Vehicular Environment Identification Based on Channel State Information and Deep Learning
This paper presents a novel vehicular environment identification approach based on deep learning. It consists of exploiting the vehicular wireless channel characteristics in the form of Channel State Information (CSI) in the receiver side of a connected vehicle in order to identify the environment t...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , , |
| منشور في: |
2022
|
| الموضوعات: | |
| الوصول للمادة أونلاين: | https://depot.sorbonne.ae/handle/20.500.12458/1331 |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1857415063996989440 |
|---|---|
| author | Hadid, Abdenour |
| author2 | Ribouh, Soheyb Sadli, Rahmad Elhillali, Yassin Rivenq, Atika |
| author2_role | author author author author |
| author_facet | Hadid, Abdenour Ribouh, Soheyb Sadli, Rahmad Elhillali, Yassin Rivenq, Atika |
| author_role | author |
| dc.creator.none.fl_str_mv | Hadid, Abdenour Ribouh, Soheyb Sadli, Rahmad Elhillali, Yassin Rivenq, Atika |
| dc.date.none.fl_str_mv | 2022-11-21T09:35:45Z 2022-11-21T09:35:45Z 2022 |
| dc.format.none.fl_str_mv | application/pdf |
| dc.identifier.none.fl_str_mv | 10.3390/s1010000 https://depot.sorbonne.ae/handle/20.500.12458/1331 10.3390/s22229018 |
| dc.language.none.fl_str_mv | en |
| dc.relation.none.fl_str_mv | Sensors |
| dc.subject.none.fl_str_mv | Vehicle-To-Everything (V2X) communications. channel state information deep learning vehicular network autonomous vehicle intelligent transportation systems |
| dc.title.none.fl_str_mv | Vehicular Environment Identification Based on Channel State Information and Deep Learning |
| dc.type.none.fl_str_mv | Controlled Vocabulary for Resource Type Genres::text::periodical::journal::contribution to journal::journal article |
| description | This paper presents a novel vehicular environment identification approach based on deep learning. It consists of exploiting the vehicular wireless channel characteristics in the form of Channel State Information (CSI) in the receiver side of a connected vehicle in order to identify the environment type in which the vehicle is driving, without any need to implement specific sensors such as cameras or radars. We consider environment identification as a classification problem, and propose a new convolutional neural network (CNN) architecture to deal with it. The estimated CSI is used as the input feature to train the model. To perform the identification process, the model is targeted for implementation in an autonomous vehicle connected to a vehicular network (VN). The proposed model is extensively evaluated, showing that it can reliably recognize the surrounding environment with high accuracy (96.48%). Our model is compared to related approaches and state-ofthe-art classification architectures. The experiments show that our proposed model yields favorable performance compared to all other considered methods. |
| id | sorbonner_60aff3be8d7040b29aab7456f163b79f |
| identifier_str_mv | 10.3390/s1010000 10.3390/s22229018 |
| language_invalid_str_mv | en |
| network_acronym_str | sorbonner |
| network_name_str | Sorbonne University Abu Dhabi repository |
| oai_identifier_str | oai:depot.sorbonne.ae:20.500.12458/1331 |
| publishDate | 2022 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| spelling | Vehicular Environment Identification Based on Channel State Information and Deep LearningHadid, AbdenourRibouh, SoheybSadli, RahmadElhillali, YassinRivenq, AtikaVehicle-To-Everything (V2X) communications.channel state informationdeep learningvehicular networkautonomous vehicleintelligent transportation systemsThis paper presents a novel vehicular environment identification approach based on deep learning. It consists of exploiting the vehicular wireless channel characteristics in the form of Channel State Information (CSI) in the receiver side of a connected vehicle in order to identify the environment type in which the vehicle is driving, without any need to implement specific sensors such as cameras or radars. We consider environment identification as a classification problem, and propose a new convolutional neural network (CNN) architecture to deal with it. The estimated CSI is used as the input feature to train the model. To perform the identification process, the model is targeted for implementation in an autonomous vehicle connected to a vehicular network (VN). The proposed model is extensively evaluated, showing that it can reliably recognize the surrounding environment with high accuracy (96.48%). Our model is compared to related approaches and state-ofthe-art classification architectures. The experiments show that our proposed model yields favorable performance compared to all other considered methods.2022-11-21T09:35:45Z2022-11-21T09:35:45Z2022Controlled Vocabulary for Resource Type Genres::text::periodical::journal::contribution to journal::journal articleapplication/pdf10.3390/s1010000https://depot.sorbonne.ae/handle/20.500.12458/133110.3390/s22229018enSensorsoai:depot.sorbonne.ae:20.500.12458/13312023-01-27T05:50:09Z |
| spellingShingle | Vehicular Environment Identification Based on Channel State Information and Deep Learning Hadid, Abdenour Vehicle-To-Everything (V2X) communications. channel state information deep learning vehicular network autonomous vehicle intelligent transportation systems |
| title | Vehicular Environment Identification Based on Channel State Information and Deep Learning |
| title_full | Vehicular Environment Identification Based on Channel State Information and Deep Learning |
| title_fullStr | Vehicular Environment Identification Based on Channel State Information and Deep Learning |
| title_full_unstemmed | Vehicular Environment Identification Based on Channel State Information and Deep Learning |
| title_short | Vehicular Environment Identification Based on Channel State Information and Deep Learning |
| title_sort | Vehicular Environment Identification Based on Channel State Information and Deep Learning |
| topic | Vehicle-To-Everything (V2X) communications. channel state information deep learning vehicular network autonomous vehicle intelligent transportation systems |
| url | https://depot.sorbonne.ae/handle/20.500.12458/1331 |