Cloud-Assisted Cyber-Physical Systems for the Implementation
of Industry 4.0
Published online: 26 April 2017
Springer Science+Business Media New York 2017
Guest Editorial: In recent years, modern industry has been
struggling against personalized consumption demands which
feature multiple types, small batches, and random orders. The
promising solution relies on Cloud-assisted Cyber-Physical
Systems (CCPS) that addresses the integration of virtual in-
formation systems with physical devices. When combining
the big data, cloud computing, internet of things, and even
artificial intelligence with industrial automation, we may
achieve a flexible, efficient, and transparent industry system.
Since German government released the Industry 4.0 initiative,
three kinds of integration with the support of cloud technolo-
gies have been widely discussed, i.e., 1) horizontal integration
through value networks; 2) vertical integration and networked
industrial systems; and 3) end-to-end digital integration of
engineering across the entire value chain. However, many
difficulties exist in integration, e.g., virtualized resource man-
agement, high-bandwidth real-time industrial wireless net-
works, industrial big data analytics, dynamical reconfigura-
tion mechanics, and unified network standards. Therefore,
industrial and academic researchers should cooperate to pro-
mote the progress of smart industrial technologies and appli-
cations. This special issue features six selected papers
with high quality related to CCPS for the implementa-
tion of industry 4.0.
This special issue kicks off with an article on smart
home system, namely BSmart Home 2.0: Innovative
Smart Home System Powered by Botanical IoT and
Emotion Detection,^ co-authored by M. Chen, et al.
The authors propose an innovative smart home solution,
in which users interconnect with home appliances and
greeneries harmoniously, to achieve the organic integra-
tion between users and greeneries.
The second article BA Lightweight Intelligent
Manufacturing System Based on Cloud Computing for Plate
Production^ by Q. Liu et al. proposes a flexible Lightweight
Plate Intelligent Manufacturing System (LPIMS) based on
cloud computing and assembly manufacturing process for in-
dustry 4.0. The framework structure and functions is de-
scribed, a real-time manufacturing information model of the
LPIMS to meet the needs of large-scale information process-
ing requirements is given, and a key concept for the system,
i.e. the optimal state is defined in this paper.
In the article BTempoRec: Temporal-Topic Based
Recommender for Social Network Services^, Y. Zhang et al.
propose a hybrid recommendation algorithm based on social
relations and time-sequenced topics, which has been evaluat-
ed through datasets from Sina Weibo that the improved hybrid
recommendation algorithm achieves better mean average pre-
cision (MAP) than other related approaches.
The fourth article BExploiting Energy Efficient
Emotion-Aware Mobile Computing^, co-authored by Y.
Peng, et al., proposes a framework of energy efficient
emotion-aware mobile computing system to consider the
energy saving from both local user part and remote data
centers part, and provide energy saving while keeping
quality of service.
The fifth paper BUnderwater Optical Image Processing: A
Comprehensive Review^ by H. Lu, et al., introduces a com-
prehensive review of recent trends of underwater optical
* Jiafu Wan
School of Mechanical & Automotive Engineering, South China
University of Technology, Guangzhou 510640, China
University of British Columbia, 2329 West Mall,
Vancouver, BC V6T 1Z4, Canada
Mobile Netw Appl (2017) 22:1157–1158