© 2018 jetir april 2018, volume 5, issue 4 a review on

© 2018 JETIR April 2018, Volume 5, Issue 4 www.jetir.org (ISSN-2349-5162)

JETIR1804420 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org 1203

A REVIEW ON MACHINE LEARNING AN ITS

USE IN MODERN AGE

Avadhesh Kumar, Professor, Department of Computer Science & Engineering,

Galgotias University

ABSTRACT

By using machine learning (ML), a system may derive information from the data. It beyond the mere

acquisition of information, including also the putting to good use and personal growth from learning. The

main benefit of machine learning is the ability to find and capitalise on patterns that are buried in training

data. Learning the patterns from past experiences allows you to assess unfamiliar material, allowing you to

discover patterns in the new material and classify it accordingly. By engaging in this new method, people

are redefining how computer programmes are developed, since they now write programmes to automate

chores. Program construction is implemented via ML. Over the last several years, ML has seen a surge of

attention. Early machine learning approaches were inflexible and could not accommodate any variance in

the training data.

KEYWORDS: Machine Learning, Technology, Review

INTRODUCTION

There have been recent breakthroughs in computer power that provide the capacity to store and process a

large amount of data for training and testing machine learning models, which are essential for dealing with

large amounts of data. Some of these cloud computing solutions, for example, promise an endless supply of

computation and storage resources. GPU's and TPU's, however, enable accelerated training and inference

for data-laden problems. In order to better comprehend this point, bear in mind that a trained ML model, for

inference, may be used on less competent devices such as smartphones. Although networks have seen

considerable advancement, operations and administration remain laborious, and defects exist because of

human mistake [1-9]. In the event of network problems, network providers are held financially liable and

have their reputations negatively affected. A great level of interest in self-healing networks exists because

they are automatically self-configuring, self-optimizing, self-protective, and self-healing.

Network operation and administration, whilst needing a fair amount of cognitive control, provides a unique

set of obstacles for ML. The first challenge is that each network is unique, and standards are not used to

provide consistency across networks. An example of this is the wide and divergent variety of corporate

networks. What has worked in one kind of network may not be applicable in another [10-16]. The second

major obstacle to effective network management is that the network is always changing and dynamic factors

impede the use of fixed sets of patterns that help the network operate and manage. Because the number of

http://www.jetir.org/



programmes operating in the network and the sorts of devices linked to the network have continuously

increased, manual network management is almost impossible [17-23].

Networking technologies that have been made possible by programmability at the network level via

Software-Defined Networking (SDN) foster the use of machine learning in networking. It has, however,

seen little use for tasks such as pattern recognition, voice synthesis, and outlier detection, whereas ML has

found a greater use in tasks like as pattern recognition, voice synthesis, and outlier detection. These are the

primary challenges, which include: How can the most relevant data be collected? What controls can be

applied to old network devices? This, together with SDN, overcomes these issues [24-28]. The cognitive

capacity from machine learning may be used to network management and operation activities. Furthermore,

it is an interesting and meaningful process to use machine learning (ML) methods for a wide range of

complicated networking challenges. As a result, ML in networking is a very intriguing topic, and it 's

necessary to have a good grasp of ML approaches and networking challenges.

Our work here concerns the advancements in the use of machine learning in networking. For our job, we

take into consideration all the many aspects of website traffic, performance, and network security.

Classification, classifiers, and routing are essential in delivering differentiated and prioritised services in

traffic engineering. Under the context of congestion control, QoS/QoE correlation, and resource and fault

management, we talk about the implementation of machine learning methods There is no question that

security is one of the key foundations of networking, and in this respect, we focus on technologies that use

machine learning (ML) approaches for network security [29-31].

USE OF ML IN MODERN TECHNOLOGY

While machine learning is often good for finding answers to problems that have a big dataset of real-world

examples, there are situations when machine learning is less practical or does not apply. In this approach,

ML algorithms are developed to find and take use of hidden patterns in data for classifying, predicting, and

evaluating future outcomes. Even though the graphic represents a two-dimensional representation of data

and outcomes, the discussion applies to multi-dimensional datasets and outcomes [32-34]. For instance,

while doing clustering, a non-linear function may be found on a hyperplane that is used to differentiate

between various groups of data. Some networking challenges may be thought of as a challenge that exploits

machine learning. In other words, given a network condition, a classification challenge for security attacks

may include probing, Denial-of-Service (DoS), User-to-Root (U2R), Root-to-Local (R2L), or other

variations. In contrast, it is possible to create a regression issue to forecast the failure that will occur in the

future [35-36].

