A lightweight temporal attention-based convolution neural network for driver's activity recognition in edge

Simple item page
dc.contributor.authorYang, Lichao
dc.contributor.authorDu, Weixiang
dc.contributor.authorZhao, Yifan
dc.date.accessioned2023-07-12T11:03:27Z
dc.date.available2023-07-12T11:03:27Z
dc.date.issued2023-07-06
dc.description.abstractLow inference latency and accurate response to environment changes play a crucial role in the automated driving system, especially in the current Level 3 automated driving. Achieving the rapid and reliable recognition of driver's non-driving related activities (NDRAs) is important for designing an intelligent takeover strategy that ensures a safe and quick control transition. This paper proposes a novel lightweight temporal attention-based convolutional neural network (LTA-CNN) module dedicated to edge computing platforms, specifically for NDRAs recognition. This module effectively learns spatial and temporal representations at a relatively low computational cost. Its superiority has been demonstrated in an NDRA recognition dataset, achieving 81.01% classification accuracy and an 8.37% increase compared to the best result of the efficient network (MobileNet V3) found in the literature. The inference latency has been evaluated to demonstrate its effectiveness in real applications. The latest NVIDIA Jetson AGX Orin could complete one inference in only 63 ms.en_UK
dc.identifier.citationYang L, Du W, Zhao Y. (2023) A lightweight temporal attention-based convolution neural network for driver's activity recognition in edge. Computers and Electrical Engineering, Volume 110, September 2023, Article number 108861en_UK
dc.identifier.issn0045-7906
dc.identifier.urihttps://doi.org/10.1016/j.compeleceng.2023.108861
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/19964
dc.language.isoenen_UK
dc.publisherElsevieren_UK
dc.rightsAttribution 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subjectNdra recognitionen_UK
dc.subjectEfficient CNNen_UK
dc.subjectAttention mechanismsen_UK
dc.subjectEdge computingen_UK
dc.titleA lightweight temporal attention-based convolution neural network for driver's activity recognition in edgeen_UK
dc.typeArticleen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
drivers_activity_recognition_in_edge-2023.pdf
Size:
6.98 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)