URBAN TRAFFIC CRASH ANALYSIS USING DEEP LEARNING TECHNIQUES

Liczba wypadków drogowych w Andhra Pradesh niepokojąco rośnie. W 2021 r. stan Andhra Pradesh odnotował 20% wzrost liczby wypadków drogowych. Niefortunna pozycja stanu, który zajmuje ósme miejsce pod względem liczby ofiar śmiertelnych, z 8 946 ofiarami śmiertelnymi w 22 311 wypadkach drogowych, podkreśla pilny charakter problemu. Znaczący wymiar finansowy dla ofiar i ich rodziny podkreśla konieczność podjęcia skutecznych działań w celu ograniczenia liczby wypadków drogowych. W niniejszym badaniu zaproponowano system gromadzenia danych o wypadkach z regionów Patamata, Penamaluru, Mylavaram, Krishnalanka, Ibrahimpatnam i Gandhinagar w Vijayawada (India) w latach 2019–2021. Zbiór danych obejmuje ponad 12 000 rekordów danych o wypadkach. Techniki głębokiego uczenia są stosowane do klasyfikowania wagi wypadków drogowych na śmiertelne, poważne i ciężkie obrażenia. Procedura klasyfikacji wykorzystuje zaawansowane modele sieci neuronowych, w tym wielowarstwowy perceptron, pamięć długoterminową i krótkoterminową, rekurencyjną sieć neuronową i Gated Recurrent Unit. Modele te są trenowane na zebranych danych w celu dokładnego przewidywania wagi wypadków drogowych. Projekt ma wnieść istotny wkład w sugerowanie proaktywnych środków i polityk mających na celu zmniejszenie dotkliwości i częstotliwości wypadków drogowych w Andhra Pradesh.

Słowa kluczowe:

klasyfikacja, gated recurrent unit, pamięć długotrwała i krótkotrwała, perceptron wielowarstwowy, rekurencyjna sieć neuronowa, wypadki drogowe

Bibliografia

Al Bataineh A., Kaur D., Jalali S. M. J.: Multi-layer perceptron training optimization using nature-inspired computing. IEEE Access 10, 2022, 36963–36977. DOI: https://doi.org/10.1109/ACCESS.2022.3164669

Alghamdi T.A., Javaid N.: A survey of preprocessing methods used for analysis of big data originated from smart grids. IEEE Access 10, 2022, 29149–29171. DOI: https://doi.org/10.1109/ACCESS.2022.3157941

Amorim B. d. S.P., et al.: A Machine Learning Approach for Classifying Road Accident Hotspots. ISPRS International Journal of Geo-Information 12(6), 2023, 227. DOI: https://doi.org/10.3390/ijgi12060227

Athiappan K., et al.: Identifying Influencing Factors of Road Accidents in Emerging Road Accident Blackspots. Advances in Civil Engineering, 2022. DOI: https://doi.org/10.1155/2022/9474323

Cai Q.: Cause analysis of traffic accidents on urban roads based on an improved association rule mining algorithm. IEEE Access 8, 2020, 75607–75615. DOI: https://doi.org/10.1109/ACCESS.2020.2988288

Chen M.-M., Chen M.-Ch.: Modeling road accident severity with comparisons of logistic regression, decision tree, and random forest. Information 11(5), 2020, 270. DOI: https://doi.org/10.3390/info11050270

Comi A., Polimeni A., Balsamo Ch.: Road accident analysis with data mining approach: evidence from Rome. Transportation research procedia 62, 2022, 798–805. DOI: https://doi.org/10.1016/j.trpro.2022.02.099

Ferreira-Vanegas C. M., Vélez J. I., García-Llinás G. A.: Analytical methods and determinants of frequency and severity of road accidents: a 20-year systematic literature review. Journal of Advanced Transportation, 2022. DOI: https://doi.org/10.1155/2022/7239464

Gatarić D., et al.: Predicting Road Traffic Accidents - Artificial Neural Network Approach. Algorithms 16(5), 2023, 257. DOI: https://doi.org/10.3390/a16050257

Gorzelanczyk P., Tylicki H.: Methodology for Optimizing Factors Affecting Road Accidents in Poland. Forecasting 5(1), 2023, 336–350. DOI: https://doi.org/10.3390/forecast5010018

Gutierrez-Osorio C., González F. A., Pedraza C. A.: Deep Learning Ensemble Model for the Prediction of Traffic Accidents Using Social Media Data. Computers 11(9), 2022, 126. DOI: https://doi.org/10.3390/computers11090126

Islam M. J., et al.: Application of min-max normalization on subject-invariant EMG pattern recognition. IEEE Transactions on Instrumentation and Measurement 71, 2022, 1–12. DOI: https://doi.org/10.1109/TIM.2022.3220286

Jia B.-B., Zhang M.-L.: Multi-dimensional classification via decomposed label encoding. IEEE Transactions on Knowledge and Data Engineering, 2021.