ML MODEL

It is crucial to use suitable and objective data to construct a successful ML model for a specific networking

challenge. Selection of appropriate representative datasets is a critical element in data collecting, as datasets




differ from one problem to the next as well as from one era to the next. The best way to collect data is

offline (collecting the data when it is first collected) and online (using an online tool to gather data) [37-38].

The vast amounts of historical data gathered offline enable you to train and test models, especially if there is

no internet connection. The feedback we get from real-time network data is both utilised for retraining the

model, and for supplying input to the model for usage in real time. In certain situations, a large variety of

offline data may be gathered from many sources, such as repositories, while a networking issue is being

investigation.

CONCLUSION

The principles of machine learning were derived from the domains of computer science, mathematics,

philosophy, economics, neurology, psychology, control theory, and more. Over the previous 75 years, a

wealth of ML approaches has emerged because to this ongoing research. A short history of ML, describing

some of the methods used in the field of computer networks, is given here. The historical roots of ML

started in 1943, when McCulloch first proposed a mathematical model of NNs for computers. Even now, the

artificial neuron remains at the heart of NN development. This early model needed human intervention to

properly set the necessary connection weights. A Hebbian learning method was used to update the

connection weights of the first NN model in 1949. Hebbian learning had a tremendous impact on the

development of NN.

1. REFERENCES

2. Jia, H.-Y., Chen, J., Yu, H.-L., & Liu, D.-Y. (2010). Soil fertility grading with Bayesian Network

transfer learning. 2010 International Conference on Machine Learning and Cybernetics, ICMLC

2010, 3, 1159–1163. https://doi.org/10.1109/ICMLC.2010.5580915

3. Jiang, Y.-L., Xu, C.-F., Yao, Y., & Zhao, K.-Q. (2004). Systems information in set pair analysis and

its applications. Proceedings of 2004 International Conference on Machine Learning and

Cybernetics, 3, 1717–1722. https://www.scopus.com/inward/record.uri?eid=2-s2.0-

6344223107&partnerID=40&md5=33869956200b1b59b3b7fc035ca2f5ae

4. Kaur, A., & Kaur, I. (2015). Improvement of K-mean clustering algorithm using support vector

machine on reusable software components. International Journal of Applied Engineering Research,

10(17), 38628–38637. https://www.scopus.com/inward/record.uri?eid=2-s2.0-

84942760674&partnerID=40&md5=976c9f2d9beea95512a56efcd4f851b0

5. Shahriar, M. S., & Rahman, M. S. (2015). Urban sensing and smart home energy optimisations: A

machine learning approach. IoT-App 2015 - Proceedings of the 2015 International Workshop on

Internet of Things Towards Applications, Co-Located with SenSys 2015, 19–22.

https://doi.org/10.1145/2820975.2820979

6. Aazam, M., & Huh, E.-N. (2015). Fog computing micro datacenter based dynamic resource




estimation and pricing model for IoT. In X. F. E. T. P. J. H. Takizawa M. Barolli L. (Ed.),

Proceedings - International Conference on Advanced Information Networking and Applications,

AINA (Vols. 2015-April, pp. 687–694). Institute of Electrical and Electronics Engineers Inc.

https://doi.org/10.1109/AINA.2015.254

7. Chiuchisan, I., Costin, H.-N., & Geman, O. (2014). Adopting the internet of things technologies in

health care systems. In H. C.-G. Gavrilas M. Ivanov O. (Ed.), EPE 2014 - Proceedings of the 2014

International Conference and Exposition on Electrical and Power Engineering (pp. 532–535).

Institute of Electrical and Electronics Engineers Inc. https://doi.org/10.1109/ICEPE.2014.6969965

8. Chung, P.-T., Chung, S. H., & Hui, C.-K. (2012). A web server design using search engine

optimization techniques for web intelligence for small organizations. 2012 IEEE Long Island

Systems, Applications and Technology Conference, LISAT 2012.

https://doi.org/10.1109/LISAT.2012.6223208

9. Bindman, J. (2002). Involuntary outpatient treatment in England and Wales. Current Opinion in

Psychiatry, 15(6), 595–598. https://doi.org/10.1097/00001504-200211000-00006

10. Chen, M., Wan, J., & Li, F. (2012). Machine-to-machine communications: Architectures, standards

and applications. KSII Transactions on Internet and Information Systems, 6(2), 480–497.

