SlideShare una empresa de Scribd logo
1 de 6
Descargar para leer sin conexión
International Journal of Electrical and Computer Engineering (IJECE)
Vol. 10, No. 2, April 2020, pp. 2031~2036
ISSN: 2088-8708, DOI: 10.11591/ijece.v10i2.pp2031-2036  2031
Journal homepage: http://ijece.iaescore.com/index.php/IJECE
Impact of big data congestion in IT: An adaptive knowledge-
based Bayesian network
Soheli Farhana, Adidah Lajis, Zalizah Awang Long, Haidawati Nasir
MIIT, Universiti Kuala Lumpur (UniKL), Malaysia
Article Info ABSTRACT
Article history:
Received May 6, 2019
Revised Oct 17, 2019
Accepted Oct 25, 2019
Recent progress on real-time systems are growing high in information
technology which is showing importance in every single innovative field.
Different applications in IT simultaneously produce the enormous measure of
information that should be taken care of. In this paper, a novel algorithm of
adaptive knowledge-based Bayesian network is proposed to deal with
the impact of big data congestion in decision processing. A Bayesian system
show is utilized to oversee learning arrangement toward all path for the basic
leadership process. Information of Bayesian systems is routinely discharged
as an ideal arrangement, where the examination work is to find
a development that misuses a measurably inspired score. By and large,
available information apparatuses manage this ideal arrangement by methods
for normal hunt strategies. As it required enormous measure of information
space, along these lines it is a tedious method that ought to be stayed away
from. The circumstance ends up unequivocal once huge information include
in hunting down ideal arrangement. A calculation is acquainted with achieve
quicker preparing of ideal arrangement by constraining the pursuit
information space. The proposed algorithm consists of recursive calculation
intthe inquiry space. The outcome demonstrates that the ideal component of
the proposed algorithm can deal with enormous information by processing
time, and a higher level of expectation rates.
Keywords:
Algorithm
Bayesian network
Big data
Copyright © 2020 Institute of Advanced Engineering and Science.
All rights reserved.
Corresponding Author:
Zalizah Awang Long
Malaysian Institute of Information technology (MIIT),
Universiti Kuala Lumpur (UniKL),
1016 Jalan Sultan Ismail, 50250 Kuala Lumpur, Malaysia.
Email: zalizah@unikl.edu.my
1. INTRODUCTION
Bayesian system is utilized to anticipate ideal arrangement in this decade. There has been
a development for undertaking research on Bayesian systems in the fieldm of information technology [1-5].
By summing up the two methodologies for discovering the complex structure of Bayesian system.
The principal approach presents learning as a requirement fulfillment issue. In this methodology, we survey
the properties of restrictive freedom among the traits in the information. Normally this is finished utilizing
a measurable speculation test for optimal solution. We at that point assemble a system that shows
the required conditions and independencies. This should be possible utilizing fruitful methods. Instances of
this methodology incorporate with some Bayesian methods [6-8]. The second methodology presents learning
as a Big-data issue. We begin by characterizing a measurably stimulated score that depicts the wellness of
every possible structure to the observed information. These scores incorporate Bayesian scores [9-12].
A vital advancement of the optimal solution for handling big data is a challenge while IT industry is
introduced by providing real-time data [13-15]. Real-time data is huge as data update to the storage in every
millisecond. Therefore, an optimal solution using Bayesian network absolutely required to handle the big
data congestion in IT industry [16-20]. Such 'conventional' look strategies don't make a difference any
 ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 10, No. 2, April 2020 : 2031- 2036
2032
information about the normal structure of the system to be scholarly. For instance, eager slope climbing seeks
techniques look at all conceivable neighbourhood changes in each progression and apply the one that
prompts the greatest enhancement in score. The standard decision for neighborhood changes is edge
expansion, edge cancellation, and edge inversion. The expense of these assessments ends up intense when we
gain from enormous informational indexes. Since the assessment of new applicants requires gathering
different insights about the information, it turns out to be progressively costly as the quantity of occurrences
develops. To gather these measurements, we for the most part need to play out a disregard the information.
Albeit, ongoing strategies might decrease the expense of this accumulation action, regardless we expect
non-minor calculation time for each new arrangement of measurements we require [21-24]. Also, on the off
chance that we consider areas with substantial number of properties, the quantity of conceivable applicants
develops exponentially. In this research, we propose and implement an adaptive knowledge-based bayesian
network algorithm to classify the impact of big data congestion in information technology and establish
the novel method by comparing the processing time with existing method.
2. PHYSICS IMPACT OF BIG DATA IN IT APPLICATION
The application in IT are nearly acquiring a huge insurgency the manner in which we interface with
"jobs". This will happen utilizing a lot of information that many keen gadgets will deliver and that will
change the manner in which Big Data is taken care of. Give us a chance to see how. As long as the data
getting from the different sources mostly considering the real-time data that are huge in size is known as big
data. It has some impact in IT application process can be identified in following sections.
2.1. Security of Big Data
Expanded information requires expanded security. In IT application, the systems will make a system
of shifted gadgets that will likewise prompt a pooling of changed sorts of information. IT Data Security will
be another test put crosswise over with Big Data Security experts. In the event that any security escape clause
occurs, the whole system of associated gadgets will be put in danger of control. The check and verification of
gadgets that are added to the IT system will wind up essential. It will end up being the undertaking of Big
Data associations to make a checkpoint to review the gadgets that are added to the system.
2.2. Storage of Big Data
The principal thing that strikes a chord with an expansion in the selection of IT is the measure of
information that will be produced. Going with such a lot of information comes the duty of putting away it
from numerous channels. Enormous Data associations are preparing up to move to the PaaS (Platform as
a Service) show with the goal that they approach an adaptable and versatile technique to deal with IT
information.
2.3. Analysis of Big Data
Big Data and information technology are interconnected with one another. IT will produce gigantic
measures of information that must be broke down if the systems work precisely. The systems may create
some excess information and that is the reason it ends up vital for Big Data associations to spend their
investigation control on the information that is essential. In this way, another component of information order
will be included so the Big Data Analytics instruments convey better execution. Different sources send in
truckloads of information for examination to Big Data associations. At the present time, Big Data
organizations are just barely getting to be fit for taking care of this colossal measure of information in an
exceedingly secure way. The change we are expecting on the Big Data front would be the selection of
adaptable and versatile answers for improve security, information putting away, and information
investigation abilities.
3. MATERIALS AND METHODS
For adapting little scale data-base system, Bayesian Network (BN) is as of now all around
investigated. However, learning in high dimensional areas e.g. informal communities and IT areas are
confronting issue of high dimensionality. These spaces deliver datasets with a few hundred or a huge number
of factors. It is really a serious issue for this kind of high dimension data for a Bayesian Network system.
In this section, a brief overview is carried out for Bayesian Network (BN). By considering the limitation of
general Bayesian Network on Big data, an algorithm is proposed to resolve the issues of BN.
Int J Elec & Comp Eng ISSN: 2088-8708 
Impact of big data congestion in IT: An adaptive knowledge-based Bayesian network (Soheli Farhana)
2033
3.1. Bayesian Network
There is only a solitary recommendation from Nielsen and Nielsen watching out for consistent
Bayesian Network modification [25]. The procedure screens of adaptable model. The circumstance suggests
to movement happened k observations back. Thusly, if we relearn show from last k cases, we will misfortune
data learned before k cases. The change recognition part consistently forms the models that gets
the information. This processes contention evaluates in every precedent v, information D in the hubs X. Strife
evaluate watches the policy of v fits the nearby B with the factor of Xi utilizing method [26-27]. The current
method will indicate the next assumption on the data handler that the individual components of a perception v
are emphatically corresponded that can be written as,
𝑙𝑜𝑔
𝑃 𝛽(𝑋 𝑖)
𝑃 𝛽(𝑋 𝑖|𝑋 𝑗(∀ 𝑗≠i).)
< 0 (1)
The (1) tracks the historical backdrop for contention evaluation as cXi for node Xi. Researchers
initially ascertain change the cosine part for the last 2k measures c1, c2 …… c2k in cXi,
𝐶2 ≡ ∑ 𝑐𝑗 𝑐𝑜𝑠 (
𝜋(𝑗+
1
2)
2𝑘
)2𝑘
𝑗=1 (2)
The part in (2) determined after gathering of every perception indicate the propensity of 2k struggle esteems
in orchestrating the inclined line. The heavy esteem shows the parameter k to handle with the perception of
next arrangement of suitable data from randomly coming from different sources of hubs. Researchers tended
to have unique instance for gradual Bayesian Network algorithm by discovering the basic adjustment.
It concluded with the past information by storing data using this method.
3.2. Proposed adaptive knowledge-based Bayesian Network algorithm
To develop adaptive knowledge-based Bayesian Network, we derive the Bayesian Network firsr.
From the Bayesian network, B can be expressed by the joint matrix E=(Cij) of its attributes and
the conditional probability table 𝑃(𝑥𝑗|𝜋𝑗), j=1,2,…,m of each node. The conditional probability table (CPT)
P(xj|πj) of each node can be equivalent to 𝑃(𝑥𝑗, 𝜋𝑗), and 𝑃(𝑥𝑗, 𝜋𝑗) satisfies the relationship below:
∑ 𝑃(𝑥𝑗, 𝜋𝑗)∀𝑥 𝑗∈𝑣(𝑗),∀𝜋 𝑗∈𝜑(𝑗) = 1 (3)
Where v(j) are value space of xj and φ (j) are value space of πj.
𝑃(𝑥𝑗, 𝜋𝑗) is more flexible than 𝑃(𝑥𝑗|𝜋𝑗) because 𝑃(𝑥𝑗, 𝜋𝑗) fulfilled the relationship. So, the encoding
below is used to descript a Bayesian network:
(𝑃(𝑥1, 𝜋1), 𝑃(𝑥2, 𝜋2)… … … . . , 𝑃(𝑥 𝑛, 𝜋 𝑛), 𝐸) (4)
Where E is the joint matrix. To adjust recently erudite parameter E from different hubs. To recycle past data
programmed to E from the past stage. In this way, E will refresh for conveyance of new information D1
dependent on the suspicion that just hubs in C require refreshing of their probabilistic ties. In learn piece
stage it takes in a somewhat coordinated sections GXi for every hub in C. At that point comparing pieces in E
additionally removed from every hub located at C. Every one of the parts at that point converged into
a solitary diagram G1, utilizing four bearing guidelines that save however much of B's structure as could
reasonably be expected and without damaging the newfound data. The factors that are restrictively free of
hub Xi molding on some arrangement of factors, are non-nearby Xi. So also, the factors discovered ward of
hub Xi are adjoining Xi in the chart sections. Generally imperative based learning techniques find just
the course of the curves of v utilizing free evaluation in bearing residual bends. Further, rest of
