Periodic Reporting for period 2 - WellCO (Wellbeing and Health Virtual Coach)
Período documentado: 2019-06-01 hasta 2021-01-31
WellCo provides a tool for training people in the adoption of the healthier behaviour choices. It leverages data from smartwatches, smartphone, validated questionnaires and the Life Plan to extract users contextual data that serves for the provision of personalized recommendations to users. According to the BCW, the personalization of recommendations is the first step to ensure acceptance, as they properly address the capability and opportunity of the user. Later, to ensure the adherence of these recommendations, we need to foster motivation. It is in this moment, when the WellCo coach, the social network with family and friends, the supporting groups and the role of experts (either through tips or through the review of recommendations) come to play.
We think that WellCo has the potential to impact society and become a tool that empower awareness on wellbeing in people. Even, this impact could be extended to another areas of society, such as sustainability. The process of training for behaviour change could be used as basis for the adoption of more environmentally friendly behaviours among European society, key goals in the 2030 agenda for Europe.
Regarding the objectives, the following ones were set in WellCo:
• Develop novel ICT approaches for useful and effective personalised recommendations and follow up in terms of preserving physical, cognitive, mental and social well-being for as long as possible.
• Validate non-obtrusive technologies for physical, cognitive, social and wellbeing.
• Evidence of user-centred design and innovation, new intuitive ways of human-computer interaction and user acceptance.
• Cost-effective analysis to maximize the quality and length of life in terms of activity and independence for people in need of guidance and care due to age related conditions because of self-care, lifestyle and care management.
We think that WellCo has the potential to impact society and become a tool that empower awareness on wellbeing in people. Even, this impact could be extended to another areas of society, such as sustainability. The process of training for behaviour change could be used as basis for the adoption of more environmentally friendly behaviours among European society, key goals in the 2030 agenda for Europe.
Regarding the objectives, the following ones were set in WellCo:
• Develop novel ICT approaches for useful and effective personalised recommendations and follow up in terms of preserving physical, cognitive, mental and social well-being for as long as possible.
• Validate non-obtrusive technologies for physical, cognitive, social and wellbeing.
• Evidence of user-centred design and innovation, new intuitive ways of human-computer interaction and user acceptance.
• Cost-effective analysis to maximize the quality and length of life in terms of activity and independence for people in need of guidance and care due to age related conditions because of self-care, lifestyle and care management.
The project started defining the basis for the proper management of quality and risks in the project. Also, with the creation of the communication tools for the project: website and social media.
In the following months, end-users’ partners started the definition of the user and recruitment plan. This phase followed a qualitative methodology using Cultural Probes, diaries and interviews with users to catch the user requirements. After this, personas and scenarios were used to get the initial mockup of WellCo.
As of M6, an initial overview of the technologies that could serve for the implementation of WellCo was carried out. This information served for the implementation of Prototype 1 (delivered in M18). Also, in M7, a study of the main variables, measurements and context that could affect the wellbeing of user was performed in D4.1. This extensive work set the basis for the implementation of the monitoring modules that constitute WP4.
In RP2, the work performed in WellCo focused on the implementation and validation of Prototype 2 and 3. From M19 till M26, main efforts were put on the design, development and integration of the modules and functionalities composing Prototype 2 and its validation by end-users.
The remaining months focused on the definition of the procedure to carry out as part of the final validation report and the implementation of the final prototype of WellCo. In between (M28), a secondary review meeting took place. The aim of this meeting was to determine if a project extension was needed. After it, it was clear that an extension was needed, thus, after voting, partners agreed on extending WellCo two months (from November 2020 to January 2021).
After that, the COVID-19 pandemic arose. The impact of this situation was reduced thanks to telework and weekly meetings so technical partners achieved to develop and integrate the remaining modules in WP, WP4 and WP5. Thus, the final prototype was submitted in October and validated by end-users from October till January 2021.
Along the whole project, special attention has been put to innovation and dissemination/exploitation; although these activities were more intensive in the last months of the project when more results were available.
As result of the project, we have achieved:
• A set of individual results, available in D6.9. These results will be exploited by the partners that owned them either as added functionalities to the current portfolio of products or for further research in the case of research organizations and universities.
• WellCo ecosystem (tsenior, expert and caregiver app). The ownership of WellCo is shared among consortium members, according to the shared distribution terms included in the Exploitation Agreement. In the coming months, intermediary organization of end-users will serve as key partners to contact municipalities and spread the results of WellCo among key customers - main step in the time-to-market phase.
In terms of dissemination, we have: published 25 scientific papers (15 in OpenAire), participate in 10 events, 8 workshops and 10 scientific workshops. Also, we have created dissemination materials such as videos, leaflets, newsletters, etc.
In the following months, end-users’ partners started the definition of the user and recruitment plan. This phase followed a qualitative methodology using Cultural Probes, diaries and interviews with users to catch the user requirements. After this, personas and scenarios were used to get the initial mockup of WellCo.
As of M6, an initial overview of the technologies that could serve for the implementation of WellCo was carried out. This information served for the implementation of Prototype 1 (delivered in M18). Also, in M7, a study of the main variables, measurements and context that could affect the wellbeing of user was performed in D4.1. This extensive work set the basis for the implementation of the monitoring modules that constitute WP4.
