Discovering correlated spatio-temporal changes in evolving graphs

Chan, Jeffrey; Bailey, James E.; Leckie, Christopher

doi:10.1007/s10115-007-0117-z

Cited by 46 publications

(42 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second part has a complexity of O(n), thanks to the fact that the groups formation in grids is done by exploring the finite and bounded set of only the closest neighbors of each of the pixels, where each pixel relation evaluation is done only onceresulting in the number of such evaluations being linear in the number of pixels. Since contains at most u groups (due to the property of at least one seed per group), the cost of the third part is simply O(um), u << n. Overall, the time complexity of IPCOSA is O((knm) 2 ).…”

Section: Spatial Averaging Of Pixel Groups Based On Inter-pixel Corrementioning

confidence: 98%

“…Next, we employ a graded group formation phase (step 5), where the correlation strength dictates the group formation order: groups having the strongest inter-similarity are generated first, ensuring that the eventually formed groups exploit the similarity property to its full extent (only positive correlation coefficient thresholds are used). 2 The group formation is subject to the following guidelines: a group of pixels must contain at least one seed within it to base the group on. Once chosen, the seed's proximate neighbors' correlation scores are examined.…”

Section: Spatial Averaging Of Pixel Groups Based On Inter-pixel Corrementioning

confidence: 99%

See 1 more Smart Citation

Obtaining scalable and accurate classification in large-scale spatio-temporal domains

et al. 2010

View full text Add to dashboard Cite

We present an approach for learning models that obtain accurate classification of data objects, collected in large-scale spatio-temporal domains. The model generation is structured in three phases: spatial dimension reduction, spatio-temporal features extraction, and feature selection. Novel techniques for the first two phases are presented, with two alternatives for the middle phase. We explore model generation based on the combinations of techniques from each phase. We apply the introduced methodology to data-sets from the Voltage-Sensitive Dye Imaging (VSDI) domain, where the resulting classification models successfully decode neuronal population responses in the visual cortex of behaving animals. VSDI is currently the best technique enabling simultaneous high spatial (10,000 points) and temporal (10 ms or less) resolution imaging from neuronal population in the cortex. We demonstrate that not only our approach is scalable enough to handle computationally challenging data, but it also contributes to the neuroimaging field of study with its decoding abilities. The effectiveness of our methodology is further explored on a data-set from the hurricanes domain, and a promising direction, based on the preliminary results of hurricane severity classification, is revealed.

show abstract

Section: Spatial Averaging Of Pixel Groups Based On Inter-pixel Corrementioning

confidence: 98%

Section: Spatial Averaging Of Pixel Groups Based On Inter-pixel Corrementioning

confidence: 99%

Obtaining scalable and accurate classification in large-scale spatio-temporal domains

et al. 2010

View full text Add to dashboard Cite

show abstract

“…[13,28], and Ref. [5], respectively. They all provide some kind of summaries, but the objective and result achieved are substantially different from those of this paper.…”

Section: Related Workmentioning

confidence: 99%

Graph OLAP: a multi-dimensional framework for graph data analysis

et al. 2009

View full text Add to dashboard Cite

Databases and data warehouse systems have been evolving from handling normalized spreadsheets stored in relational databases, to managing and analyzing diverse application-oriented data with complex interconnecting structures. Responding to this emerging trend, graphs have been growing rapidly and showing their critical importance in many applications, such as the analysis of XML, social networks, Web, biological data, multimedia data and spatiotemporal data. Can we extend useful functions of databases and data warehouse systems to handle graph structured data? In particular, OLAP (On-Line Analytical Processing) has been a popular tool for fast and user-friendly multi-dimensional analysis of data warehouses. Can we OLAP graphs? Unfortunately, to our best knowledge, there are no OLAP tools available that can interactively view and analyze graph data from different perspectives and with multiple granularities. In this paper, we argue that it is critically important to OLAP graph structured data and propose a novel Graph OLAP framework. According to this framework, given a graph dataset with its nodes and edges associated with respective attributes, a multi-dimensional model can be built to enable efficient online analytical processing so that any portions of the graphs can be generalized/specialized dynamically, offering multiple, versatile views of the data. The contributions of this work are three-fold. First, starting from basic definitions, i.e., what are dimensions and measures in the Graph OLAP scenario, we develop a conceptual framework for data cubes on graphs. We also look into different semantics of OLAP operations, and classify the framework into two major subcases: informational OLAP and topological OLAP. Second, we show how a graph cube can be materialized by calculating a special kind of measure called aggregated graph and how to implement it efficiently. This includes both full materialization and partial materialization where constraints are enforced to obtain an iceberg cube. As we can see, due to the increased structural complexity of data, aggregated graphs that depend on the underlying "network" properties of the graph dataset are much harder to compute than their traditional OLAP counterparts. Third, to provide more flexible, interesting and informative OLAP of graphs, we further propose a discovery-driven multi-dimensional analysis model to ensure that OLAP is performed in an intelligent manner, guided by expert rules and knowledge discovery processes. We outline such a framework and discuss some challenging research issues for discovery-driven Graph OLAP.