the connections in conclusive chart coordinates utilizing conditions bellow,
- In the event that the difference between A and E is a connection, C tends to A is a circular segment, and
the nearby point coordinate the connection the differences between A and E as A tend to E.
- On the off chance that the differences between A and E is a connection and there is a coordinated way
from A to B, at that point coordinate the connection A - E as AE.
- In the event that Rules 1 and 2 can't be connected, picked a connecti on A - E at arbitrary with the end
goal that the hubs discovered unaltered at main period calculation in β state.
- In the event that Rules 1 and 3 can't be connected, picked a connection indiscriminately and guide it
haphazardly.
 ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 10, No. 2, April 2020 : 2031- 2036
2034
4. RESULTS AND DISCUSSIONS
4.1. Experimental setup
In this area, a few trials are completed by contrasting proposed calculation and the ordinary
Bayesian Network calculation. The objective of this work is to assess the proposed calculation's capacity to
manage high dimensional information and portraying the circumstance where it beats alternate calculations.
The outcomes will demonstrate the adaptability of the calculation and observational assessment of
the proposed calculation is to legitimize its adequacy.
4.2. Results
Here we examine the conduct of client characterized parameter K. The impact of various
introductions for hunt period of the proposed calculation. As a matter of first importance, we examine
the adequacy of recurrence counter reserve. It is utilized in the various investigations displayed in this
examination. Here, we demonstrate how recurrence counter store proposed to lessen the learning time over
steady process over enormous number of employments. Figure 1 shows about the execution time for colossal
number of employments by utilizing proposed algorithm and regular Bayesian Network.
Client characterized of k which indicate quantity for occupations that put away at each progression
of executing the calculation. Along these lines, it reserves all connected factors with the objective k
information. The conduct of the proposed calculation with various k esteems is appeared in Figure 2. We can
see that the estimation of k could be among normal and most extreme level of the hypothetical chart.
Sensibly, the multifaceted nature straightly increments regarding k. This expansion in the multifaceted nature
is immaterial when contrasted with the aggregate capacity calls, though it is important that the proposed
calculation took in a decent estimation from k. The information has been tested from non-stationary area, and
the calculation don't experience any float.
Figure 1. Comparison of big data processing time Figure 2. Comparison on different k value
5. CONCLUSION
This examination demonstrates an experimental assessment of the proposed calculation on Bayesian
Network to take care the effect of Bigdata in IT industry application. The proposed adaptive knowledge-
based Bayesian Network was developed and examined. From the analysis, it was found that the proposed
algorithm processing time is better than the existing algorithm. Diverse reenactment has been taken care of
assess the flawlessness and the time utilization of the proposed calculation. The reproduction led dependent
on the diverse information sources applications. Examination were led with the customary and proposed
Bayesian Network calculation for big information control on IT industry application.
REFERENCES
[1] Mahler, R. P., "Statistical multisource-multitarget information fusion," Artech House, Inc, 2007.
[2] Li C., Zhang R., Li J. & Stoica P., "Model order determination for signed measurements via the Bayesian
information criterion," 2018 IEEE 10th Sensor Array and Multichannel Signal Processing Workshop (SAM),
pp. 366-370, 2018.
[3] Liu X., Lu R., Ma J., Chen L. & Qin B., "Privacy-preserving patient-centric clinical decision support system on
naive Bayesian classification," IEEE journal of biomedical and health informatics, vol. 20(2), pp. 655-668, 2016.
Int J Elec & Comp Eng ISSN: 2088-8708 
Impact of big data congestion in IT: An adaptive knowledge-based Bayesian network (Soheli Farhana)
2035
[4] Koudas N. & Bansal N. U.S. Patent No. 9,256,667. Washington, DC: U.S. Patent and Trademark Office, 2016.
[5] Liu D., Liang D. & Wang C., "A novel three-way decision model based on incomplete information system,"
Knowledge-Based Systems, vol. 91, pp. 32-45, 2016.
[6] Vandekerckhove J., Rouder J. N. & Kruschke J. K., "Bayesian methods for advancing psychological science," 2018
[7] Linkov I., Massey O., Keisler J., Rusyn I. & Hartung T., "From weight of evidence" to quantitative data integration
using multicriteria decision analysis and Bayesian methods," Altex, vol. 32(1), p. 3, 2015.
[8] Dorazio R. M., "Bayesian data analysis in population ecology: motivations, methods, and benefits," Population
ecology, vol. 58(1), pp. 31-44, 2016.
[9] Perryman A. L., Patel J. S., Russo R., Singleton E., Connell N., Ekins S. & Freundlich J. S., "Naïve bayesian models
for vero cell cytotoxicity," Pharmaceutical research, vol. 35(9), p. 170, 2018.
[10] Christinaki E., Poli R. & Citi L., "Bayesian transfer learning for the prediction of self-reported well-being scores,"
2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC),
pp. 41-44, 2018.
[11] Contaldi C., Vafaee F. & Nelson P. C., "Bayesian network hybrid learning using an elite-guided genetic algorithm,"
Artificial Intelligence Review, pp. 1-28, 2018.
[12] Tang Y., Zhang Q., Liu H. & Wang W., "Adaptive bayesian network structure learning from big datasets,"
International Conference on Database Systems for Advanced Applications, pp. 158-168, 2017.
[13] De Francisci Morales G., Bifet A., Khan L., Gama J. & Fan W., "IoT big data stream mining," Proceedings of
the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 2119-2120, 2016.
[14] Mishra N., Lin C. C. & Chang H. T., "A cognitive adopted framework for IoT big-data management and knowledge
discovery prospective," International Journal of Distributed Sensor Networks, vol. 11(10), 718390, 2015.
[15] Cai H., Xu B., Jiang L. & Vasilakos A. V., "IoT-based big data storage systems in cloud computing: Perspectives
and challenges," IEEE Internet of Things Journal, vol. 4(1), pp. 75-87, 2017.
[16] Sagiroglu S, Sinanc D., "Big data: A review," 2013 International Conference on Collaboration Technologies and
Systems (CTS), pp. 42-47, 2013.
[17] Raghupathi W, Raghupathi V., "Big data analytics in healthcare: promise and potential," Health information science
and systems, vol. 2(1), p. 3, 2014.
[18] Lee J, Kao HA, Yang S., "Service innovation and smart analytics for industry 4.0 and big data environment,"
Procedia Cirp, vol. 16, pp. 3-8, 2014.
[19] Tao F., Cheng J., Qi Q., Zhang M., Zhang H., Sui F., "Digital twin-driven product design, manufacturing and service
with big data," The International Journal of Advanced Manufacturing Technology, vol. 94(9-12), pp. 3563-76, 2018.
[20] Flyverbom M, Deibert R, Matten D., "The governance of digital technology, big data, and the internet: New roles
and responsibilities for business," Business & Society, vol. 58(1), pp. 3-19, 2019.
[21] Suciu G., Vulpe A., Fratu O. & Suciu V., "M2M remote telemetry and cloud IoT big data processing in viticulture,"
Wireless Communications and Mobile Computing Conference (IWCMC), 2015 International, pp. 1117-1121, 2015.
[22] Chawla S., Malec D. & Sivan B., "The power of randomness in bayesian optimal mechanism design," Games and
Economic Behavior, vol. 91, pp. 297-317, 2015.
[23] Dong G. & Chen Z., "Data driven energy management in a home microgrid based on bayesian optimal algorithm,"
IEEE Transactions on Industrial Informatics, 2018.
[24] Ryan E. G., Drovandi C. C., McGree J. M., & Pettitt A. N., "A review of modern computational algorithms for
bayesian optimal design," International Statistical Review, vol. 84(1), pp. 128-154, 2016.
[25] Nielsen S. H. & Nielsen T. D., "Adapting bayes network structures to non-stationary domains," International
Journal of Approximate Reasoning, vol. 49(2), pp. 379-397, 2008.
[26] Jensen F. V., Chamberlain B., Nordahl T. & Jensen F., "Analysis in HUGIN of data conflict," Proceedings of
the Sixth Annual Conference on Uncertainty in Artificial Intelligence, Elsevier Science Inc., pp. 519-528, 1990.
[27] Crimins F., "Numerical recipes in C++: The art of scientific computing," Applied Biochemistry and Biotechnology,
vol. 104(1), pp. 95-96, 2003.
BIOGRAPHIES OF AUTHORS
Dr. Soheli Farhana joined University of Kuala Lumpur, Malaysia in December 2018.
She received her PhD in Electrical Engineering from the International Islamic University Malaysia
(IIUM) in 2016 where she was developed a new model of Carbon Nanotube. She was the Post-
Doctoral Fellow at IIUM in 2016 where her research focused on the Development of Nano-Soft
Tools. Dr. Farhana was the Visiting Scholar at MIT, MA, USA in 2017. Dr. Farhana’s research
focuses on the Carbon Nanotube, Computer Graphics, Software Engineering, and Artificial
Intelligence. She is currently doing research on Big Data Analytics and Real-time Distributed
Systems. Dr. Farhana received the IIUM Faculty of Engineering Best Doctoral Dissertation Award
at 32nd
IIUM Convocation in 2016. She was the recipient of IIUM President Award, Gold Medal
from International Invention, Innovation & Technology Exhibition (ITEX), and the Best Paper
Award from the engineering congress in 2015 at Imperial College, United Kingdom. She was also
the recipient of the Professional of the Year Award from Worldwide Who’s Who in 2018.
 ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 10, No. 2, April 2020 : 2031- 2036
2036
Associate Prof Dr Adidah Lajis is an established lecturer and researcher in artificial intelligence
and cognitive computing. Her research interests include natural language processing, text mining,
cognitive assessment and intelligent system. She actively participated in short terms research
projects and received several research grants include Fundamental Research Grant Scheme by
Malaysia Ministry of Education. She is a reviewer for Cognitive Computation Journal and some of
conference proceedings paper.
Assoc. Prof. Dr. Zalizah Awang Long's passion is for the improvement in student character
building, can be traced back to 2015 where she spent significant time working on designing and
developing frameworks, models and various activities focusing on student development.
As a Director of the Center for Student Development then, she led the way by introducing a new
paradigm in student development. Assoc. Prof. Zalizah is the individual responsible for the new
student transcripts model known as GHOCS - Graduate Higher Order Critical Thinking Skills.
In addition to that, she also initiated the establishment of Ulul Albab and Wakaf at UniKL.
As a dedicated educator for more than 20 years, Assoc. Prof. Zalizah's life evolves very much
around teaching activities, as well as research. To add on, she has contributed to a number of
publications related to her passion on student character building and also her interest in data
mining. In 2012, her PhD thesis received the Excellence Thesis Award.Her passion in research
drives her to be constantly active in research matters, as she participates in both local and
international conferences as part of the reviewer team, co-chair and board member. Assoc. Prof.
Dr. Zalizah Awang Long is now serving as the Dean of Universiti Kuala Lumpur - Malaysian
Institute of Information Technology (UniKL MIIT).
Assoc. Prof. Dr. Haidawati Mohamad Nasir is a senior lecturer at the Universiti Kuala Lumpur,
Malaysian Institute of Information Technology. She obtained her PhD degree from the department
of Electrical and Electronic, University of Strathclyde, Glasgow in 2012. Her research interest is in
the signal and image processing with application to super-resolution image reconstruction,
machine learning, and image enhancement and computer vision.

