{"id":"W2385412997","doi":"","title":"An Improved K-means Algorithm for Web Document Clustering","year":2007,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Advanced Computational Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Cluster analysis; Algorithm; Similarity (geometry); k-means clustering; Canopy clustering algorithm; Document clustering; Data mining; Correlation clustering; Artificial intelligence; Image (mathematics)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001409285,0.001177762,0.002049496,0.003284001,0.001715776,0.001362085,0.002250452,0.001602318,0.001972167],"category_scores_gemma":[0.00425243,0.0006572789,0.001775103,0.004802821,0.000623917,0.002636423,0.001285559,0.0019845,0.002566413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001139424,"about_ca_system_score_gemma":0.001873357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01211309,"about_ca_topic_score_gemma":0.0134262,"domain_scores_codex":[0.9963727,0.000556307,0.0002625933,0.0006936236,0.00194858,0.0001662071],"domain_scores_gemma":[0.9980045,0.0003580969,0.00008902614,0.0002269893,0.001269736,0.00005158928],"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":[0.0002613665,0.0001263936,0.001025254,0.0004294742,0.0002370968,0.0001081521,0.0003031349,0.08062797,0.02239876,0.01171188,0.01258796,0.8701826],"study_design_scores_gemma":[0.00006899541,0.0001117284,0.001497996,0.00004145249,0.0001193634,0.0004073953,0.00009059119,0.9257728,0.02125071,0.009521268,0.04096678,0.0001509537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003297919,0.000623643,0.9935389,0.00008390686,0.0001535816,0.00006940252,0.00009563538,0.001310496,0.0008264706],"genre_scores_gemma":[0.02603891,0.0004492785,0.969765,0.00009608673,0.000130274,0.0001403757,0.0004558512,0.0002039552,0.002720255],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01211309,"threshold_uncertainty_score":0.02408516,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009155241307754386,"score_gpt":0.3015569390585168,"score_spread":0.2924016977507624,"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."}}