DNN Layer Specialization Through Sequential Training for Applications With Smart Road-User Interactions
The deployment of a large number of sensors in vehicles makes it possible to analyze road-user interactions which is crucial for most applications in vehicular scenarios. In this context, Deep Neural Networks (DNNs) are a powerful tool for recognizing complex data patterns stemming from interactions...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11059952/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839638808951259136 |
|---|---|
| author | Joannes Sam Mertens Salvatore Cafiso Laura Galluccio Giacomo Morabito Giuseppina Pappalardo |
| author_facet | Joannes Sam Mertens Salvatore Cafiso Laura Galluccio Giacomo Morabito Giuseppina Pappalardo |
| author_sort | Joannes Sam Mertens |
| collection | DOAJ |
| description | The deployment of a large number of sensors in vehicles makes it possible to analyze road-user interactions which is crucial for most applications in vehicular scenarios. In this context, Deep Neural Networks (DNNs) are a powerful tool for recognizing complex data patterns stemming from interactions between users and smart roads. However, the user behaviour changes depending on the road environment and the user features. Hence, it is not possible to have a unique DNN model that is effective for all the users, in all kinds of road environments. On the contrary, a specific model might be needed for each different user interacting with each type of environment. Unfortunately, this would imply the need to collect and process a very large amount of data for the training of each DNN model, which is not practical. Therefore, this work proposes a novel training technique called Sequential Training that partitions the Neural Network (NN) layers of the DNN model into two sets of layers that are trained so that one is specific of the user while the other is trained cooperatively to be specific of the road environment. The proposed training technique is realized by means of Vehicle-to-Infrastructure (V2I) communication in which the vehicle user can download the layers of the DNN model specific of the road environment where the vehicle is currently located. Such layers are then concatenated with the user-specific layers. |
| format | Article |
| id | doaj-art-3ae7f518f32f48449a6f06b059aa75a8 |
| institution | Matheson Library |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-3ae7f518f32f48449a6f06b059aa75a82025-07-04T23:00:41ZengIEEEIEEE Access2169-35362025-01-011311249411250710.1109/ACCESS.2025.358446111059952DNN Layer Specialization Through Sequential Training for Applications With Smart Road-User InteractionsJoannes Sam Mertens0https://orcid.org/0000-0001-8536-007XSalvatore Cafiso1https://orcid.org/0000-0002-7247-0365Laura Galluccio2https://orcid.org/0000-0001-6644-0787Giacomo Morabito3https://orcid.org/0000-0002-8714-4001Giuseppina Pappalardo4https://orcid.org/0000-0002-9793-1885Department of Electrical, Electronics, and Informatics Engineering (DIEEI), CNIT, University of Catania, Catania, ItalyDepartment of Civil Engineering and Architecture (DICAR), University of Catania, Catania, ItalyDepartment of Electrical, Electronics, and Informatics Engineering (DIEEI), CNIT, University of Catania, Catania, ItalyDepartment of Electrical, Electronics, and Informatics Engineering (DIEEI), CNIT, University of Catania, Catania, ItalyDepartment of Civil Engineering and Architecture (DICAR), University of Catania, Catania, ItalyThe deployment of a large number of sensors in vehicles makes it possible to analyze road-user interactions which is crucial for most applications in vehicular scenarios. In this context, Deep Neural Networks (DNNs) are a powerful tool for recognizing complex data patterns stemming from interactions between users and smart roads. However, the user behaviour changes depending on the road environment and the user features. Hence, it is not possible to have a unique DNN model that is effective for all the users, in all kinds of road environments. On the contrary, a specific model might be needed for each different user interacting with each type of environment. Unfortunately, this would imply the need to collect and process a very large amount of data for the training of each DNN model, which is not practical. Therefore, this work proposes a novel training technique called Sequential Training that partitions the Neural Network (NN) layers of the DNN model into two sets of layers that are trained so that one is specific of the user while the other is trained cooperatively to be specific of the road environment. The proposed training technique is realized by means of Vehicle-to-Infrastructure (V2I) communication in which the vehicle user can download the layers of the DNN model specific of the road environment where the vehicle is currently located. Such layers are then concatenated with the user-specific layers.https://ieeexplore.ieee.org/document/11059952/Vehicle to infrastructuredeep neural networksintelligent transportation systemstransfer learningroad side unit |
| spellingShingle | Joannes Sam Mertens Salvatore Cafiso Laura Galluccio Giacomo Morabito Giuseppina Pappalardo DNN Layer Specialization Through Sequential Training for Applications With Smart Road-User Interactions IEEE Access Vehicle to infrastructure deep neural networks intelligent transportation systems transfer learning road side unit |
| title | DNN Layer Specialization Through Sequential Training for Applications With Smart Road-User Interactions |
| title_full | DNN Layer Specialization Through Sequential Training for Applications With Smart Road-User Interactions |
| title_fullStr | DNN Layer Specialization Through Sequential Training for Applications With Smart Road-User Interactions |
| title_full_unstemmed | DNN Layer Specialization Through Sequential Training for Applications With Smart Road-User Interactions |
| title_short | DNN Layer Specialization Through Sequential Training for Applications With Smart Road-User Interactions |
| title_sort | dnn layer specialization through sequential training for applications with smart road user interactions |
| topic | Vehicle to infrastructure deep neural networks intelligent transportation systems transfer learning road side unit |
| url | https://ieeexplore.ieee.org/document/11059952/ |
| work_keys_str_mv | AT joannessammertens dnnlayerspecializationthroughsequentialtrainingforapplicationswithsmartroaduserinteractions AT salvatorecafiso dnnlayerspecializationthroughsequentialtrainingforapplicationswithsmartroaduserinteractions AT lauragalluccio dnnlayerspecializationthroughsequentialtrainingforapplicationswithsmartroaduserinteractions AT giacomomorabito dnnlayerspecializationthroughsequentialtrainingforapplicationswithsmartroaduserinteractions AT giuseppinapappalardo dnnlayerspecializationthroughsequentialtrainingforapplicationswithsmartroaduserinteractions |