Más contenido relacionado

La actualidad más candente

SEAMLESS AUTOMATION AND INTEGRATION OF MACHINE LEARNING CAPABILITIES FOR BIG ...
SEAMLESS AUTOMATION AND INTEGRATION OF MACHINE LEARNING CAPABILITIES FOR BIG ...SEAMLESS AUTOMATION AND INTEGRATION OF MACHINE LEARNING CAPABILITIES FOR BIG ...
SEAMLESS AUTOMATION AND INTEGRATION OF MACHINE LEARNING CAPABILITIES FOR BIG ...
ijdpsjournal
 
Big data - a review (2013 4)
Big data - a review (2013 4)Big data - a review (2013 4)
Big data - a review (2013 4)
Sonu Gupta
 
CIKM2020 Keynote: Accelerating discovery science with an Internet of FAIR dat...
CIKM2020 Keynote: Accelerating discovery science with an Internet of FAIR dat...CIKM2020 Keynote: Accelerating discovery science with an Internet of FAIR dat...
CIKM2020 Keynote: Accelerating discovery science with an Internet of FAIR dat...
Michel Dumontier
 
Cluster Based Access Privilege Management Scheme for Databases
Cluster Based Access Privilege Management Scheme for DatabasesCluster Based Access Privilege Management Scheme for Databases
Cluster Based Access Privilege Management Scheme for Databases
Editor IJMTER
 

La actualidad más candente (16)

A COMPREHENSIVE STUDY ON POTENTIAL RESEARCH OPPORTUNITIES OF BIG DATA ANALYTI...
A COMPREHENSIVE STUDY ON POTENTIAL RESEARCH OPPORTUNITIES OF BIG DATA ANALYTI...A COMPREHENSIVE STUDY ON POTENTIAL RESEARCH OPPORTUNITIES OF BIG DATA ANALYTI...
A COMPREHENSIVE STUDY ON POTENTIAL RESEARCH OPPORTUNITIES OF BIG DATA ANALYTI...
 
SEAMLESS AUTOMATION AND INTEGRATION OF MACHINE LEARNING CAPABILITIES FOR BIG ...
SEAMLESS AUTOMATION AND INTEGRATION OF MACHINE LEARNING CAPABILITIES FOR BIG ...SEAMLESS AUTOMATION AND INTEGRATION OF MACHINE LEARNING CAPABILITIES FOR BIG ...
SEAMLESS AUTOMATION AND INTEGRATION OF MACHINE LEARNING CAPABILITIES FOR BIG ...
 
