Araştırma Makalesi
BibTex RIS Kaynak Göster

Yapay Öğrenme ile Farklı Akıllı Ulaşım Senaryoları Altında Araçtan Her Şeye Haberleşme Standardı Seçimi

Yıl 2023, Cilt: 6 Sayı: 1, 67 - 74, 15.03.2023
https://doi.org/10.38016/jista.1189314

Öz

Akıllı ulaşım sistemlerine yönelik çalışmaların son yıllarda artmasıyla birlikte araçtan her şeye (V2X) haberleşme konsepti için farklı standartların geliştirilmesi önem kazanmıştır. Bu doğrultuda 5. Nesil (5G) haberleşmesine yön veren 3GPP ve Wi-Fi haberleşmesine yön veren IEEE gibi organizasyonlar farklı V2X standartları geliştirmişlerdir. Farklı senaryolarda bu iki kritik standardın birbirlerine karşı üstünlükleri olabileceğini gösteren çeşitli çalışmalar bulunmaktadır. Önerilen yöntem ile birlikte farklı şartlar altında 3GPP ve IEEE standartlarından hangisinin kullanılmasının daha avantajlı olacağı yapay öğrenme teknikleri ile belirlenmekte ve uygun V2X standardı otomatik olarak seçtirilmektedir. Bu kapsamda araçta ve çevre sistemlerinde her iki standartla ilişkili donanımların bulunduğu varsayılmaktadır. Bu amaca yönelik yeni bir yapay veri seti oluşturulmuş ve K-en yakın komşu, karar ağacı, yapay sinir ağı ile TabNet sınıflandırıcıları kullanılarak çeşitli yapay öğrenme modelleri eğitilmiştir. Ayrıca çapraz doğrulama ile hiperparametre optimizasyonu gerçekleştirilmiştir. TabNet sınıflandırıcısı ile doğruluk değeri ve ağırlıklı F1 skoru 0.88 olarak elde edilmiştir. Tüm bu çalışmalar beraber ele alındığında, V2X haberleşmesine yönelik özgün bir çalışma yapılarak literatüre önemli bir katkı sağlandığı görülmüştür. Geliştirilen yapay öğrenme tabanlı V2X standardı seçtirme yönteminin akıllı ulaşım sistemleri altındaki araçlara entegre edilebileceği düşünülmektedir.

Destekleyen Kurum

Tübitak

Proje Numarası

122E400

Teşekkür

Bu çalışma 122E400 no’lu Türkiye Bilimsel ve Teknolojik Araştırma Kurumu (TÜBİTAK) projesi kapsamında desteklenmiştir.

