Mitigating Sensor Data Bias from User Operational Variability via Causal Intervention

Tactile sensing is essential for human monitoring because people unconsciously touch ambient surfaces all the time. Recent development in multiplexed pressure sensor matrices enables scalable tactile sensing platforms. However, the multiplexing matrix design, combined with human interaction variability (location and orientation), introduces sensor data bias. This significantly limits the scalability of the solutions in real-world deployments. This work addresses this limitation through a causal inference framework to systematically mitigate this data bias without requiring extensive calibration or specialized hardware. By formulating the placement location as a confounding factor, our backdoor-adjustment-based solution learns a de-biased representation of the sensor data, enabling accurate human interaction inference with diverse user behaviors. We demonstrate the efficacy of our approach through a case study on a pressure sensor matrix-based sensing system. The proposed solution achieves over 20% improvement in F1 score compared to baseline methods, while at the same time is tiny-weight enough to enable fully on-edge continuous model adaptation.