DATA MINIG SUPERVISED CLASSIFICATION TECHNIQUE TO IDENTIFY LOW-LYING AREAS WITH REMOTE SENSING
IMAGES
Dr.K.Jeyanthi Dr. D.Napoleon
Assistant Professor Assistant Professor
Department of Computer Science Department of Computer Science Government Arts and Science College School of Computer Science and
Kangeyam Engineering, Bharathiar University Coimbatore- 641046 Coimbatore- 641046
Tamil Nadu Tamil Nadu
Abstract
The higher numbers of cholera widespread death in minimum established republics is a dare for healthiness amenities. It is essential to prepare the situation by way of epidemiological investigation. Towards emphasize the capability of epidemiological shadowing, this article emphases on remote sensing satellite records handling by means of data mining approaches to ascertain threat zones of the widespread illness through linking the surroundings, weather and healthiness. These outpost information are pooled through arena records composed throughout the similar set of periods in direction to clarify plus abstract the reasons of the widespread progression commencing one era to an additional in relative to the surroundings.
The prevailing methodological (procedures) for handling satellite imageries are matured then well-organized, thus the contest nowadays is to offer the furthermost appropriate resources permitting the finest analysis of acquired outcomes. In lieu of that, we emphasis taking place supervised grouping procedure towards course a customary of satellite imageries as of the similar zone but on dissimilar stages.
Keywords: Threat Proof of identity, Data mining, Remote sensing, Low Lying areas.
INTRODUCTION
Cholera leftovers a chief community healthiness difficult in emerging republics. Additional fifty republics in the sphere undergo cholera epidemics by way of an middling of 200,000 numbers plus lethality level of 4 percentage. Close to that no nominal serum comprised in the WHO vaccination programs. Chennai is treated as the capital of Tamilnadu. Observing that the topographical influence
shows a chief part in this widespread, since it is 78 percentage of public remained the soaking proceeds habitation in the lakes, watercourses or rivers agreeing to the training, predominantly in wintering times. Certainly, all low lying zones are situated sideways of the River pathways of Chennai on its span South to the North. The development of the widespread has happened in the movement track of the West Stream State to the North. The transmittable infections are ahead further powdered each day thus swelling the threat of sick spreading. They consume in public minor viruses, frequently arthropods (lice or fleas, ticks, virus, mosquitoes, flies.) which are named vectors for the reason that they communicate the viruses from individual host to additional plus crowd. The spreading part of these virus is increasingly growing, with weather alteration initial up about prospects for the comeback of virus in beforehand secure residents.
Occasionally new susceptible areas are therefore extremely exaggerated. To overwhelm the boundaries of customary methods to battle beside waves, it is vital to adore the welfares of space tools in the battle of communicable viruses. The possible returns of the galaxy technology are abundant:
• Money matters: satellites shelter a huge zone without lengthy travel of the arena sides,
• Safety: the satellites shelter hazardous otherwise unreachable zones,
•Changing aspects: decryption of the virus spatial-temporal dynamic forces of sicknesses,
• Nursing: establishment of threat charts and epidemiological shadowing dais for healthier nursing and anticipation of waves.
METHODOLOGY AND ADOPTED APPROACHES This approach involves of six stages:
Epidemic field Satellite data
acquisition,
Data derived from images
Remote sensing measurements Discretization of data
Interpretation of results.
Data treatment
Fig 1: Data Flow chart
The methodology consists of six phases as described the 1 stage starts with Acquirement of data from the arena about widespread and satellite information acquisition, the 2 stage concerns the assortment and alteration of the valuable information, the 3 stage defines remote sensing dimensions NDVI-Normalized Difference Vegetation Index.
ACQUISITION OF SATELLITE DATA
There are numerous satellites placed everywhere in the sphere: approximately for geostationary overhead a area, and roughly others are revolving around the Earth, then all are conveying a non-stop link of information to the ground server : AVIRIS, Landsat, Quickbird, Ikonos, SPOT, ASTER, RadarSat, TMS, DTED, AVHRR.