Kaynakça

  • Abdellah, A. R., Alshahrani, A., Muthanna, A., Koucheryavy, A., 2021. Performance Estimation in V2X Networks Using Deep Learning-Based M-Estimator Loss Functions in the Presence of Outliers. Symmetry, 13(11), 2207.
  • Arık, S. Ö., Pfister, T., 2021. Tabnet: Attentive interpretable tabular learning. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 35, No. 8, pp. 6679-6687).
  • Chen, T., He, T., Benesty, M., Khotilovich, V., Tang, Y., Cho, H., Chen, K., 2015. Xgboost: extreme gradient boosting. R package version 0.4-2, 1(4), 1-4.
  • Chollet, F., 2018. Keras: The python deep learning library. Astrophysics source code library, ascl-1806.
  • Filippi, A., Moerman, K., Martinez, V., Turley, A., Haran, O., Toledano, R., 2017. IEEE802. 11p ahead of LTE-V2V for safety applications. Autotalks NXP, 1, 1-19.
  • Gupta, B., Rawat, A., Jain, A., Arora, A., Dhami, N., 2017. Analysis of various decision tree algorithms for classification in data mining. International Journal of Computer Applications, 163(8), 15-19.
  • Gyawali, S., Qian, Y., 2019. Misbehavior detection using machine learning in vehicular communication networks. In ICC 2019-2019 IEEE International Conference on Communications (ICC) (pp. 1-6). IEEE.
  • Harris, C. R., Millman, K. J., Van Der Walt, S. J., Gommers, R., Virtanen, P., Cournapeau, D., ... & Oliphant, T. E., 2020. Array programming with NumPy. Nature, 585(7825), 357-362.
  • Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., Liu, T. Y., 2017. Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30.
  • Kramer, O., 2013. Dimensionality reduction with unsupervised nearest neighbors (Vol. 51, pp. 13-23). Berlin: Springer.
  • MacHardy, Z., Khan, A., Obana, K., Iwashina, S., 2018. V2X access technologies: Regulation, research, and remaining challenges. IEEE Communications Surveys & Tutorials, 20(3), 1858-1877.
  • McKinney, W., 2010. Data structures for statistical computing in python. In Proceedings of the 9th Python in Science Conference (Vol. 445, No. 1, pp. 51-56).
  • Moreira, D. C., Guerreiro, I. M., Sun, W., Cavalcante, C. C., Sousa, D. A., 2020. QoS predictability in V2X communication with machine learning. In 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring) (pp. 1-5). IEEE.
  • Naik, G., Choudhury, B., Park, J. M., 2019. IEEE 802.11 bd & 5G NR V2X: Evolution of radio access technologies for V2X communications. IEEE access, 7, 70169-70184.
  • Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Duchesnay, E., 2011. Scikit-learn: Machine learning in Python. the Journal of machine Learning research, 12, 2825-2830.
  • Rahmati, O., Avand, M., Yariyan, P., Tiefenbacher, J. P., Azareh, A., Bui, D. T., 2020. Assessment of Gini-, entropy-and ratio-based classification trees for groundwater potential modelling and prediction. Geocarto International, 1-20.
  • Sevgican, S., Turan, M., Gökarslan, K., Yilmaz, H. B., Tugcu, T., 2020. Intelligent network data analytics function in 5G cellular networks using machine learning. Journal of Communications and Networks, 22(3), 269-280.
  • Shrestha, R., Nam, S. Y., Bajracharya, R., Kim, S., 2020. Evolution of V2X communication and integration of blockchain for security enhancements. Electronics, 9(9), 1338.
  • Skiribou, C., Elbahhar, F., 2021. V2X wireless technology identification using time–frequency analysis and random forest classifier. Sensors, 21(13), 4286.
  • Tangirala, S., 2020. Evaluating the impact of GINI index and information gain on classification using decision tree classifier algorithm. International Journal of Advanced Computer Science and Applications, 11(2), 612-619.
  • Ullah, H., Nair, N. G., Moore, A., Nugent, C., Muschamp, P., Cuevas, M., 2019. 5G communication: an overview of vehicle-to-everything, drones, and healthcare use-cases. IEEE Access, 7, 37251-37268.
  • Yazar, A., Dogan-Tusha, S., Arslan, H., 2020. 6G vision: An ultra-flexible perspective. ITU Journal on Future and Evolving Technologies, 1(1), 121-140.
  • Yazar, A., 2021. Requirement Analysis and Clustering Study for Possible Service Types in 6G Communications. In IEEE Sinyal İşleme ve İletişim Uygulamaları Kurultayı (pp. 1-4). IEEE.
  • Zhang, W., Feng, M., Krunz, M., Volos, H., 2020. Latency prediction for delay-sensitive v2x applications in mobile cloud/edge computing systems. In GLOBECOM 2020-2020 IEEE Global Communications Conference (pp. 1-6). IEEE.
  • Zhang, X., Peng, M., Yan, S., Sun, Y., 2019. Deep-reinforcement-learning-based mode selection and resource allocation for cellular V2X communications. IEEE Internet of Things Journal, 7(7), 6380-6391.
  • Zhao, L., Fang, J., Hu, J., Li, Y., Lin, L., Shi, Y., Li, C., 2018. The performance comparison of LTE-V2X and IEEE 802.11p. In 2018 IEEE 87th Vehicular Technology Conference (VTC Spring) (pp. 1-5). IEEE.

Vehicle-to-Everything Communications Standard Selection Under Different Intelligent Transportation Scenarios with Artificial Learning

Yıl 2023, Cilt: 6 Sayı: 1, 67 - 74, 15.03.2023
https://doi.org/10.38016/jista.1189314

Öz

It has become important to develop different standards for vehicle-to-everything (V2X) communications concept with the increase in studies on intelligent transportation systems in recent years. In this direction, organizations such as 3GPP, which leads 5th Generation (5G) communications, and IEEE, which leads Wi-Fi communications, have developed different V2X standards. There are various studies showing that these two critical standards may have advantages over each other in different scenarios. With the proposed method, which of 3GPP and IEEE standards will be more advantageous under different conditions is determined by artificial learning techniques and appropriate V2X standard is selected automatically. In this context, it is assumed that there is related equipment for each of the two standards in the vehicle and its environmental systems. For this purpose, a new artificial dataset was created, and various artificial learning models were trained using K-nearest neighbor, decision tree, artificial neural network and TabNet classifiers. In addition, hyperparameter optimization was performed with cross validation. With the TabNet classifier, the accuracy value and the weighted F1 score were obtained as 0.88. When all these studies are considered together, it has been seen that a significant contribution to the literature has been made by conducting a novel study on V2X communications. It is thought that the developed artificial learning based V2X standard selection method can be integrated into vehicles under intelligent transportation systems.

