Internet rzeczy i modele uczenia głębokiego w zrównoważonym rozwoju inteligentnych miast.

• Autorzy: Honorata Balicka

Warianty tytułu

Internet of Things and Deep Learning Models for Sus -Tainable Development of Smart Cities.

• Języki publikacji: PL

Abstrakty

Celem artykułu jest scharakteryzowanie kierunków zrównoważonego rozwoju inteligentnych miast w oparciu o wykorzystanie Internetu Rzeczy oraz modeli uczenia głębokiego. Zdaniem autorki taka strategia stwarza ogromną szansę na uniknięcie kryzysu w dużych miastach, wynikającego z negatywnych skutków pandemii, zagęszczania miast, zmian klimatycznych oraz zanieczyszczenia środowiska. W literaturze przedmiotu istnieje w tym zakresie luka, ponieważ brakuje jasnych koncepcji, jak wykorzystać wybrane technologie do zrównoważonego rozwoju inteligentnych miast.Z powyższych względów w artykule rozważa się strategie zastosowania Internetu Rzeczy oraz uczenia głębokiego,opartego na sieciach neuronowych do zwiększenia efektywności funkcjonowania miasta oraz poprawy jakości życia mieszkańców, dbając jednocześnie o środowisko naturalne.Scharakteryzowano zintegrowany system zarządzania miastem z zastosowaniem inteligentnych i ekologicznych technologii. Rolę i znaczenie Internetu Rzeczy opisano w kontekście zarządzania krytycznymi zasobami miasta. Natomiast zagadnienia związane z modelami uczenia głębokiego zaprezentowano pod kątem możliwości doskonalenia predykcji i przewidywania wyników.Przedstawiono rozważania dotyczące szczególnego przypadku architektury głębokiego uczenia opartej na sztucznych sieciach neuronowych (ANN). Rekurencyjne ANN klasy LSTM zweryfikowano pod kątem inwestycji finansowych na giełdzie. Na zakończenie przedstawiono konkluzje i planowane przyszłe prace.Wnioski wyciągnięte na podstawie przeprowadzonych badań jednoznacznie potwierdzają postawioną w pracy tezę, że Internet Rzeczy oraz modele uczenia głębokiego odgrywają kluczową rolę w zrównoważonym rozwoju inteligentnych miast.(abstrakt oryginalny)

EN

The aim of the article is to characterize the directions of sustainable development of smart cities based on the use of theInternet of Things anddeep learning models. According to the author, such a strategy creates a great opportunity to avoid the crisis in large cities re-sulting from the negative effects of the pandemic, urban density, climate change and envi-ronmental pollution. There is a gap in the literature on the subject, because there are no clear concepts on how to use selected technologies for the sustainable development of smart cities. For the above reasons, the article considers the strategies of using the Inter-net of Things and deep learning based on neural networks to increase the efficiency of the city's functioning and improve the quality of life of residents, while caring for the natural environment. An integrated city management system with the use of intelligent and eco-logical technologies has been characterized. The role and importance of the Internet of Things has been described in the context of managing critical city resources. On the other hand, issues related to deep learning models were presented in terms of the possibilityof improving prediction and predicting results. Considerations on a special case of a deep learning architecture based on artificial neural networks (ANN) are presented. Recursive ANNs of the LSTM class were verified in terms of financial investments on the stock ex-change. Finally, conclusions and planned future work were presented. The conclusions drawn on the basis of the conducted research clearly indicate that the IoTand deep learning models play an important role in the sustainable development of smart cities.(original abstract)

Słowa kluczowe

PL

Funkcje miasta; Inteligentne miasto; Internet rzeczy; Długa pamięć krótkotrwała (LSTM)

EN

Town function; Smart city; Internet of Things (IoT); Long-short term memory (LSTM)

• Czasopismo: Współczesna Gospodarka
• Rocznik: 2023
• Tom: 16
• Numer: nr 1
• Strony: 27--43

