Congested road networks are negatively impacting the sustainability of many cities due to worsening air contamination. In this Study, Neural Networks with Deep Learning Are used Traffic in Smart Cities. I used a data Set Called Traffic, Which Was Collected by Sensors Placement at Four Intersects, and then the time server situations are produced based on the GRU model, which is thoroughly investigated using different settings.
Anotace v angličtině
Congested road networks are negatively impacting the sustainability of many cities due to worsening air contamination. In this Study, Neural Networks with Deep Learning Are used Traffic in Smart Cities. I used a data Set Called Traffic, Which Was Collected by Sensors Placement at Four Intersects, and then the time server situations are produced based on the GRU model, which is thoroughly investigated using different settings.
Klíčová slova
smart transportation, smart city, internet of things, machine learning, neural networks
Klíčová slova v angličtině
smart transportation, smart city, internet of things, machine learning, neural networks
Rozsah průvodní práce
35
Jazyk
AN
Anotace
Congested road networks are negatively impacting the sustainability of many cities due to worsening air contamination. In this Study, Neural Networks with Deep Learning Are used Traffic in Smart Cities. I used a data Set Called Traffic, Which Was Collected by Sensors Placement at Four Intersects, and then the time server situations are produced based on the GRU model, which is thoroughly investigated using different settings.
Anotace v angličtině
Congested road networks are negatively impacting the sustainability of many cities due to worsening air contamination. In this Study, Neural Networks with Deep Learning Are used Traffic in Smart Cities. I used a data Set Called Traffic, Which Was Collected by Sensors Placement at Four Intersects, and then the time server situations are produced based on the GRU model, which is thoroughly investigated using different settings.
Klíčová slova
smart transportation, smart city, internet of things, machine learning, neural networks
Klíčová slova v angličtině
smart transportation, smart city, internet of things, machine learning, neural networks
Zásady pro vypracování
Objective:
Characterize smart traffic management, introduce neural networks for time-series prediction, propose an IoT-based traffic prediction system based on neural networks, pre-process traffic time-series datasets, validate the proposed prediction system using the datasets, and discuss implications for smart city governance.
Outline:
-- The use of IoT in the city and the factors affecting it - an assessment of the current situation. -- Compare the world's major urban IoT transportation sectors and related factors. -- Collection and processing of data. -- Prediction system using neural networks. -- Interpretation of the results.
Zásady pro vypracování
Objective:
Characterize smart traffic management, introduce neural networks for time-series prediction, propose an IoT-based traffic prediction system based on neural networks, pre-process traffic time-series datasets, validate the proposed prediction system using the datasets, and discuss implications for smart city governance.
Outline:
-- The use of IoT in the city and the factors affecting it - an assessment of the current situation. -- Compare the world's major urban IoT transportation sectors and related factors. -- Collection and processing of data. -- Prediction system using neural networks. -- Interpretation of the results.
Seznam doporučené literatury
ALI SHAH, S. A., ILIANKO, K., FERNANDO, X. Deep learning based traffic flow prediction for autonomous vehicular mobile networks. In 2021 IEEE 94th Vehicular Technology Conference (VTC2021-Fall), 2021, p. 1-5.
NEELAKANDAN, S., BERLIN, M. A., TRIPATHI, S., DEVI, V. B., BHARDWAJ, I., ARULKUMAR, N. IoT-based traffic prediction and traffic signal control system for smart city. Soft Computing, 2021, 25, p. 12241–12248.
SAID, O., TOLBA, A. Accurate performance prediction of IoT communication systems for smart cities: An efficient deep learning based solution. Sustainable Cities and Society, 2021, 69, 102830.
LUO, T., NAGARAJAN, S. G. Distributed anomaly detection using autoencoder neural networks in WSN for IoT. In 2018 IEEE International Conference on Communications (ICC), 2018, p. 1-6.
Seznam doporučené literatury
ALI SHAH, S. A., ILIANKO, K., FERNANDO, X. Deep learning based traffic flow prediction for autonomous vehicular mobile networks. In 2021 IEEE 94th Vehicular Technology Conference (VTC2021-Fall), 2021, p. 1-5.
NEELAKANDAN, S., BERLIN, M. A., TRIPATHI, S., DEVI, V. B., BHARDWAJ, I., ARULKUMAR, N. IoT-based traffic prediction and traffic signal control system for smart city. Soft Computing, 2021, 25, p. 12241–12248.
SAID, O., TOLBA, A. Accurate performance prediction of IoT communication systems for smart cities: An efficient deep learning based solution. Sustainable Cities and Society, 2021, 69, 102830.
LUO, T., NAGARAJAN, S. G. Distributed anomaly detection using autoencoder neural networks in WSN for IoT. In 2018 IEEE International Conference on Communications (ICC), 2018, p. 1-6.
Přílohy volně vložené
-
Přílohy vázané v práci
grafy, tabulky
Převzato z knihovny
Ne
Plný text práce
Přílohy
Posudek(y) oponenta
Hodnocení vedoucího
Záznam průběhu obhajoby
The student presented the defense of the thesis with the title: Predicting IoT-based Traffic in Smart Cities Using Neural Networks. The aim of the thesis is to propose and validate an IoT-based traffic forecasting system based on neural networks.
Questions according to the assessment of the supervisor of the thesis:
Characterize the traffic behaviour patterns at the studied intersections, are they representative?
What other input variables from IoT sensors could be used to further refine the neural network model?
The student responded to the committee's questions.