Proje Numarası

122E400

Kaynakça

  • Abdellah, A. R., Alshahrani, A., Muthanna, A., Koucheryavy, A., 2021. Performance Estimation in V2X Networks Using Deep Learning-Based M-Estimator Loss Functions in the Presence of Outliers. Symmetry, 13(11), 2207.
  • Arık, S. Ö., Pfister, T., 2021. Tabnet: Attentive interpretable tabular learning. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 35, No. 8, pp. 6679-6687).
  • Chen, T., He, T., Benesty, M., Khotilovich, V., Tang, Y., Cho, H., Chen, K., 2015. Xgboost: extreme gradient boosting. R package version 0.4-2, 1(4), 1-4.
  • Chollet, F., 2018. Keras: The python deep learning library. Astrophysics source code library, ascl-1806.
  • Filippi, A., Moerman, K., Martinez, V., Turley, A., Haran, O., Toledano, R., 2017. IEEE802. 11p ahead of LTE-V2V for safety applications. Autotalks NXP, 1, 1-19.
  • Gupta, B., Rawat, A., Jain, A., Arora, A., Dhami, N., 2017. Analysis of various decision tree algorithms for classification in data mining. International Journal of Computer Applications, 163(8), 15-19.
  • Gyawali, S., Qian, Y., 2019. Misbehavior detection using machine learning in vehicular communication networks. In ICC 2019-2019 IEEE International Conference on Communications (ICC) (pp. 1-6). IEEE.
  • Harris, C. R., Millman, K. J., Van Der Walt, S. J., Gommers, R., Virtanen, P., Cournapeau, D., ... & Oliphant, T. E., 2020. Array programming with NumPy. Nature, 585(7825), 357-362.
  • Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., Liu, T. Y., 2017. Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30.
  • Kramer, O., 2013. Dimensionality reduction with unsupervised nearest neighbors (Vol. 51, pp. 13-23). Berlin: Springer.
  • MacHardy, Z., Khan, A., Obana, K., Iwashina, S., 2018. V2X access technologies: Regulation, research, and remaining challenges. IEEE Communications Surveys & Tutorials, 20(3), 1858-1877.
  • McKinney, W., 2010. Data structures for statistical computing in python. In Proceedings of the 9th Python in Science Conference (Vol. 445, No. 1, pp. 51-56).
  • Moreira, D. C., Guerreiro, I. M., Sun, W., Cavalcante, C. C., Sousa, D. A., 2020. QoS predictability in V2X communication with machine learning. In 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring) (pp. 1-5). IEEE.
  • Naik, G., Choudhury, B., Park, J. M., 2019. IEEE 802.11 bd & 5G NR V2X: Evolution of radio access technologies for V2X communications. IEEE access, 7, 70169-70184.
  • Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Duchesnay, E., 2011. Scikit-learn: Machine learning in Python. the Journal of machine Learning research, 12, 2825-2830.
  • Rahmati, O., Avand, M., Yariyan, P., Tiefenbacher, J. P., Azareh, A., Bui, D. T., 2020. Assessment of Gini-, entropy-and ratio-based classification trees for groundwater potential modelling and prediction. Geocarto International, 1-20.
  • Sevgican, S., Turan, M., Gökarslan, K., Yilmaz, H. B., Tugcu, T., 2020. Intelligent network data analytics function in 5G cellular networks using machine learning. Journal of Communications and Networks, 22(3), 269-280.
  • Shrestha, R., Nam, S. Y., Bajracharya, R., Kim, S., 2020. Evolution of V2X communication and integration of blockchain for security enhancements. Electronics, 9(9), 1338.
  • Skiribou, C., Elbahhar, F., 2021. V2X wireless technology identification using time–frequency analysis and random forest classifier. Sensors, 21(13), 4286.
  • Tangirala, S., 2020. Evaluating the impact of GINI index and information gain on classification using decision tree classifier algorithm. International Journal of Advanced Computer Science and Applications, 11(2), 612-619.
  • Ullah, H., Nair, N. G., Moore, A., Nugent, C., Muschamp, P., Cuevas, M., 2019. 5G communication: an overview of vehicle-to-everything, drones, and healthcare use-cases. IEEE Access, 7, 37251-37268.
  • Yazar, A., Dogan-Tusha, S., Arslan, H., 2020. 6G vision: An ultra-flexible perspective. ITU Journal on Future and Evolving Technologies, 1(1), 121-140.
  • Yazar, A., 2021. Requirement Analysis and Clustering Study for Possible Service Types in 6G Communications. In IEEE Sinyal İşleme ve İletişim Uygulamaları Kurultayı (pp. 1-4). IEEE.
  • Zhang, W., Feng, M., Krunz, M., Volos, H., 2020. Latency prediction for delay-sensitive v2x applications in mobile cloud/edge computing systems. In GLOBECOM 2020-2020 IEEE Global Communications Conference (pp. 1-6). IEEE.
  • Zhang, X., Peng, M., Yan, S., Sun, Y., 2019. Deep-reinforcement-learning-based mode selection and resource allocation for cellular V2X communications. IEEE Internet of Things Journal, 7(7), 6380-6391.
  • Zhao, L., Fang, J., Hu, J., Li, Y., Lin, L., Shi, Y., Li, C., 2018. The performance comparison of LTE-V2X and IEEE 802.11p. In 2018 IEEE 87th Vehicular Technology Conference (VTC Spring) (pp. 1-5). IEEE.
Toplam 26 adet kaynakça vardır.