Twórcy

autor

Honorata Balicka

• Sopocka Akademia Nauk Stosowanych

Bibliografia

• 1. Aguirre K., BadranE., Muggah R. (2019). Future crime:Assessing twenty first century crime prediction. Igarapé Institute. Strategic Note 33, July. Pozyskano z: https://igarape.org.br/wp-content/uploads/2019/07/2019-07-12-NE_33_Future_Crime.pdf, (27.03.2023).
• 2. Aldrich E., Fernández-Villaverde M., Gallant J.R.,Rubio Ramírez A., Juan F.(2011).Tapping the supercomputer under your desk: Solving dynamic equilibrium models with graphics processors."Journal of Economic Dynamics and Control",Vol. 35(3), p.387.
• 3. Amoruso F.M., DietrichU., SchuetzeT.(2018).Development of a Building Information Mo-deling-Parametric Workflow Based Renovation Strategy for an Exemplary Apartment Bu-ildinginSeoul.Korea."Sustainability",10(12),4494; https://doi.org/10.3390/su10124494,pp. 1-30.
• 4. Aslam S., Rasool A., Jiang Q., Qu Q.(2021).LSTM based Model for Real-time Stock Market Prediction on Unexpected Incidents. RCAR, p. 1149.
• 5. Awad M., Khanna R.(2015).Support Vector Regression: Efficient learning machines. Apress, Berkeley, CA, p. 223.
• 6. Baesens B., Setiono R., Mues C., Vanthien J.(2003).Using neural network rule extraction and decision tables forcredit-riskevaluation."Management Science", Vol. 49, No. 3, March, p. 317.
• 7. Balicka H., Balicki J.,Korłub W., Paluszak J., Zadroga M.(2014).Superkomputery do wspomagania procesów gospodarczych ze szczególnym uwzględnieniem sektora bankowego. "Współczesna Gospodarka", Issue 5, Vol.4, ss. 1-16,https://doi.org/10.23830/16/II/2019/5788,pp. 57-88.
• 8. Balicka H.(2019).Cloud computing and selected models of deep learning in banking. " Przestrzeń, Ekonomia, Społeczeństwo", Issue No. 16 II.
• 9. Balicka H.(2023).Digitaltechnologies in the accounting information system supporting decision-making processes."Scientific Papers of Silesian University of Technology-Organization and Management Series", Issue No. 169.
• 10. Balicki J., Balicka H., Dryja P. (2021).Big Data from Sensor Network via Internet of Things to Edge Deep Learning for SmartCity. [in:]K. Saeed, J. Dvorský(eds.),Computer In-formation Systems andIndustrial Management. CISIM: "Lecture Notes in Computer Science", Vol. 12883. Cham:Springer, https://doi.org/10.1007/978-3-030-84340-3_29, pp. 357-368.
• 11. Balicki J., Korłub W., Paluszak J.(2015).Big data processing by volunteer computing supported by intelligent agents.Proceedings of 6th International Conference, PReMI, Warsaw.Poland, June 30 -July 3."Lecture Notes in Computer Science", Vol. 9124, p.342.
• 12. Balicki J., Korłub W.,Tyszka M.(2016).Harmony search to self-configuration of fault tole-rant grids for big data."Advances in Intelligent Systems and Computing", Vol. 386, p.411.
• 13. Balicki J., Szymański J., Kępa M., Draszawka K., Korłub W.(2015).Improving effectiveness of svm classifier for large scale data.Proc. on 14th Int. Conf., ICAISC 2015, Zakopane, Poland, June 14-18.Part I"Lecture Notes in Computer Science", Vol. 9119, p. 677.
• 14. Balicki J., PrzybyłekP., Zadroga M., Zakidalski M.(2013).Artificial neural networks and the support vector method in banking information systems."Contemporary Economy", Vol4.
• 15. Balicki J.(2009).Multi-criterion decision making by artificial intelligence techniques.Proceedings on the 8th Int. Con. on Artificial Intelligence.Knowledge Engineering and Data Bases, February, Cambridge, p. 322.
• 16. Benbouzid B.(2019).To predict and to manage. Predictive policing in the United States. "Big Data & Society", January-June 2019, p. 7.
• 17. Bosse T., Siddiqui G.F., Treur J.(2010).Supporting Financial Decision Makingby an Intelligent Agent Estimating Greed and Risk.Proc. the IEEE/WIC/ACM Int. Conf. on Web In-telligence and Intelligent Agent Technology, Vol. 3, Aug. 31-Sept. 3, p. 367.
