Skip to main content

CO-ADAPT: Adaptive Environments and Conversational Agent Based approaches for Healthy Ageing and Work Ability

Periodic Reporting for period 1 - CO-ADAPT (CO-ADAPT: Adaptive Environments and Conversational Agent Based approaches for Healthy Ageing and Work Ability)

Reporting period: 2018-12-01 to 2019-11-30

The overall objective of the CO-ADAPT project is to provide a framework that guide the development of co-adaption resources in the work environment as well as personal life to support active ageing. In order to achieve the main objective, several specific objectives have to be met:
OBJ 1. Propose a comprehensive CO-ADAPT framework to support change for healthy ageing that describes types of adaptations required in work environments and how to approach adaptation of ageing citizens in form of change behaviour and learning ICT. The framework is produced as a participatory effort including relevant stakeholder representative including prospective ageing users.
OBJ 2. Create a personalised conversational application with comprehensive change support for ageing citizens based on data analytics focusing on high-level strategies and latest change psychology approaches considering wellbeing and digitalisation across work and personal life. Studying cross cultural applicability by evaluating the CO-ADAPT application and adaptations in work systems in two different cultural context in Italy and Finland.
OBJ 3. Develop secure and GDPR compliant AI techniques capable to contextually recommend change programs.
OBJ 4. Investigate three types of smart adaptations in work systems to age thresholds, to individual capabilities, information adaptations to tasks for cognitive augmentation aiming at 2 digits percent improvements on most indexes:
OBJ 4.1 Evaluate how interactive smart worktime planning tools that support individual work-time control and guidelines for health-promoting working hour practices.
OBJ 4.2 Evaluate adaptive assembly workstation with collaborative robotics to ageing workers cognitive and ergonomic capabilities.
OBJ 4.3 Evaluate adaptive information management systems, which support ageing workers by contextual recommendations of people to contact, tools to be used, documents and other work related entities.
We have summarized the available knowledge on the introduction of technology to ageing users andconcluded that the association of some characteristics of working hours with sickness absence, retirement intentions and work ability change with age. Gathered knowledge around health recommendations and demonstrated that exploit conversational personal healthcare agents require that the design of such agents meet a set of principles.

We have engaged with different groups of elderly workers in the project as participants on a voluntary basis. Initial experiments and participatory design were performed to guide the development of systems. We developed a prototype of a collaborative assembly station, a entity recommender for computer use and a mobile applications.
We provided a privacy preserving platform for managing the trials based on a conceptual data model. We selected wearable physiology devices with a interfaces to get data from the sensors and save them on files or databases.

The conversational technology development has been established with the design of the data collection protocol. The protocol consists of three steps, including information and educational interventions on work related stress; such interventions are delivered to the target population of COADAPT users. The second step includes the recruitment and selection of the sample of subjects; the third step included the delivering of 8 sessions of supportive therapy on a remote basis with a licensed CBT psychotherapist. FIOH has started the Task 6.1 by making written contracts with six new hospital districts in Finland covering approx. 50 000 new employees and collected pay-roll based working hour data from these organizations. The data collection will be finalized in spring 2020.

The sustainability of the CO-ADAPT solution and its outcomes depends largely on the dissemination & communication strategy and techniques ensuring the outcomes are made available to all relevant audiences in a timely, comprehensible and effective manner.
Smart Shift scheduling
Based on our pilot study (n=238 shift planning units with more than 9 000 employees) the use of the smart shift scheduling tool decreased sickness absence by 6-10% on unit level. The D1.1 “Work Ability Framework” report showed that among older employees’ sickness absence was associated especially with long working hours and decreased recovery (short shift intervals) between the shifts. We assume that if the smart shift scheduling tool will be used to shorten the working hours and to improve recovery between the shifts in addition to improving worktime control, our ongoing wide-scale intervention to use smart shift scheduling software will decrease sickness absence remarkably among the older employees.

Collaborative robot/s
The collaborative robot (cobot) installed within the Adaptive Assembly Workstation was tested, by involving a group of senior workers (N = 10; age > 55). The outcomes showed a high level of usability regardless of the tool to operate the cobot (i.e. direct physical contact or tablet). The workload experienced, related to tasks accomplishment, was low. These findings suggest that senior workers positively received the technology. Furthermore, an additional experiment (N = 30; mean age = 32.03) identified a set of suitable metrics of cognitive load and stress (i.e. eye behaviour and cardiac activity).

Proactive Entity rec
Participatory design session for entity recommender system suggests both young and older adults appreciate the support of the recommender in a variety of situations ranging from reminding important events, people, proactive retrieval of applications and documents they will use in everyday tasks. Results from pilot study, in which two individuals were asked to resume their own real-world tasks after a 14 days monitoring, suggest that proactive entity recommender was found useful and obtained large improvements in the user’s task performance and the improvements were significant.

Conversational Agent CO-ADAPT Application
In this first period we have investigated one of the main component of the personal conversational agent that will support COADAPT project and psychotherapeutic interventions. In particular we have addressed the novel problem of understanding personal narratives (PN) - spoken or written - recollections of facts, events, and thoughts. In PN, emotion carriers are the speech or text segments that best explain the emotional state of the user.
We have defined the problem of PN understanding as the prediction not only of the user emotional state but also to identify which events (e.g. the loss of relative or the visit of granpa) or people ( e.g. the old group of high school mates) carry the emotion manifested during the personal recollection. This work will propose and evaluate an annotation model for identifying emotion carriers in spoken personal narratives.