Distributed edge intelligence is a disruptive research area that enables the execution of machine learning and deep learning (ML/DL) algorithms close to where data are generated. Since edge devices are more limited and heterogeneous than typical cloud devices, many hindrances have to be overcome to fully extract the potential benefits of such an approach (such as data-in-motion analytics). In this paper, we investigate the challenges of running ML/DL on edge devices in a distributed way, paying special attention to how techniques are adapted or designed to execute on these restricted devices. The techniques under discussion pervade the processes of caching, training, inference, and offloading on edge devices. We also explore the benefits and drawbacks of these strategies.

International audienceThe Internet of Things (IoT) is a paradigm in which smart objects actively collaborate among them and with other physical and virtual objects available in the Web in order to perform high-level tasks for the benefit of end-users. In the e-health scenario, these communicating smart objects can be body sensors that enable a continuous real-time monitoring of vital signs of patients. Data produced by such sensors can be used for several purposes and by different actors, such as doctors, patients, relatives, and health care centers, in order to provide remote assistance to users. However, major challenges arise mainly in terms of the interoperability among several heterogeneous devices from a variety of manufacturers. In this context, we introduce EcoHealth (Ecosystem of Health Care Devices), a Web middleware platform for connecting doctors and patients using attached body sensors, thus aiming to provide improved health monitoring and diagnosis for patients. This platform is able to integrate information obtained from heterogeneous sensors in order to provide mechanisms to monitor, process, visualize, store, and send notifications regarding patients’ conditions and vital signs at real-time by using Internet standards. In this paper, we present blueprints of our proposal to EcoHealth and its logical architecture and implementation, as well as an e-health motivational scenario where such a platform would be useful

In the near future, it will be possible that every object on Earth can be identifiable and addressable. Such objects will be able to be monitored and monitor their physical environments, and of executing actions on such environments in benefit of human users. Moreover, these so-called smart objects will be endowed with wireless communication capabilities. By being uniquely addressed, wireless endowed and through the use of existing protocols and standardized formats, smart things can be integrated in the Internet and accessed as any other Web resource. In this context, the Internet of Things (IoT) emerges as a paradigm in which smart things actively collaborate among them and with other physical and virtual objects available in the Web, providing value-added information and functionalities for users. The IoT paradigm has recently showed its potential of considerably impacting the daily lives of human beings mainly due to the use and interaction of physical devices in several domains, including complex systems composed of other systems. In this paper we discuss the IoT paradigm from the perspective of Systems-of-Systems and present EcoDiF, a IoT platform that integrates heterogeneous devices to provide real-time data control, visualization, processing, and storage. In EcoDiF, devices, information, users and applications are integrated to create an IoT ecosystem in which new ideas and products can be developed in an organic way.