{"id":"W2604272310","doi":"10.1609/aaai.v31i2.19102","title":"Crowdsensing Air Quality with Camera-Enabled Mobile Devices","year":2017,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Nanyang Technological University; National Research Foundation","keywords":"Crowdsensing; Computer science; Air quality index; Scalability; Mobile device; Quality (philosophy); Analytics; Real-time computing; Artificial intelligence; Data mining; Data science; Database","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":[0.0004679046,0.0006814409,0.0005726295,0.000718952,0.0004867797,0.000725307,0.0007855929,0.0007481146,0.001618947],"category_scores_gemma":[0.002253854,0.0002902378,0.0004207548,0.0004845991,0.0003280884,0.0007356089,0.00164743,0.0005579686,0.0005919221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004755289,"about_ca_system_score_gemma":0.0004130363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006676659,"about_ca_topic_score_gemma":0.008251197,"domain_scores_codex":[0.9992425,0.0001727798,0.00002557334,0.0001834314,0.0003015566,0.00007405943],"domain_scores_gemma":[0.9990659,0.0004430688,0.00009258689,0.000130318,0.0001932826,0.00007487125],"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":[0.002908447,0.0009137976,0.03360029,0.001827705,0.0005176305,0.002043034,0.002522801,0.07337429,0.1577893,0.007610003,0.03187472,0.685018],"study_design_scores_gemma":[0.0005015604,0.001452203,0.03405343,0.0003408822,0.0003401314,0.001181762,0.001539311,0.7950949,0.07372133,0.02029432,0.0712099,0.0002703006],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5347744,0.004195672,0.3929635,0.00301703,0.0009924282,0.001769086,0.002956913,0.008322546,0.05100844],"genre_scores_gemma":[0.9177807,0.0005157725,0.07649627,0.000567871,0.0001603316,0.0002748243,0.0004539464,0.00007020572,0.003680206],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006676659,"threshold_uncertainty_score":0.01327562,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07407773828354826,"score_gpt":0.318293629477468,"score_spread":0.2442158911939197,"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."}}