%0 Journal Article %1 SinghReddy14jobd %A Singh, Dilpreet %A Reddy, Chandan K. %D 2014 %J Journal of Big Data %K v1500 springer paper ai data pattern recognition analysis processing tool zzz.big %N 8 %P 8:1--8:20 %R 10.1186/s40537-014-0008-6 %T A Survey on Platforms for Big Data Analytics %V 2 %X The primary purpose of this paper is to provide an in-depth analysis of different platforms available for performing big data analytics. This paper surveys different hardware platforms available for big data analytics and assesses the advantages and drawbacks of each of these platforms based on various metrics such as scalability, data I/O rate, fault tolerance, real-time processing, data size supported and iterative task support. In addition to the hardware, a detailed description of the software frameworks used within each of these platforms is also discussed along with their strengths and drawbacks. Some of the critical characteristics described here can potentially aid the readers in making an informed decision about the right choice of platforms depending on their computational needs. Using a star ratings table, a rigorous qualitative comparison between different platforms is also discussed for each of the six characteristics that are critical for the algorithms of big data analytics. In order to provide more insights into the effectiveness of each of the platform in the context of big data analytics, specific implementation level details of the widely used k-means clustering algorithm on various platforms are also described in the form pseudocode.

@article{SinghReddy14jobd, abstract = {The primary purpose of this paper is to provide an in-depth analysis of different platforms available for performing big data analytics. This paper surveys different hardware platforms available for big data analytics and assesses the advantages and drawbacks of each of these platforms based on various metrics such as scalability, data I/O rate, fault tolerance, real-time processing, data size supported and iterative task support. In addition to the hardware, a detailed description of the software frameworks used within each of these platforms is also discussed along with their strengths and drawbacks. Some of the critical characteristics described here can potentially aid the readers in making an informed decision about the right choice of platforms depending on their computational needs. Using a star ratings table, a rigorous qualitative comparison between different platforms is also discussed for each of the six characteristics that are critical for the algorithms of big data analytics. In order to provide more insights into the effectiveness of each of the platform in the context of big data analytics, specific implementation level details of the widely used k-means clustering algorithm on various platforms are also described in the form pseudocode.}, added-at = {2015-03-31T15:36:29.000+0200}, author = {Singh, Dilpreet and Reddy, Chandan K.}, biburl = {https://www.bibsonomy.org/bibtex/2229a988f2a29708e21b0b7d0e81ad902/flint63}, doi = {10.1186/s40537-014-0008-6}, file = {SpringerOpen:2014/SinghReddy14jobd.pdf:PDF}, groups = {public}, interhash = {3851832d9bc65baed3170bf8c837c347}, intrahash = {229a988f2a29708e21b0b7d0e81ad902}, issn = {2196-1115}, journal = {Journal of Big Data}, keywords = {v1500 springer paper ai data pattern recognition analysis processing tool zzz.big}, month = {#oct#}, number = 8, pages = {8:1--8:20}, timestamp = {2018-04-16T12:03:04.000+0200}, title = {A Survey on Platforms for Big Data Analytics}, username = {flint63}, volume = 2, year = 2014 }