Big data - a review (2013 4)
Big data - a review (2013 4)Big data - a review (2013 4)
Big data - a review (2013 4)
 
CIKM2020 Keynote: Accelerating discovery science with an Internet of FAIR dat...
CIKM2020 Keynote: Accelerating discovery science with an Internet of FAIR dat...CIKM2020 Keynote: Accelerating discovery science with an Internet of FAIR dat...
CIKM2020 Keynote: Accelerating discovery science with an Internet of FAIR dat...
 
Mining Social Media Data for Understanding Drugs Usage
Mining Social Media Data for Understanding Drugs  UsageMining Social Media Data for Understanding Drugs  Usage
Mining Social Media Data for Understanding Drugs Usage
 
Ijet v5 i6p12
Ijet v5 i6p12Ijet v5 i6p12
Ijet v5 i6p12
 
Survey on Medical Data Sharing Systems with NTRU
Survey on Medical Data Sharing Systems with NTRUSurvey on Medical Data Sharing Systems with NTRU
Survey on Medical Data Sharing Systems with NTRU
 
Full Paper: Analytics: Key to go from generating big data to deriving busines...
Full Paper: Analytics: Key to go from generating big data to deriving busines...Full Paper: Analytics: Key to go from generating big data to deriving busines...
Full Paper: Analytics: Key to go from generating big data to deriving busines...
 
A REVIEW ON CLASSIFICATION OF DATA IMBALANCE USING BIGDATA
A REVIEW ON CLASSIFICATION OF DATA IMBALANCE USING BIGDATAA REVIEW ON CLASSIFICATION OF DATA IMBALANCE USING BIGDATA
A REVIEW ON CLASSIFICATION OF DATA IMBALANCE USING BIGDATA
 
IRJET- Scope of Big Data Analytics in Industrial Domain
IRJET- Scope of Big Data Analytics in Industrial DomainIRJET- Scope of Big Data Analytics in Industrial Domain
IRJET- Scope of Big Data Analytics in Industrial Domain
 
Challenges in Analytics for BIG Data
Challenges in Analytics for BIG DataChallenges in Analytics for BIG Data
Challenges in Analytics for BIG Data
 
Internet of Things (IoT) and Artificial Intelligence (AI) role in Medical and...
Internet of Things (IoT) and Artificial Intelligence (AI) role in Medical and...Internet of Things (IoT) and Artificial Intelligence (AI) role in Medical and...
Internet of Things (IoT) and Artificial Intelligence (AI) role in Medical and...
 
A Novel Framework for Big Data Processing in a Data-driven Society
A Novel Framework for Big Data Processing in a Data-driven SocietyA Novel Framework for Big Data Processing in a Data-driven Society
A Novel Framework for Big Data Processing in a Data-driven Society
 
Big Data analytics
Big Data analyticsBig Data analytics
Big Data analytics
 
Cluster Based Access Privilege Management Scheme for Databases
Cluster Based Access Privilege Management Scheme for DatabasesCluster Based Access Privilege Management Scheme for Databases
Cluster Based Access Privilege Management Scheme for Databases
 
Causal networks, learning and inference - Introduction
Causal networks, learning and inference - IntroductionCausal networks, learning and inference - Introduction
Causal networks, learning and inference - Introduction
 

Similar a Impact of big data congestion in IT: An adaptive knowledgebased Bayesian network

Big data challenges for e governance
Big data challenges for e governanceBig data challenges for e governance
Big data challenges for e governance
bharati k
 
Efficient Data Filtering Algorithm for Big Data Technology in Telecommunicati...
Efficient Data Filtering Algorithm for Big Data Technology in Telecommunicati...Efficient Data Filtering Algorithm for Big Data Technology in Telecommunicati...
Efficient Data Filtering Algorithm for Big Data Technology in Telecommunicati...
Onyebuchi nosiri
 
wireless sensor network
wireless sensor networkwireless sensor network
wireless sensor network
parry prabhu
 
SEAMLESS AUTOMATION AND INTEGRATION OF MACHINE LEARNING CAPABILITIES FOR BIG ...
SEAMLESS AUTOMATION AND INTEGRATION OF MACHINE LEARNING CAPABILITIES FOR BIG ...SEAMLESS AUTOMATION AND INTEGRATION OF MACHINE LEARNING CAPABILITIES FOR BIG ...
SEAMLESS AUTOMATION AND INTEGRATION OF MACHINE LEARNING CAPABILITIES FOR BIG ...
ijdpsjournal
 
SECURITY AND PRIVACY AWARE PROGRAMMING MODEL FOR IOT APPLICATIONS IN CLOUD EN...
SECURITY AND PRIVACY AWARE PROGRAMMING MODEL FOR IOT APPLICATIONS IN CLOUD EN...SECURITY AND PRIVACY AWARE PROGRAMMING MODEL FOR IOT APPLICATIONS IN CLOUD EN...
SECURITY AND PRIVACY AWARE PROGRAMMING MODEL FOR IOT APPLICATIONS IN CLOUD EN...
ijccsa
 

Similar a Impact of big data congestion in IT: An adaptive knowledgebased Bayesian network (20)

Big data challenges for e governance
Big data challenges for e governanceBig data challenges for e governance
Big data challenges for e governance
 
Next generation big data analytics state of the art
Next generation big data analytics state of the artNext generation big data analytics state of the art
Next generation big data analytics state of the art
 
CASE STUDY ON METHODS AND TOOLS FOR THE BIG DATA ANALYSIS
CASE STUDY ON METHODS AND TOOLS FOR THE BIG DATA ANALYSISCASE STUDY ON METHODS AND TOOLS FOR THE BIG DATA ANALYSIS
CASE STUDY ON METHODS AND TOOLS FOR THE BIG DATA ANALYSIS
 
Comparing and analyzing various method of data integration in big data
Comparing and analyzing various method of data integration in big dataComparing and analyzing various method of data integration in big data
Comparing and analyzing various method of data integration in big data
 
A Deep Dissertion Of Data Science Related Issues And Its Applications
A Deep Dissertion Of Data Science  Related Issues And Its ApplicationsA Deep Dissertion Of Data Science  Related Issues And Its Applications
A Deep Dissertion Of Data Science Related Issues And Its Applications
 
IOT DATA AND BIG DATA
IOT DATA AND BIG DATAIOT DATA AND BIG DATA
IOT DATA AND BIG DATA
 
Insights on critical energy efficiency approaches in internet-ofthings applic...
Insights on critical energy efficiency approaches in internet-ofthings applic...Insights on critical energy efficiency approaches in internet-ofthings applic...
Insights on critical energy efficiency approaches in internet-ofthings applic...
 
Big Data in Bioinformatics & the Era of Cloud Computing
Big Data in Bioinformatics & the Era of Cloud ComputingBig Data in Bioinformatics & the Era of Cloud Computing
Big Data in Bioinformatics & the Era of Cloud Computing
 
Challenges and outlook with Big Data
Challenges and outlook with Big Data Challenges and outlook with Big Data
Challenges and outlook with Big Data
 
Efficient Data Filtering Algorithm for Big Data Technology in Telecommunicati...
Efficient Data Filtering Algorithm for Big Data Technology in Telecommunicati...Efficient Data Filtering Algorithm for Big Data Technology in Telecommunicati...
Efficient Data Filtering Algorithm for Big Data Technology in Telecommunicati...
 
Efficient Data Filtering Algorithm for Big Data Technology in Telecommunicati...
Efficient Data Filtering Algorithm for Big Data Technology in Telecommunicati...Efficient Data Filtering Algorithm for Big Data Technology in Telecommunicati...
Efficient Data Filtering Algorithm for Big Data Technology in Telecommunicati...
 
wireless sensor network
wireless sensor networkwireless sensor network
wireless sensor network
 
SEAMLESS AUTOMATION AND INTEGRATION OF MACHINE LEARNING CAPABILITIES FOR BIG ...
SEAMLESS AUTOMATION AND INTEGRATION OF MACHINE LEARNING CAPABILITIES FOR BIG ...SEAMLESS AUTOMATION AND INTEGRATION OF MACHINE LEARNING CAPABILITIES FOR BIG ...
SEAMLESS AUTOMATION AND INTEGRATION OF MACHINE LEARNING CAPABILITIES FOR BIG ...
 
