Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/121776
Title: Clustering and Time Series Prediction for Spatio Temporal Geographic Dataset
Researcher: Agrawal Kedar Prasad
Guide(s): Garg Sanjay
Keywords: Clustering
dataset
forecasting
geographic
spatio
Temporal
University: Nirma University
Completed Date: 29/07/2016
Abstract: Owing to the generation of petabytes of data (may be of type classical, spatial, temporal or hybrid) newlineon daily basis from different sources, work is required to be carried out such that these voluminous newlineamount of data can be utilized meaningfully using relevant data mining tasks. When it is required newlineto deal with Spatio-Temporal dataset, data mining related tasks becomes more challenging newlinespecially in case of obtaining arbitrary shaped clusters of good quality and reliable forecasting. newlineBased on reliable forecasting, some anticipatory action like Land Usage, availability of good and newlinehealthy crops or no crops, good rains, flood or detecting drought areas etc. can be taken which is newlinebeneficial to masses. In clustering, issues like detection of arbitrary shaped clusters, handling high newlinedimensional data, independence from order of data input, interpretability, ability to deal with newlinenested clusters, scalability etc. and while forecasting, issues like handling non-stationarity of time newlineseries, non-linear domain, selection and tuning of parameters of existing or newly developed newlinetechnique(s) needs to be addressed with utmost care. newlineSpatio-Temporal Data Mining (STDM) is a process of the extraction of implicit knowledge, spatial newlineand temporal relationships, or other patterns not explicitly stored in spatio-temporal databases. As newlinedata is growing not only from static view point, but they also evolve spatially and temporally which newlineis dynamic in nature that is the reason why this field is now becoming very important field of newlineresearch. In addition Spatio-Temporal (ST) -Data tends to be highly auto-correlated, because of newlinewhich assumptions which are taken in Gaussian distribution models fails, as in Gaussian newlineDistribution, an assumption of independence is taken into consideration, which is not the case with newlineST Data. Vital issues in spatio temporal clustering technique for Earth observation data is to obtain newlinegood quality arbitrarily shaped clusters and its validation. The presented research work addresses newlinethese issues and presents t
Pagination: 
URI: http://hdl.handle.net/10603/121776
Appears in Departments:Institute of Technology

Files in This Item:
File Description SizeFormat 
02_certificate.pdfAttached File183.05 kBAdobe PDFView/Open
03_abstract.pdf77.65 kBAdobe PDFView/Open
04_declaration.pdf195.76 kBAdobe PDFView/Open
10_chapter1.pdf88.06 kBAdobe PDFView/Open
11_chpater2.pdf706.78 kBAdobe PDFView/Open
12_chapter3.pdf274.59 kBAdobe PDFView/Open
13_chapter4.pdf1.66 MBAdobe PDFView/Open
14_chapter 5.pdf761.34 kBAdobe PDFView/Open
15_conclusion.pdf9.02 kBAdobe PDFView/Open
16_summary.pdf179.8 kBAdobe PDFView/Open
17_bibliography.pdf242.81 kBAdobe PDFView/Open
1_title.pdf3.54 kBAdobe PDFView/Open
5_acknowledgement.pdf67.64 kBAdobe PDFView/Open
6_contents.pdf79.06 kBAdobe PDFView/Open
7_list_of_tables.pdf81.53 kBAdobe PDFView/Open
8_list_of_figures.pdf84.88 kBAdobe PDFView/Open


Items in Shodhganga are protected by copyright, with all rights reserved, unless otherwise indicated.