Thomas Ploetz

TL;DR: This work generates explanations for smart home activity recognition systems that explain what about an activity led to the given classification, and introduces four computational techniques for generating natural language explanations of smart home data and compares their effectiveness at generating meaningful explanations.

TL;DR: The algorithm, which uses correlation to determine whether the user is rotating their wrist in synchrony with a tactile and visual prompt, minimizes false-trigger events while maintaining fast input during situational impairments.

TL;DR: In this paper, an automated processing pipeline that integrates existing computer vision and signal processing techniques to convert videos of human activity into virtual streams of IMU data is introduced, which represent accelerometry at a wide variety of locations on the human body.

TL;DR: SeeSaw as discussed by the authors is a gesture interface for commodity smartwatches to support watch-hand only input with no additional hardware, which uses correlation to determine whether the user is rotating their wrist in synchrony with tactile and visual prompts, minimizes false-trigger events while maintaining fast input during situational impairments.

TL;DR: This work proposes a transfer learning framework, TransFall, for sensor-based activity recognition that contains a two-tier data transformation, a label estimation layer, and a model generation layer to recognize activities for the new scenario.