Qualification: 
M.Tech
geethuth@am.amrita.edu

Geethu T. H. currently serves as Research Associate at the Amrita Center for Wireless Networks & Applications (Amrita WNA), Amritapuri Campus, since August 2014. She is doing the data analysis part of Landslide project. Geethu pursued her MTech in Computer Science and Engineering.

Areas of Interest

  • Data analysis
  • Machine learning

Publications

Publication Type: Conference Paper

Year of Publication Publication Type Title

2014

Conference Paper

D. P., B Thottungal, G., Geethalekshmy, C. V., and D Ramesh, M. V., “Automated Statistical Data Mining of a Real World Landslide Detection System”, in Proceedings of the International Conference on Data Mining (DMIN), 2014.[Abstract]


Wireless sensor network for landslide detection deployed in Munnar consists of 150 geophysical sensors which are spatially distributed over 20 Deep Earth Probes (DEP) located at different areas in the deployment site. The data received from each of these heterogeneous sensors are mined to retrieve the correlation between the various parameters contributing to landslide, using appropriate statistical methods. This paper presents an architecture which we have developed for automatic data mining of landslide data which will ultimately help in issuing an early warning for occurrence of landslides. Several algorithms were developed towards achieving this objective of effective data analysis of the continuous real time data collected from the deployment field. The results show that the slope instability in a region is dependent not only the intensity of rainfall but also the antecedent rainfall conditions and soil layer parameters. Each of these different algorithms and its results are explained in detail in this paper.

More »»
Faculty Research Interest: