{"id":"W4413344241","doi":"10.1109/jiot.2025.3600386","title":"Adaptive-Prompt-Driven Few-Shot Class-Incremental Learning for Human Activity Recognition With Radar Modality","year":2025,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Advanced SAR Imaging Techniques","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Modality (human–computer interaction); Radar; Artificial intelligence; Incremental learning; Radar imaging; Class (philosophy); Pattern recognition (psychology); Speech recognition; Telecommunications","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000375326,0.0002012901,0.0002920898,0.0001921921,0.000110181,0.00007054315,0.000264387,0.00007954708,0.00001997583],"category_scores_gemma":[0.00004033433,0.0001944138,0.0001212923,0.00009195769,0.00007827452,0.0006528347,0.00003946527,0.0007967016,0.00000151659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003509874,"about_ca_system_score_gemma":0.00002643805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000729524,"about_ca_topic_score_gemma":0.00001536132,"domain_scores_codex":[0.9989737,0.00005795555,0.0003232953,0.0001837714,0.0002076385,0.0002536335],"domain_scores_gemma":[0.9993775,0.00006974184,0.000212806,0.0001241126,0.0001601452,0.00005564687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007422505,0.0001548661,0.001965956,0.0003329779,0.0006772218,0.00002650537,0.001192237,0.006846461,0.927369,0.0002924834,0.003505214,0.05689481],"study_design_scores_gemma":[0.001215556,0.0005448399,0.0005726381,0.001253308,0.00009703599,0.00009994041,0.0001474203,0.08843269,0.894844,0.01156065,0.000871244,0.000360653],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4455723,0.00002469221,0.5523743,0.00008318481,0.0001908697,0.0001772292,0.000004262281,0.0002285704,0.001344621],"genre_scores_gemma":[0.9386396,0.00001119802,0.0610025,0.00003823119,0.00007380887,0.0000175697,0.000005063033,0.00003806012,0.0001739704],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4930673,"threshold_uncertainty_score":0.7927966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03408799000846264,"score_gpt":0.2950957662837258,"score_spread":0.2610077762752632,"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."}}