{"id":"W4411599595","doi":"10.1109/iotm.001.2400202","title":"Edge-IoT and MLLMs for Education and Scene Understanding: Assisting Vision and Hearing-Impaired Individuals","year":2025,"lang":"en","type":"article","venue":"IEEE Internet of Things Magazine","topic":"Robotics and Automated Systems","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Hearing impaired; Enhanced Data Rates for GSM Evolution; Internet of Things; Low vision; Visually impaired; Psychology; Audiology; Computer vision; Artificial intelligence; Computer science; Optometry; Human–computer interaction; Medicine; Internet privacy","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":[0.0002959456,0.0003795499,0.0002299123,0.0003174113,0.0003768561,0.0009833449,0.000694557,0.0008642841,0.002615914],"category_scores_gemma":[0.0007326971,0.0001613652,0.0003376488,0.0002335445,0.0004731367,0.001526224,0.002277873,0.000518869,0.001048201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002392457,"about_ca_system_score_gemma":0.0004589864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001851756,"about_ca_topic_score_gemma":0.003857245,"domain_scores_codex":[0.9998265,0.00004197662,0.00001072609,0.00003337068,0.0000599478,0.00002750367],"domain_scores_gemma":[0.9998784,0.0000429643,0.00000994977,0.00001908259,0.00002788662,0.00002170433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008200789,0.0005177611,0.009506461,0.0006307944,0.00007310029,0.003366748,0.006113889,0.02137074,0.1035701,0.04274342,0.02524477,0.7860422],"study_design_scores_gemma":[0.00008752962,0.0007427441,0.01446737,0.0005868942,0.0002080059,0.007114093,0.007299765,0.619327,0.1078171,0.07651196,0.1655671,0.0002703829],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1336049,0.001343667,0.8260111,0.002708731,0.0001692545,0.0001661579,0.0004320456,0.005526424,0.03003768],"genre_scores_gemma":[0.7350937,0.00115706,0.2479901,0.001132175,0.00006187033,0.0001453668,0.0004126961,0.0002229242,0.01378413],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002615914,"threshold_uncertainty_score":0.008751035,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.023525539045221,"score_gpt":0.2712807627315207,"score_spread":0.2477552236862997,"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."}}