- Trending Categories
- Data Structure
- Networking
- RDBMS
- Operating System
- Java
- MS Excel
- iOS
- HTML
- CSS
- Android
- Python
- C Programming
- C++
- C#
- MongoDB
- MySQL
- Javascript
- PHP
- Physics
- Chemistry
- Biology
- Mathematics
- English
- Economics
- Psychology
- Social Studies
- Fashion Studies
- Legal Studies

- Selected Reading
- UPSC IAS Exams Notes
- Developer's Best Practices
- Questions and Answers
- Effective Resume Writing
- HR Interview Questions
- Computer Glossary
- Who is Who

# What is STING grid-based clustering?

The grid-based clustering methods use a multi-resolution grid data structure. It quantizes the object areas into a finite number of cells that form a grid structure on which all of the operations for clustering are implemented. The benefit of the method is its quick processing time, which is generally independent of the number of data objects, still dependent on only the multiple cells in each dimension in the quantized space.

The grid-based clustering uses a multi-resolution grid data structure and uses dense grid cells to form clusters. There are several interesting methods are STING, wave cluster, and CLIQUE.

**STING** − A statistical information Grid approach. The spatial area is split into rectangular cells. There are various levels of cells corresponding to different methods of resolution. Each cell at a high level is separated into multiple smaller cells in the next lower level. Statistical data of each cell is computed and stored beforehand and can answer queries. The specification of higher-level cells can be simply computed from the specification of lower-level cells:

- count, mean, s, min, max
- type of distribution-normal, uniform, etc.

The statistical information grid-based approach (STING) follows a hierarchical approach to divide the spatial area into rectangular cells similar to a quadtree. The spatial database is scanned once, and statistical parameters are determined for each cell. The STING technique can be viewed as a type of hierarchical approach. The first step is to make a hierarchical description. The created tree separately divides the area into quadrants.

The process to create the tree is shown in the algorithm given below. Each cell in the space corresponds to a node in the tree and is described with both attributeindependent (count) data and attribute-dependent (mean, standard deviation,minimum, maximum distribution) data. Since the number of nodes in the tree is less than the number of items in the database, the complexity of STING BUILD is O (n).

## Algorithm

**Input**

D // Data to be placed in the hierarchical structure k // Number of desired cells at the lowest level

**Output**

T // Tree STING BUILD algorithm // Create an empty tree from top-down T = root node with data values initialized; // Initially only root node i = 1; repeat for each node in level i do create 4 children nodes with initial values; i = i +1; until 4^{i}= k; // Populate tree from bottom-up for each item in D do determine leaf node j related to the position of D; update values of j based on attribute values in item; i := log_{4}(k); repeat i: = i - 1; for each node j in level i do update values of j based on attribute values in its 4 children; until i = 1;

- Related Articles
- What are the algorithms of Grid-Based Clustering?
- What is Prototype-Based Clustering?
- What is model-based clustering?
- What is Grid Based Methods?
- What are the approaches of Graph-based clustering?
- What is STING?
- What is Clustering?
- What is Conceptual Clustering?
- What is Multirelational clustering?
- What is Multi-relational Clustering?
- What is K-means clustering?
- What is Agglomerative Hierarchical Clustering?
- What is Document Clustering Analysis?
- What is clustering Index in DBMS?
- What is an Agglomerative Clustering Algorithm?