Spatial Co-location Patterns Research Articles

Point process decomposition method for multi-scale spatial co-location pattern mining

Point process decomposition method for multi-scale spatial co-location pattern mining

Source Apportionment of Soil Heavy Metals Based on Spatial Co-Location Patterns

Source Apportionment of Soil Heavy Metals Based on Spatial Co-Location Patterns

High Influencing Pattern Discovery over Time Series Data

A spatial co-location pattern denotes a subset of spatial features whose instances frequently appear nearby. High influence co-location pattern mining is used to find co-location patterns with high influence in specific aspects. Studies of such pattern mining usually rely on spatial distance for measuring nearness between instances, a method that cannot be applied to an influence propagation process concluded from epidemic dispersal scenarios. To discover meaningful patterns by using fruitful results in this field, we extend existing approaches and propose a mining framework. We first defined a new concept of proximity to depict semantic nearness between instances of distinct features, thus applying a star-shaped materialized model to mine influencing patterns. Then, we designed attribute descriptors to perceive attributes of instances and edges from time series data, and we calculated the attribute weights via an analytic hierarchy process, thereby computing the influence between instances and the influence of features in influencing patterns. Next, we constructed influencing metrics and set a threshold to discover high influencing patterns. Since the metrics do not satisfy the downward closure property, we propose two improved algorithms to boost efficiency. Extensive experiments conducted on real and synthetic datasets verified the effectiveness, efficiency, and scalability of our method.

Discovering co-location patterns in multivariate spatial flow data

ABSTRACT Spatial flow co-location patterns (FCLPs) are important for understanding the spatial dynamics and associations of movements. However, conventional point-based co-location pattern discovery methods ignore spatial movements between locations and thus may generate erroneous findings when applied to spatial flows. Despite recent advances, there is still a lack of methods for analyzing multivariate flows. To bridge the gap, this paper formulates a novel problem of FCLP discovery and presents an effective detection method based on frequent-pattern mining and spatial statistics. We first define a flow co-location index to quantify the co-location frequency of different features in flow neighborhoods, and then employ a bottom-up method to discover all frequent FCLPs. To further establish the statistical significance of the results, we develop a flow pattern reconstruction method to model the benchmark null hypothesis of independence conditioning on univariate flow characteristics (e.g. flow autocorrelation). Synthetic experiments with predefined FCLPs verify the advantages of our method in terms of correctness over available alternatives. A case study using individual home-work commuting flow data in the Chicago Metropolitan Area demonstrates that residence- or workplace-based co-location patterns tend to overestimate the co-location frequency of people with different occupations and could lead to inconsistent results.

Multilayer network structure and city size: A cross-sectional analysis of global cities to detect the correlation between street and terrain

The high share of impermeable surfaces in cities modifies the terrain characteristics that facilitate natural water flow and balance. The street network, an impervious surface on its own, is also the impetus for developing other impervious surfaces by facilitating access. The purpose of this work is to assess the interconnectedness between the underlying structural lines of the terrain and the street network for making informed decisions on locating green infrastructure to maintain water balance. For this purpose, the work measures the spatio-structural similarity between the co-located networks, assesses the variation of the measure with city size and relation to an indicator of water balance. Cross-sectional analysis is performed across a large sample of cities of varying sizes to extract generalized patterns of spatial structure and variations to size. The larger cities have low index values of spatio-structural similarity ranging between –0.2 and 0.2. The low index values for larger cities relate to the emergence of small-world properties in large street networks for functional efficiency and large street networks' web-like shape. Next, the paper identifies two zones based on the interconnectedness of the roads and the terrain. The spatial extent of a zone based on points where the arterial road intersects higher orders of drainage channels and ridgelines is associated with the number of above-normal wet conditions (SPEI ≥ 2.0) with the r-value of –0.30 at a p-value of 0.05. In summary, spatial statistics on spatial network data are helpful to extract trends inherent in the multi-layered network structure of cities to provide informed solutions. The policymakers and planners can use the spatial co-location patterns between street and terrain to make data-driven decisions to locate interventions for a nature-based resilient city.

