Abstract
With the development of the spatial data mining technologies the researcher are grouping towards using the same in various domains. Once such domain is the high resolution images of the urban land. The process includes the collection of segmented image for the various scenes and the classification technique is used to check the probability that segment belongs to the same urban cover along with the class assignment. The classifier previously make use of the random forest tree classification algorithm to develop the network model for semantic web and attribute selection process. However the attribute selection process accuracy can be further improved using the Hoeffding decision tree algorithm where the node split is controlled through the error rate. It’s an incremental, anytime decision tree induction algorithm that is capable of learning from massive data streams, assuming that the distribution generating examples does not change over time. The leaf predicting strategy is optimized for the Hoeffding tree through Naïve Bayes adaptive process for predicting the land cover with high accuracy rate. The result were simluated using weka as an open source software.
Similar content being viewed by others
References
Aksoy S, et al (2004) Interactive training of advanced classifiers for mining remote sensing image archives. In: ACM international conference on knowledge discovery and data mining, Seattle, WA
Datcu M et al (2003) Information mining in remote sensing image archives—part a: system concepts. IEEE Trans Geosci Remote Sens 4:2923–2936
Domingos P, Hulten G (2000) Mining high-speed data stream. Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining, pp 71–80
Han W, Burian S (2009) Determining effective impervious area for urban hydrologic modelling. J Hydrol Eng 14:111–120
Herold M, Liu X, Clarke KC (2003) Spatial metrics and image texture for mapping urban land use. Photogramm Eng Remote Sens 69(9):991–1001
Johnson B, Xie Z (2013) Classifying a high resolution image of an urban area using super-object information. ISPRS J Photogramm Remote Sens 83:40–49
Kumari SR, KrishnaKumari P (2015) Adaptive anomaly intrusion detection system using optimized Hoeffding tree and adaptive drift detection method. Middle-East J Sci Res 22:1212–1218
Lang S, Schopfer E, Holbling D (2008) Quantifying and qualifying urban green by integrating remote sensing, GIS, and social science methods. In: Petrosillo I, Jones KB, Kepner WG, Krauze K, Li BL, Muller F, Victorov S, Zurlini G (eds) Use of landscape sciences for the assessment of environmental security. Springer, Dordrecht, pp 93–105
Pal M (2005) Random forest classifier for remote sensing classification. Int J Remote Sens 26:217–222
Utgo PE (1989) Incremental induction of decision trees. Mach Learn 4:161–186
Walton J, Nowak D (2008) Assessing urban forest canopy cover using airborne or satellite imagery. Arboricult Urban For 34:334–340
Witten IH, Frank H (1999) Data mining: practical machine learning tools and techniques with java implementations. Morgan Kaufmann, San Francisco
Acknowledgments
I would like to thank the Mr. Brian Robinson for sharing and authorizing me to use the dataset through UCI machine learning Repository [6].
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Srivastava, S. Improved Classification of the High-Resolution Image Data Using Hoeffding Algoritm. Ann. Data. Sci. 3, 63–70 (2016). https://doi.org/10.1007/s40745-016-0070-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40745-016-0070-3