During my FMP project, I continued upon the exploration and design criteria that concluded from my Pre-FMP. This project has explored and addressed the design challenges that emerge when implementing a Machine Learning system (AI-Kit) in Smart Home environments.
During the initial phases of the project, the features a potential user would require to interact with such a system were defined. Over the course of several iterations, the defined features were integrated in an interactive prototype used for evaluation in an Expert Panel study. Concluding from the iterations and the findings of the study, two distinct feature modes were defined as crucial to allow the functionality of AI-Kit to be integrated into daily life.
In the Label Monitoring mode, a user is able to provide feedback to AI-Kit while monitoring the overall state of the system. In this mode, the labels detected by AI-Kit are communicated to the user including details on duration and detection certainty. Moreover, a user is able to confirm, flag, edit, and remove (in case of a false positive) labels using the interface. On top of that, users can select a non-detected label (false negative) through various layers, providing more detailed control as the interaction progresses.