Spatio-Temporal Sensor Graphs (STSG): A data model for the discovery of spatio-temporal patterns1

Abstract

Developing a model that facilitates the representation and knowledge discovery on sensor data presents many challenges. With sensors reporting data at a very high frequency, resulting in large volumes of data, there is a need for a model that is memory efficient. Since sensor data is spatio-temporal in nature, the model must also support the time dependence of the data. Balancing the conflicting requirements of simplicity, expressiveness and storage efficiency is challenging. The model should also provide adequate support for the formulation of efficient algorithms for knowledge discovery. Though spatio-temporal data can be modeled using time expanded graphs, this model replicates the entire graph across time instants, resulting in high storage overhead and computationally expensive algorithms. In this paper, we propose Spatio-Temporal Sensor Graphs (STSG) to model sensor data at the conceptual. logical and physical levels. This model allows the properties of edges and nodes to be modeled as a time series of measurement data. Data at each instant would consist of the measured value and the expected error. Also, we evaluate the model using methods to find interesting patterns such as growing hotspots in sensor data and present analytical comparison of the algorithms with methods based on existing models.

Managing large-scale transient data in IoT systems

“…Data Modeling: The citation [3] presents spatio-temporal sensor graphs, a data model for representing sensor data. Its key usefulness is a memory-efficient model for representing fastchanging sensor data, that also supports adequate support for knowledge discovery from the model.…”

Characterizing sensor datasets with multi-granular spatio-temporal intervals

“…A number of approaches use graphs to represent spatio-temporal features for the purposes of data mining [11,8,7,4]. Finally, a rich body of literature is focused on time series segmentation which divides a temporal sequence into a set of meaningful intervals [2,10,9,15,15,5,13,6].…”

Spatio-temporal Networks

“…TAG keeps track of these changes through a time series attached to each node and edge that indicates their presence at various instants of time. The stochastic nature of the physical relationships between the sensors (e.g., the flow rate of the river stream that connects the sensors) is accounted for by expressing each element in the attribute time series as a pair of values (i.e., ¡measured value, error¿) [15].…”

“…A modified breadth first strategy is used to find the nodes that indicate the hot spots at any time instant. The pseudo-code is provided in Algorithm 1 [15].…”