Issues

Journal & Issues

Volume 22 (2022): Issue 3 (September 2022)

Volume 22 (2022): Issue 2 (June 2022)

Volume 22 (2022): Issue 1 (March 2022)

Volume 21 (2021): Issue 4 (December 2021)

Volume 21 (2021): Issue 3 (September 2021)

Volume 21 (2021): Issue 2 (June 2021)

Volume 21 (2021): Issue 1 (March 2021)

Volume 20 (2020): Issue 6 (December 2020)
Special Issue on New Developments in Scalable Computing

Volume 20 (2020): Issue 5 (December 2020)
Special issue on Innovations in Intelligent Systems and Applications

Volume 20 (2020): Issue 4 (November 2020)

Volume 20 (2020): Issue 3 (September 2020)

Volume 20 (2020): Issue 2 (June 2020)

Volume 20 (2020): Issue 1 (March 2020)

Volume 19 (2019): Issue 4 (November 2019)

Volume 19 (2019): Issue 3 (September 2019)

Volume 19 (2019): Issue 2 (June 2019)

Volume 19 (2019): Issue 1 (March 2019)

Volume 18 (2018): Issue 5 (May 2018)
Special Thematic Issue on Optimal Codes and Related Topics

Volume 18 (2018): Issue 4 (November 2018)

Volume 18 (2018): Issue 3 (September 2018)

Volume 18 (2018): Issue 2 (June 2018)

Volume 18 (2018): Issue 1 (March 2018)

Volume 17 (2017): Issue 5 (December 2017)
Special Issue With Selected Papers From The Workshop “Two Years Avitohol: Advanced High Performance Computing Applications 2017

Volume 17 (2017): Issue 4 (November 2017)

Volume 17 (2017): Issue 3 (September 2017)

Volume 17 (2017): Issue 2 (June 2017)

Volume 17 (2017): Issue 1 (March 2017)

Volume 16 (2016): Issue 6 (December 2016)
Special issue with selection of extended papers from 6th International Conference on Logistic, Informatics and Service Science LISS’2016

Volume 16 (2016): Issue 5 (October 2016)
Issue Title: Special Issue on Application of Advanced Computing and Simulation in Information Systems

Volume 16 (2016): Issue 4 (December 2016)

Volume 16 (2016): Issue 3 (September 2016)

Volume 16 (2016): Issue 2 (June 2016)

Volume 16 (2016): Issue 1 (March 2016)

Volume 15 (2015): Issue 7 (December 2015)
Special Issue on Information Fusion

Volume 15 (2015): Issue 6 (December 2015)
Special Issue on Logistics, Informatics and Service Science

Volume 15 (2015): Issue 5 (April 2015)
Special Issue on Control in Transportation Systems

Volume 15 (2015): Issue 4 (November 2015)

Volume 15 (2015): Issue 3 (September 2015)

Volume 15 (2015): Issue 2 (June 2015)

Volume 15 (2015): Issue 1 (March 2015)

Volume 14 (2014): Issue 5 (December 2014)
Special Issue

Volume 14 (2014): Issue 4 (December 2014)

Volume 14 (2014): Issue 3 (September 2014)

Volume 14 (2014): Issue 2 (June 2014)

Volume 14 (2014): Issue 1 (March 2014)

Volume 13 (2013): Issue Special-Issue (December 2013)

Volume 13 (2013): Issue 4 (December 2013)
The publishing of the present issue (Volume 13, No 4, 2013) of the journal “Cybernetics and Information Technologies” is financially supported by FP7 project “Advanced Computing for Innovation” (ACOMIN), grant agreement 316087 of Call FP7 REGPOT-2012-2013-1.

Volume 13 (2013): Issue 3 (September 2013)

Volume 13 (2013): Issue 2 (June 2013)

Volume 13 (2013): Issue 1 (March 2013)

Volume 12 (2012): Issue 4 (December 2012)

Volume 12 (2012): Issue 3 (September 2012)

Volume 12 (2012): Issue 2 (June 2012)

Volume 12 (2012): Issue 1 (March 2012)

Journal Details
Format
Journal
eISSN
1314-4081
First Published
13 Mar 2012
Publication timeframe
4 times per year
Languages
English

Search

Volume 17 (2017): Issue 1 (March 2017)

Journal Details
Format
Journal
eISSN
1314-4081
First Published
13 Mar 2012
Publication timeframe
4 times per year
Languages
English