• 18. Brown C.(2011).Technical Analysis for the Trading Professional, Second Edition: Strategies and Techniques for Today's Turbulent Global Financial Markets. New York:The McGrawHill Companies, p. 226.
• 19. Ceny energii elektrycznej dla gospodarstw domowych na świecie. Pozyskano z:https://pl.globalpetrolprices.com/electricity_prices/,(27.03.2023).
• 20. Ceny energii elektrycznej dla gospodarstw domowych w Polsce. Pozyskano z:http://cena-pradu.pl/mapa.html, (27.03.2023).
• 21. Chen S.-H., Kuoand T.-W. HoiK.-M.(2006).Genetic Programming and Financial Trading: How Muchabout "What we Know".[in:]4th NTU International Conference on Economics.Finance and Accounting, April, p. 2.
• 22. Davis E. P., Karim D.(2008).Comparing early warning systems for banking crises."Journal of Financial Stability", Vol. 4, No. 2, p. 89.
• 23. Eurostat.(2021).Pozyskano z: http://ec.europa.eu/eurostat/, 12.03.2023.
• 24. Gately E.(1999). Neural networks. Financial forecasting and design of transaction system.Warsaw:WIG-Press,s. 232.
• 25. German Credit dataset. Pozyskano z:http://archive.ics.uci.edu/ml/datasets/Statlog+%28German+Credit+Data%29,2.09.2022.
• 26. GieruszJ., KoleśnikK.(2021).Plan kont z komentarzem. Gdańsk:ODDK.
• 27. Hanschel E., Monnin P.(2005).Measuring and forecasting stress in the banking sector: evidence from Switzerland."Investigating the Relationship between the Financial and Real Economy.BIS Papers", No. 22, pp. 435.
• 28. Henley W.E., Hand D.J.(1996).A k-nearest-neighbourclassifier for assessing consumer credit risk."The Statistician", Vol. 45, Issue 1,p. 77.
• 29. Jonek-KowalskaI., KurdelskiT.(2022).The usage of renewable energy sources by countries in the Visegrád Group. Diagnosis and environmental effects."Scientific Papers of Sile-sian University of Technology -Organization and Management Series",Issue No. 161, http://dx.doi.org/10.29119/1641-3466.2022.161.3,pp.37-51.
• 30. Kumar K., Haider T.U.(2021).Enhanced Prediction of Intraday Stock Market Using Meta-heuristic Optimization on RNN-LSTM Network."New Gener. Comput", Vol. 39(1), pp. 231-272.
• 31. Mylonakis J., Diacogiannis G.(2010).Evaluating the likelihood of using lineardiscriminant analysis as a commercial bank card owners credit scoring model."International Business Research", Vol. 3, No. 2, p. 12.
• 32. Nazari M., Alidadi M.(2013).Measuring credit risk of bank customers using artificial neural network."Journal of Management Research", Vol. 5, No. 2, p. 322.
• 33. Oet M., Eiben R., Bianco T., Gramlich D., Ong S., Wang J.(2011).SAFE: an early warning system for systemic banking risk. Proceedings of the 24th Australasian Finance and Banking Conference, SSRN.
• 34. Potvin J.-Y., Soriano P., Vall M.(2004).
• Generating trading rules on the stock markets with genetic programming."Computers & Operations Research", Vol. 31, p. 1033.
• 35. Schwaerzel R.(2006).Financial Time Series Prediction and Evaluation by Genetic Programming with Trigonometric Functions and High-Order Statistics.Ph.D. Dissertation.The University of Texas at San Antonio. Advisor(s) Tom Bylander.
• 36. Shouwei L., Mingliang W., Jianmin H.(2013).Prediction of Banking Systemic Risk Based on Support Vector Machine."Mathematical Problems in Engineering", Vol. 12, April, p.5.
• 37. Staniec I.(2003).Application of artificial neural networks and selected statistical methods to support credit decisions.Applications of statistical methods in scientific research II.Cracow:StatSoft Poland, p. 20.
• 38. Svangard N., Nordin P., Lloyd S., Wihlborg C.(2002). Evolving short-term trading strategies using genetic programming.Proc. of the Congress on Evolutionary Computation, Vol. 2, pp. 2006-2010.
• 39. Yobas M.B., Crook J.N., Ross P.(2000).Credit scoring using neural and evolutionary techniques."IMA Journal of Mathematics Applied in Business and Industry", Vol. 11, p. 112.
• 40. Zan H. et al.(2004).Credit rating analysis with support vector machines and neural networks: a marketcomparative study."DecisionSupport Systems", Vol.37, p. 543.