Abstract
A wide range of assistive technologies have beendeveloped to support the elderly population with the goal ofpromoting independent living. The adoption of these technologybased solutions is, however, critical to their overarching success. Inour previous research we addressed the significance of modellinguser adoption to reminding technologies based on a range ofphysical, environmental and social factors. In our current work webuild upon our initial modeling through considering a wider rangeof computational approaches and identify a reduced set of relevantfeatures that can aid the medical professionals to make an informedchoice of whether to recommend the technology or not. Theadoption models produced were evaluated on a multi-criterionbasis: in terms of prediction performance, robustness and bias inrelation to two types of errors. The effects of data imbalance onprediction performance was also considered. With handling theimbalance in the dataset, a 16 feature-subset was evaluatedconsisting of 173 instances, resulting in the ability to differentiatebetween adopters and non-adopters with an overall accuracy of99.42 %.
| Original language | English |
|---|---|
| Title of host publication | Unknown Host Publication |
| Publisher | IEEE |
| Number of pages | 4 |
| ISBN (Print) | 978-1-4577-0220-4 |
| Publication status | Accepted/In press - 23 Jun 2016 |
| Event | The 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Duration: 23 Jun 2016 → … |
Conference
| Conference | The 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society |
|---|---|
| Period | 23/06/16 → … |
Keywords
- Technology adoption modelling
- Dementia
- Reminding
- mHealth
- Assistive technology