https://doi.org/10.3837/tiis.2012.02.002

11. Cune, M. S., de Putter, C., & Hoogstraten, J. (1994). Treatment outcome with implant-retained

overdentures: Part II-Patient satisfaction and predictability of subjective treatment outcome. The

Journal of Prosthetic Dentistry, 72(2), 152–158. https://doi.org/10.1016/0022-3913(94)90073-6

12. Doukas, C., & Maglogiannis, I. (2012). Bringing IoT and cloud computing towards pervasive

healthcare. Proceedings - 6th International Conference on Innovative Mobile and Internet Services

in Ubiquitous Computing, IMIS 2012, 922–926. https://doi.org/10.1109/IMIS.2012.26

13. Fok, C.-L., Julien, C., Roman, G.-C., & Lu, C. (2011). Challenges of satisfying multiple

stakeholders: Quality of service in the internet of things. Proceedings - International Conference on

Software Engineering, 55–60. https://doi.org/10.1145/1988051.1988062

14. Geller, J., Grudzinskas Jr., A. J., McDermeit, M., Fisher, W. H., & Lawlor, T. (1998). The efficacy

of involuntary outpatient treatment in Massachusetts. Administration and Policy in Mental Health,

25(3), 271–285. https://doi.org/10.1023/A:1022239322212

15. Geller, J. L., Fisher, W. H., Grudzinskas Jr., A. J., Clayfield, J. C., & Lawlor, T. (2006). Involuntary

outpatient treatment as “desintitutionalized coercion”: The net-widening concerns. International

Journal of Law and Psychiatry, 29(6), 551–562. https://doi.org/10.1016/j.ijlp.2006.08.003

16. Istepanaian, R. S. H., & Zhang, Y.-T. (2012). Guest editorial introduction to the special section: 4G

health-the long-term evolution of m-health. IEEE Transactions on Information Technology in




Biomedicine, 16(1), 1–5. https://doi.org/10.1109/TITB.2012.2183269

17. Istepanian, R. S. H. (2011). The potential of Internet of Things (IOT) for assisted living applications.

IET Seminar Digest, 2011(13611). https://doi.org/10.1049/ic.2011.0040

18. Istepanian, R. S. H., Hu, S., Philip, N. Y., & Sungoor, A. (2011). The potential of Internet of m-

health Things m-IoT for non-invasive glucose level sensing. Proceedings of the Annual

International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 5264–5266. https://doi.org/10.1109/IEMBS.2011.6091302

19. Istepanian, R. S. H., Sungoor, A., Faisal, A., & Philip, N. (2011). Internet of m-health things “m-

IoT.” IET Seminar Digest, 2011(13611). https://doi.org/10.1049/ic.2011.0036

20. Jara, A. J., Alcolea, A. F., Zamora, M. A., Gómez Skarmeta, A. F., & Alsaedy, M. (2010). Drugs

interaction checker based on IoT. 2010 Internet of Things, IoT 2010.

https://doi.org/10.1109/IOT.2010.5678458

21. Krogstie, J. (2011). Business information systems utilizing the future internet. Lecture Notes in

Business Information Processing, 90 LNBIP, 1–18. https://doi.org/10.1007/978-3-642-24511-4_1

22. Lintzeris, N., Strang, J., Metrebian, N., Byford, S., Hallam, C., Lee, S., & Zador, D. (2006).

Methodology for the randomised injecting opioid treatment trial (RIOTT): Evaluating injectable

methadone and injectable heroin treatment versus optimised oral methadone treatment in the UK.

Harm Reduction Journal, 3. https://doi.org/10.1186/1477-7517-3-28

23. Mainetti, L., Patrono, L., & Vilei, A. (2011). Evolution of wireless sensor networks towards the

Internet of Things: A survey. 2011 International Conference on Software, Telecommunications and

Computer Networks, SoftCOM 2011, 16–21. https://www.scopus.com/inward/record.uri?eid=2-s2.0-

81455142290&partnerID=40&md5=8089ed723b1c1056c9a6ae8fa767fa4f

24. Nain, G., Fouquet, F., Morin, B., Barais, O., & Jézéquel, J.-M. (2010). Integrating IoT and IoS with

a component-based approach. Proceedings - 36th EUROMICRO Conference on Software

Engineering and Advanced Applications, SEAA 2010, 191–198.

https://doi.org/10.1109/SEAA.2010.50

25. Pu, C. (2011). A world of opportunities: CPS, IOT, and beyond. DEBS’11 - Proceedings of the 5th

ACM International Conference on Distributed Event-Based Systems, 229.

