{"id":"W4416927521","doi":"10.1145/3737903.3768570","title":"FreqLT: Frequency-Domain Linear Transformation for Privacy-Preserving and Efficient Machine Learning on Wearable Sensor Signals","year":2025,"lang":"","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Wearable computer; Discriminative model; Information privacy; Encryption; Wearable technology; Cryptography; Transformation (genetics); Functional encryption; Activity recognition","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001538411,0.0007746307,0.0006007479,0.0005904372,0.0004193856,0.001207051,0.001087143,0.0008869658,0.003519565],"category_scores_gemma":[0.005757675,0.0002673393,0.000722228,0.0008836515,0.001165115,0.001958953,0.002085628,0.001670186,0.002032273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004843661,"about_ca_system_score_gemma":0.0009014394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007969749,"about_ca_topic_score_gemma":0.001070228,"domain_scores_codex":[0.9984246,0.0004664989,0.00009759788,0.000325117,0.0005553861,0.0001308068],"domain_scores_gemma":[0.9986882,0.0005514532,0.0001377279,0.0004445669,0.0001349435,0.00004322812],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004859135,0.0001795866,0.001402728,0.0002745117,0.00009022235,0.0004475687,0.0002979845,0.2210093,0.04621953,0.08080602,0.01242122,0.6363654],"study_design_scores_gemma":[0.00003248902,0.0001564156,0.0004068053,0.0000254362,0.00001103584,0.0003388459,0.00005550814,0.9083316,0.0229051,0.05905584,0.008647578,0.00003337739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00317465,0.000102947,0.9949479,0.0001529625,0.00002114495,0.00002232596,0.00009880545,0.0009385734,0.0005406917],"genre_scores_gemma":[0.4233456,0.0006449876,0.5655746,0.0008059732,0.0002151351,0.0003574159,0.001444461,0.000545517,0.007066379],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003519565,"threshold_uncertainty_score":0.01177412,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02540579559205949,"score_gpt":0.2816430919129042,"score_spread":0.2562372963208447,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}