Abstract : The availability of digital technology in the hands of every citizenry worldwide makes an availableunprecedented massive amount of data. The capability to process these gigantic amounts of data in real-time with Big Data Analytics (BDA) tools and Machine Learning (ML) algorithms carries many paybacks. However, the highnumber of free BDA tools, platforms, and data mining tools makes it challenging to select the appropriate one for theright task. This paper presents a comprehensive mini-literature review of ML in BDA, using a keyword search; a totalof 1512 published articles was identi?ed.
 ? None of the existing demonstrated clear statistical information on the BDA platforms and modelling tools ? Thus, big data are high-dimensional, diverse, gigantic,complex, incomplete, amorphous, noisy, and erroneous,making data pre-processing dif?cult in BDA. However, itis essential to make machine learning models effectivelyperform well with high accuracy. Nevertheless, thispaper can af?rm that this challenge still exist in BDAtoday
 ? This outcome can be attributed to LSTM’s storing memory and solving the gradient vanishing problem ? CNN canautomatically notice and extract the appropriate internalstructure from a time series dataset to create in-depthinput features, using convolution and pooling operations. ? Also, CNN and LSTM algorithms are resilient to noisetolerance and accuracy for time-series classi?cation.
 ? The articles were screened to 140 based on the study proposed novel taxonomy. ? We further screened the remaining basedon its title abstract, publishers and publication type, andpapers that were not connected with the proposed studywere discarded. ? However, the tools and platforms employed for the empirical analysis also count. Detailed study results based on the proposed taxonomy are presented in the following sections of this paper
 ? The aim was to measure the correlation between keywords used in big data analytics. ? As seen in big data, machine learning, analytics, network, and Spark are frequently used by research papers in BDA. ? several evaluation metrics can be used to measure a machine learning model’s performance, depending on the ML task. ? Appendix summarises the papers reviewed in this study; it presents the application area, the papers’ objective, and the data size used.
Download DOC Download PPT

We have more than 145000 Documents , PPT and Research Papers

Have a question ?

Mail us : info@nibode.com