Search

12 Articles
Open Access

An Optimization of Closed Frequent Subgraph Mining Algorithm

Published Online: 06 Apr 2017
Page range: 3 - 15

Abstract

Abstract

Graph mining isamajor area of interest within the field of data mining in recent years. Akey aspect of graph mining is frequent subgraph mining. Central to the entire discipline of frequent subgraph mining is the concept of subgraph isomorphism. One major issue in early subgraph isomorphism research concerns computational complexity. Normally, the subgraph isomorphism problem is NP-complete. Previous studies of frequent subgraph mining have not solved NP-complete problem in the subgraph isomorphism. In this paper, we proposeanew algorithm which can deal with this problem. The proposed algorithm can solve the subgraph isomorphism in polynomial time in some settings. Moreover, the new algorithm is proved theoretically more effective than previous studies in closed frequent subgraph mining.

Keywords

  • Frequent patterns
  • closed frequent subgraph
  • frequent subgraphs
  • subgraph mining
  • subgraph isomorphism
Open Access

Fast Matrix Multiplication with Big Sparse Data

Published Online: 06 Apr 2017
Page range: 16 - 30

Abstract

Abstract

Big Data becameabuzz word nowadays due to the evolution of huge volumes of data beyond peta bytes. This article focuses on matrix multiplication with big sparse data. The proposed FASTsparse MULalgorithm outperforms the state-of-the-art big matrix multiplication approaches in sparse data scenario.

Keywords

  • Sparse data
  • sparse matrices multiplication
  • Big Data
  • Mapreduce
Open Access

Group Decision Analysis with Interval Type-2 Fuzzy Numbers

Published Online: 06 Apr 2017
Page range: 31 - 44

Abstract

Abstract

This paper presentsagroup multi-criteria DEMATELand VIKORdecision analysis method with interval type-2 fuzzy sets. In order to compare normal fuzzy trapezoidal numbers, we convert them into crisp values using graded mean integration representation. Byacase study for selection of business intelligence platform, we prove that the proposed combination isafeasible solution that can work with benefits and costs criteria, while also reducing uncertainty in experts’assessments.

Keywords

  • Group decision making
  • multi-criteria decision analysis
  • DEMATEL
  • VIKOR
  • interval type-2 fuzzy sets
  • business intelligence
Open Access

On Improving the Classification of Imbalanced Data

Published Online: 06 Apr 2017
Page range: 45 - 62

Abstract

Abstract

Mining of imbalanced data isachallenging task due to its complex inherent characteristics. The conventional classifiers such as the nearest neighbor severely bias towards the majority class, as minority class data are under-represented and outnumbered. This paper focuses on building an improved Nearest Neighbor Classifier foratwo class imbalanced data. Three oversampling techniques are presented, for generation of artificial instances for the minority class for balancing the distribution among the classes. Experimental results showed that the proposed methods outperformed the conventional classifier.

Keywords

  • Imbalance data
  • nearest neighbor classifier
  • oversampling
  • synthetic data
  • Data Mining
Open Access

Axiomatic Design Approach for Nonlinear Multiple Objective Optimizaton Problem and Robustness in Spring Design

Published Online: 06 Apr 2017
Page range: 63 - 71

Abstract

Abstract

This paper gives general information about multi-objective, axiomatic and robust design approaches and considersasolution model of nonlinear multi-objective optimization problem based on applyinganew robust design approach. Both axiomatic and robust design approaches were used complementarily inacase study with distinct multi-objectives. In this case study, the main target was achieving each objective optimum to minimize the mass and the shear stress ofaspring by integrating robustness and durability at the design stage due to trade off between objectives. This spring problem was examined using the independence axiom of the axiomatic design methodology. Also, semangularity and reangularity concepts were used and design matrices were formed to find coupled and decoupled solutions. It was observed that there were some acceptable design parameter values for which the design became decoupled. Graphical and numerical results were checked to see if they were compatible with each other. Finally, this decoupled design was given appropriate tolerances by using robust design method. This way,arobust and durable spring was designed which would satisfy the given specifications with minimum cost in the existing literature from the view point of axiomatic design approach.

