Temporal Activity Analysis.
Isaac J. Sledge, James M. Keller, Timothy Craig Havens, Gregory L. Alexander, M. Skubic · National Conference on Artificial Intelligence · 2008
When monitoring elders daily routines, it is desirable to detect aberrant activity trends, as they may foreshadow a need for medical attention. But, traditional, unsupervised pattern classification techniques are ill-suited for this task, because the data distributions formed by the captured patterns are temporal in nature. To overcome this algorithmic deficit, we craft a framework for analyzing and displaying additive trends in feature data extracted from passive sensors.