Ensampling Data Prediction using Sparse Data in Mobile Intelligent System

Dhamodaran S, Lakshmi M

Abstract


Rain is an important source of water. The Indian economy is heavily dependent on agriculture and the livelihood of Indian farmer largely depends on rains. The farms are more dependent on rainfall than any other water resource. As we observe there is a lot of climate change in recent years due to industrialization, because of these climate changes there are a lot of floods and droughts. So, it might be helpful to predict the rainfall beforehand and take necessary precautions to protect crops and other sorts of damages that might occur due to the irregular rainfall. So, we present a model that could reasonably predict the future rainfall using very fewer variables. The reason why we developed a model which uses sparse data is that sometimes it could be hard to obtain a large amount of data due to lack or improper working of recording equipment and so on. So, it will be good to have a working model in those situations and applications are implemented.This paper affords a overview of system learning and offers a brief take a look at on distinctive machine gaining knowledge of strategies together with their programs on mobile devices. It also affords an outline of overall performance-associated parameters of gadget studying techniques useful for mobile devices.


Keywords


Bagging; Boosting; Data analysis; Mobile Application; Mobile Intelligent System; Machine Learning techniques: Rainfall Prediction SVM.

Full Text:

PDF



International Journal of Interactive Mobile Technologies (iJIM) – eISSN: 1865-7923
Creative Commons License
Indexing:
Scopus logo IET Inspec logo DBLP logo EBSCO logo Ulrich's logo MAS logo