Vehicular Environment Identification Based on Channel State Information and Deep Learning
Abstract
:1. Introduction
2. Related Work
3. System Model
4. Vehicular Environment Identification Methodology
4.1. The Proposed Model
4.2. Data-Set Generation
5. Evaluation and Results
5.1. LTS Approach Performance Evaluation
5.2. CSI Approach Performance Evaluation
5.3. Comparison between Our Model and State-of-the-Art Architectures
5.4. Minimum Performance Overhead and Reliability
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Kockelman, K.; Boyles, S.; Stone, P.; Fagnant, D.; Patel, R.; Levin, M.W.; Sharon, G.; Simoni, M.; Albert, M.; Fritz, H.; et al. An Assessment of Autonomous Vehicles: Traffic Impacts and Infrastructure Needs; Technical Report; University of Texas at Austin, Center for Transportation Research: Austin, TX, USA, 2017. [Google Scholar]
- Uhlemann, E. Time for autonomous vehicles to connect [connected vehicles]. IEEE Veh. Technol. Mag. 2018, 13, 10–13. [Google Scholar] [CrossRef]
- Yue, L.; Abdel-Aty, M.; Wu, Y.; Wang, L. Assessment of the safety benefits of vehicles’ advanced driver assistance, connectivity and low level automation systems. Accid. Anal. Prev. 2018, 117, 55–64. [Google Scholar] [CrossRef] [PubMed]
- Nahar, A.; Das, D. MetaLearn: Optimizing routing heuristics with a hybrid meta-learning approach in vehicular ad-hoc networks. Ad Hoc Netw. 2023, 138, 102996. [Google Scholar] [CrossRef]
- Abuelsamid, S. Toyota Has Big Plans to Get Cars Talking to Each Other and Infrastructure in the US. Forbes. 2018. Available online: https://www.forbes.com/sites/samabuelsamid/2018/04/16/toyota-launches-aggressive-v2x-communications-roll-out-from-2021/?sh=2eee16b4146c (accessed on 20 October 2022).
- Chen, C.; Seff, A.; Kornhauser, A.; Xiao, J. Deepdriving: Learning affordance for direct perception in autonomous driving. In Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, 7–13 December 2015; pp. 2722–2730. [Google Scholar]
- Okamoto, K.; Itti, L.; Tsiotras, P. Vision-based autonomous path following using a human driver control model with reliable input-feature value estimation. IEEE Trans. Intell. Veh. 2019, 4, 497–506. [Google Scholar] [CrossRef]
- Zhang, Y.; Sun, P.; Yin, Y.; Lin, L.; Wang, X. Human-like autonomous vehicle speed control by deep reinforcement learning with double Q-learning. In Proceedings of the 2018 IEEE Intelligent Vehicles Symposium (IV), Changshu, China, 26–30 June 2018; pp. 1251–1256. [Google Scholar]
- Seo, Y.W.; Lee, J.; Zhang, W.; Wettergreen, D. Recognition of highway workzones for reliable autonomous driving. IEEE Trans. Intell. Transp. Syst. 2014, 16, 708–718. [Google Scholar] [CrossRef]
- Sauer, A.; Savinov, N.; Geiger, A. Conditional affordance learning for driving in urban environments. arXiv 2018, arXiv:1806.06498. [Google Scholar]
- Kim, B.; Kim, D.; Park, S.; Jung, Y.; Yi, K. Automated complex urban driving based on enhanced environment representation with GPS/map, radar, lidar and vision. IFAC-PapersOnLine 2016, 49, 190–195. [Google Scholar] [CrossRef]
- Varga, R.; Costea, A.; Florea, H.; Giosan, I.; Nedevschi, S. Super-sensor for 360-degree environment perception: Point cloud segmentation using image features. In Proceedings of the 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), Yokohama, Japan, 16–19 October 2017; pp. 1–8. [Google Scholar]
- Duan, X.; Jiang, H.; Tian, D.; Zou, T.; Zhou, J.; Cao, Y. V2I based environment perception for autonomous vehicles at intersections. China Commun. 2021, 18, 1–12. [Google Scholar] [CrossRef]
- Lee, D.H.; Chen, K.L.; Liou, K.H.; Liu, C.L.; Liu, J.L. Deep learning and control algorithms of direct perception for autonomous driving. Appl. Intell. 2021, 51, 237–247. [Google Scholar] [CrossRef]
- Florea, H.; Petrovai, A.; Giosan, I.; Oniga, F.; Varga, R.; Nedevschi, S. Enhanced perception for autonomous driving using semantic and geometric data fusion. Sensors 2022, 22, 5061. [Google Scholar] [CrossRef]
- Kabir, M.F.; Roy, S. Real-time vehicular accident prevention system using deep learning architecture. Expert Syst. Appl. 2022, 206, 117837. [Google Scholar] [CrossRef]
- Zhu, H.; Yuen, K.V.; Mihaylova, L.; Leung, H. Overview of environment perception for intelligent vehicles. IEEE Trans. Intell. Transp. Syst. 2017, 18, 2584–2601. [Google Scholar] [CrossRef] [Green Version]
- Ribouh, S.; Phan, K.; Malawade, A.V.; El Hillali, Y.; Rivenq, A.; Al Faruque, M.A. Channel State Information Based Cryptographic KeyGeneration for Intelligent Transportation Systems. IEEE Trans. Intell. Transp. Syst. 2020; to appear. [Google Scholar]
- Alexander, P.; Haley, D.; Grant, A. Cooperative intelligent transport systems: 5.9-GHz field trials. Proc. IEEE 2011, 99, 1213–1235. [Google Scholar] [CrossRef]
- Wan, J.; Lopez, A.B.; Al Faruque, M.A. Exploiting wireless channel randomness to generate keys for automotive cyber-physical system security. In Proceedings of the 2016 ACM/IEEE 7th International Conference on Cyber-Physical Systems (ICCPS), Vienna, Austria, 11–14 April 2016; pp. 1–10. [Google Scholar]
- ETSI, T. 103 257-1 V1. 1.1 (2019-05) Intelligent Transport Systems (ITS). Access Layer. Available online: https://www.etsi.org/deliver/etsi_tr/103200_103299/10325701/01.01.01_60/tr_10325701v010101p.pdf (accessed on 20 October 2022).
