The Activity Recognition Repository: Towards Competitive Benchmarking in Ambient Intelligence

Rapid development in the area of ambient intelligence introduced numerous applications. One of the fundamental underpinnings in such applications is an effective and reliable context-aware system able to recognize and understand activities performed by a human, and context in which it happened. However, there are two pending issues: (i) transferability, i.e., a specific implementation is tightly interrelated with a selected algorithm, available sensors, and a scenario/environment where they are employed; and (ii) comparability, i.e., there is no established benchmark problem that would enable a direct comparison of the developed context-aware systems. This paper first reviews some recent initiatives that address the abovementioned problems and then proposes a centralized collection of resources related to design and evaluation of context-aware systems. The main idea is to establish an online repository of datasets accompanied with the task, result and applied approach. Ideally, the contributors will provide the dataset with short description of the data, task and results, relevant paper, and link to resources such as implementation of the approach, preprocessing tools, and filtering. This would allow the community to quickly start building upon the latest state-of-the-art approaches, to benchmark newly developed techniques, and ultimately, to advance the frontiers in ambient intelligence.