Segregation or integration? Exploring activity disparities between migrants and settled urban residents using human mobility data

AbstractDue to the difficulty of tracking large numbers of new migrants, how their daily activity behaviors differ from those of settled residents has not been well investigated, leading to a lack of understanding of new migrants' integration. Meanwhile, existing research largely emphasized residential space and ignored other activity disparities. To obtain a more comprehensive picture of urban segregation, we identified new migrants and two settled urban groups from two kinds of human mobility data. A S‐T‐A‐D‐I interactive framework was proposed to measure segregation from multiple activity dimensions, including spatial colocation, temporal coexistence, accessibility, activity diversity, and social interaction. Two‐scale analysis of spatial colocation patterns reveals residential segregation by both residential location and housing type, suggesting the effectiveness of the mobility data in profiling socioeconomic groups. The temporal disparity in undertaking activities was unveiled by identifying temporal coexistence patterns. Moreover, the groups presented significant inequality in accessibility owing to the use of different travel modes, leading to a notable disparity in activity diversity. Jointly determined by the disparities in space, time, and diversity, the three groups generated a high level of self‐segregation, and new migrants and transit users presented very low interaction potentials with the car group.

Spatial Colocation Pattern Discovery Incorporating Fuzzy Theory

Spatial colocation patterns are subsets of spatial feature sets that are frequently “neighboring” in space. In the majority of existing mining methods, neighboring is determined by a single distance threshold and does not take the neighboring degree into consideration causing many neighbor relationships to be lost and they also cannot objectively describe the correlation between spatial features. In addition, existing methods ignore the instance-sharing problem of spatial neighbor relationships when calculating the prevalence of colocation patterns. In order to overcome these weaknesses, this article introduces the fuzzy theory into the spatial colocation pattern discovery. Through the fuzziness of spatial neighbor relationships between spatial instances, we develop a reasonable fuzzy proximity metric, which takes the instance-sharing problem into account and which measures the similarity between different spatial features. Three effective fuzzy clustering methods are proposed, which ensure that colocation patterns can be extracted accurately and quickly. Finally, extensive experiments on five synthetic datasets and five real-world datasets prove the practicability and efficiency of the proposed methods.

Efficient discovery of co-location patterns from massive spatial datasets with or without rare features

A co-location pattern indicates a group of spatial features whose instances are frequently located together in proximate geographic area. Spatial co-location pattern mining (SCPM) is valuable for many practical applications. Numerous previous SCPM studies emphasize the equal participation per feature. As a result, the interesting co-locations with rare features cannot be captured. In this paper, we propose a novel interest measure, i.e., the weighted participation index (WPI), to identify co-locations with or without rare features. The WPI measure possesses a conditional anti-monotone property which can be utilized to prune the search space. In addition, a fast row instance identification mechanism based on the ordered NR-tree is proposed to enhance efficiency. Subsequently, the ordered NR-tree-based algorithm is developed. To further improve efficiency and process massive spatial data, we break the ordered NR-tree into multiple independent subtrees, and parallelize the ordered NR-tree-based algorithm on MapReduce framework. Extensive experiments are conducted on both real and synthetic datasets to verify the effectiveness, efficiency and scalability of our techniques.

A spatial co-location pattern mining framework insensitive to prevalence thresholds based on overlapping cliques

Discovering spatial co-location patterns is a process of finding groups of distinct spatial features whose instances are frequently located together in spatial proximity. A co-location pattern is prevalent if its participation index is no less than a minimum prevalence threshold given by users. Most of the existing algorithms are very sensitive to the prevalence threshold, when users change the prevalence threshold, these algorithms have to re-collect table instances and re-calculate participation indexes of all patterns for mining the prevalent patterns that users expect to acquire. To tackle this issue, we propose an overlapping clique-based spatial co-location pattern mining framework (OCSCP). In our framework, we design a two-level filter mechanism with the first level is a feature type filter and the second level is a neighboring instance filter. By employing the mechanism, under a certain neighbor relationship, spatial instances are divided into a set of overlapping cliques and each clique is also a co-location instance of a pattern. And then, a co-location pattern hash map structure is designed to store table instances of patterns based on these overlapping cliques. The participation index of each pattern can be fast and directly calculated from the hash map structure. Thus, when the prevalence threshold is changed, the proposed framework does not need to re-gather table instances, and the mining result can be adaptively and quickly given to users. The proposed algorithms are performed on both synthetic and real-world data sets to demonstrate that our algorithms can rapidly respond to user requirements compared to the previous algorithms.

