The Experts below are selected from a list of 84 Experts worldwide ranked by ideXlab platform
Giuliano Casale - One of the best experts on this subject based on the ideXlab platform.
-
Artificial neural networks based techniques for anomaly detection in Apache Spark
Cluster Computing, 2019Co-Authors: Ahmad Alnafessah, Giuliano CasaleAbstract:Late detection and manual resolutions of performance anomalies in Cloud Computing and Big Data systems may lead to performance violations and financial penalties. Motivated by this issue, we propose an artificial neural network based methodology for anomaly detection tailored to the Apache Spark in-memory processing platform. Apache Spark is widely adopted by industry because of its speed and generality, however there is still a shortage of comprehensive performance anomaly detection methods applicable to this platform. We propose an artificial neural networks driven methodology to quickly sift through Spark logs data and operating system monitoring metrics to accurately detect and classify anomalous behaviors based on the Spark resilient distributed dataset characteristics. The proposed method is evaluated against three popular machine learning algorithms, decision trees, nearest neighbor, and support vector machine, as well as against four variants that consider different monitoring datasets. The results prove that our proposed method outperforms other methods, typically achieving 98–99% F-scores, and offering much greater accuracy than alternative techniques to detect both the period in which anomalies occurred and their type.
Ahmad Alnafessah - One of the best experts on this subject based on the ideXlab platform.
-
Artificial neural networks based techniques for anomaly detection in Apache Spark
Cluster Computing, 2019Co-Authors: Ahmad Alnafessah, Giuliano CasaleAbstract:Late detection and manual resolutions of performance anomalies in Cloud Computing and Big Data systems may lead to performance violations and financial penalties. Motivated by this issue, we propose an artificial neural network based methodology for anomaly detection tailored to the Apache Spark in-memory processing platform. Apache Spark is widely adopted by industry because of its speed and generality, however there is still a shortage of comprehensive performance anomaly detection methods applicable to this platform. We propose an artificial neural networks driven methodology to quickly sift through Spark logs data and operating system monitoring metrics to accurately detect and classify anomalous behaviors based on the Spark resilient distributed dataset characteristics. The proposed method is evaluated against three popular machine learning algorithms, decision trees, nearest neighbor, and support vector machine, as well as against four variants that consider different monitoring datasets. The results prove that our proposed method outperforms other methods, typically achieving 98–99% F-scores, and offering much greater accuracy than alternative techniques to detect both the period in which anomalies occurred and their type.
Casale G - One of the best experts on this subject based on the ideXlab platform.
-
Artificial neural networks based techniques for anomaly detection in Apache Spark
'Springer Science and Business Media LLC', 2019Co-Authors: Alnafessah A, Casale GAbstract:Late detection and manual resolutions of performance anomalies in Cloud Computing and Big Data systems may lead to performance violations and financial penalties. Motivated by this issue, we propose an artificial neural network based methodology for anomaly detection especially for the Apache Spark in-memory processing platforms. Apache Spark has become widely adopted by industry because of its speed and generality, however there is still a shortage of comprehensive performance anomaly detection methods applicable to this platform. We propose artificial neural networks driven methodology to quickly sift through Spark logs data and operating system monitoring metrics to accurately detect and classify anomalous behaviors based on the Spark resilient distributed dataset (RDD) characteristics. The proposed method is evaluated against three popular machine learning algorithms, decision trees, nearest neighbor, and support vector machine (SVM), as well as against four variants that consider different monitoring datasets. The results prove that our proposed method outperforms other methods, typically achieving 98%-99% F-scores, and offering much greater accuracy than alternative techniques to detect both the period in which anomalies occurred and their type
Santanu Kumar Rath - One of the best experts on this subject based on the ideXlab platform.
-
fast computing of microarray data using resilient distributed dataset of apache spark
2016Co-Authors: Ransingh Biswajit Ray, Mukesh Kumar, Santanu Kumar RathAbstract:Microarray technology is one of the emerging technologies in the field of genetic research that many biologists use to monitor expression levels of genes in a given organism. Microarray experiments are used to investigate genome-wide expression changes in health care aspects. Analysis of large Microarray datasets has become a challenging task, as the number of genes available in commercial probe sets and the number of test samples for an experimental set increases. The colossal amount of raw gene expression data often leads to computational and analytical challenges including feature selection and classification of the dataset into correct group or class. In this paper, statistical method (test), i.e., ANOVA based on Spark framework is proposed to select the pertinent features. After feature selection, various classifiers i.e., Naive Bayes (sf-NB) and Logistic Regression (sf-LoR) based on Spark framework are applied to classify the Microarray dataset. A detail comparative analysis in terms of execution time and accuracy is done on these feature selection and classifier methodologies that are based on Spark framework and conventional system respectively.
Raju Kumar Mishra - One of the best experts on this subject based on the ideXlab platform.
-
spark architecture and the resilient distributed dataset
2018Co-Authors: Raju Kumar MishraAbstract:You learned Python in the preceding chapter. Now it is time to learn PySpark and utilize the power of a distributed system to solve problems related to big data. We generally distribute large amounts of data on a cluster and perform processing on that distributed data.