Keywords

  • Axiomatic design
  • multi objective design
  • robustness
Open Access

Mutation: A New Operator in Gravitational Search Algorithm Using Fuzzy Controller

Published Online: 06 Apr 2017
Page range: 72 - 86

Abstract

Abstract

Gravitational Search Algorithm (GSA) isanovel meta-heuristic algorithm. Despite it has high exploring ability, this algorithm faces premature convergence and gets trapped in some problems, therefore it has difficulty in finding the optimum solution for problems, which is considered as one of the disadvantages of GSA. In this paper, this problem has been solved through definingamutation function which uses fuzzy controller to control mutation parameter. The proposed method has been evaluated on standard benchmark functions including unimodal and multimodal functions; the obtained results have been compared with Standard Gravitational Search Algorithm (SGSA), Gravitational Particle Swarm algorithm (GPS), Particle Swarm Optimization algorithm (PSO), Clustered Gravitational Search Algorithm (CGSA) and Real Genetic Algorithm (RGA). The observed experiments indicate that the proposed approach yields better results than other algorithms compared with it.

Keywords

  • Gravitational search algorithm
  • heuristic search algorithm
  • mutation function
  • exploration and exploitation
  • fuzzy controller
Open Access

A Two-Stage Placement Algorithm with Multi-Objective Optimization and Group Decision Making

Published Online: 06 Apr 2017
Page range: 87 - 103

Abstract

Abstract

Atwo-stage placement algorithm with multi-objective optimization and group decision making is proposed. The first stage aims to determineaset of design alternatives for objects placement by multi-objective combinatorial optimization. The second stage relies on business intelligence via group decision-making based on solution of optimization task to makeachoice of the most suitable alternative. The design alternatives are determined by means of weighted sum and lexicographic methods. The group decision making is used to evaluate determined design alternatives toward the design parameters. The described algorithm is used for wind farm layout optimization problem. The results of numerical testing demonstrate the applicability of the proposed algorithm.

Keywords

  • Placement algorithm
  • multi objective alternatives determination
  • business intelligence
  • group decision making
  • wind farm layout design
Open Access

Multi-Band Spectrum Allocation Algorithm Based on First-Price Sealed Auction

Published Online: 06 Apr 2017
Page range: 104 - 112

Abstract

Abstract

Auction is often applied in cognitive wireless networks due to its fairness properties and efficiency. To solve the allocation issues of cognitive wireless network inamulti-band spectrum, multi-item auction mechanism and models were discussed in depth. Multi-item highest price sealed auction was designed for cognitive wireless networks’multi-band spectrum allocation algorithm. This algorithm divided the spectrum allocation process into several stages which was along with low complexity. Experiments show that the algorithm improves the utilization of spectrum frequency, because it takes into account the spectrum owner’s economic efficiency and the users’equity.

Keywords

  • Cognitive radio networks
  • spectrum allocation
  • auction
  • secondary user
Open Access

Improvement of Range Estimation with Microphone Array

Published Online: 06 Apr 2017
Page range: 113 - 125

Abstract

Abstract

This paper presentsanew approach for the three-dimensional (3-D) localization of sound sources. An acoustic camera uses an angular beamforming to measure the Direction of Arrival (Do A) of an incoming signal, to localize the emission source. The acoustic sensor used in this article is the Brüel & Kjaer acoustic camera transformed to operate inabistatic mode. The transformation consists inaplacing of one of the microphones of the acoustic camera outside of its microphone array. This allows simultaneous estimation of the Do Aand the Time Difference of Arrival (TDo A) of the incoming signal(s). Such sensors were not found. The paper proposes emitter localization in range - cross range - elevation coordinates by combining estimates of TDo Aand Do Aand presents the signal processing method for that purpose. The range resolution of 0.2mwas achieved in an experiment. Experimental results were obtained using different emission sources. Adescription of resolution cell limitations is presented. The obtained results show acoustic noise source localization without the pre-metering of the range of the imaging plane, i.e., withoutaneed to use the additional range meter which is notapart of the acoustic camera. The latter is important in tasks of non-destructive testing.

Keywords

  • Acoustic noise source localization
  • acoustic camera
  • bistatic reception
  • time difference of arrival
  • stationary acoustic noise signal
Open Access

Data Receiving Method Based on Multimedia Timing in Real- Time System

Published Online: 06 Apr 2017
Page range: 126 - 134

Abstract

Abstract

Several methods, such as polling, multithread, timing, and so on, can be used in data receiving course. Low-efficiency and high level of system resource consumption may bring about data loss in polling and multithread methods when the data transmission rate is very high. Software timing methods are discussed and analyzed in Visual C++. Timing method would improve the system resource availability and decrease the risk of data loss. According to the demand ofatesting system,areal-time monitoring system based on memory sharing and multimedia timer is presented. After testing, the average timing error of the multimedia timer in the given instance is not bigger than 0.05%, so the continuity and integrity of data receiving can be assured under the conditions of high-speed data transmission.

