Authors
Kyriacos Talattinis, Aikaterini Sidiropoulou, Konstantinos Chalkias, George Stephanides
Publication date
2010/9/10
Conference
2010 14th Panhellenic Conference on Informatics
Pages
66-71
Publisher
IEEE
Description
Hadoop is a fault tolerant Java framework that supports data distribution and process parallelization using commodity hardware. Based on the provided scalability and the independence of task execution, we combined Hadoop with crawling techniques to implement various applications that deal with large amount of data. Our experiments show that Hadoop is a very useful and trustworthy tool for creating distributed programs that perform better in terms of computational efficiency.
Scholar articles
K Talattinis, A Sidiropoulou, K Chalkias, G Stephanides - 2010 14th Panhellenic Conference on Informatics, 2010