Wednesday, 23 July 2014

Fast Nearest Neighbor Search with Keywords

Conventional spatial queries, such as range search and nearest neighbor retrieval, involve only conditions on objects’ geometric properties. Today, many modern applications call for novel forms of queries that aim to find objects satisfying both a spatial predicate, and a predicate on their associated texts. For example, instead of considering all the restaurants, a nearest neighbor query would instead ask for the restaurant that is the closest among those whose menus contain “steak, spaghetti, brandy” all at the same time. Currently, the best solution to such queries is based on the IR2-tree, which, as shown in this paper, has a few deficiencies that seriously impact its efficiency. Motivated by this, we develop a new access method called the spatial inverted index that extends the conventional inverted index to cope with multidimensional data, and comes with algorithms that can answer nearest neighbor queries with keywords in real time. As verified by experiments, the proposed techniques outperform the IR2-tree in query response time significantly, often by a factor of orders of magnitude.
The widespread use of search engines has made it realistic to write spatial queries in a brand new way. Conventionally, queries focus on objects’ geometric properties only, such as whether a point is in a rectangle, or how close two points are from each other. We have seen some modern applications that call for the ability to select objects based on both of their geometric coordinates and their associated texts. For example, it would be fairly useful if a search engine can be used to find the nearest restaurant that offers “steak, spaghetti, and brandy” all at the same time. Note that this is not the “globally” nearest restaurant (which would have been returned by a traditional nearest neighbor query), but the nearest restaurant among only those providing all the demanded foods and drinks. There are easy ways to support queries that combine spatial and text features. For example, for the above query, we could first fetch all the restaurants whose menus contain the set of keywords {steak, spaghetti, brandy}, and then from the retrieved restaurants, find the nearest one. Similarly, one could also do it reversely by targeting first the spatial conditions—browse all the restaurants in ascending order of their distances to the query point until encountering one whose menu has all the keywords.

·       It will fail to provide real time answers on difficult inputs.
·       Its closer neighbors are missing at least one of the query keywords.

In this paper, we design a variant of inverted index that is optimized for multidimensional points, and is thus named the spatial inverted index (SI-index). This access method successfully incorporates point coordinates into a conventional inverted index with small extra space, owing to a delicate compact storage scheme. Meanwhile, an SI-index preserves the spatial locality of data points, and comes with an R-tree built on every inverted list at little space overhead. As a result, it offers two competing ways for query processing. We can (sequentially) merge multiple lists very much like merging traditional inverted lists by ids. Alternatively, we can also leverage the R-trees to browse the points of all relevant lists in ascending order of their distances to the query point. As demonstrated by experiments, the SI-index significantly outperforms the IR2-tree in query efficiency, often by a factor of orders of magnitude.
·       It offers two competing ways for query processing.
·       It uses Inverted indexes (I-index), it have proved to be an effective access method for keyword-based document retrieval.



ü Processor                  -        Pentium –IV

ü Speed                        -        1.1 Ghz
ü RAM                         -        512 MB(min)
ü Hard Disk                 -        40 GB
ü Key Board                -        Standard Windows Keyboard
ü Mouse                       -        Two or Three Button Mouse
ü Monitor                     -        LCD/LED


         Operating system :         Windows XP
         Coding Language :         Java
         Data Base             :         MySQL
         Tool                     :         Net Beans IDE


Yufei Tao and Cheng Sheng Fast Nearest Neighbor Search with Keywords IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, VOL. 26, NO. 4, APRIL 2014.

No comments:

Post a Comment