Maximal Instance Algorithm for Fast Mining of Spatial Co-Location Patterns

The explosive growth of spatial data and the widespread use of spatial databases emphasize the need for spatial data mining. The subsets of features frequently located together in a geographic space are called spatial co-location patterns. It is difficult to discover co-location patterns because of the huge amount of data brought by the instances of spatial features. A large fraction of the computation time is devoted to generating row instances and candidate co-location patterns. This paper makes three main contributions for mining co-location patterns. First, the definition of maximal instances is given and a row instance (RI)-tree is constructed to find maximal instances from a spatial data set. Second, a fast method for generating all row instances and candidate co-locations is proposed and the feasibility of this method is proved. Third, a maximal instance algorithm with no join operations for mining co-location patterns is proposed. Finally, experimental evaluations using synthetic data sets and a real data set show that maximal instance algorithm is feasible and has better performance.

Mining Maximal Dynamic Spatial Colocation Patterns.

A spatial colocation pattern represents a subset of spatial features with instances that are prevalently located together in a geographic space. Although many algorithms for mining spatial colocation patterns have been proposed, the following problems still remain. these methods miss certain meaningful patterns (e.g., {Ganoderma_lucidumnew, maple_treedead} and {water_hyacinthnew(increase), algaedead(decrease)}) and obtain a wrong conclusion if the instances of two or more features increase/decrease (i.e., new/dead) in the same/approximate proportion, which has no effect on the prevalent patterns; and the efficiency of existing methods is low in mining prevalent spatial colocation patterns, because the number of prevalent spatial colocation patterns is quite large. Therefore, we first propose the concept of a dynamic spatial colocation pattern that can reflect the dynamic relationships among spatial features. Second, we mine a small number of prevalent maximal dynamic spatial colocation patterns that can derive all prevalent dynamic spatial colocation patterns, which can improve the efficiency of obtaining all prevalent dynamic spatial colocation patterns. Third, we propose an algorithm for mining prevalent maximal dynamic spatial colocation patterns and two pruning strategies. Finally, the effectiveness and efficiency of the proposed method and the pruning strategies are verified by extensive experiments over real/synthetic data sets.

Computing Co-Location Patterns in Spatial Data with Extended Objects: A Scalable Buffer-Based Approach

Spatial co-location patterns are subsets of spatial features usually located together in geographic space. Recent literature has provided different approaches to discover co-location patterns over point spatial data. However, most approaches consider the neighborhood relationship among spatial objects as binary and are mainly designed for point spatial features, thus are not appropriate for extended spatial features such as line strings and polygons, the neighborhood relationship among which is naturally continuous. This paper adopts a buffer-based model for measuring the spatial relationship of extended objects and mining co-location patterns. While the buffer-based model has several advantages for extended spatial features, it involves high computational complexity due to the expensive buffer-level overlay operation. To tackle this challenge, we introduce a coarse-level co-location mining framework, which follows a filter-and-refine paradigm. Within the framework, we develop a serious of rigorous upper bounds based on geometric property and progressively prune search space with these upper bounds. Moreover, we develop a join-less schema to further reduce computation cost of size-k( $k>2$ k > 2 ) co-location patterns. Finally, we conduct experiments with large-scale spatial data to validate the efficiency of the developed algorithms against several state-of-art methods. All experimental results demonstrate the superiority of our methods.