SECURITY AND PRIVACY AWARE PROGRAMMING MODEL FOR IOT APPLICATIONS IN CLOUD EN...
SECURITY AND PRIVACY AWARE PROGRAMMING MODEL FOR IOT APPLICATIONS IN CLOUD EN...SECURITY AND PRIVACY AWARE PROGRAMMING MODEL FOR IOT APPLICATIONS IN CLOUD EN...
SECURITY AND PRIVACY AWARE PROGRAMMING MODEL FOR IOT APPLICATIONS IN CLOUD EN...
 
Nikita rajbhoj(a 50)
Nikita rajbhoj(a 50)Nikita rajbhoj(a 50)
Nikita rajbhoj(a 50)
 
A Model Design of Big Data Processing using HACE Theorem
A Model Design of Big Data Processing using HACE TheoremA Model Design of Big Data Processing using HACE Theorem
A Model Design of Big Data Processing using HACE Theorem
 
A survey of big data and machine learning
A survey of big data and machine learning A survey of big data and machine learning
A survey of big data and machine learning
 
Complete-SRS.doc
Complete-SRS.docComplete-SRS.doc
Complete-SRS.doc
 
DEALING CRISIS MANAGEMENT USING AI
DEALING CRISIS MANAGEMENT USING AIDEALING CRISIS MANAGEMENT USING AI
DEALING CRISIS MANAGEMENT USING AI
 
DEALING CRISIS MANAGEMENT USING AI
DEALING CRISIS MANAGEMENT USING AIDEALING CRISIS MANAGEMENT USING AI
DEALING CRISIS MANAGEMENT USING AI
 

Más de IJECEIAES

Predicting churn with filter-based techniques and deep learning
Predicting churn with filter-based techniques and deep learningPredicting churn with filter-based techniques and deep learning
Predicting churn with filter-based techniques and deep learning
IJECEIAES
 
Automatic customer review summarization using deep learningbased hybrid senti...
Automatic customer review summarization using deep learningbased hybrid senti...Automatic customer review summarization using deep learningbased hybrid senti...
Automatic customer review summarization using deep learningbased hybrid senti...
IJECEIAES
 
Situational judgment test measures administrator computational thinking with ...
Situational judgment test measures administrator computational thinking with ...Situational judgment test measures administrator computational thinking with ...
Situational judgment test measures administrator computational thinking with ...
IJECEIAES
 
Hand LightWeightNet: an optimized hand pose estimation for interactive mobile...
Hand LightWeightNet: an optimized hand pose estimation for interactive mobile...Hand LightWeightNet: an optimized hand pose estimation for interactive mobile...
Hand LightWeightNet: an optimized hand pose estimation for interactive mobile...
IJECEIAES
 
Application of deep learning methods for automated analysis of retinal struct...
Application of deep learning methods for automated analysis of retinal struct...Application of deep learning methods for automated analysis of retinal struct...
Application of deep learning methods for automated analysis of retinal struct...
IJECEIAES
 
Predictive modeling for breast cancer based on machine learning algorithms an...
Predictive modeling for breast cancer based on machine learning algorithms an...Predictive modeling for breast cancer based on machine learning algorithms an...
Predictive modeling for breast cancer based on machine learning algorithms an...
IJECEIAES
 

Más de IJECEIAES (20)

Predicting churn with filter-based techniques and deep learning
Predicting churn with filter-based techniques and deep learningPredicting churn with filter-based techniques and deep learning
Predicting churn with filter-based techniques and deep learning
 
Taxi-out time prediction at Mohammed V Casablanca Airport
Taxi-out time prediction at Mohammed V Casablanca AirportTaxi-out time prediction at Mohammed V Casablanca Airport
Taxi-out time prediction at Mohammed V Casablanca Airport
 
Automatic customer review summarization using deep learningbased hybrid senti...
Automatic customer review summarization using deep learningbased hybrid senti...Automatic customer review summarization using deep learningbased hybrid senti...
Automatic customer review summarization using deep learningbased hybrid senti...
 
Ataxic person prediction using feature optimized based on machine learning model
Ataxic person prediction using feature optimized based on machine learning modelAtaxic person prediction using feature optimized based on machine learning model
Ataxic person prediction using feature optimized based on machine learning model
 
Situational judgment test measures administrator computational thinking with ...
Situational judgment test measures administrator computational thinking with ...Situational judgment test measures administrator computational thinking with ...
Situational judgment test measures administrator computational thinking with ...
 
Hand LightWeightNet: an optimized hand pose estimation for interactive mobile...
Hand LightWeightNet: an optimized hand pose estimation for interactive mobile...Hand LightWeightNet: an optimized hand pose estimation for interactive mobile...
Hand LightWeightNet: an optimized hand pose estimation for interactive mobile...
 
An overlapping conscious relief-based feature subset selection method
An overlapping conscious relief-based feature subset selection methodAn overlapping conscious relief-based feature subset selection method
An overlapping conscious relief-based feature subset selection method
 
Recognition of music symbol notation using convolutional neural network
Recognition of music symbol notation using convolutional neural networkRecognition of music symbol notation using convolutional neural network
Recognition of music symbol notation using convolutional neural network
 
A simplified classification computational model of opinion mining using deep ...
A simplified classification computational model of opinion mining using deep ...A simplified classification computational model of opinion mining using deep ...
A simplified classification computational model of opinion mining using deep ...
 
An efficient convolutional neural network-extreme gradient boosting hybrid de...
An efficient convolutional neural network-extreme gradient boosting hybrid de...An efficient convolutional neural network-extreme gradient boosting hybrid de...
An efficient convolutional neural network-extreme gradient boosting hybrid de...
 
Generating images using generative adversarial networks based on text descrip...
Generating images using generative adversarial networks based on text descrip...Generating images using generative adversarial networks based on text descrip...
Generating images using generative adversarial networks based on text descrip...
 
Collusion-resistant multiparty data sharing in social networks
Collusion-resistant multiparty data sharing in social networksCollusion-resistant multiparty data sharing in social networks
Collusion-resistant multiparty data sharing in social networks
 
Application of deep learning methods for automated analysis of retinal struct...
Application of deep learning methods for automated analysis of retinal struct...Application of deep learning methods for automated analysis of retinal struct...
Application of deep learning methods for automated analysis of retinal struct...
 
Proposal of a similarity measure for unified modeling language class diagram ...
Proposal of a similarity measure for unified modeling language class diagram ...Proposal of a similarity measure for unified modeling language class diagram ...
Proposal of a similarity measure for unified modeling language class diagram ...
 
Efficient criticality oriented service brokering policy in cloud datacenters
Efficient criticality oriented service brokering policy in cloud datacentersEfficient criticality oriented service brokering policy in cloud datacenters
Efficient criticality oriented service brokering policy in cloud datacenters
 
System call frequency analysis-based generative adversarial network model for...
System call frequency analysis-based generative adversarial network model for...System call frequency analysis-based generative adversarial network model for...
System call frequency analysis-based generative adversarial network model for...
 
Comparison of Iris dataset classification with Gaussian naïve Bayes and decis...
Comparison of Iris dataset classification with Gaussian naïve Bayes and decis...Comparison of Iris dataset classification with Gaussian naïve Bayes and decis...
Comparison of Iris dataset classification with Gaussian naïve Bayes and decis...
 
Efficient intelligent crawler for hamming distance based on prioritization of...
Efficient intelligent crawler for hamming distance based on prioritization of...Efficient intelligent crawler for hamming distance based on prioritization of...
Efficient intelligent crawler for hamming distance based on prioritization of...
 
Predictive modeling for breast cancer based on machine learning algorithms an...
Predictive modeling for breast cancer based on machine learning algorithms an...Predictive modeling for breast cancer based on machine learning algorithms an...
Predictive modeling for breast cancer based on machine learning algorithms an...
 
