{"id":"W2963857932","doi":"10.1109/access.2018.2889017","title":"The Feasibility of Automated Identification of Six Algae Types Using Feed-Forward Neural Networks and Fluorescence-Based Spectral-Morphological Features","year":2018,"lang":"en","type":"article","venue":"IEEE Access","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Spectral signature; Artificial intelligence; Computer science; Pattern recognition (psychology); Identification (biology); Fluorescence; Artificial neural network; Spectral bands; Algae; Fluorescence microscope; Remote sensing; Biological system; Optics; Biology; Geography; Ecology; Physics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002159781,0.0001363767,0.0002475913,0.00006030986,0.0001682828,0.00009062298,0.0004461466,0.0001371112,0.00009137664],"category_scores_gemma":[0.0001987395,0.00009323352,0.00008079624,0.0005500742,0.0005824658,0.0001220013,0.00005339751,0.0001463433,6.743214e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004072846,"about_ca_system_score_gemma":0.00003292128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001961538,"about_ca_topic_score_gemma":0.00002948578,"domain_scores_codex":[0.9989076,0.00003652009,0.0003706228,0.0002675052,0.0002012815,0.0002164747],"domain_scores_gemma":[0.9988374,0.0002094689,0.0003352035,0.0003759941,0.0001930219,0.00004897437],"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":[0.0002688,0.0001232179,0.09964809,0.00009383156,0.00009085582,0.00000330378,0.00003506817,0.001593984,0.8969321,0.00003752954,0.0006423483,0.0005309088],"study_design_scores_gemma":[0.0002266202,0.00003609699,0.05875916,0.00001321614,0.0001184902,0.000005880055,0.00003378009,0.1015436,0.8390574,0.0001073123,0.000002659332,0.00009574284],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.998365,0.0004278904,0.0006564797,0.00008302464,0.0001124804,0.00007337628,0.0000123118,0.00008058171,0.000188813],"genre_scores_gemma":[0.9996098,0.00002758406,0.0001324254,0.00002702316,0.0001416076,0.000002944615,0.000007913687,0.000009719874,0.00004102387],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09994963,"threshold_uncertainty_score":0.3801953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04532889033171898,"score_gpt":0.3552518967731205,"score_spread":0.3099230064414015,"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."}}