TY - GEN
T1 - MAT-CNN-SOPC
T2 - 2018 NASA/ESA Conference on Adaptive Hardware and Systems
AU - Dey, Somdip
AU - Kalliatakis, Grigorios
AU - Saha, Sangeet
AU - Singh, Amit Kumar
AU - Ehsan, Shoaib
AU - McDonald-Maier, Klaus
N1 - Funding Information:
This work is supported by the UK Engineering and Physical Sciences Research Council EPSRC [EP/R02572X/1 and EP/P017487/1].
Funding Information:
This work is supported by the UK Engineering and Physical Sciences Research Council EPSRC [EP/R02572X/1 and EP/P017487/1] and the authors would like to thank the people associated with National Centre for Nuclear Robotics (NCNR) and Extreme Environments for their support and feedback. Somdip would also like to thank everyone from the Embedded and Intelligent Systems Laboratory at the University of Essex for their feedback on this project.
Publisher Copyright:
© 2018 IEEE.
Copyright:
Copyright 2019 Elsevier B.V., All rights reserved.
PY - 2018/11/22
Y1 - 2018/11/22
N2 - Intelligent Transportation Systems (ITS) have become an important pillar in modern 'smart city' framework which demands intelligent involvement of machines. Traffic load recognition can be categorized as an important and challenging issue for such systems. Recently, Convolutional Neural Network (CNN) models have drawn considerable amount of interest in many areas such as weather classification, human rights violation detection through images, due to its accurate prediction capabilities. This work tackles real-life traffic load recognition problem on System-On-a-Programmable-Chip (SOPC) platform and coin it as MAT-CNN-SOPC, which uses an intelligent retraining mechanism of the CNN with known environments. The proposed methodology is capable of enhancing the efficacy of the approach by 2.44x in comparison to the state-of-art and proven through experimental analysis. We have also introduced a mathematical equation, which is capable of quantifying the suitability of using different CNN models over the other for a particular application based implementation.
AB - Intelligent Transportation Systems (ITS) have become an important pillar in modern 'smart city' framework which demands intelligent involvement of machines. Traffic load recognition can be categorized as an important and challenging issue for such systems. Recently, Convolutional Neural Network (CNN) models have drawn considerable amount of interest in many areas such as weather classification, human rights violation detection through images, due to its accurate prediction capabilities. This work tackles real-life traffic load recognition problem on System-On-a-Programmable-Chip (SOPC) platform and coin it as MAT-CNN-SOPC, which uses an intelligent retraining mechanism of the CNN with known environments. The proposed methodology is capable of enhancing the efficacy of the approach by 2.44x in comparison to the state-of-art and proven through experimental analysis. We have also introduced a mathematical equation, which is capable of quantifying the suitability of using different CNN models over the other for a particular application based implementation.
KW - Convolutional neural network (CNN)
KW - system-on-a-programmable-chip (SOPC)
KW - traffic analysis
KW - traffic density
KW - transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85059937576&partnerID=8YFLogxK
U2 - 10.1109/AHS.2018.8541406
DO - 10.1109/AHS.2018.8541406
M3 - Conference contribution
AN - SCOPUS:85059937576
SN - 9781538677544
T3 - Proceedings of Conference on Adaptive Hardware and Systems
SP - 291
EP - 298
BT - 2018 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2018
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 6 August 2018 through 9 August 2018
ER -
