{"id":"W2809317444","doi":"10.3390/en11071636","title":"Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches †","year":2018,"lang":"en","type":"article","venue":"Energies","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":902,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"United Arab Emirates University","keywords":"Computer science; Machine learning; Artificial intelligence; Hyperparameter; Mean absolute percentage error; Mean squared error; Feature selection; Artificial neural network; Time series; Scheduling (production processes); Feature engineering; Feature (linguistics); Genetic algorithm; Model selection; Deep learning; Algorithm; Mathematical optimization; Mathematics; Statistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001448614,0.0003052183,0.0002906687,0.0001506006,0.0005381189,0.0001227505,0.00008814233,0.0001390603,0.000003014211],"category_scores_gemma":[0.00004146008,0.0002842465,0.00004687075,0.0003300228,0.00004637944,0.0001975001,0.00003666662,0.0004203962,5.203057e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009980975,"about_ca_system_score_gemma":0.00003094204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004136504,"about_ca_topic_score_gemma":0.0001233224,"domain_scores_codex":[0.9987563,0.00003339912,0.0002075253,0.0003185619,0.000178459,0.0005057717],"domain_scores_gemma":[0.9995821,0.00008183064,0.00008997529,0.00007837392,0.00009140149,0.00007635614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003194001,0.000007453474,0.001828049,0.00005833848,0.00006205313,0.000001464877,0.001257577,0.9374834,0.003081522,0.00002427544,0.000009477033,0.05615447],"study_design_scores_gemma":[0.0004048045,0.0002731001,0.00009165822,0.00006458208,0.00006773309,0.0001085076,0.0001901444,0.9907103,0.007282781,0.00001586232,0.0004252863,0.0003652452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.525897,0.001890741,0.4715687,0.000003488432,0.00005755206,0.00007594959,0.00000103886,0.0002720705,0.0002334052],"genre_scores_gemma":[0.7195566,0.00003858496,0.2798149,0.000003548058,0.0002974998,0.00001949266,0.00001453212,0.00007660784,0.0001781601],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1936596,"threshold_uncertainty_score":0.999961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02982244564177539,"score_gpt":0.2186246528030399,"score_spread":0.1888022071612645,"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."}}