Keywords

  • Real-time monitoring system
  • data receiving
  • timing
  • multimedia timer
  • memory sharing
Open Access

Research on Quick Response Code Defect Detection Algorithm

Published Online: 06 Apr 2017
Page range: 135 - 145

Abstract

Abstract

Defect Detection is one of the most important parts of Automatic Identification and Data transmission. Quick Response code (QRcode) is one of the most popular types of two-dimensional barcodes. It isachallenge to detect defect of various QRcode images efficiently and accurately. In this paper, we propose the procedure byaserial of carefully designed preprocessing methods. The defect detection procedure consists of QRcode identification, QRcode reconstruction, perspective transformation, image binarization, morphological operation, image matching, and Blob analysis. By these steps, we can detect defect of different types of QRcode images. The experiment results show that our method has stronger robustness and higher efficiency. Moreover, experiment results on QRcode images show that the prediction accuracy of proposed method reaches 99.07%with an average execution time of 6.592 ms. This method can detect defect of these images in real time.

Keywords

  • QR Code
  • defect detection
  • perspective transformation
  • blob analysis
  • correlation matching
Open Access

Empirical Study of Job Scheduling Algorithms in Hadoop MapReduce

Published Online: 06 Apr 2017
Page range: 146 - 163

Abstract

Abstract

Several Job scheduling algorithms have been developed for Hadoop-Map Reduce model, which vary widely in design and behavior for handling different issues such as locality of data, user share fairness, and resource awareness. This article focuses on empirically evaluating the performance of three schedulers: First In First Out (FIFO), Fair scheduler, and Capacity scheduler. To carry out the experimental evaluation, we implement our own Hadoop cluster testbed, consisting of four machines, in which one of the machines works as the master node and all four machines work as slave nodes. The experiments include variation in data sizes, use of two different data processing applications, and variation in the number of nodes used in processing. The article analyzes the performance of the job scheduling algorithms based on various relevant performance measures. The results of the experiments are evident of the performance being affected by the job scheduling parameters, the type of applications, the number of nodes in the cluster, and size of the input data.

Keywords

  • Big Data
  • Hadoop
  • Map Reduce
  • job scheduling
  • analysis
  • experimental evaluation
12 Articles
Open Access

An Optimization of Closed Frequent Subgraph Mining Algorithm

Published Online: 06 Apr 2017
Page range: 3 - 15

Abstract

Abstract

Graph mining isamajor area of interest within the field of data mining in recent years. Akey aspect of graph mining is frequent subgraph mining. Central to the entire discipline of frequent subgraph mining is the concept of subgraph isomorphism. One major issue in early subgraph isomorphism research concerns computational complexity. Normally, the subgraph isomorphism problem is NP-complete. Previous studies of frequent subgraph mining have not solved NP-complete problem in the subgraph isomorphism. In this paper, we proposeanew algorithm which can deal with this problem. The proposed algorithm can solve the subgraph isomorphism in polynomial time in some settings. Moreover, the new algorithm is proved theoretically more effective than previous studies in closed frequent subgraph mining.

Keywords

  • Frequent patterns
  • closed frequent subgraph
  • frequent subgraphs
  • subgraph mining
  • subgraph isomorphism
Open Access

Fast Matrix Multiplication with Big Sparse Data

Published Online: 06 Apr 2017
Page range: 16 - 30

Abstract

Abstract

Big Data becameabuzz word nowadays due to the evolution of huge volumes of data beyond peta bytes. This article focuses on matrix multiplication with big sparse data. The proposed FASTsparse MULalgorithm outperforms the state-of-the-art big matrix multiplication approaches in sparse data scenario.

Keywords

  • Sparse data
  • sparse matrices multiplication
  • Big Data
  • Mapreduce
Open Access

Group Decision Analysis with Interval Type-2 Fuzzy Numbers

Published Online: 06 Apr 2017
Page range: 31 - 44

Abstract

Abstract

This paper presentsagroup multi-criteria DEMATELand VIKORdecision analysis method with interval type-2 fuzzy sets. In order to compare normal fuzzy trapezoidal numbers, we convert them into crisp values using graded mean integration representation. Byacase study for selection of business intelligence platform, we prove that the proposed combination isafeasible solution that can work with benefits and costs criteria, while also reducing uncertainty in experts’assessments.

