNNs rarely consider the spatio-temporal intervals between neighbor check-ins, which are essential for modeling user check-in behaviors in next POI recommendation.
To this end, in this paper, we propose a new Spatio-Temporal Gated Network STGN by enhancing long-short term memory network, where spatio-temporal gates are introduced to capture the spatio-temporal relationships between successive checkins. Specifically, two pairs of time gate and distance gate are designed to control the short-term interest and the longterm interest updates, respectively.
Moreover, we introduce coupled input and forget gates to reduce the number of parameters and further improve efficiency. Finally, we evaluate the proposed model using four real-world datasets from various location-based social networks. The experimental results show that our model significantly outperforms the state-ofthe-art approaches for next POI recommendation. Skip to main content Skip to main navigation menu Skip to site footer. Abstract Next Point-of-Interest POI recommendation is of great value for both location-based service providers and users.
Copyright c Association for the Advancement of Artificial Intelligence. Open Journal Systems. Subscription Login to access subscriber-only resources.Plant environmental responses involve dynamic changes in growth and signaling, yet little is understood as to how progress through these events is regulated. Here, we explored the phenotypic and transcriptional events involved in the acclimation of the Arabidopsis thaliana seedling root to a rapid change in salinity.
Using live-imaging analysis, we show that growth is dynamically regulated with a period of quiescence followed by recovery then homeostasis. Through the use of a new high-resolution spatio-temporal transcriptional map, we identify the key hormone signaling pathways that regulate specific transcriptional programs, predict their spatial domain of action, and link the activity of these pathways to the regulation of specific phases of growth. We use tissue-specific approaches to suppress the abscisic acid ABA signaling pathway and demonstrate that ABA likely acts in select tissue layers to regulate spatially localized transcriptional programs and promote growth recovery.
Finally, we show that salt also regulates many tissue-specific and time point—specific transcriptional responses that are expected to modify water transport, Casparian strip formation, and protein translation.
Together, our data reveal a sophisticated assortment of regulatory programs acting together to coordinate spatially patterned biological changes involved in the immediate and long-term response to a stressful shift in environment. Multicellular organisms are composed of complex assortments of tissues and cell types that must coordinate biological activities to enable survival. Through recent studies, the root of Arabidopsis thaliana has become an informative model organ system for dissecting the response of plants to changes in the environment Dinneny and Benfey, ; Dinneny, The Arabidopsis root is essentially composed of concentric layers of different tissue types surrounding a central core of stele tissue where the vasculature is housed Scheres et al.
Currently, several methodologies have been developed that enable the profiling of cell type—specific biological information in this organ Birnbaum et al.
The most widely applied method uses fluorescence-activated cell sorting FACS of cells after a brief protoplasting treatment of roots expressing tissue-specific green fluorescent protein GFP reporters Birnbaum et al. This method has been used to characterize the transcriptome of nearly every cell type in the root and has provided an important resource for studies in developmental biology, signal transduction, and physiology Birnbaum et al.
In addition to transcript profiling, deep sequencing of small RNAs, hormone quantitation, and proteomic and metabolomic analyses have also been performed on FACS -isolated cells, illustrating the tremendous versatility of the method and the validity of the biological information generated Petersson et al. Nonstressful growth conditions are useful for understanding cellular processes at steady state levels or processes that change over developmental time.
In nature, however, roots will encounter a constantly changing environment due to the heterogeneity of soil. As such, displacement of the root tip, through growth, leads to a constant flux of encountered environmental conditions that require the regulation of context appropriate acclimatory mechanisms. FACS has proven useful for exploring the response of root tissues to changes in abiotic conditions, such as nitrogen content Gifford et al. Meta-analyses of these data has shown that each environmental condition targets a distinct set of tissue layers in the root and regulates changes in transcriptional states that affect growth and physiology Dinneny et al.
High salinity is an important agricultural contaminant that causes damage to the plant, in part, through ionic and osmotic stress Flowers et al. Sodium chloride NaCl elicits rapid and dynamic changes in gene expression, which overlap with responses to the hormone abscisic acid ABA Zhu, ; Fujita et al.
ABA biosynthesis increases under salt stress conditions and can mediate growth suppression Finkelstein and Rock, ; Achard et al. Water stress elicits many similar responses as high salinity, and several studies in maize Zea mays and tomato Solanum lycopersicum have shown that ABA can also have growth promoting activity in the root and shoot by limiting ethylene biosynthesis, which is activated under water stress Sharp et al. The role of ABA in this context is quite intriguing, as ABA activates growth at low levels and represses it at moderate to high levels under normal conditions Finkelstein and Rock, When and where these signals act to regulate growth and if these responses are dynamically regulated during acclimation are not fully understood.
Studies using time-lapse imaging have begun to transform the analysis of growth and signaling in plants Miller et al. Live imaging enables a more complete understanding of the changes that occur during environmental flux. Analysis of gravitropism in seeds of varying size Brooks et al. These studies have also identified phases of the response, which suggest the occurrence of important regulatory events. Recent work examining osmotic stress responses in the shoot have highlighted the dynamic nature of the acclimation process Skirycz et al.
Upon treatment of seedlings with mannitol, an osmotic stress simulant, leaves exhibit temporally dynamic changes in gene expression and growth. These changes are dependent upon the developmental stage of the leaf and the length of treatment.
Temporally regulated fluctuations in hormone signaling are thought to play a major role in regulating these events. Here, we describe an in-depth investigation of growth regulation in the Arabidopsis root during the salt stress response. Using live imaging, we reveal that salt stress induces a brief period of quiescence followed by growth recovery. To identify the key signaling pathways regulating such dynamics and to understand the broader impact of salt stress at the spatio-temporal level, we generated a tissue-specific, multi—time point global transcriptional data set.
Gene expression was examined in two control conditions and at six time points between 1 and 48 h after salt treatment. These data provide a highly resolved resource that enables the use of spatial and temporal trends to generate hypotheses regarding the regulation of these expression patterns. Environmental responses in plants are regulated, in part, through a complex secondary signaling network enacted by changes in hormone biosynthesis Dinneny et al.