English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

With the development of Internet of Things (IoT), data is increasinglyappearing on the edge of the network. Processing tasks on the edge of thenetwork can effectively solve the problems of personal privacy leaks and serveroverload. As a result, it has attracted a great deal of attention and madesubstantial progress. This progress includes efficient convolutional neuralnetwork (CNN) models such as MobileNet and ShuffleNet. However, all of thesenetworks appear as a common network model and they usually need to identifymultiple targets when applied. So the size of the input is very large. In somespecific cases, only the target needs to be classified. Therefore, a smallinput network can be designed to reduce computation. In addition, otherefficient neural network models are primarily designed for mobile phones.Mobile phones have faster memory access, which allows them to use groupconvolution. In particular, this paper finds that the recently widely usedgroup convolution is not suitable for devices with very slow memory access.Therefore, the EdgeCNN of this paper is designed for edge computing deviceswith low memory access speed and low computing resources. EdgeCNN has been runsuccessfully on the Raspberry Pi 3B+ at a speed of 1.37 frames per second. Theaccuracy of facial expression classification for the FER-2013 and RAF-DBdatasets outperforms other proposed networks that are compatible with theRaspberry Pi 3B+. The implementation of EdgeCNN is available athttps://github.com/yangshunzhi1994/EdgeCNN

EdgeCNN: Convolutional Neural Network Classification Model with small inputs for Edge Computing