Big Data Analytics Framework using Machine Learning on Multiple Datasets
Journal: International Journal of Science and Research (IJSR) (Vol.4, No. 8)Publication Date: 2015-08-05
Authors : Surekha Sharad Muzumdar; Jharna Majumdar;
Page : 414-418
Keywords : Big data; Hive; Hadoop; HDFS; Machine Learning; COBWEB;
Abstract
Over 2.5 quintillion bytes of data have been created in last two years alone. These kinds of data comes from various sources such as healthcare informatics, weather information, sensors data, cell phone GPS signals, social media, digital images and videos, transactional information, etc. Big Data refers to huge collection of data sets that are so complex that it becomes so difficult to process using traditional data processing applications. Therefore it requires new set of framework to manage and process Big Data. Map Reduce plays a significant role in processing Big Data. In this paper, the multiple datasets such as data from healthcare organization, weather dataset and movie ratings dataset are stored and organized directly to distributed file system like HDFS. Then finally data is analyzed using Apache Hive for faster query access. In this paper Machine learning techniques are used to solve a big data analytics in a better and simple way.
Other Latest Articles
- Behavioural Correlates of Predation by Tiger (Panthera tigris) & Leopard (Panthera pardus) in Corbett Tiger Reserve, Ramnagar UK. India
- Providing Privacy-Aware Incentives for Mobile Sensing
- Comparative Study of Phosphate Solubilizing Bacteria from Paddy Field
- Assess Knowledge and Attitude of Parents regarding Childhood Seizures in Selected Hospital of Haryana
- Joint Design in Wireless Mesh Network
Last modified: 2021-06-30 21:52:09