show abstract

“…Several recent studies have touched on the analysis of dynamic networks including analyzing changes of global properties, detecting anomalous changes, mining dynamic frequent subnets, and discovering similar evolving regions in evolving networks [7] and even the dynamic communities by combining the information of communities in each network using traditional community detection methods. However, the community structure in two or more slices of a series of time-varying networks has not been well addressed directly [8,9].…”

Section: Pacs Numbers: Valid Pacs Appear Herementioning

confidence: 99%

“…A typical example is the protein interaction network in biology which represent all proteins of an organism and all interactions regardless of the conditions and time under which interactions may take place [5]. In reality, most of relationships modeled by networks evolve with time or conditions [6].Several recent studies have touched on the analysis of dynamic networks including analyzing changes of global properties, detecting anomalous changes, mining dynamic frequent subnets, and discovering similar evolving regions in evolving networks [7] and even the dynamic communities by combining the information of communities in each network using traditional community detection methods. However, the community structure in two or more slices of a series of time-varying networks has not been well addressed directly [8,9].…”

mentioning

confidence: 99%

Common community structure in time-varying networks

Zhang

Zhao²,

Xia³

2012

Phys. Rev. E

View full text Add to dashboard Cite

In this report, we introduce the concept of co-community structure in time-varying networks. We propose a novel optimization algorithm to rapidly detect co-community structure in these networks. Both theoretical and numerical results show that the proposed method not only can resolve detailed co-communities, but also can effectively identify the dynamical phenomena in these networks. PACS numbers: Valid PACS appear hereNetworks consisting of vertices and edges connecting some pairs of vertices are powerful abstractions of relational data, hence have become very popular tools in many fields including sociology, biology and physics [1]. The characteristic of community structure in networks, i.e., networks are naturally divided into modules or communities, has attracted huge attention in the past decade which can provide insights into the structure and dynamic formation of networks. Many methods for community detection in one network have been developed and studied even including the fuzzy community structure identification problem [2] and the more challenging community detection problem in directed networks [3] (see Ref.[4] for recent comprehensive reviews).However, previous studies have concentrated on uncovering community structure in a static network which only represents a summarized picture of all possible relations. A typical example is the protein interaction network in biology which represent all proteins of an organism and all interactions regardless of the conditions and time under which interactions may take place [5]. In reality, most of relationships modeled by networks evolve with time or conditions [6].Several recent studies have touched on the analysis of dynamic networks including analyzing changes of global properties, detecting anomalous changes, mining dynamic frequent subnets, and discovering similar evolving regions in evolving networks [7] and even the dynamic communities by combining the information of communities in each network using traditional community detection methods. However, the community structure in two or more slices of a series of time-varying networks has not been well addressed directly [8,9].In this report, we propose the concept of co-community structure in two or more networks of a series of timevarying networks. The basic assumption is that an essential and common community structure may exist in two or more networks, and local dynamic changes may happen. This is very realistic in time-varying networks of many robust systems.Suppose that we are given the structure of two or * Electronic address: zsh@amss.ac.cn more networks of the same vertices, we aim to determine whether there exists any co-community structure, or say similar groups or communities in these networks. Moreover, along this goal, we attempt to uncover the dynamic characteristics of some vertices. Mathematically, the co-community structure and dynamical characteristic are stored in matrices which can be determined by an efficient optimization procedure. Let us focus initially on the problem in two networks ...

show abstract

Discovering correlated spatio-temporal changes in evolving graphs

Cited by 46 publications

References 36 publications

Obtaining scalable and accurate classification in large-scale spatio-temporal domains

Obtaining scalable and accurate classification in large-scale spatio-temporal domains

Graph OLAP: a multi-dimensional framework for graph data analysis

Common community structure in time-varying networks

Contact Info

Product

Resources

About