- Bernado, L.; Zemen, T.; Tufvesson, F.; Molisch, A.F.; Mecklenbräuker, C.F. Delay and Doppler spreads of nonstationary vehicular channels for safety-relevant scenarios. IEEE Trans. Veh. Technol. 2013, 63, 82–93. [Google Scholar] [CrossRef] [Green Version]
- Tan, I.; Tang, W.; Laberteaux, K.; Bahai, A. Measurement and analysis of wireless channel impairments in DSRC vehicular communications. In Proceedings of the 2008 IEEE International Conference on Communications, Beijing, China, 19–23 May 2008; pp. 4882–4888. [Google Scholar]
- Zemen, T.; Bernadó, L.; Czink, N.; Molisch, A.F. Iterative time-variant channel estimation for 802.11 p using generalized discrete prolate spheroidal sequences. IEEE Trans. Veh. Technol. 2012, 61, 1222–1233. [Google Scholar] [CrossRef]
- Zhuang, Y.; Hua, J.; Wen, H.; Meng, L. An iterative Doppler shift estimation in vehicular communication systems. Procedia Eng. 2012, 29, 4129–4134. [Google Scholar] [CrossRef] [Green Version]
- Ghanavati, A.Z.; Pareek, U.; Muhaidat, S.; Lee, D. On the performance of imperfect channel estimation for vehicular ad-hoc networks. In Proceedings of the 2010 IEEE 72nd Vehicular Technology Conference-Fall, Ottawa, ON, Canada, 6–9 September 2010; pp. 1–5. [Google Scholar]
- Sutar, M.B.; Patil, V.S. LS and MMSE estimation with different fading channels for OFDM system. In Proceedings of the 2017 International conference of Electronics, Communication and Aerospace Technology (ICECA), Coimbatore, India, 20–22 April 2017; Volume 1, pp. 740–745. [Google Scholar]
- Kukačka, J.; Golkov, V.; Cremers, D. Regularization for deep learning: A taxonomy. arXiv 2017, arXiv:1710.10686. [Google Scholar]
- Abadi, M.; Barham, P.; Chen, J.; Chen, Z.; Davis, A.; Dean, J.; Devin, M.; Ghemawat, S.; Irving, G.; Isard, M.; et al. Tensorflow: A system for large-scale machine learning. In Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), Savannah, GA, USA, 2–4 November 2016; pp. 265–283. [Google Scholar]
- Kingma, D.P.; Ba, J. Adam: A method for stochastic optimization. arXiv 2014, arXiv:1412.6980. [Google Scholar]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Identity mappings in deep residual networks. 2016. arXiv 2016, arXiv:1603.05027. [Google Scholar]
- Chollet, F. Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 1251–1258. [Google Scholar]
- Szegedy, C.; Vanhoucke, V.; Ioffe, S.; Shlens, J.; Wojna, Z. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 2818–2826. [Google Scholar]
- Szegedy, C.; Ioffe, S.; Vanhoucke, V.; Alemi, A. Inception-v4, inception-resnet and the impact of residual connections on learning. arXiv 2016, arXiv:1602.07261. [Google Scholar] [CrossRef]
- Huang, G.; Liu, Z.; Van Der Maaten, L.; Weinberger, K.Q. Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 4700–4708. [Google Scholar]
- Sandler, M.; Howard, A.; Zhu, M.; Zhmoginov, A.; Chen, L.C. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 4510–4520. [Google Scholar]
