Memory-Based Pruning of Deep Neural Networks for IoT Devices Applied to Flood Detection

Sensors

Jó Ueyama¹  Luis Gustavo Nonato¹  Caetano Mazzoni Ranieri¹  Francisco Erivaldo Fernandes Junior² 

[1] Institute of Mathematical and Computer Sciences, University of São Paulo (USP), São Carlos 13566-590, Brazil;SIDIA R&D Institute, Manaus 69055-035, Brazil;

关键词: deep neural networks;    semantic segmentation;    random pruning;    Internet of Things;    flood detection;    user preference;   

DOI  :  10.3390/s21227506

来源: DOAJ

【 摘 要 】

Automatic flood detection may be an important component for triggering damage control systems and minimizing the risk of social or economic impacts caused by flooding. Riverside images from regular cameras are a widely available resource that can be used for tackling this problem. Nevertheless, state-of-the-art neural networks, the most suitable approach for this type of computer vision task, are usually resource-consuming, which poses a challenge for deploying these models within low-capability Internet of Things (IoT) devices with unstable internet connections. In this work, we propose a deep neural network (DNN) architecture pruning algorithm capable of finding a pruned version of a given DNN within a user-specified memory footprint. Our results demonstrate that our proposed algorithm can find a pruned DNN model with the specified memory footprint with little to no degradation of its segmentation performance. Finally, we show that our algorithm can be used in a memory-constraint wireless sensor network (WSN) employed to detect flooding events of urban rivers, and the resulting pruned models have competitive results compared with the original models.

【 授权许可】

Unknown