Efficient Prediction of Spatio-Temporal Events on the Example of the Availability of Vehicles Rented per Minute

Abstract. The length of streamflow observations is generally limited to the last 50 years even in data-rich countries like France. It therefore offers too small a sample of extreme low-flow events to properly explore the long-term evolution of their characteristics and associated impacts. To overcome this limit, this work first presents a daily 140-year ensemble reconstructed streamflow dataset for a reference network of near-natural catchments in France. This dataset, called SCOPE Hydro (Spatially COherent Probabilistic Extended Hydrological dataset), is based on (1) a probabilistic precipitation, temperature, and reference evapotranspiration downscaling of the Twentieth Century Reanalysis over France, called SCOPE Climate, and (2) continuous hydrological modelling using SCOPE Climate as forcings over the whole period. This work then introduces tools for defining spatio-temporal extreme low-flow events. Extreme low-flow events are first locally defined through the sequent peak algorithm using a novel combination of a fixed threshold and a daily variable threshold. A dedicated spatial matching procedure is then established to identify spatio-temporal events across France. This procedure is furthermore adapted to the SCOPE Hydro 25-member ensemble to characterize in a probabilistic way unrecorded historical events at the national scale. Extreme low-flow events are described and compared in a spatially and temporally homogeneous way over 140 years on a large set of catchments. Results highlight well-known recent events like 1976 or 1989–1990, but also older and relatively forgotten ones like the 1878 and 1893 events. These results contribute to improving our knowledge of historical events and provide a selection of benchmark events for climate change adaptation purposes. Moreover, this study allows for further detailed analyses of the effect of climate variability and anthropogenic climate change on low-flow hydrology at the scale of France.

Download Full-text

Sensing as a Service for the Internet of Things

International Journal of Recent Contributions from Engineering Science & IT (iJES) ◽

10.3991/ijes.v4i3.6087 ◽

2016 ◽

Vol 4 (3) ◽

pp. 28

Author(s):

Omar Subhi Aldabbas

Keyword(s):

Internet Of Things ◽

Cost Effective ◽

Sensor Data ◽

Detection Accuracy ◽

Heterogeneous Services ◽

Coordination Languages ◽

Spatio Temporal ◽

Temporal Events ◽

New Applications ◽

Common Application

Internet of Things (IoT) is a ubiquitous embedded ecosystem known for its capability to perform common application functions through coordinating resources, which are distributed on-object or on-network domains. As new applications evolve, the challenge is in the analysis and usage of multimodal data streamed by diverse kinds of sensors. This paper presents a new service-centric approach for data collection and retrieval. This approach considers objects as highly decentralized, composite and cost effective services. Such services can be constructed from objects located within close geographical proximity to retrieve spatio-temporal events from the gathered sensor data. To achieve this, we advocate Coordination languages and models to fuse multimodal, heterogeneous services through interfacing with every service to achieve the network objective according to the data they gather and analyze. In this paper we give an application scenario that illustrates the implementation of the coordination models to provision successful collaboration among IoT objects to retrieve information. The proposed solution reduced the communication delay before service composition by up to 43% and improved the target detection accuracy by up to 70%, while maintaining energy consumption 20% lower than its best rivals in the literature.

Download Full-text

Spatio-temporal deixis and cognitive models in early Indo-European

Cognitive Linguistics ◽

10.1515/cog-2017-0023 ◽

2018 ◽

Vol 29 (1) ◽

pp. 1-44

Author(s):

Annamaria Bartolotta

Keyword(s):

Cognitive Models ◽

Temporal Sequence ◽

Point Mapping ◽

The Past ◽

European Languages ◽

Linguistic Evidence ◽

Future Events ◽

Spatial Terms ◽

Spatio Temporal ◽

Temporal Events

AbstractThis paper is a comparative study based on the linguistic evidence in Vedic Sanskrit and Homeric Greek, aimed at reconstructing the space-time cognitive models used in the Proto-Indo-European language in a diachronic perspective. While it has been widely recognized that ancient Indo-European languages construed earlier (and past) events as in front of later ones, as predicted in the Time-Reference-Point mapping, it is less clear how in the same languages the passage took place from this ‘archaic’ Time-RP model or non-deictic sequence, in which future events are behind or follow the past ones in a temporal sequence, to the more recent ‘post-archaic’ Ego-RP model that is found only from the classical period onwards, in which the future is located in front and the past in back of a deictic observer. Data from the Rigveda and the Homeric poems show that an Ego-RP mapping with an ego-perspective frame of reference (FoR) could not have existed yet at an early Indo-European stage. In particular, spatial terms of front and behind turn out to be used with reference not only to temporal events, but also to east and west respectively, thus presupposing the existence of an absolute field-based FoR which the temporal sequence is metaphorically related to. Specifically, sequence is relative position on a path appears to be motivated by what has been called day orientation frame, in which the different positions of the sun during the day motivate the mapping of front onto ‘earlier’ and behind onto ‘later’, without involving ego’s ‘now’. These findings suggest that early Indo-European still had not made use of spatio-temporal deixis based on the tense-related ego-perspective FoR found in modern languages.