Spatial co-location pattern mining based on the improved density peak clustering and the fuzzy neighbor relationship

<abstract> <p>Spatial co-location pattern mining discovers the subsets of spatial features frequently observed together in nearby geographic space. To reduce time and space consumption in checking the clique relationship of row instances of the traditional co-location pattern mining methods, the existing work adopted density peak clustering to materialize the neighbor relationship between instances instead of judging the neighbor relationship by a specific distance threshold. This approach had two drawbacks: first, there was no consideration in the fuzziness of the distance between the center and other instances when calculating the local density; second, forcing an instance to be divided into each cluster resulted in a lack of accuracy in fuzzy participation index calculations. To solve the above problems, three improvement strategies are proposed for the density peak clustering in the co-location pattern mining in this paper. Then a new prevalence measurement of co-location pattern is put forward. Next, we design the spatial co-location pattern mining algorithm based on the improved density peak clustering and the fuzzy neighbor relationship. Many experiments are executed on the synthetic and real datasets. The experimental results show that, compared to the existing method, the proposed algorithm is more effective, and can significantly save the time and space complexity in the phase of generating prevalent co-location patterns.</p> </abstract>

Efficiently mining maximal co-locations in a spatial continuous field under directed road networks

Extracting useful spatial co-location patterns from urban service facilities can help planners allocate limited resources effectively. These facilities are mostly distributed within man-made spatial fields with road-network constraints. To promote urban-space adaptivity, co-location algorithms for this network circumstance have been designed with distance decay effects and topological relationships of roads. However, these algorithms neglect the traffic direction, which affects the accuracy of the results. Moreover, the efficiency problem is more severe than with the traditional algorithm (i.e., no constraints). To address these problems, we propose an efficient maximal co-location mining algorithm with directed road-network constraints and spatial-continuity consideration (CMDS). To improve the accuracy, we design a network-based prevalence index, combined with both distance decay effects and road direction interference, to measure the significance of a pattern. To promote the execution speed, we use a key-node-separating approach and an improved shortest-path batch task for the co-location mining process. The experiments with both the synthetic and real datasets show that the CMDS algorithm is more efficient and accurate than the state-of-the-art network co-location when applied to problems in an urban space.

Delaunay triangulation‐based spatial colocation pattern mining without distance thresholds

AbstractA spatial colocation pattern is a group of spatial features whose instances frequently appear together in close proximity to each other. The proximity of instances is generally measured by the distance between them. If the distance is smaller than a distance threshold that is specified by users, they have a neighbor relationship. However, it is difficult for users to give a suitable distance threshold and mining results also vary widely with different distance thresholds. In addition, using distance thresholds are hard to accurately obtain neighborhoods of instances in heterogeneous distribution density data sets. In this study, we propose a new method for determining the neighbor relationship of instances in space without the distance threshold based on Delaunay triangulation (DT). We design three filtering strategies, such as a feature invalid edge, a global positive edge, and a local positive edge, to constrain the original DT to accurately extract the neighborhoods of instances in space. Then, a miner called DT‐based colocation (DTC) pattern mining is developed. Different from the traditional algorithms which adopt the time‐consuming generate‐test candidate model, DTC directly collects the table instances of colocation patterns from the constrained DT by building neighboring polygons and filters prevalent patterns. We compare the results mined by DTC with by the traditional algorithms at macrolevel and microlevel on both real and synthetic data sets to prove that the DTC algorithm improves the effectiveness and fineness of mining results.

THE IMPLEMENTATION OF HESITANT FUZZY SPATIAL CO-LOCATION PATTERN MINING ALGORITHM BASED ON PYTHON

Abstract. As one of the important research directions in the spatial data mining, spatial co-location pattern mining aimed at finding the spatial features whose the instances are frequent co-locate in neighbouring domain. With the introduction of fuzzy sets into traditional spatial co-location pattern mining, the research on fuzzy spatial co-location pattern mining has been deepened continuously, which extends traditional spatial co-location pattern mining to deal with fuzzy spatial objects and discover their laws of spatial symbiosis. In this paper, the operation principle of a classical join-based algorithm for mining spatial co-location patterns is briefly described firstly. Then, combining with the definition of classical participation rate and participation degree, a novel hesitant fuzzy spatial co-location pattern mining algorithm is proposed based on the establishment of the hesitant fuzzy participation rate and hesitant fuzzy participation formula according to the characteristics in fusion of hesitant fuzzy set theory, the score function and spatial co-location pattern mining. Finally, the proposed algorithm is written and implemented based on Python language, which uses a NumPy system to the expansion of the open source numerical calculation. The Python program of the proposed algorithm includes the method of computing hesitant fuzzy membership based on score function, the implementation of generating k-order candidate patterns, k-order frequent patterns and k-order table instances. A hesitant fuzzy spatial co-location pattern mining experiment is carried out and the experimental results show that the proposed and implemented algorithm is effective and feasible.

