Please use this identifier to cite or link to this item:
https://gnanaganga.inflibnet.ac.in:8443/jspui/handle/123456789/15105
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Haider, Sami Ahmed | - |
dc.contributor.author | Ramesh, Janjhyam Venkata Naga | - |
dc.contributor.author | Raina, Vikas | - |
dc.contributor.author | Maaliw, Renato R | - |
dc.contributor.author | Soni, Mukesh | - |
dc.contributor.author | Nasurova, Kamolakhon | - |
dc.contributor.author | Patni, Jagdish Chandra | - |
dc.contributor.author | Singh, Pavitar Parkash | - |
dc.date.accessioned | 2024-04-08T04:11:10Z | - |
dc.date.available | 2024-04-08T04:11:10Z | - |
dc.date.issued | 2024 | - |
dc.identifier.citation | pp. 1-1 | en_US |
dc.identifier.issn | 0098-3063 | - |
dc.identifier.uri | https://doi.org/10.1109/TCE.2024.3369399 | - |
dc.identifier.uri | http://gnanaganga.inflibnet.ac.in:8080/jspui/handle/123456789/15105 | - |
dc.description.abstract | In the context of Secure Artificial Intelligence for 6G Consumer Electronics, accurately predicting vehicle behavior in dynamic traffic scenarios is a significant challenge in intelligent transportation. To avoid sending all raw data to a centralized cloud server, this study presents an artificial intelligence (AI) based distributed machine learning framework (AICEML) that can run on local edge devices. This method protects user privacy while minimizing transmission and processing delays. Accurate predictions are maintained despite the presence of many cars because to AICEML’s use of the model on edge devices, which incorporates edge-enhanced attention and graph convolutional neural network features to swiftly collect and transmit vehicle interaction information. Each edge device can adapt its neural network type and scale based on its computing capabilities, accommodating various application scenarios. Experimental results using the NGGSIM dataset demonstrate AICEML’s superiority, achieving precision, recall, and F1 scores of 0.9391, 0.9557, and 0.9473, respectively. With a 1-second prediction horizon, it maintains 91.21% accuracy and low time complexity even as the number of vehicles increases. This framework holds promise for enhancing intelligent transportation systems in the 6G era while prioritizing security and efficiency. IEEE | en_US |
dc.language.iso | en | en_US |
dc.publisher | IEEE Transactions on Consumer Electronics | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | en_US |
dc.subject | 6G Consumer Electronics | en_US |
dc.subject | Behavioral Sciences | en_US |
dc.subject | Communication Efficiency | en_US |
dc.subject | Computational Modeling | en_US |
dc.subject | Data Models | en_US |
dc.subject | Edge Computing | en_US |
dc.subject | Hidden Markov Models | en_US |
dc.subject | Neural Networks | en_US |
dc.subject | Secure Artificial Intelligence | en_US |
dc.subject | Servers | en_US |
dc.subject | Training | en_US |
dc.subject | Vehicle Behavior Prediction | en_US |
dc.title | Secure Artificial Intelligence for Precise Vehicle Behavior Prediction in 6G Consumer Electronics | en_US |
dc.type | Article | en_US |
Appears in Collections: | Journal Articles |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.