Download Full-text

Exploiting Graph Regularized Multi-dimensional Hawkes Processes for Modeling Events with Spatio-temporal Characteristics

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2018/343 ◽

2018 ◽

Author(s):

Yanchi Liu ◽

Tan Yan ◽

Haifeng Chen

Keyword(s):

Spatial Structure ◽

Spatial Information ◽

Low Rank ◽

Interaction Patterns ◽

Influence Matrix ◽

Hawkes Processes ◽

Temporal Characteristics ◽

Connection Graph ◽

Spatio Temporal ◽

Temporal Events

Multi-dimensional Hawkes processes (MHP) has been widely used for modeling temporal events. However, when MHP was used for modeling events with spatio-temporal characteristics, the spatial information was often ignored despite its importance. In this paper, we introduce a framework to exploit MHP for modeling spatio-temporal events by considering both temporal and spatial information. Specifically, we design a graph regularization method to effectively integrate the prior spatial structure into MHP for learning influence matrix between different locations. Indeed, the prior spatial structure can be first represented as a connection graph. Then, a multi-view method is utilized for the alignment of the prior connection graph and influence matrix while preserving the sparsity and low-rank properties of the kernel matrix. Moreover, we develop an optimization scheme using an alternating direction method of multipliers to solve the resulting optimization problem. Finally, the experimental results show that we are able to learn the interaction patterns between different geographical areas more effectively with prior connection graph introduced for regularization.

Download Full-text

Finding Sequential Patterns from Massive Number of Spatio-Temporal Events

Proceedings of the 2006 SIAM International Conference on Data Mining ◽

10.1137/1.9781611972764.75 ◽

2006 ◽

Cited By ~ 7

Author(s):

Yan Huang ◽

Liqin Zhang ◽

Pusheng Zhang

Keyword(s):

Sequential Patterns ◽

Massive Number ◽

Spatio Temporal ◽

Temporal Events

Download Full-text

Ensemble reconstruction of spatio-temporal extreme low-flow events in France since 1871

10.5194/hess-2016-405 ◽

2016 ◽

Cited By ~ 1

Author(s):

Laurie Caillouet ◽

Jean-Philippe Vidal ◽

Eric Sauquet ◽

Alexandre Devers ◽

Benjamin Graff

Keyword(s):

Climate Change ◽

Low Flow ◽

Reference Network ◽

Large Set ◽

Historical Events ◽

Variable Threshold ◽

Spatio Temporal ◽

Set Up ◽

Temporal Events ◽

Rich Countries

Abstract. The historical depth of streamflow observations is generally limited to the last 50 years even in data-rich countries like France. It therefore offers too small a sample of extreme low-flow events to properly explore the long-term evolution of their characteristics and associated impacts. In order to overcome this limit, this work first presents a daily 140-year ensemble reconstructed streamflow dataset for a reference network of near-natural catchments in France. This dataset, called SCOPE Hydro (Spatially COherent Probabilistic Extended Hydrological dataset), is based on (1) a probabilistic precipitation, temperature and reference evapotranspiration downscaling of the Twentieth Century Reanalysis over France, called SCOPE Climate, and (2) a continuous hydrological modelling using SCOPE Climate as forcings over the whole period. This work then introduces tools for defining spatio-temporal extreme low-flow events. Extreme low-flow events are first locally defined through the Sequent Peak Algorithm using a novel combination of a fixed threshold and a daily variable threshold. A dedicated spatial matching procedure is then set up to identify spatio-temporal events across France. This procedure is furthermore adapted to the SCOPE Hydro 25-member ensemble in order to characterize in a probabilistic way unrecorded historical events at the national scale. For the first time, extreme low-flow events are described and compared in a spatially and temporally homogeneous way over 140 years on a large set of catchments. Initial results bring forward well-known recent events like 1976 or 1989–1990, but also older and relatively forgotten ones like the 1878 and 1893 events. These results contribute to improve our knowledge on historical events and provide a selection of benchmark events for climate change adaptation purposes. This study moreover allows for further detailed analyses of the effect of climate variability and anthropogenic climate change on low-flow hydrology at the scale of France.

Download Full-text

Early classification of spatio-temporal events using partial information

PLoS ONE ◽

10.1371/journal.pone.0236331 ◽

2020 ◽

Vol 15 (8) ◽

pp. e0236331

Author(s):

Sevvandi Kandanaarachchi ◽

Rob J. Hyndman ◽

Kate Smith-Miles

Keyword(s):

Partial Information ◽

Early Classification ◽

Spatio Temporal ◽

Temporal Events

Download Full-text

A public data set of spatio-temporal match events in soccer competitions

Scientific Data ◽

10.1038/s41597-019-0247-7 ◽

2019 ◽

Vol 6 (1) ◽

Cited By ~ 12

Author(s):

Luca Pappalardo ◽

Paolo Cintia ◽

Alessio Rossi ◽

Emanuele Massucco ◽

Paolo Ferragina ◽

...

Keyword(s):

Data Science ◽

Social Systems ◽

Team Sports ◽

Data Set ◽

Evaluation Of Performance ◽

Public Data ◽

Wide Range ◽

Spatio Temporal ◽

Measurement And Evaluation ◽

Temporal Events

Abstract Soccer analytics is attracting increasing interest in academia and industry, thanks to the availability of sensing technologies that provide high-fidelity data streams for every match. Unfortunately, these detailed data are owned by specialized companies and hence are rarely publicly available for scientific research. To fill this gap, this paper describes the largest open collection of soccer-logs ever released, containing all the spatio-temporal events (passes, shots, fouls, etc.) that occured during each match for an entire season of seven prominent soccer competitions. Each match event contains information about its position, time, outcome, player and characteristics. The nature of team sports like soccer, halfway between the abstraction of a game and the reality of complex social systems, combined with the unique size and composition of this dataset, provide an ideal ground for tackling a wide range of data science problems, including the measurement and evaluation of performance, both at individual and at collective level, and the determinants of success and failure.

Download Full-text