Kaffash Charandabi N., Gholami A., Abdollahzadeh Bina A.: Road accident risk prediction using generalized regression neural network optimized with self-organizing map. Neural Computing and Applications 34(11), 2022, 8511–8524. DOI: https://doi.org/10.1007/s00521-021-06549-8

Komol, M.M.R., et al.: Deep RNN Based Prediction of Driver’s Intended Movements at Intersection Using Cooperative Awareness Messages. IEEE Transactions on Intelligent Transportation Systems 24(7), 2023, 6902–6921. DOI: https://doi.org/10.1109/TITS.2023.3254905

Le X.-H., et al.: Application of long short-term memory (LSTM) neural network for flood forecasting. Water 11(7), 2019, 1387. DOI: https://doi.org/10.3390/w11071387

Mandal V., et al.: Artificial intelligence-enabled traffic monitoring system. Sustainability 12(21), 2020, 9177. DOI: https://doi.org/10.3390/su12219177

Novikov A., Shevtsova A., Vasilieva V.: Development of an approach to reduce the number of accidents caused by drivers. Transportation research procedia 50, 2020, 491–498. DOI: https://doi.org/10.1016/j.trpro.2020.10.090

Östh J., et al.: Driver kinematic and muscle responses in braking events with standard and reversible pre-tensioned restraints: validation data for human models. SAE Technical Paper, 2013, 2013-22-0001. DOI: https://doi.org/10.4271/2013-22-0001

Rahman M.M., et al.: Towards sustainable road safety in Saudi Arabia: Exploring traffic accident causes associated with driving behavior using a Bayesian belief network. Sustainability 14(10), 2022, 6315. DOI: https://doi.org/10.3390/su14106315

Rezk N. M., et al.: Recurrent neural networks: An embedded computing perspective. IEEE Access 8, 2020, 57967–57996. DOI: https://doi.org/10.1109/ACCESS.2020.2982416

Saravanarajan V.S., et al.: Car crash detection using ensemble deep learning. Multimedia Tools and Applications, 2023, 1–19. DOI: https://doi.org/10.1007/s11042-023-15906-9

Sobhana M., et al.: A Hybrid Machine Learning Approach for Performing Predictive Analytics on Road Accidents. 6th International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS), 2022. DOI: https://doi.org/10.1109/CSITSS57437.2022.10026404

Upadhyay D., et al.: Intrusion detection in SCADA based power grids: Recursive feature elimination model with majority vote ensemble algorithm. IEEE Transactions on Network Science and Engineering 8(3), 2021, 2559–2574. DOI: https://doi.org/10.1109/TNSE.2021.3099371

Yan J., et al.: Relationship between Highway Geometric Characteristics and Accident Risk: A Multilayer Perceptron Model (MLP) Approach. Sustainability 15(3), 2023, 1893. DOI: https://doi.org/10.3390/su15031893

Yin Y., et al.: SE-GRU: Structure Embedded Gated Recurrent Unit Neural Networks for Temporal Link Prediction. IEEE Transactions on Network Science and Engineering 9(4), 2022, 2495–2509. DOI: https://doi.org/10.1109/TNSE.2022.3164659

Zarei M., Hellinga B., Izadpanah P.: CGAN-EB: A non-parametric empirical Bayes method for crash frequency modeling using conditional generative adversarial networks as safety performance functions. International Journal of Transportation Science and Technology 12(3), 2023, 753–764. DOI: https://doi.org/10.1016/j.ijtst.2022.06.006

Zheng H., et al.: A hybrid deep learning model with attention-based conv-LSTM networks for short-term traffic flow prediction. IEEE Transactions on Intelligent Transportation Systems 22(11), 2020, 6910–6920. DOI: https://doi.org/10.1109/TITS.2020.2997352

Road Accidents in Malaysia: Top 10 Causes & Prevention. Kurnia, 21 Sept. 2022 [http://www.kurnia.com/blog/road-accidents-causes].

Sobhana, M., Vemulapalli, N., Siva Sai Venkatesh Mendu, G., Deepika Ginjupalli, N., Dodda, P., & Subramanyam, R. B. V. (2023). ANALIZA KOLIZJI W RUCHU MIEJSKIM Z WYKORZYSTANIEM TECHNIK GŁĘBOKIEGO UCZENIA. Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska, 13(3), 56-63. https://doi.org/10.35784/iapgos.5350

##plugins.themes.bootstrap3.article.sidebar##

Numer Tom 13 Nr 3 (2023)

Archiwum

##plugins.themes.bootstrap3.article.main##

Authors

Abstrakt

Słowa kluczowe:

Bibliografia

##plugins.themes.bootstrap3.article.details##

Licencja