Keywords

  • Group decision making
  • multi-criteria decision analysis
  • DEMATEL
  • VIKOR
  • interval type-2 fuzzy sets
  • business intelligence
Open Access

On Improving the Classification of Imbalanced Data

Published Online: 06 Apr 2017
Page range: 45 - 62

Abstract

Abstract

Mining of imbalanced data isachallenging task due to its complex inherent characteristics. The conventional classifiers such as the nearest neighbor severely bias towards the majority class, as minority class data are under-represented and outnumbered. This paper focuses on building an improved Nearest Neighbor Classifier foratwo class imbalanced data. Three oversampling techniques are presented, for generation of artificial instances for the minority class for balancing the distribution among the classes. Experimental results showed that the proposed methods outperformed the conventional classifier.

Keywords

  • Imbalance data
  • nearest neighbor classifier
  • oversampling
  • synthetic data
  • Data Mining
Open Access

Axiomatic Design Approach for Nonlinear Multiple Objective Optimizaton Problem and Robustness in Spring Design

Published Online: 06 Apr 2017
Page range: 63 - 71

Abstract

Abstract

This paper gives general information about multi-objective, axiomatic and robust design approaches and considersasolution model of nonlinear multi-objective optimization problem based on applyinganew robust design approach. Both axiomatic and robust design approaches were used complementarily inacase study with distinct multi-objectives. In this case study, the main target was achieving each objective optimum to minimize the mass and the shear stress ofaspring by integrating robustness and durability at the design stage due to trade off between objectives. This spring problem was examined using the independence axiom of the axiomatic design methodology. Also, semangularity and reangularity concepts were used and design matrices were formed to find coupled and decoupled solutions. It was observed that there were some acceptable design parameter values for which the design became decoupled. Graphical and numerical results were checked to see if they were compatible with each other. Finally, this decoupled design was given appropriate tolerances by using robust design method. This way,arobust and durable spring was designed which would satisfy the given specifications with minimum cost in the existing literature from the view point of axiomatic design approach.

Keywords

  • Axiomatic design
  • multi objective design
  • robustness
Open Access

Mutation: A New Operator in Gravitational Search Algorithm Using Fuzzy Controller

Published Online: 06 Apr 2017
Page range: 72 - 86

Abstract

Abstract

Gravitational Search Algorithm (GSA) isanovel meta-heuristic algorithm. Despite it has high exploring ability, this algorithm faces premature convergence and gets trapped in some problems, therefore it has difficulty in finding the optimum solution for problems, which is considered as one of the disadvantages of GSA. In this paper, this problem has been solved through definingamutation function which uses fuzzy controller to control mutation parameter. The proposed method has been evaluated on standard benchmark functions including unimodal and multimodal functions; the obtained results have been compared with Standard Gravitational Search Algorithm (SGSA), Gravitational Particle Swarm algorithm (GPS), Particle Swarm Optimization algorithm (PSO), Clustered Gravitational Search Algorithm (CGSA) and Real Genetic Algorithm (RGA). The observed experiments indicate that the proposed approach yields better results than other algorithms compared with it.

Keywords

  • Gravitational search algorithm
  • heuristic search algorithm
  • mutation function
  • exploration and exploitation
  • fuzzy controller
Open Access

A Two-Stage Placement Algorithm with Multi-Objective Optimization and Group Decision Making

Published Online: 06 Apr 2017
Page range: 87 - 103

Abstract

Abstract

Atwo-stage placement algorithm with multi-objective optimization and group decision making is proposed. The first stage aims to determineaset of design alternatives for objects placement by multi-objective combinatorial optimization. The second stage relies on business intelligence via group decision-making based on solution of optimization task to makeachoice of the most suitable alternative. The design alternatives are determined by means of weighted sum and lexicographic methods. The group decision making is used to evaluate determined design alternatives toward the design parameters. The described algorithm is used for wind farm layout optimization problem. The results of numerical testing demonstrate the applicability of the proposed algorithm.

Keywords

  • Placement algorithm
  • multi objective alternatives determination
  • business intelligence
  • group decision making
  • wind farm layout design
Open Access

Multi-Band Spectrum Allocation Algorithm Based on First-Price Sealed Auction

Published Online: 06 Apr 2017
Page range: 104 - 112

Abstract

Abstract

Auction is often applied in cognitive wireless networks due to its fairness properties and efficiency. To solve the allocation issues of cognitive wireless network inamulti-band spectrum, multi-item auction mechanism and models were discussed in depth. Multi-item highest price sealed auction was designed for cognitive wireless networks’multi-band spectrum allocation algorithm. This algorithm divided the spectrum allocation process into several stages which was along with low complexity. Experiments show that the algorithm improves the utilization of spectrum frequency, because it takes into account the spectrum owner’s economic efficiency and the users’equity.

