Difference between revisions of "PRIME"
| Line 1: | Line 1: | ||
{{ResearchProjInfo | {{ResearchProjInfo | ||
| − | |Title= | + | |Title=iMedA |
| − | |ContactInformation= | + | |ContactInformation=Slawomir Nowaczyk |
| − | |ShortDescription= | + | |ShortDescription=Improving MEDication Adherence through Person Centered Care and Adaptive Interventions |
| − | |Description=The | + | |Description=The iMedA project will improve medication adherence for hypertensive patients through an AI agent that supports doctor and patient in collaboratively understanding key individual adherence risk factors and designing an appropriate intervention plan. iMedA will deliver the selected intervention through a mobile App and follow-up on its effectiveness improving the system over time. The combination of person-centered care and self-management interventions will lead to significantly improved health outcomes and reduced healthcare costs. |
| − | + | iMedA empowers hypertensive patients to take responsibility for their health through self-management, and provides doctors with information they need for person-centered care. To identify risks and intervention strategies, iMedA uses health records as well as self-reported input. The AI agent understands how both medical and personal factors interact with respect to medication adherence, and display this information on a "dashboard" that guides patient-doctor conversation. The AI monitors the effectiveness of interventions in order to improve over time. | |
| − | + | The iMedA agent will be built by combining three important AI techniques. First is to create a meaningful and comprehensive representation of each patient based on information fusion and representation learning. Second is to use peer group analysis and interpretable supervised machine learning methods to predict non-adherence for concrete patients. Finally, intervention strategies that are the most appropriate for a particular patient we will selected by combining data-driven and knowledge-driven approaches. | |
| − | |||
| − | |||
| − | |||
|LogotypeFile=Sterilizer photo.png | |LogotypeFile=Sterilizer photo.png | ||
| − | |ProjectResponsible= | + | |ProjectResponsible=Slawomir Nowaczyk |
| − | |ProjectStart= | + | |ProjectStart=2017/11/20 |
| − | |ProjectEnd= | + | |ProjectEnd=2020/11/19 |
| − | |ApplicationArea= | + | |ApplicationArea= |
| − | |||
| − | |||
| − | |||
}} | }} | ||
__NOTOC__ | __NOTOC__ | ||
{{ShowResearchProject}} | {{ShowResearchProject}} | ||
| − | + | [[Image:iMedA.png|250px]] | |
| − | |||
| − | [[Image: | ||
Revision as of 23:17, 23 November 2017
PRedictive Intelligent Maintenance Enabler
| PRIME | |
| Project start: | |
|---|---|
| 1 September 2016 | |
| Project end: | |
| 1 March 2021 | |
| More info (PDF): | |
| [[media: | pdf]] | |
| Contact: | |
| [[Pablo del Moral]] | |
| Application Area: | |
| [[Intelligent Vehicles]] | |
Involved internal personnel
| |
Involved external personnel
| |
Involved partners
| |
- Test
| |
Abstract
The goal of this project is predicting failures in a fleet of sterilizers deployed in hospitals all over the world. The characteristics of this problem are general to the field of predictive maintenance for different application fields.
Companies are interested in predictive maintenance to reduce the down time of their machines. In general the list of critical components, whose unexpected breakdowns would result in stopping the machine, is long. Therefore, the scope of a predictive maintenance system should be predicting failures in a big number of different components.
For several years, systems such as cars, sterilizers or industrial equipment have been equipped with a significant amount of sensors. Which signals to record is in general not decided based on the predictive maintenance needs, but on the requirements of security or controllers among other reasons. The sensors mounted usually don’t describe the particular behavior of the components of interest, but measure physical quantities that can be influenced by the different behavior of several components.
Predicting what component will fail when requires historic data about the operation of the machines, but also needs to be linked to the occurrence of failures, so that we can label the recorded data. In general, companies have access and store data coming from their machines, but don’t necessary have access to the whole history of repairs. The owner of the machines can decide whether to perform maintenance and repairs with the official service or any other unofficial service.
The main research goal of this project is to build a framework that allows predicting all type of failures that can happen in a machine.