- Elwekeil, M.; Wang, T.; Zhang, S. Deep Learning for Environment Identification in Vehicular Networks. IEEE Wirel. Commun. Lett. 2019, 9, 576–580. [Google Scholar] [CrossRef]
- Dixit, V.V.; Chand, S.; Nair, D.J. Autonomous vehicles: Disengagements, accidents and reaction times. PLoS ONE 2016, 11, e0168054. [Google Scholar] [CrossRef] [PubMed]
Taps | Power [dB] | Delay [ns] | Doppler [Hz] | |
---|---|---|---|---|
U-LOS | Tap 1 | 0 | 0 | 0 |
Tap 2 | −8 | 117 | 236 | |
Tap 3 | −10 | 183 | −157 | |
Tap 4 | −15 | 333 | 492 | |
U-NLOS | Tap 1 | 0 | 0 | 0 |
Tap 2 | −3 | 267 | 295 | |
Tap 3 | −4 | 400 | −98 | |
Tap 4 | −10 | 533 | 591 | |
R-LOS | Tap 1 | 0 | 0 | 0 |
Tap 2 | −14 | 83 | 492 | |
Tap 3 | −17 | 183 | −295 | |
H-LOS | Tap 1 | 0 | 0 | 0 |
Tap 2 | −10 | 100 | 689 | |
Tap 3 | −15 | 167 | −492 | |
Tap 4 | −20 | 500 | 886 | |
H-NLOS | Tap 1 | 0 | 0 | 0 |
Tap 2 | −2 | 200 | 689 | |
Tap 3 | −5 | 433 | −492 | |
Tap 4 | −7 | 700 | 886 |
Vehicular Environment | Label | Speed Limits |
---|---|---|
Highway NLOS | 0 | |
Highway LOS | 1 | |
Rural LOS | 2 | |
Urban LOS | 3 | |
Urban NLOS | 4 |
Configuration | Accuracy |
---|---|
Magnitude | 92.22% |
Angle | 91.78% |
2-Channel | 93.42% |
Approach | Accuracy (%) | Prediction Time (s) |
---|---|---|
Proposed CNN | 93.42 | 51.33 |
ANN | 86.16 | 23.11 |
RF | 68.34 | 25.71 |
K-NN | 63.18 | 7180 |
GBN | 20.62 | 4.11 |
SVM | 31.38 | 10499 |
Configuration | Accuracy |
---|---|
Magnitude | 90.63% |
Angle | 91.50% |
2-Channel | 96.48% |
Approach | Accuracy (%) | Prediction Time () |
---|---|---|
Proposed CNN | 96.48 | 39.56 |
ANN | 85.64 | 21.11 |
RF | 67.77 | 24.04 |
K-NN | 59.26 | 8999 |
GNB | 27.06 | 4.38 |
SVM | 32.33 | 15756 |
Architecture | H-NLOS Acc (%) | H-LOS Acc (%) | R-LOS Acc (%) | U-LOS Acc (%) | U-NLOS Acc (%) | Acc (%) | Prediction Time () |
---|---|---|---|---|---|---|---|
Our Model | 99.9 | 95.2 | 92.7 | 97.4 | 97.2 | 96.48 | 39.56 |
ResNet50 | 98.1 | 88.2 | 77.8 | 90.1 | 93.5 | 89.54 | 672 |
Xception | 97.8 | 91.7 | 81.4 | 91.2 | 94.5 | 91.32 | 794 |
InceptionV3 | 99.1 | 79.8 | 86.9 | 96.1 | 93.9 | 91.08 | 683 |
Inception ResNetV2 | 98.5 | 89.1 | 80 | 86.5 | 95.8 | 89.98 | 1621 |
DenseNet201 | 98.5 | 92.7 | 85.7 | 91.2 | 96.6 | 92.94 | 1349 |
MobileNetV2 | 96.8 | 77.8 | 96 | 58.2 | 65.5 | 78.86 | 318 |
DCNN [37] | 98.9 | 96.9 | 94.3 | 95.8 | 99.2 | 97.02 | 125 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Ribouh, S.; Sadli, R.; Elhillali, Y.; Rivenq, A.; Hadid, A. Vehicular Environment Identification Based on Channel State Information and Deep Learning. Sensors 2022, 22, 9018. https://doi.org/10.3390/s22229018
Ribouh S, Sadli R, Elhillali Y, Rivenq A, Hadid A. Vehicular Environment Identification Based on Channel State Information and Deep Learning. Sensors. 2022; 22(22):9018. https://doi.org/10.3390/s22229018
Chicago/Turabian StyleRibouh, Soheyb, Rahmad Sadli, Yassin Elhillali, Atika Rivenq, and Abdenour Hadid. 2022. "Vehicular Environment Identification Based on Channel State Information and Deep Learning" Sensors 22, no. 22: 9018. https://doi.org/10.3390/s22229018