BIG DATA PROCESSING TECHNOLOGIES IN COMPUTER SCIENCE TEACHING
Keywords:
Big Data, machine learning, competences, KNIME, PythonAbstract
The article considers basic concepts of data science. The technologies of Machine Learning and Data Mining and the corresponding free software and data sources suitable for use in the educational process are analyzed. Elements of the methodology of teaching the basics of Data Science to future computer science teachers and computer scientists are offered.
Article’s purpose is to select appropriate free Data Mining tools and develop some components of the methodology of teaching disciplines of the cycle of professional training of future computer science teachers and computer scientists.
Methodology. Study and analysis of scientific publications, educational and methodical publications, comparative analysis of software, generalization of experience of specialists in education and computer science, modeling and synthesis of components of teaching methods, a systematic approach to teaching computer science.
Scientific novelty. Appropriate freely available Data Mining tools have been selected, and some components of the methodology for teaching future computer science teachers and computer scientists have been developed.
Conclusions. The main concepts and terms of modern technologies of processing and analysis of big data such as Data Science, Machine Learning, Data Mining are considered in the article. Machine learning algorithms are analyzed, sources of educational data are reviewed, freely distributed tools are selected, and methodological approaches to training Data Mining and Machine Learning of future computer science teachers and computer science specialists are presented. These methodological approaches to teaching modern methods and tools for processing large data are aimed at forming in future professionals the special competencies needed for effective modeling, design, development, maintenance, implementation and training of information technology in professional activities. Such formation can be carried out at studying courses «Information and communication technologies», «Programming in Python», «Fundamentals of artificial intelligence and data mining», «Introduction to Data Science and machine learning», which actualizes the subjects of these courses.
References
Aksyutina E. M., Belov Yu. S. (2016). Obzor arhitektur i metodov mashinnogo obucheniya dlya analiza bolshih dannyh [Overview of architecture and machine learning methods for big d ata analysis]. Elektronnyiy zhurnal : nauka, tehnika i obrazovanie – Electronic journal : Science, Technology and Education, 1 (5), 132–139. Retrieved from : http://nto-journal.ru/uploads/articles/0b9bd6d9833003ed0d6f9 bb/16fab81f1.pdf.
Kovalchuk, Yurii (2016). Poshuk, otrymannia y analiz danykh v osviti: suchasnyi stan i perspektyvy rozvytku [Data mining in education : current state and perspectives of development]. Informatsіinі tekhnolohіi і zasoby navchannia – Information Technologies and Learning Tools, 50, 152–164. DOI: 10.33407/ itlt.v50i6.1284.
Kuzmina, O. M. Zastosuvannia metodiv intelektualnoho analizu danykh u biznes-seredovyshchi [Application of data mining methods in the business environment]. Retrieved from : https://ir.vtei.edu.ua/g.php?fname=25802.pdf.
Pronin, S.V., Usychenko, O.Iu. Analiz instrumentiv mashynnoho navchannia dlia analizu velykykh masyviv danykh [Analysis of machine learning tools for analysis of large data sets]. Retrieved from : http:// publications.ntu.edu.ua/avtodorogi_i_stroitelstvo/108/67.pdf.
Konspekt lektsii z dystsypliny «Intelektualnyi analiz danykh» dlia studentiv spetsialnosti 8.04030301 «Systemnyi analiz i upravlinnia» [Summary of lectures on the subject «Data Mining» for students majoring in 8.04030301 «Systems Analysis and Management»]. Dnipropetrovsk, 2014. Retrieved from : URL:https://sau.nmu.org.ua/ua/osvita/metod/magistr/Intellectual_data_analysis/(Lecture)_NMU_SAU.pdf.
Mohylnyi, S. B. (2019). Mashynne navchannia z vykorystanniam mikrokompiuteriv: navch.-metod. Posib [Machine learning using microcomputers : training manual]. Kyiv.
Motoryn, R.M. (2020). Rol statystyky u pidhotovtsi fakhivtsiv z doslidzhenniam danykh (Data Science). [The role of statistics in the training of specialists in data research] (Data Science). Novі dzherela ta metody poshyrennia danykh u statystytsі: materіaly XVIII Mіzhnarodnoi naukovo-praktychnoi konferentsіi z nahody Dnia pratsіvnykіv statystyky – New sources and methods of data dissemination in statistics. Materials of the XVIII International scientific-practical conference on the occasion of the Day of Statistics. Kyiv. «Informatsiino-analitychne ahentstvo», 103–106.
Dobuvannia danykh [Data Mining]. Retrieved from : https://uk.wikipedia.org/wiki/Добування_даних.
Lavreniuk, M. S., Novykov, O. M. (2018). Ohliad metodiv mashynnoho navchannia dlia klasyfikatsii velykykh obsiahiv suputnykovykh danykh [Overview of machine learning methods for classifying large amounts of satellite data]. Systemnі doslіdzhennia ta іnformatsіinі tekhnolohіi – Systems research and information technology. Kyiv, 1, 52–71.
Horoshko, Y V. (2012). Informatsiine modeliuvannia u pidhotovtsi uchyteliv matematyky ta informatyky : Navchalno-metodychnyi posibnyk dlia studentiv [Information modeling in the training of future teachers of mathematics and computer science : training manual]. Chernihiv : Vydavets Lozovyi V.M.
Cherednychenko, A. O., Shura, N. O. (2015). Zastosuvannia shtuchnykh neironnykh merezh yak diievoho mekhanizmu pryiniattia efektyvnykh upravlinskykh rishen na pidpryiemstvi [The use of artificial neural networks as an effective mechanism for making effective management decisions in the enterprise]. Hlobalnі ta natsіonalnі problemy ekonomіky – Global and national economic problems. Mykolaiv, Ukraine, 4, 628–630.
Kuznietsova, N.V., Bidiuk, P.I. (2011). Informatsiina tekhnolohiia analizu finansovykh danykh na osnovi intehrovanoho metodu [Information technology of financial data analysis based on an integrated method]. Systemnі doslіdzhennia ta іnformatsіinі tekhnolohіi – Systems research and information technology, 1, 22–33.
Haykin S. Neural networks and learning machines. Upper Saddle River. NJ, USA : Pearson, 2009. Vol. 3. 938 p.
Pirotti F., Sunar F., Piragnolo M. Benchmark of machine learning methods for classification of a Sentinel-2 image. International Archives of the photogrammetry, Remote Sensing & Spatial Information Sciences. 2016. Vol. 41. P. 335–340.
Obzor Knime Analytics Platform – open source systemy dlia analyza dannykh [Review of Knime Analytics Platform – open source systems for data analysis]. Retrieved from : https://habr.com/ru/post/320500/.
Joel Grus (2019). Nauka o dannyih s nulya [Data Science from Scratch]. St. Petersburg. BHV-Peterburg.
Andreas Myuller, Sara Gvido. (2020). Vvedenie v mashinnoe obuchenie s pomoschyu Python. Rukovodstvo dlya spetsialistov po rabote s dannyimi [Introduction to Machine Learning with Python A Guide for Data Scientists]. Moscow. Vilyams.
Mashinnoe zrenie na Python. Obuchaem neyroset raspoznavat tsifryi [Machine vision by Python. We train the neural network to recognize numbers] Retrieved from : https://medium.com/@enduranceprog/machinevision-digits-94eb258c6ff8.