An algorithm for decomposing variations of 3D model
An algorithm for decomposing variations of 3D modelAn algorithm for decomposing variations of 3D model
An algorithm for decomposing variations of 3D model
 

Último

Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
Integrated Test Rig For HTFE-25 - Neometrix
Integrated Test Rig For HTFE-25 - NeometrixIntegrated Test Rig For HTFE-25 - Neometrix
Integrated Test Rig For HTFE-25 - Neometrix
Neometrix_Engineering_Pvt_Ltd
 
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort ServiceCall Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak HamilCara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Kandungan 087776558899
 

Último (20)

Call Girls Wakad Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Wakad Call Me 7737669865 Budget Friendly No Advance BookingCall Girls Wakad Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Wakad Call Me 7737669865 Budget Friendly No Advance Booking
 
University management System project report..pdf
University management System project report..pdfUniversity management System project report..pdf
University management System project report..pdf
 
Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024
 
Block diagram reduction techniques in control systems.ppt
Block diagram reduction techniques in control systems.pptBlock diagram reduction techniques in control systems.ppt
Block diagram reduction techniques in control systems.ppt
 
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
 
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
 
Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...
Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...
Hazard Identification (HAZID) vs. Hazard and Operability (HAZOP): A Comparati...
 
Thermal Engineering -unit - III & IV.ppt
Thermal Engineering -unit - III & IV.pptThermal Engineering -unit - III & IV.ppt
Thermal Engineering -unit - III & IV.ppt
 
Work-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptxWork-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptx
 
Double Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torqueDouble Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torque
 
DC MACHINE-Motoring and generation, Armature circuit equation
DC MACHINE-Motoring and generation, Armature circuit equationDC MACHINE-Motoring and generation, Armature circuit equation
DC MACHINE-Motoring and generation, Armature circuit equation
 
chapter 5.pptx: drainage and irrigation engineering
chapter 5.pptx: drainage and irrigation engineeringchapter 5.pptx: drainage and irrigation engineering
chapter 5.pptx: drainage and irrigation engineering
 
Thermal Engineering Unit - I & II . ppt
Thermal Engineering  Unit - I & II . pptThermal Engineering  Unit - I & II . ppt
Thermal Engineering Unit - I & II . ppt
 
Bhosari ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready For ...
Bhosari ( Call Girls ) Pune  6297143586  Hot Model With Sexy Bhabi Ready For ...Bhosari ( Call Girls ) Pune  6297143586  Hot Model With Sexy Bhabi Ready For ...
Bhosari ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready For ...
 
Integrated Test Rig For HTFE-25 - Neometrix
Integrated Test Rig For HTFE-25 - NeometrixIntegrated Test Rig For HTFE-25 - Neometrix
Integrated Test Rig For HTFE-25 - Neometrix
 
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort ServiceCall Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
 
(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7
(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7
(INDIRA) Call Girl Meerut Call Now 8617697112 Meerut Escorts 24x7
 
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak HamilCara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
 
Unit 1 - Soil Classification and Compaction.pdf
Unit 1 - Soil Classification and Compaction.pdfUnit 1 - Soil Classification and Compaction.pdf
Unit 1 - Soil Classification and Compaction.pdf
 
VIP Model Call Girls Kothrud ( Pune ) Call ON 8005736733 Starting From 5K to ...
VIP Model Call Girls Kothrud ( Pune ) Call ON 8005736733 Starting From 5K to ...VIP Model Call Girls Kothrud ( Pune ) Call ON 8005736733 Starting From 5K to ...
VIP Model Call Girls Kothrud ( Pune ) Call ON 8005736733 Starting From 5K to ...
 