Ayrıntılar

Birincil Dil Türkçe
Konular Yapay Zeka
Bölüm Araştırma Makalesi
Yazarlar

Hakan Alp Eren 0000-0001-6105-158X

Nihat Adar 0000-0002-0555-0701

Ahmet Yazar 0000-0001-9348-9092

Proje Numarası 122E400
Erken Görünüm Tarihi 27 Aralık 2022
Yayımlanma Tarihi 15 Mart 2023
Gönderilme Tarihi 21 Ekim 2022
Yayımlandığı Sayı Yıl 2023 Cilt: 6 Sayı: 1

Kaynak Göster

APA Eren, H. A., Adar, N., & Yazar, A. (2023). Yapay Öğrenme ile Farklı Akıllı Ulaşım Senaryoları Altında Araçtan Her Şeye Haberleşme Standardı Seçimi. Journal of Intelligent Systems: Theory and Applications, 6(1), 67-74. https://doi.org/10.38016/jista.1189314
AMA Eren HA, Adar N, Yazar A. Yapay Öğrenme ile Farklı Akıllı Ulaşım Senaryoları Altında Araçtan Her Şeye Haberleşme Standardı Seçimi. jista. Mart 2023;6(1):67-74. doi:10.38016/jista.1189314
Chicago Eren, Hakan Alp, Nihat Adar, ve Ahmet Yazar. “Yapay Öğrenme Ile Farklı Akıllı Ulaşım Senaryoları Altında Araçtan Her Şeye Haberleşme Standardı Seçimi”. Journal of Intelligent Systems: Theory and Applications 6, sy. 1 (Mart 2023): 67-74. https://doi.org/10.38016/jista.1189314.
EndNote Eren HA, Adar N, Yazar A (01 Mart 2023) Yapay Öğrenme ile Farklı Akıllı Ulaşım Senaryoları Altında Araçtan Her Şeye Haberleşme Standardı Seçimi. Journal of Intelligent Systems: Theory and Applications 6 1 67–74.
IEEE H. A. Eren, N. Adar, ve A. Yazar, “Yapay Öğrenme ile Farklı Akıllı Ulaşım Senaryoları Altında Araçtan Her Şeye Haberleşme Standardı Seçimi”, jista, c. 6, sy. 1, ss. 67–74, 2023, doi: 10.38016/jista.1189314.
ISNAD Eren, Hakan Alp vd. “Yapay Öğrenme Ile Farklı Akıllı Ulaşım Senaryoları Altında Araçtan Her Şeye Haberleşme Standardı Seçimi”. Journal of Intelligent Systems: Theory and Applications 6/1 (Mart 2023), 67-74. https://doi.org/10.38016/jista.1189314.
JAMA Eren HA, Adar N, Yazar A. Yapay Öğrenme ile Farklı Akıllı Ulaşım Senaryoları Altında Araçtan Her Şeye Haberleşme Standardı Seçimi. jista. 2023;6:67–74.
MLA Eren, Hakan Alp vd. “Yapay Öğrenme Ile Farklı Akıllı Ulaşım Senaryoları Altında Araçtan Her Şeye Haberleşme Standardı Seçimi”. Journal of Intelligent Systems: Theory and Applications, c. 6, sy. 1, 2023, ss. 67-74, doi:10.38016/jista.1189314.
Vancouver Eren HA, Adar N, Yazar A. Yapay Öğrenme ile Farklı Akıllı Ulaşım Senaryoları Altında Araçtan Her Şeye Haberleşme Standardı Seçimi. jista. 2023;6(1):67-74.

Zeki Sistemler Teori ve Uygulamaları Dergisi