2019
DOI: 10.30699/fhi.v8i1.180
|View full text |Cite
|
Sign up to set email alerts
|

BigData Analysis in Healthcare: Apache Hadoop , Apache spark and Apache Flink

Abstract: Introduction: Health care data is increasing. The correct analysis of such data will improve the quality of care and reduce costs. This kind of data has certain features such as high volume, variety, high-speed production, etc. It makes it impossible to analyze with ordinary hardware and software platforms. Choosing the right platform for managing this kind of data is very important. The purpose of this study is to introduce and compare the most popular and most widely used platform for processing big data, Ap… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
18
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
7
2
1

Relationship

1
9

Authors

Journals

citations
Cited by 46 publications
(18 citation statements)
references
References 31 publications
0
18
0
Order By: Relevance
“…Flink allows users to store data in memory and load them several times. A mechanism provides continuous fault tolerance for restoring the flow of data, and in case of a failure, it can return to snapshots of the system and be used to rebuild the missing data set (119)(120)(121). Given its popularity, Python and its growing number of packages should also be taken into consideration, especially with deep learning, for which specialized languages, such as Tensor flow is necessary (122).…”
Section: Discussionmentioning
confidence: 99%
“…Flink allows users to store data in memory and load them several times. A mechanism provides continuous fault tolerance for restoring the flow of data, and in case of a failure, it can return to snapshots of the system and be used to rebuild the missing data set (119)(120)(121). Given its popularity, Python and its growing number of packages should also be taken into consideration, especially with deep learning, for which specialized languages, such as Tensor flow is necessary (122).…”
Section: Discussionmentioning
confidence: 99%
“…Considering the importance of focusing on the Big Data Area [49] and providing a lot of frameworks in this area, it is recommended that other important health care sectors provide frameworks in this regard, and it is also recommended in future studies of other widely used tools for software engineering in the field of health care Including modeling, simulations, etc., are being investigated, introduced and used [50].…”
Section: Discussionmentioning
confidence: 99%
“…For example, in [36] the authors study the financial problem in data from the National Stock Exchange of India (NSE) for a period of one year, using ARMA, ARIMA, ARCH and GARCH models, using Apache Spark for processing. Works such as [37] predict traffic flow through time series with Spark and in others, such as in [38], the authors work with time series related to health care data. However, most of the literature we find are limited to the analysis of time series, but do not provide an architecture that integrates the entire flow of data from sending the data from the IoT to providing a result to the user or interested entity.…”
Section: Related Workmentioning
confidence: 99%