Semantic Communication Enabling Robust Edge Intelligence for Time-Critical IoT Applications

TY - GEN

T1 - Semantic Communication Enabling Robust Edge Intelligence for Time-Critical IoT Applications

AU - Cavagna, Andrea

AU - Li, Nan

AU - Iosifidis, Alexandros

AU - Zhang, Qi

PY - 2023/10

Y1 - 2023/10

N2 - This paper aims to design robust Edge Intelligence using semantic communication for time-critical IoT applications. We systematically analyze the effect of image DCT coefficients on inference accuracy and propose the channel-agnostic effectiveness encoding for offloading by transmitting the most meaningful task data first. This scheme can well utilize all available communication resource and strike a balance between transmission latency and inference accuracy. Then, we design an effectiveness decoding by implementing a novel image augmentation process for convolutional neural network (CNN) training, through which an original CNN model is transformed into a Robust CNN model. We use the proposed training method to generate Robust MobileNet-v2 and Robust ResNet-50. The proposed Edge Intelligence framework consists of the proposed effectiveness encoding and effectiveness decoding. The experimental results show that the effectiveness decoding using the Robust CNN models perform consistently better under various image distortions caused by channel errors or limited communication resource. The proposed Edge Intelligence framework using semantic communication significantly outperforms the conventional approach under latency and data rate constraints, in particular, under ultra stringent deadlines and low data rate.

AB - This paper aims to design robust Edge Intelligence using semantic communication for time-critical IoT applications. We systematically analyze the effect of image DCT coefficients on inference accuracy and propose the channel-agnostic effectiveness encoding for offloading by transmitting the most meaningful task data first. This scheme can well utilize all available communication resource and strike a balance between transmission latency and inference accuracy. Then, we design an effectiveness decoding by implementing a novel image augmentation process for convolutional neural network (CNN) training, through which an original CNN model is transformed into a Robust CNN model. We use the proposed training method to generate Robust MobileNet-v2 and Robust ResNet-50. The proposed Edge Intelligence framework consists of the proposed effectiveness encoding and effectiveness decoding. The experimental results show that the effectiveness decoding using the Robust CNN models perform consistently better under various image distortions caused by channel errors or limited communication resource. The proposed Edge Intelligence framework using semantic communication significantly outperforms the conventional approach under latency and data rate constraints, in particular, under ultra stringent deadlines and low data rate.

KW - CNN inference

KW - Edge Intelligence

KW - Semantic communication

KW - low latency

KW - service reliability

UR - http://www.scopus.com/inward/record.url?scp=85177830978&partnerID=8YFLogxK

U2 - 10.1109/ICCWorkshops57953.2023.10283786

DO - 10.1109/ICCWorkshops57953.2023.10283786

M3 - Article in proceedings

T3 - IEEE International Conference on Communications workshops

SP - 1617

EP - 1622

BT - 2023 IEEE International Conference on Communications Workshops (ICC Workshops)

PB - IEEE

T2 - 2nd International Workshop on Semantic Communications

Y2 - 28 May 2023 through 1 June 2023

ER -