When monitoring elders' daily routines, it is desirable to track significant deviations from a baseline pattern, as consecutive, aberrant days may foreshadow a need for medical attention. However, many traditional, unsupervised methods for pattern classification are ill-suited for this task, as they are incapable for adapting to additive datasets. To surmount this shortcoming, we establish a framework for recognizing temporal trends in feature data extracted from passive sensors.