Keywords

  • Cognitive radio networks
  • spectrum allocation
  • auction
  • secondary user
Open Access

Improvement of Range Estimation with Microphone Array

Published Online: 06 Apr 2017
Page range: 113 - 125

Abstract

Abstract

This paper presentsanew approach for the three-dimensional (3-D) localization of sound sources. An acoustic camera uses an angular beamforming to measure the Direction of Arrival (Do A) of an incoming signal, to localize the emission source. The acoustic sensor used in this article is the Brüel & Kjaer acoustic camera transformed to operate inabistatic mode. The transformation consists inaplacing of one of the microphones of the acoustic camera outside of its microphone array. This allows simultaneous estimation of the Do Aand the Time Difference of Arrival (TDo A) of the incoming signal(s). Such sensors were not found. The paper proposes emitter localization in range - cross range - elevation coordinates by combining estimates of TDo Aand Do Aand presents the signal processing method for that purpose. The range resolution of 0.2mwas achieved in an experiment. Experimental results were obtained using different emission sources. Adescription of resolution cell limitations is presented. The obtained results show acoustic noise source localization without the pre-metering of the range of the imaging plane, i.e., withoutaneed to use the additional range meter which is notapart of the acoustic camera. The latter is important in tasks of non-destructive testing.

Keywords

  • Acoustic noise source localization
  • acoustic camera
  • bistatic reception
  • time difference of arrival
  • stationary acoustic noise signal
Open Access

Data Receiving Method Based on Multimedia Timing in Real- Time System

Published Online: 06 Apr 2017
Page range: 126 - 134

Abstract

Abstract

Several methods, such as polling, multithread, timing, and so on, can be used in data receiving course. Low-efficiency and high level of system resource consumption may bring about data loss in polling and multithread methods when the data transmission rate is very high. Software timing methods are discussed and analyzed in Visual C++. Timing method would improve the system resource availability and decrease the risk of data loss. According to the demand ofatesting system,areal-time monitoring system based on memory sharing and multimedia timer is presented. After testing, the average timing error of the multimedia timer in the given instance is not bigger than 0.05%, so the continuity and integrity of data receiving can be assured under the conditions of high-speed data transmission.

Keywords

  • Real-time monitoring system
  • data receiving
  • timing
  • multimedia timer
  • memory sharing
Open Access

Research on Quick Response Code Defect Detection Algorithm

Published Online: 06 Apr 2017
Page range: 135 - 145

Abstract

Abstract

Defect Detection is one of the most important parts of Automatic Identification and Data transmission. Quick Response code (QRcode) is one of the most popular types of two-dimensional barcodes. It isachallenge to detect defect of various QRcode images efficiently and accurately. In this paper, we propose the procedure byaserial of carefully designed preprocessing methods. The defect detection procedure consists of QRcode identification, QRcode reconstruction, perspective transformation, image binarization, morphological operation, image matching, and Blob analysis. By these steps, we can detect defect of different types of QRcode images. The experiment results show that our method has stronger robustness and higher efficiency. Moreover, experiment results on QRcode images show that the prediction accuracy of proposed method reaches 99.07%with an average execution time of 6.592 ms. This method can detect defect of these images in real time.

Keywords

  • QR Code
  • defect detection
  • perspective transformation
  • blob analysis
  • correlation matching
Open Access

Empirical Study of Job Scheduling Algorithms in Hadoop MapReduce

Published Online: 06 Apr 2017
Page range: 146 - 163

Abstract

Abstract

Several Job scheduling algorithms have been developed for Hadoop-Map Reduce model, which vary widely in design and behavior for handling different issues such as locality of data, user share fairness, and resource awareness. This article focuses on empirically evaluating the performance of three schedulers: First In First Out (FIFO), Fair scheduler, and Capacity scheduler. To carry out the experimental evaluation, we implement our own Hadoop cluster testbed, consisting of four machines, in which one of the machines works as the master node and all four machines work as slave nodes. The experiments include variation in data sizes, use of two different data processing applications, and variation in the number of nodes used in processing. The article analyzes the performance of the job scheduling algorithms based on various relevant performance measures. The results of the experiments are evident of the performance being affected by the job scheduling parameters, the type of applications, the number of nodes in the cluster, and size of the input data.

Keywords

  • Big Data
  • Hadoop
  • Map Reduce
  • job scheduling
  • analysis
  • experimental evaluation

Plan your remote conference with Sciendo