Abstract
Wearable human-activity recognition (HAR) models operate across sensors, subjects, and backbones, yet a smooth waveform may appear temporal while exploiting a persistent sensor offset primarily. We introduce SpectrumAudit, a label-sealed audit that fits a phase-randomized full-window stimulus on calibration windows from subjects held out from training and testing. After selection, it replays its exact DC projection and budget-constrained zero-mean residual on the same frozen victim without refitting. Across 27 victims from three datasets and three backbones, the selected waveforms cause 2.87-40.83-point three-phase robust accuracy losses. Under this replay budget, DC is more damaging than AC on 24/27 victims and recovers at least 90% of the full drop on 22/27; all 5 failures occur on WISDM. In a held-out UTD-MHAD check, the selected waveform causes 13.49-pp accuracy and 11.68-pp macro-F1 losses, versus -0.66 pp for matched random changes. The audit diagnoses offset versus zero-mean variation under a common peak-budget cap. The code will be released upon acceptance.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Wu, Q., Wei, Y., Liu, R., & Cheng, H. (2026). When Temporal Perturbations Act Like Sensor Biases: Label-Free Auditing of Wearable Activity Recognizers. https://omanscience.com/en/articles/when-temporal-perturbations-act-like-sensor-biases-label-free-auditing-of-wearable-activity-recognizers
MLA 9
Wu, Qingyu, et al. "When Temporal Perturbations Act Like Sensor Biases: Label-Free Auditing of Wearable Activity Recognizers." https://omanscience.com/en/articles/when-temporal-perturbations-act-like-sensor-biases-label-free-auditing-of-wearable-activity-recognizers.
Chicago (author–date)
Wu, Qingyu, Yuan Wei, Renju Liu, and Hua Cheng. 2026. "When Temporal Perturbations Act Like Sensor Biases: Label-Free Auditing of Wearable Activity Recognizers." https://omanscience.com/en/articles/when-temporal-perturbations-act-like-sensor-biases-label-free-auditing-of-wearable-activity-recognizers.
Harvard
Wu, Q., Wei, Y., Liu, R. and Cheng, H. (2026) 'When Temporal Perturbations Act Like Sensor Biases: Label-Free Auditing of Wearable Activity Recognizers', Available at: https://omanscience.com/en/articles/when-temporal-perturbations-act-like-sensor-biases-label-free-auditing-of-wearable-activity-recognizers.
Vancouver
Wu Q, Wei Y, Liu R, Cheng H. When Temporal Perturbations Act Like Sensor Biases: Label-Free Auditing of Wearable Activity Recognizers. https://omanscience.com/en/articles/when-temporal-perturbations-act-like-sensor-biases-label-free-auditing-of-wearable-activity-recognizers
IEEE
Q. Wu, Y. Wei, R. Liu, and H. Cheng, "When Temporal Perturbations Act Like Sensor Biases: Label-Free Auditing of Wearable Activity Recognizers," https://omanscience.com/en/articles/when-temporal-perturbations-act-like-sensor-biases-label-free-auditing-of-wearable-activity-recognizers.