In RP2, the work performed in WellCo focused on the implementation and validation of Prototype 2 and 3. From M19 till M26, main efforts were put on the design, development and integration of the modules and functionalities composing Prototype 2 and its validation by end-users.
The remaining months focused on the definition of the procedure to carry out as part of the final validation report and the implementation of the final prototype of WellCo. In between (M28), a secondary review meeting took place. The aim of this meeting was to determine if a project extension was needed. After it, it was clear that an extension was needed, thus, after voting, partners agreed on extending WellCo two months (from November 2020 to January 2021).
After that, the COVID-19 pandemic arose. The impact of this situation was reduced thanks to telework and weekly meetings so technical partners achieved to develop and integrate the remaining modules in WP, WP4 and WP5. Thus, the final prototype was submitted in October and validated by end-users from October till January 2021.
Along the whole project, special attention has been put to innovation and dissemination/exploitation; although these activities were more intensive in the last months of the project when more results were available.
As result of the project, we have achieved:
• A set of individual results, available in D6.9. These results will be exploited by the partners that owned them either as added functionalities to the current portfolio of products or for further research in the case of research organizations and universities.
• WellCo ecosystem (tsenior, expert and caregiver app). The ownership of WellCo is shared among consortium members, according to the shared distribution terms included in the Exploitation Agreement. In the coming months, intermediary organization of end-users will serve as key partners to contact municipalities and spread the results of WellCo among key customers - main step in the time-to-market phase.
In terms of dissemination, we have: published 25 scientific papers (15 in OpenAire), participate in 10 events, 8 workshops and 10 scientific workshops. Also, we have created dissemination materials such as videos, leaflets, newsletters, etc.
The following actions have been upon the current state of the art:
• Behaviour Change Wheel model as part of an ICT tool. Although the BCW is a well-known model in related literature, the process of implementing an ICT tool that leverages technology for their implementation goes beyond the state of the art. Capability and opportunity is achieved by collecting and analyzing the data coming from users in a non-intrusive way and personalizing interventions while motivation is achieved through the coach and the different functionalities that form WellCo.
• Metamodel for Affecting computing. WellCo initially developed a deep learning classifier that incorporated several convolutional layers aimed at catching the facial features indicating the emotion of the user. However, due to the difficulty of categorizing some emotions using only on face visual features, e.g. fear could be mislabeled as surprise and vice versa, WellCo project has created a meta-model that ensembles the outputs from the classifier of visual features and speech at decision level in order to provide more accurate classifications.
• Nutrition Monitoring. Most of current literature for nutrition monitoring focuses on the use of smart devices (dishes, fork, spoon, necklaces) or even digital nutrition diaries. For the case of the devices, most users cannot afford to spend money in these devices and even, some of them are directly rejected.
Thus, the challenge in this area was important and from it, we have learnt that it is possible to monitor nutrition both qualitatively and quantitatively without disturbing the user.
This, together with the results derived from the qualitative and quantitative analysis performed in the final prototype, motivates us to think that WellCo has the potential to achieve societal impact. Hence, we think that WellCo has the potential to impact society and become a tool that empowers awareness on wellbeing in people.
In terms of economic impact, we have achieved a solution that has been validated along the trials (TRL7); thus, we plan to go ahead with the commercialization of WellCo in order to increase its economic impact. In this stage, the role of intermediate end-user associations is key; they were crucial for the recruitment and validation of WellCo and they constitute the main contact point to reach public administrations during this exploitation phase.
• Behaviour Change Wheel model as part of an ICT tool. Although the BCW is a well-known model in related literature, the process of implementing an ICT tool that leverages technology for their implementation goes beyond the state of the art. Capability and opportunity is achieved by collecting and analyzing the data coming from users in a non-intrusive way and personalizing interventions while motivation is achieved through the coach and the different functionalities that form WellCo.
• Metamodel for Affecting computing. WellCo initially developed a deep learning classifier that incorporated several convolutional layers aimed at catching the facial features indicating the emotion of the user. However, due to the difficulty of categorizing some emotions using only on face visual features, e.g. fear could be mislabeled as surprise and vice versa, WellCo project has created a meta-model that ensembles the outputs from the classifier of visual features and speech at decision level in order to provide more accurate classifications.
• Nutrition Monitoring. Most of current literature for nutrition monitoring focuses on the use of smart devices (dishes, fork, spoon, necklaces) or even digital nutrition diaries. For the case of the devices, most users cannot afford to spend money in these devices and even, some of them are directly rejected.
Thus, the challenge in this area was important and from it, we have learnt that it is possible to monitor nutrition both qualitatively and quantitatively without disturbing the user.
This, together with the results derived from the qualitative and quantitative analysis performed in the final prototype, motivates us to think that WellCo has the potential to achieve societal impact. Hence, we think that WellCo has the potential to impact society and become a tool that empowers awareness on wellbeing in people.
In terms of economic impact, we have achieved a solution that has been validated along the trials (TRL7); thus, we plan to go ahead with the commercialization of WellCo in order to increase its economic impact. In this stage, the role of intermediate end-user associations is key; they were crucial for the recruitment and validation of WellCo and they constitute the main contact point to reach public administrations during this exploitation phase.