Deep learning for smart manufacturing: Methods and applications

Industry 4.0: A bibliometric analysis and detailed overview

Service-Oriented Computing

Industry 4.0 (I4.0) encompasses a plethora of digital technologies effecting on manufacturing enterprises. Most research on this topic examines the effects in the smart factory domain, focusing on ...

The applications of Industry 4.0 technologies in manufacturing context: a systematic literature review

The world is marching into a new development period when the digital technology, physical technology, and biological technology have achieved an unprecedented development respectively in their own fields, and at the same time their applications are converging greatly. These are the three major technological drivers for the Fourth Industrial Revolution. This paper discusses the specific technology niches of each kind technological driver behind the Fourth Industrial Revolution, and then evaluates impacts of the Fourth Industrial Revolution on global industrial, economic, and social development. At last this paper proposes possible measures and policies for both firms and governments to cope with the changes brought by the Fourth Industrial Revolution.

http://egeoscien.neigae.ac.cn/EN/article/downloadArticleFile.do?attachType=PDF&id=9896

Fourth Industrial Revolution: technological drivers, impacts and coping methods

Pervasive applications are often executed in fluctuating conditions and need frequent adaptations to meet requirements. Autonomic computing techniques are frequently used to automate adaptations to changing execution conditions. However, some administration tasks still have to be performed by human administrators. Such tasks are very complex because of a lack of understanding of the system current state. In this paper, we propose to build and link models at runtime of supervised applications in order to ease the administrators' job. Our approach is illustrated on a health application called actimetrics, developed with Orange Labs.

Linked models@runtime to ease the administration of pervasive applications

Connected devices are deployed at a rapid rate and in broad domains like home automation or industry, forming the Internet of Things. Those devices need to be secure and trusted to prevent malicious use. However some connected devices are low-cost, memory constrained, power constrained, etc.. This greatly limits the deployment of usual security solutions. As the absence of security is not acceptable, it is necessary to search for lightweight security solutions adapted to such devices. Physical Unclonable Function (PUF) technology can support new lightweight security mechanisms and several lightweight security protocols using this technology have been proposed over the years. Those protocols look promising, however there are still some unaddressed challenges which have slowed down a large scale adoption. This article presents the design of a new authentication protocol for constrained devices which takes into account those challenges. This protocol is implemented on a hardware platform used for connected devices development, which is then used to evaluate the security level and performances of the protocol in a realistic scenario. This evaluation shows that the protocol is secure and can meet industrial time constraints.

Stephanie Chollet

Papers

Linked models@runtime to ease the administration of pervasive applications

Refillable PUF authentication protocol for constrained devices