α=cos-1
Where m=the number of bands.
ti=pixel spectrum.
ri=reference spectrum. α= radian of the spectral angle x = randn(10000,1);
h = histogram(x)
Fig 2: Satellite view
(a)
Fig 3: Detection of Low Lying areas
(b)
Fig 4: Real time view
(c)
(d)
h = Histogram with properties:
Data: [10000x1 double]
Values: [1x37 double]
NumBins: 37
BinEdges: [1x38 double]
BinWidth: 0.2000
BinLimits: [-3.8000 3.6000]
Normalization: 'count' FaceColor: 'auto' EdgeColor: [0 0 0]
CONCLUSION AND RELATED WORKS
Humankind will continuously be tackled with waves and the development of different virus. Worldwide observing plus struggles to report possible interruptions possessions of communicable viruses whose advent with multifactorial features are stimulating. For observing of communicable diseases, the usage of remote sensing is precise advantageous in the tele- epidemiology that comprises to gather data in the arena and satellite information to appearance and prevent pollution sickness associated to the surroundings discoverable by satellites. We emphasis on the use of data mining method to determine threat or not threat zones of widespread disaster from satellite imageries. For the study, we used supervised organization technique to practice a set of satellite imageries from the similar zone but on unalike stages. A matchless method of six phases is labeled to confirm appropriate means for altering truths, breeding facts and removing data. The deliberate method was efficiently assessed with the process in quantified area, to realize cholera widespread.
The chief contributions of the article are: discretization in the early stages and enlightening the value of acquired outcomes, establishing of the connection among the atmosphere and the widespread, and identification of maximum risky zones for the spread and occurrence of the widespread.
REFERENCES
[1] Abkar Ali-Akbar, Sharifi Mohammed Ali, Mulder Nanno J. Likelihood-based image segmentation and classification: a framework for the incorporation of expert knowledge in image classification procedures. International Journal of Applied Earth Observation and Geoinformation, Volume 2, Issue 2, 2000, Pages 104-119.
[2] Agrawal R. and Srikant R. Fast algorithms for mining suggestion rules in large databases.
Research Report RJ 9839, IBM Almaden Investigation Center, San Jose, California, June1994.
Ahmad Asmala, Quegan Shaun. Analysis of Maximum Likelihood Classification on Multispectral Data. Applied Mathematical Sciences, Vol. 6, 2012, no. 129, 6425 – 6436
[3] González Mariela Palacios, Bonaccorso Elisa, Papeş Monica. Applications of geographic material organizations and remote sensing techniques to conservation of amphibians in northwestern Ecuador. Global Ecology and Conservation, Volume 3, January 2015, Pages 562- 574.
[4] Hinton, G. E.; Osindero, S.; Teh, Y. W. (2006). A Fast Learning Algorithm for Deep Belief Nets. Neural Computation. 18 (7): 1527–1554
[5] Kansakar Pratistha, Hossain Faisal. A review of applications of satellite earth observation data for global societal benefit and stewardship of planet earth. Space Policy, Volume 36, May 2016, Pages 46-5ss
[6] M. Chen, S. Lu, Q. Liu, Uniform regularity for a Keller–Segel–Navier–Stokes system, Appl.
Math. Lett. 107 (2020) 106476, 2020.106476.
[7] U.Petrillo Ferraro, et al., Informational and linguistic analysis of large genomic sequence collections via efficient hadoop cluster algorithms, Bioinformatics 34 (11) (2018) 1–11.
[8] D. Kesavaraja, A. Shenbagavalli, Framework for fast and efficient cloud video transcoding system using intelligent splitter and hadoop mapreduce, Wirel. Pers. Commun. 2 (2018) 1–16.
[9] Abedin, Z., Dhar, P, Hossenand, M. K., Deb, K., 2017. Traffic Sign Detection and Recognition Using Fuzzy Segmentation Approach and Artificial Neural Network Classifier Respectively. International Conference on Electrical, Computer and Communication Engineering (ECCE), pp. 518-523.
[10] Cook, D., Youngblood, M., Heierman, I. Gopalratnam, E.O.K, Rao, S., Litvin, A., Khawaja, F., 2003. Mavhome: An Agent-Based Smart Home. In Proc. First IEEE Int’l Conf.
Pervasive Computing and Communication, pp. 521–524.