Discovering the joint influence of urban facilities on crime occurrence using spatial co-location pattern mining

The presence or absence of some urban facilities can shape the spatial distribution of crime occurrence. Exploring the joint influence of various types of facilities on crime occurrence has been a major concern for both crime prevention and urban planning. Previous research (e.g., the spatial conjunctive analysis of case configurations) have tried to ascertain the joint influence of facilities by identifying the frequent spatial configurations (combinations of facility types) that exist near criminal incidents. However, such a method neglects the prevalence of facilities and the spatial autocorrelation of crime occurrence, thus resulting in some spurious conclusions. To resolve this problem, borrowing methods from spatial pattern recognition and ecology, this study applied the spatial co-location pattern mining and pattern reconstruction approach to identify statistically significant spatial configurations for crime occurrence. The results show that the adopted approach effectively eliminates the influence of independent facility types with abundant instances, thus revealing statistically significant spatial configurations with better accuracy. These identified high-risk spatial configurations both confirm and expand on previous research; these configurations can also make a positive contribution to crime prevention and urban planning.

Mining Spatial Co-location Patterns from Vague Set

The target of mining spatial co-location patterns is discovering spatial association rule from spatial database, which plays an important role in many fields, investigate the distribution of plants for instance. Vague set extend the concept of fuzzy set, more flexible in terms of express and process fuzzy information. Some concepts such as vague spatial neighborhood relationship, vague participation ratio and vague participation index are defined in this paper first, after that, vague data filter rule and the algorithm of mining co-location patterns form vague set are proposed, the efficient prune strategy is presented in order to improve the efficiency of algorithm finally. The significance and efficiency of the techniques we propose are verified by experiments.

A MapReduce approach for spatial co-location pattern mining via ordered-clique-growth

Spatial co-location pattern is a subset of spatial features whose instances are frequently located together in geography. Mining co-location patterns are particularly valuable for discovering spatial dependencies. Traditional co-location pattern mining algorithms are computationally expensive with rapidly increasing of data volume. In this paper, we explore a novel iterative framework based on parallel ordered-clique-growth for co-location pattern mining. The ordered clique extension can re-use previously processed information and be executed in parallel, and hence speed up the identification of co-location instances. Based on the iterative framework, a MapReduce algorithm is designed to search for prevalent co-location patterns in a level-wise manner, namely PCPM_OC. To narrow the search space of ordered cliques, two pruning techniques are suggested for filtering invalid clique instances as much as possible. The completeness and correctness of PCPM_OC are proven and we also discuss its complexity in this paper. Moreover, we compare PCPM_OC with two advanced MapReduce based co-location pattern mining algorithms on multiple perspectives. At last, substantial experiments are conducted on synthetic and real-world spatial datasets to study the performance of PCPM_OC. Experimental results demonstrate that PCPM_OC has a significant improvement in efficiency and shows better scalability on massive spatial data.

Mining high influence co-location patterns from instances with attributes

A spatial co-location pattern describes coexistence of spatial features whose instances frequently appear together in geographic space. Numerous studies have been proposed to discover interesting co-location patterns from spatial data sets, but most of them only use the location information of instances. As a result, they cannot adequately reflect the influence between instances. In this paper, we take additional attributes of instances into account in the process of co-location pattern mining, and propose a new approach for discovering the high influence co-location patterns. In our approach, we consider the spatial neighboring relationships and the similarity of instances simultaneously, and utilize the information entropy approach to measure the influence of any instance exerting on its neighbors and the influence of any feature in a co-location pattern. Then, an influence index for measuring the interestingness of a co-location pattern is proposed and we prove the influence index measure satisfies the downward closure property that can be used for pruning the search space, and thus an efficient high influence co-location pattern mining algorithm is designed. At last, extensive experiments are conducted on synthetic and real spatial data sets. Experimental results reveal the effectiveness and efficiency of our method.