Impact of big data congestion in IT: An adaptive knowledgebased Bayesian network

  • 1. International Journal of Electrical and Computer Engineering (IJECE) Vol. 10, No. 2, April 2020, pp. 2031~2036 ISSN: 2088-8708, DOI: 10.11591/ijece.v10i2.pp2031-2036  2031 Journal homepage: http://ijece.iaescore.com/index.php/IJECE Impact of big data congestion in IT: An adaptive knowledge- based Bayesian network Soheli Farhana, Adidah Lajis, Zalizah Awang Long, Haidawati Nasir MIIT, Universiti Kuala Lumpur (UniKL), Malaysia Article Info ABSTRACT Article history: Received May 6, 2019 Revised Oct 17, 2019 Accepted Oct 25, 2019 Recent progress on real-time systems are growing high in information technology which is showing importance in every single innovative field. Different applications in IT simultaneously produce the enormous measure of information that should be taken care of. In this paper, a novel algorithm of adaptive knowledge-based Bayesian network is proposed to deal with the impact of big data congestion in decision processing. A Bayesian system show is utilized to oversee learning arrangement toward all path for the basic leadership process. Information of Bayesian systems is routinely discharged as an ideal arrangement, where the examination work is to find a development that misuses a measurably inspired score. By and large, available information apparatuses manage this ideal arrangement by methods for normal hunt strategies. As it required enormous measure of information space, along these lines it is a tedious method that ought to be stayed away from. The circumstance ends up unequivocal once huge information include in hunting down ideal arrangement. A calculation is acquainted with achieve quicker preparing of ideal arrangement by constraining the pursuit information space. The proposed algorithm consists of recursive calculation intthe inquiry space. The outcome demonstrates that the ideal component of the proposed algorithm can deal with enormous information by processing time, and a higher level of expectation rates. Keywords: Algorithm Bayesian network Big data Copyright © 2020 Institute of Advanced Engineering and Science. All rights reserved. Corresponding Author: Zalizah Awang Long Malaysian Institute of Information technology (MIIT), Universiti Kuala Lumpur (UniKL), 1016 Jalan Sultan Ismail, 50250 Kuala Lumpur, Malaysia. Email: zalizah@unikl.edu.my 1. INTRODUCTION Bayesian system is utilized to anticipate ideal arrangement in this decade. There has been a development for undertaking research on Bayesian systems in the fieldm of information technology [1-5]. By summing up the two methodologies for discovering the complex structure of Bayesian system. The principal approach presents learning as a requirement fulfillment issue. In this methodology, we survey the properties of restrictive freedom among the traits in the information. Normally this is finished utilizing a measurable speculation test for optimal solution. We at that point assemble a system that shows the required conditions and independencies. This should be possible utilizing fruitful methods. Instances of this methodology incorporate with some Bayesian methods [6-8]. The second methodology presents learning as a Big-data issue. We begin by characterizing a measurably stimulated score that depicts the wellness of every possible structure to the observed information. These scores incorporate Bayesian scores [9-12]. A vital advancement of the optimal solution for handling big data is a challenge while IT industry is introduced by providing real-time data [13-15]. Real-time data is huge as data update to the storage in every millisecond. Therefore, an optimal solution using Bayesian network absolutely required to handle the big data congestion in IT industry [16-20]. Such 'conventional' look strategies don't make a difference any
  • 2.  ISSN: 2088-8708 Int J Elec & Comp Eng, Vol. 10, No. 2, April 2020 : 2031- 2036 2032 information about the normal structure of the system to be scholarly. For instance, eager slope climbing seeks techniques look at all conceivable neighbourhood changes in each progression and apply the one that prompts the greatest enhancement in score. The standard decision for neighborhood changes is edge expansion, edge cancellation, and edge inversion. The expense of these assessments ends up intense when we gain from enormous informational indexes. Since the assessment of new applicants requires gathering different insights about the information, it turns out to be progressively costly as the quantity of occurrences develops. To gather these measurements, we for the most part need to play out a disregard the information. Albeit, ongoing strategies might decrease the expense of this accumulation action, regardless we expect non-minor calculation time for each new arrangement of measurements we require [21-24]. Also, on the off chance that we consider areas with substantial number of properties, the quantity of conceivable applicants develops exponentially. In this research, we propose and implement an adaptive knowledge-based bayesian network algorithm to classify the impact of big data congestion in information technology and establish the novel method by comparing the processing time with existing method. 2. PHYSICS IMPACT OF BIG DATA IN IT APPLICATION The application in IT are nearly acquiring a huge insurgency the manner in which we interface with "jobs". This will happen utilizing a lot of information that many keen gadgets will deliver and that will change the manner in which Big Data is taken care of. Give us a chance to see how. As long as the data getting from the different sources mostly considering the real-time data that are huge in size is known as big data. It has some impact in IT application process can be identified in following sections. 2.1. Security of Big Data Expanded information requires expanded security. In IT application, the systems will make a system of shifted gadgets that will likewise prompt a pooling of changed sorts of information. IT Data Security will be another test put crosswise over with Big Data Security experts. In the event that any security escape clause occurs, the whole system of associated gadgets will be put in danger of control. The check and verification of gadgets that are added to the IT system will wind up essential. It will end up being the undertaking of Big Data associations to make a checkpoint to review the gadgets that are added to the system. 2.2. Storage of Big Data The principal thing that strikes a chord with an expansion in the selection of IT is the measure of information that will be produced. Going with such a lot of information comes the duty of putting away it from numerous channels. Enormous Data associations are preparing up to move to the PaaS (Platform as a Service) show with the goal that they approach an adaptable and versatile technique to deal with IT information. 2.3. Analysis of Big Data Big Data and information technology are interconnected with one another. IT will produce gigantic measures of information that must be broke down if the systems work precisely. The systems may create some excess information and that is the reason it ends up vital for Big Data associations to spend their investigation control on the information that is essential. In this way, another component of information order will be included so the Big Data Analytics instruments convey better execution. Different sources send in truckloads of information for examination to Big Data associations. At the present time, Big Data organizations are just barely getting to be fit for taking care of this colossal measure of information in an exceedingly secure way. The change we are expecting on the Big Data front would be the selection of adaptable and versatile answers for improve security, information putting away, and information investigation abilities. 3. MATERIALS AND METHODS For adapting little scale data-base system, Bayesian Network (BN) is as of now all around investigated. However, learning in high dimensional areas e.g. informal communities and IT areas are confronting issue of high dimensionality. These spaces deliver datasets with a few hundred or a huge number of factors. It is really a serious issue for this kind of high dimension data for a Bayesian Network system. In this section, a brief overview is carried out for Bayesian Network (BN). By considering the limitation of general Bayesian Network on Big data, an algorithm is proposed to resolve the issues of BN.
  • 3. Int J Elec & Comp Eng ISSN: 2088-8708  Impact of big data congestion in IT: An adaptive knowledge-based Bayesian network (Soheli Farhana) 2033 3.1. Bayesian Network There is only a solitary recommendation from Nielsen and Nielsen watching out for consistent Bayesian Network modification [25]. The procedure screens of adaptable model. The circumstance suggests to movement happened k observations back. Thusly, if we relearn show from last k cases, we will misfortune data learned before k cases. The change recognition part consistently forms the models that gets the information. This processes contention evaluates in every precedent v, information D in the hubs X. Strife evaluate watches the policy of v fits the nearby B with the factor of Xi utilizing method [26-27]. The current method will indicate the next assumption on the data handler that the individual components of a perception v are emphatically corresponded that can be written as, 𝑙𝑜𝑔 𝑃 𝛽(𝑋 𝑖) 𝑃 𝛽(𝑋 𝑖|𝑋 𝑗(∀ 𝑗≠i).) < 0 (1) The (1) tracks the historical backdrop for contention evaluation as cXi for node Xi. Researchers initially ascertain change the cosine part for the last 2k measures c1, c2 …… c2k in cXi, 𝐶2 ≡ ∑ 𝑐𝑗 𝑐𝑜𝑠 ( 𝜋(𝑗+ 1 2) 2𝑘 )2𝑘 𝑗=1 (2) The part in (2) determined after gathering of every perception indicate the propensity of 2k struggle esteems in orchestrating the inclined line. The heavy esteem shows the parameter k to handle with the perception of next arrangement of suitable data from randomly coming from different sources of hubs. Researchers tended to have unique instance for gradual Bayesian Network algorithm by discovering the basic adjustment. It concluded with the past information by storing data using this method. 3.2. Proposed adaptive knowledge-based Bayesian Network algorithm To develop adaptive knowledge-based Bayesian Network, we derive the Bayesian Network firsr. From the Bayesian network, B can be expressed by the joint matrix E=(Cij) of its attributes and the conditional probability table 𝑃(𝑥𝑗|𝜋𝑗), j=1,2,…,m of each node. The conditional probability table (CPT) P(xj|πj) of each node can be equivalent to 𝑃(𝑥𝑗, 𝜋𝑗), and 𝑃(𝑥𝑗, 𝜋𝑗) satisfies the relationship below: ∑ 𝑃(𝑥𝑗, 𝜋𝑗)∀𝑥 𝑗∈𝑣(𝑗),∀𝜋 𝑗∈𝜑(𝑗) = 1 (3) Where v(j) are value space of xj and φ (j) are value space of πj. 𝑃(𝑥𝑗, 𝜋𝑗) is more flexible than 𝑃(𝑥𝑗|𝜋𝑗) because 𝑃(𝑥𝑗, 𝜋𝑗) fulfilled the relationship. So, the encoding below is used to descript a Bayesian network: (𝑃(𝑥1, 𝜋1), 𝑃(𝑥2, 𝜋2)… … … . . , 𝑃(𝑥 𝑛, 𝜋 𝑛), 𝐸) (4) Where E is the joint matrix. To adjust recently erudite parameter E from different hubs. To recycle past data programmed to E from the past stage. In this way, E will refresh for conveyance of new information D1 dependent on the suspicion that just hubs in C require refreshing of their probabilistic ties. In learn piece stage it takes in a somewhat coordinated sections GXi for every hub in C. At that point comparing pieces in E additionally removed from every hub located at C. Every one of the parts at that point converged into a solitary diagram G1, utilizing four bearing guidelines that save however much of B's structure as could reasonably be expected and without damaging the newfound data. The factors that are restrictively free of hub Xi molding on some arrangement of factors, are non-nearby Xi. So also, the factors discovered ward of hub Xi are adjoining Xi in the chart sections. Generally imperative based learning techniques find just the course of the curves of v utilizing free evaluation in bearing residual bends. Further, rest of the connections in conclusive chart coordinates utilizing conditions bellow, - In the event that the difference between A and E is a connection, C tends to A is a circular segment, and the nearby point coordinate the connection the differences between A and E as A tend to E. - On the off chance that the differences between A and E is a connection and there is a coordinated way from A to B, at that point coordinate the connection A - E as AE. - In the event that Rules 1 and 2 can't be connected, picked a connecti on A - E at arbitrary with the end goal that the hubs discovered unaltered at main period calculation in β state. - In the event that Rules 1 and 3 can't be connected, picked a connection indiscriminately and guide it haphazardly.
