Ghent University Academic Bibliography

Advanced

The cascading neural network : building the Internet of Smart Things

Sam Leroux UGent, Steven Bohez UGent, Elias De Coninck UGent, Tim Verbelen UGent, Bert Vankeirsbilck UGent, Pieter Simoens UGent and Bart Dhoedt UGent (2017) KNOWLEDGE AND INFORMATION SYSTEMS. 52(3). p.791-814
abstract
Most of the research on deep neural networks so far has been focused on obtaining higher accuracy levels by building increasingly large and deep architectures. Training and evaluating these models is only feasible when large amounts of resources such as processing power and memory are available. Typical applications that could benefit from these models are, however, executed on resource-constrained devices. Mobile devices such as smartphones already use deep learning techniques, but they often have to perform all processing on a remote cloud. We propose a new architecture called a cascading network that is capable of distributing a deep neural network between a local device and the cloud while keeping the required communication network traffic to a minimum. The network begins processing on the constrained device, and only relies on the remote part when the local part does not provide an accurate enough result. The cascading network allows for an early-stopping mechanism during the recall phase of the network. We evaluated our approach in an Internet of Things context where a deep neural network adds intelligence to a large amount of heterogeneous connected devices. This technique enables a whole variety of autonomous systems where sensors, actuators and computing nodes can work together. We show that the cascading architecture allows for a substantial improvement in evaluation speed on constrained devices while the loss in accuracy is kept to a minimum.
Please use this url to cite or link to this publication:
author
organization
year
type
journalArticle (original)
publication status
published
keyword
IBCN, Neural networks, Internet of Things (IoT), Deep learning, Distributed systems and applications, Cloud computing, Mobile systems, Ubiquitous and pervasive computing
journal title
KNOWLEDGE AND INFORMATION SYSTEMS
volume
52
issue
3
pages
791 - 814
Web of Science type
Article
Web of Science id
000407048700008
ISSN
0219-1377
0219-3116
DOI
10.1007/s10115-017-1029-1
language
English
UGent publication?
yes
classification
A1
id
8533435
handle
http://hdl.handle.net/1854/LU-8533435
date created
2017-10-06 08:59:25
date last changed
2017-10-12 06:44:22
@article{8533435,
  abstract     = {Most of the research on deep neural networks so far has been focused on obtaining higher accuracy levels by building increasingly large and deep architectures. Training and evaluating these models is only feasible when large amounts of resources such as processing power and memory are available. Typical applications that could benefit from these models are, however, executed on resource-constrained devices. Mobile devices such as smartphones already use deep learning techniques, but they often have to perform all processing on a remote cloud. We propose a new architecture called a cascading network that is capable of distributing a deep neural network between a local device and the cloud while keeping the required communication network traffic to a minimum. The network begins processing on the constrained device, and only relies on the remote part when the local part does not provide an accurate enough result. The cascading network allows for an early-stopping mechanism during the recall phase of the network. We evaluated our approach in an Internet of Things context where a deep neural network adds intelligence to a large amount of heterogeneous connected devices. This technique enables a whole variety of autonomous systems where sensors, actuators and computing nodes can work together. We show that the cascading architecture allows for a substantial improvement in evaluation speed on constrained devices while the loss in accuracy is kept to a minimum.},
  author       = {Leroux, Sam and Bohez, Steven and De Coninck, Elias and Verbelen, Tim and Vankeirsbilck, Bert and Simoens, Pieter and Dhoedt, Bart},
  issn         = {0219-1377},
  journal      = {KNOWLEDGE AND INFORMATION SYSTEMS},
  keyword      = {IBCN,Neural networks,Internet of Things (IoT),Deep learning,Distributed systems and applications,Cloud computing,Mobile systems,Ubiquitous and pervasive computing},
  language     = {eng},
  number       = {3},
  pages        = {791--814},
  title        = {The cascading neural network : building the Internet of Smart Things},
  url          = {http://dx.doi.org/10.1007/s10115-017-1029-1},
  volume       = {52},
  year         = {2017},
}

Chicago
Leroux, Sam, Steven Bohez, Elias De Coninck, Tim Verbelen, Bert Vankeirsbilck, Pieter Simoens, and Bart Dhoedt. 2017. “The Cascading Neural Network : Building the Internet of Smart Things.” Knowledge and Information Systems 52 (3): 791–814.
APA
Leroux, S., Bohez, S., De Coninck, E., Verbelen, T., Vankeirsbilck, B., Simoens, P., & Dhoedt, B. (2017). The cascading neural network : building the Internet of Smart Things. KNOWLEDGE AND INFORMATION SYSTEMS, 52(3), 791–814.
Vancouver
1.
Leroux S, Bohez S, De Coninck E, Verbelen T, Vankeirsbilck B, Simoens P, et al. The cascading neural network : building the Internet of Smart Things. KNOWLEDGE AND INFORMATION SYSTEMS. 2017;52(3):791–814.
MLA
Leroux, Sam, Steven Bohez, Elias De Coninck, et al. “The Cascading Neural Network : Building the Internet of Smart Things.” KNOWLEDGE AND INFORMATION SYSTEMS 52.3 (2017): 791–814. Print.