https://doi.org/10.1145/2002259.2002290

26. Rao, B. B. P., Saluia, P., Sharma, N., Mittal, A., & Sharma, S. V. (2012). Cloud computing for

Internet of Things & sensing based applications. Proceedings of the International Conference on

Sensing Technology, ICST, 374–380. https://doi.org/10.1109/ICSensT.2012.6461705

27. Roach, S. M., & Downes, S. (2007). Caring for Australia’s most remote communities: obstetric

services in the Indian Ocean Territories. Rural and Remote Health, 7(2), 699.




https://doi.org/10.22605/rrh699

28. Rohokale, V. M., Prasad, N. R., & Prasad, R. (2011). A cooperative Internet of Things (IoT) for

rural healthcare monitoring and control. 2011 2nd International Conference on Wireless

Communication, Vehicular Technology, Information Theory and Aerospace and Electronic Systems

Technology, Wireless VITAE 2011. https://doi.org/10.1109/WIRELESSVITAE.2011.5940920

29. Sell, L., & Zador, D. (2004). Patients prescribed injectable heroin or methadone - Their opinions and

experiences of treatment. Addiction, 99(4), 442–449. https://doi.org/10.1111/j.1360-

0443.2003.00668.x

30. Swan, M. (2012). Sensor mania! the internet of things, wearable computing, objective metrics, and

the quantified self 2.0. Journal of Sensor and Actuator Networks, 1(3), 217–253.

https://doi.org/10.3390/jsan1030217

31. Tarouco, L. M. R., Bertholdo, L. M., Granville, L. Z., Arbiza, L. M. R., Carbone, F., Marotta, M., &

De Santanna, J. J. C. (2012). Internet of Things in healthcare: Interoperatibility and security issues.

IEEE International Conference on Communications, 6121–6125.

https://doi.org/10.1109/ICC.2012.6364830

32. Alyas, T., Tabassum, N., Naseem, S., Ahmed, F. and Ein, Q. T. (2014) “Learning-Based Routing in

Cognitive Networks”, IARS’ International Research Journal. Vic. Australia, 4(2). doi:

10.51611/iars.irj.v4i2.2014.40.

33. Vong, C.-M., Wong, P.-K., & Ip, W.-F. (2011). Framework of vehicle emission inspection and

control through RFID and traffic lights. Proceedings 2011 International Conference on System

Science and Engineering, ICSSE 2011, 597–600. https://doi.org/10.1109/ICSSE.2011.5961973

34. Willenbring, M. L., & Olson, D. H. (1999). A randomized trial of integrated outpatient treatment for

medically ill alcoholic men. Archives of Internal Medicine, 159(16), 1946–1952.

https://doi.org/10.1001/archinte.159.16.1946

35. You, L., Liu, C., & Tong, S. (2011). Community Medical Network (CMN): Architecture and

implementation. 2011 Global Mobile Congress, GMC 2011.

https://doi.org/10.1109/GMC.2011.6103930

36. Zhang, X. M., & Zhang, N. (2011). An open, secure and flexible platform based on internet of things

and cloud computing for ambient aiding living and telemedicine. 2011 International Conference on

Computer and Management, CAMAN 2011. https://doi.org/10.1109/CAMAN.2011.5778905

37. Asplund, M., & Nadjm-Tehrani, S. (2016). Attitudes and Perceptions of IoT Security in Critical

Societal Services. IEEE Access, 4, 2130–2138. https://doi.org/10.1109/ACCESS.2016.2560919

38. Bagheri, M., & Movahed, S. H. (2017). The Effect of the Internet of Things (IoT) on Education

Business Model. In C. R. G. L. Y. K. De Pietro G. Dipanda A. (Ed.), Proceedings - 12th




International Conference on Signal Image Technology and Internet-Based Systems, SITIS 2016 (pp.

435–441). Institute of Electrical and Electronics Engineers Inc.

https://doi.org/10.1109/SITIS.2016.74

39. Bertino, E., Choo, K.-K. R., Georgakopolous, D., & Nepal, S. (2016). Internet of things (IoT): Smart

and secure service delivery. ACM Transactions on Internet Technology, 16(4).

https://doi.org/10.1145/3013520

40. Bietz, M. J., Bloss, C. S., Calvert, S., Godino, J. G., Gregory, J., Claffey, M. P., Sheehan, J., &

Patrick, K. (2016). Opportunities and challenges in the use of personal health data for health research.

Journal of the American Medical Informatics Association, 23(e1), 1–7.

https://doi.org/10.1093/jamia/ocv118


© 2018 jetir april 2018, volume 5, issue 4 a review on

Documents