  • 4.  ISSN: 2088-8708 Int J Elec & Comp Eng, Vol. 10, No. 2, April 2020 : 2031- 2036 2034 4. RESULTS AND DISCUSSIONS 4.1. Experimental setup In this area, a few trials are completed by contrasting proposed calculation and the ordinary Bayesian Network calculation. The objective of this work is to assess the proposed calculation's capacity to manage high dimensional information and portraying the circumstance where it beats alternate calculations. The outcomes will demonstrate the adaptability of the calculation and observational assessment of the proposed calculation is to legitimize its adequacy. 4.2. Results Here we examine the conduct of client characterized parameter K. The impact of various introductions for hunt period of the proposed calculation. As a matter of first importance, we examine the adequacy of recurrence counter reserve. It is utilized in the various investigations displayed in this examination. Here, we demonstrate how recurrence counter store proposed to lessen the learning time over steady process over enormous number of employments. Figure 1 shows about the execution time for colossal number of employments by utilizing proposed algorithm and regular Bayesian Network. Client characterized of k which indicate quantity for occupations that put away at each progression of executing the calculation. Along these lines, it reserves all connected factors with the objective k information. The conduct of the proposed calculation with various k esteems is appeared in Figure 2. We can see that the estimation of k could be among normal and most extreme level of the hypothetical chart. Sensibly, the multifaceted nature straightly increments regarding k. This expansion in the multifaceted nature is immaterial when contrasted with the aggregate capacity calls, though it is important that the proposed calculation took in a decent estimation from k. The information has been tested from non-stationary area, and the calculation don't experience any float. Figure 1. Comparison of big data processing time Figure 2. Comparison on different k value 5. CONCLUSION This examination demonstrates an experimental assessment of the proposed calculation on Bayesian Network to take care the effect of Bigdata in IT industry application. The proposed adaptive knowledge- based Bayesian Network was developed and examined. From the analysis, it was found that the proposed algorithm processing time is better than the existing algorithm. Diverse reenactment has been taken care of assess the flawlessness and the time utilization of the proposed calculation. The reproduction led dependent on the diverse information sources applications. Examination were led with the customary and proposed Bayesian Network calculation for big information control on IT industry application. REFERENCES [1] Mahler, R. P., "Statistical multisource-multitarget information fusion," Artech House, Inc, 2007. [2] Li C., Zhang R., Li J. & Stoica P., "Model order determination for signed measurements via the Bayesian information criterion," 2018 IEEE 10th Sensor Array and Multichannel Signal Processing Workshop (SAM), pp. 366-370, 2018. [3] Liu X., Lu R., Ma J., Chen L. & Qin B., "Privacy-preserving patient-centric clinical decision support system on naive Bayesian classification," IEEE journal of biomedical and health informatics, vol. 20(2), pp. 655-668, 2016.
  • 5. Int J Elec & Comp Eng ISSN: 2088-8708  Impact of big data congestion in IT: An adaptive knowledge-based Bayesian network (Soheli Farhana) 2035 [4] Koudas N. & Bansal N. U.S. Patent No. 9,256,667. Washington, DC: U.S. Patent and Trademark Office, 2016. [5] Liu D., Liang D. & Wang C., "A novel three-way decision model based on incomplete information system," Knowledge-Based Systems, vol. 91, pp. 32-45, 2016. [6] Vandekerckhove J., Rouder J. N. & Kruschke J. K., "Bayesian methods for advancing psychological science," 2018 [7] Linkov I., Massey O., Keisler J., Rusyn I. & Hartung T., "From weight of evidence" to quantitative data integration using multicriteria decision analysis and Bayesian methods," Altex, vol. 32(1), p. 3, 2015. [8] Dorazio R. M., "Bayesian data analysis in population ecology: motivations, methods, and benefits," Population ecology, vol. 58(1), pp. 31-44, 2016. [9] Perryman A. L., Patel J. S., Russo R., Singleton E., Connell N., Ekins S. & Freundlich J. S., "Naïve bayesian models for vero cell cytotoxicity," Pharmaceutical research, vol. 35(9), p. 170, 2018. [10] Christinaki E., Poli R. & Citi L., "Bayesian transfer learning for the prediction of self-reported well-being scores," 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 41-44, 2018. [11] Contaldi C., Vafaee F. & Nelson P. C., "Bayesian network hybrid learning using an elite-guided genetic algorithm," Artificial Intelligence Review, pp. 1-28, 2018. [12] Tang Y., Zhang Q., Liu H. & Wang W., "Adaptive bayesian network structure learning from big datasets," International Conference on Database Systems for Advanced Applications, pp. 158-168, 2017. [13] De Francisci Morales G., Bifet A., Khan L., Gama J. & Fan W., "IoT big data stream mining," Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 2119-2120, 2016. [14] Mishra N., Lin C. C. & Chang H. T., "A cognitive adopted framework for IoT big-data management and knowledge discovery prospective," International Journal of Distributed Sensor Networks, vol. 11(10), 718390, 2015. [15] Cai H., Xu B., Jiang L. & Vasilakos A. V., "IoT-based big data storage systems in cloud computing: Perspectives and challenges," IEEE Internet of Things Journal, vol. 4(1), pp. 75-87, 2017. [16] Sagiroglu S, Sinanc D., "Big data: A review," 2013 International Conference on Collaboration Technologies and Systems (CTS), pp. 42-47, 2013. [17] Raghupathi W, Raghupathi V., "Big data analytics in healthcare: promise and potential," Health information science and systems, vol. 2(1), p. 3, 2014. [18] Lee J, Kao HA, Yang S., "Service innovation and smart analytics for industry 4.0 and big data environment," Procedia Cirp, vol. 16, pp. 3-8, 2014. [19] Tao F., Cheng J., Qi Q., Zhang M., Zhang H., Sui F., "Digital twin-driven product design, manufacturing and service with big data," The International Journal of Advanced Manufacturing Technology, vol. 94(9-12), pp. 3563-76, 2018. [20] Flyverbom M, Deibert R, Matten D., "The governance of digital technology, big data, and the internet: New roles and responsibilities for business," Business & Society, vol. 58(1), pp. 3-19, 2019. [21] Suciu G., Vulpe A., Fratu O. & Suciu V., "M2M remote telemetry and cloud IoT big data processing in viticulture," Wireless Communications and Mobile Computing Conference (IWCMC), 2015 International, pp. 1117-1121, 2015. [22] Chawla S., Malec D. & Sivan B., "The power of randomness in bayesian optimal mechanism design," Games and Economic Behavior, vol. 91, pp. 297-317, 2015. [23] Dong G. & Chen Z., "Data driven energy management in a home microgrid based on bayesian optimal algorithm," IEEE Transactions on Industrial Informatics, 2018. [24] Ryan E. G., Drovandi C. C., McGree J. M., & Pettitt A. N., "A review of modern computational algorithms for bayesian optimal design," International Statistical Review, vol. 84(1), pp. 128-154, 2016. [25] Nielsen S. H. & Nielsen T. D., "Adapting bayes network structures to non-stationary domains," International Journal of Approximate Reasoning, vol. 49(2), pp. 379-397, 2008. [26] Jensen F. V., Chamberlain B., Nordahl T. & Jensen F., "Analysis in HUGIN of data conflict," Proceedings of the Sixth Annual Conference on Uncertainty in Artificial Intelligence, Elsevier Science Inc., pp. 519-528, 1990. [27] Crimins F., "Numerical recipes in C++: The art of scientific computing," Applied Biochemistry and Biotechnology, vol. 104(1), pp. 95-96, 2003. BIOGRAPHIES OF AUTHORS Dr. Soheli Farhana joined University of Kuala Lumpur, Malaysia in December 2018. She received her PhD in Electrical Engineering from the International Islamic University Malaysia (IIUM) in 2016 where she was developed a new model of Carbon Nanotube. She was the Post- Doctoral Fellow at IIUM in 2016 where her research focused on the Development of Nano-Soft Tools. Dr. Farhana was the Visiting Scholar at MIT, MA, USA in 2017. Dr. Farhana’s research focuses on the Carbon Nanotube, Computer Graphics, Software Engineering, and Artificial Intelligence. She is currently doing research on Big Data Analytics and Real-time Distributed Systems. Dr. Farhana received the IIUM Faculty of Engineering Best Doctoral Dissertation Award at 32nd IIUM Convocation in 2016. She was the recipient of IIUM President Award, Gold Medal from International Invention, Innovation & Technology Exhibition (ITEX), and the Best Paper Award from the engineering congress in 2015 at Imperial College, United Kingdom. She was also the recipient of the Professional of the Year Award from Worldwide Who’s Who in 2018.
  • 6.  ISSN: 2088-8708 Int J Elec & Comp Eng, Vol. 10, No. 2, April 2020 : 2031- 2036 2036 Associate Prof Dr Adidah Lajis is an established lecturer and researcher in artificial intelligence and cognitive computing. Her research interests include natural language processing, text mining, cognitive assessment and intelligent system. She actively participated in short terms research projects and received several research grants include Fundamental Research Grant Scheme by Malaysia Ministry of Education. She is a reviewer for Cognitive Computation Journal and some of conference proceedings paper. Assoc. Prof. Dr. Zalizah Awang Long's passion is for the improvement in student character building, can be traced back to 2015 where she spent significant time working on designing and developing frameworks, models and various activities focusing on student development. As a Director of the Center for Student Development then, she led the way by introducing a new paradigm in student development. Assoc. Prof. Zalizah is the individual responsible for the new student transcripts model known as GHOCS - Graduate Higher Order Critical Thinking Skills. In addition to that, she also initiated the establishment of Ulul Albab and Wakaf at UniKL. As a dedicated educator for more than 20 years, Assoc. Prof. Zalizah's life evolves very much around teaching activities, as well as research. To add on, she has contributed to a number of publications related to her passion on student character building and also her interest in data mining. In 2012, her PhD thesis received the Excellence Thesis Award.Her passion in research drives her to be constantly active in research matters, as she participates in both local and international conferences as part of the reviewer team, co-chair and board member. Assoc. Prof. Dr. Zalizah Awang Long is now serving as the Dean of Universiti Kuala Lumpur - Malaysian Institute of Information Technology (UniKL MIIT). Assoc. Prof. Dr. Haidawati Mohamad Nasir is a senior lecturer at the Universiti Kuala Lumpur, Malaysian Institute of Information Technology. She obtained her PhD degree from the department of Electrical and Electronic, University of Strathclyde, Glasgow in 2012. Her research interest is in the signal and image processing with application to super-resolution image reconstruction, machine learning, and image enhancement and computer vision.