by Maria Pateraki (FORTH-ICS), Manolis Lourakis (FORTH-ICS), Leonidas Kallipolitis (AEGIS IT Research), Frank Werner (Software AG), Petros Patias (AUTH) and Christos Pikridas (AUTH)

Industrial environments can benefit from smart solutions developed on top of an infrastructure combining IoT and smart sensors that monitor workers in an non-invasive way, allowing the early detection and prevention of health risks. The sustAGE project aims to improve occupational safety and workforce productivity through personalised recommendations in two key industrial environments. 

The use of health and well-being technologies in smart IoT ecosystems has been steadily increasing, and they are now found in environments such as smart homes, age-friendly workplaces and public spaces [1]. The deployment of smart sensors aims to support functional, physiological and behavioral monitoring, which can benefit both older adults facing gradual degradation of their motor and cognitive skills due to aging and workers in harsh environments performing arduous, stressful or health hazardous tasks [2]. Such smart systems can promote a reactive living and working environment, which provides appropriate and timely recommendations, acts preventively and mitigates health risks.

 

sustAGE [L1] is a H2020 EU project that aims to develop a person-centered smart solution fostering the concept of “sustainable work” for EU industries, thus supporting the well-being, wellness at work and productivity of ageing employees along three main dimensions. The first dimension is directed towards improving occupational safety and health based on workplace and person-centered health surveillance monitoring. The second aims to promote the well-being of employees via personalised recommendations for physical and mental health whilst the third supports decision making related to task/job role modifications aiming to optimise overall workforce productivity. The sustAGE solution is deployed in two challenging industry domains, specifically: (i) manufacturing, focusing on car assembly line workers; and (ii) transportation & logistics, focusing on dock workers involved in vessel loading/unloading operations.

The system functionalities build upon an IoT ecosystem, based on off-the-shelf sensors integrated into daily devices and in the work environment, considering both indoor (manufacturing) and outdoor (port) working conditions. The system gathers contextual information from the working environment and users’ physiological signals, tasks, activities and behavioural patterns, in order to support user profiling and provide personalised recommendations. Measurements collected from different devices and system modules support the definition of key micro-moments related to the user’s daily schedule, work environment, workload, physical/emotional/mental state and social activities, whilst taking into account associated temporal variables. The IoT infrastructure comprises of: (i) Environmental sensors measuring air temperature, humidity, air quality, pressure, dust concentration and noise with custom, low cost Raspberry Pi/Arduino sensors; (ii) Passive cameras installed in key working locations, specifically stereo cameras for monitoring posture and repetitive user actions in the indoor manufacturing environment and mono cameras in the outdoor port environment for monitoring crane operators and dock workers involved in vessel loading/unloading; (iii) Beacons for localisation in indoor environments, achieving a precision of up to 10-20 cm within a range of 100 m; (iv) GNSS receivers built in smartphones for localisation in outdoor environments; (v) Wristwatch devices gathering physiological measurements, able to deliver notifications to users from the system; and (vi) Galileo-enabled Smartphone devices, offering centimetre accuracy and ability to communicate with the wristwatches.

The aforementioned devices/sensors collaboratively provide information on different user activities/actions (e.g. walking, bending, standing/sitting, pushing/pulling objects) and states (e.g. fatigue, discomfort), integrating temporal aspects and detecting specific events in the environment (e.g. user presence in specific areas, proximity to hazardous conditions). Moreover, the smartphone is the primary device for communication and multimodal interaction supporting natural language understanding and voice sentiment analysis. The adopted IoT configuration exhibits the advantages of unobtrusive user context interaction monitoring in a privacy-preserving way, since in private life, outside the working environment, only the wristwatch and the smartphone are used.

Figure 1: sustAGE system architecture.
Figure 1: sustAGE system architecture.

Figure 1 shows the system’s architecture, which is conceptually divided into four layers, namely monitoring, streaming, personalisation and recommendation. The monitoring layer includes components that receive raw data from various sources, supporting processing near the end-devices that prevents potentially privacy-sensitive information from being sent to the system’s upper layers. Cameras, wristwatches, environmental and location sensors as well as users’ speech comprise the list of data sources that feed the system. The streaming layer includes the sustAGE “Bridge and Universal Messaging” modules that ingest the data through a secure gateway and prepare them for distribution to the rest of the system. Data streams of different protocols are buffered, homogenised and further sent to subsequent components via a common communication protocol that ensures speed and scalability in delivery of near real-time data. The Universal Messaging bus supports streaming of the real-time data, through the topics/messages across the IoT infrastructure and all other platform components. The personalisation layer includes personalisation mechanisms generating new information, through distilling the short-, medium-term states and long term traits, extracting knowledge abstractions and enabling user profiling to be updated regularly by exploring association with past episodes. The Apama streaming analytics engine [L2] performs analytics on the incoming data, referencing historical information where necessary, to identify previously occurred patterns. Generated knowledge is stored in the respective knowledge base to constantly improve analytics, reasoning and thus user recommendations. The recommendation layer consists of reasoning and recommendation modules which determine user recommendations, taking into account spatiotemporal constraints.

Environmental sensor measurements along with user state parameters are collected by the IoT platform of the streaming layer through dedicated gateways for monitoring and analytics. In sustAGE, the main requirements of the IoT management solution relate to: (i) interoperability, that is the ability to acquire data from devices from different vendors that use different protocols; (ii) scalability, i.e. the ability to handle increased amounts of data; and (iii) security and privacy of the communicated data. Apart from these challenges, efforts are focused on robust data analysis techniques to efficiently handle the data streams and support the determination of proper actions.

sustAGE is a multidisciplinary project involving ten European partners: Foundation for Research and Technology – Hellas (Greece, coordinator), Centro Ricerche Fiat, (Italy), Heraklion Port Authority (Greece), Software AG (Germany), Imaginary Srl. (Italy), AEGIS IT Research UG (Germany), Leibniz Research Centre for Working Environment and Human Factors (Germany), University of Augsburg (Germany), National Distance Education University (Spain) and Aristotle University of Thessaloniki (Greece).

Links:
[L1] https://www.sustage.eu
[L2] https://en.wikipedia.org/wiki/Apama_(software)

References:
[1] A. Kumar, H. Kim and G.P. Hancke: “Environmental monitoring systems: A review”, IEEE Sensors Journal 13(4):1329-1339. 2013. https://www.doi.org/10.1109/JSEN.2012.2233469
[2] A. Almeida, et al: “A critical analysis of an IoT—aware AAL system for elderly monitoring”, Future Generation Computer Systems, Vol.97: 598-619, 2019. https://www.doi.org/10.1016/j.future.2019.03.019.

Please contact:
Maria Pateraki, Manolis Lourakis
FORTH-ICS, Greece
This email address is being protected from spambots. You need JavaScript enabled to view it.
This email address is being protected from spambots. You need JavaScript enabled to view it.

Leonidas Kallipolitis
AEGIS IT Research, Greece
This email address is being protected from spambots. You need JavaScript enabled to view it.

Frank Werner
Software AG, Germany
This email address is being protected from spambots. You need JavaScript enabled to view it.

Petros Patias, Christos Pikridas
Aristotle University of Thessaloniki (AUTH), Greece
This email address is being protected from spambots. You need JavaScript enabled to view it., This email address is being protected from spambots. You need JavaScript enabled to view it.

Next issue: January 2020
Special theme:
Educational Technology
Call for the next issue
Image ERCIM News 119 epub
This issue in ePub format

Get the latest issue to your desktop
RSS Feed