These models use a hybrid algorithm of discrete wavelet decomposition and bidirectional long short-term memory (BILSTM). The inputs of the first model contain GHI and weather type data. The other model allows for observation of the effect of meteorological values including GHI, temperature, ...
2021年11月水力发电资源基于SGA+DWT的BiLSTM滚动预测优化模型 刘鑫V,桑学锋2,常家轩-郑阳彳 (1.华北水利水电大学水利学院，河南郑州450046；2.中国水利水电科学研究院水资源管理研究室，北京100038)摘要：根据深圳市2015年1月1日~2019年12月31日的无空缺逐日供水序列，运用自适应矩估计(AME)+最小二乘(LS)求解...
Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services - dwtcourses/BERT-BiLSTM-CRF-NER
关键词 预测优化模型 自发式遗传算法 离散小波变换 双向长短时记忆 滚动预测 泛化能力 预测精度 prediction optimization model spontaneous genetic algorithm(SGA) discrete wavelet transform(DWT) bidirectional long short term memory(BiLSTM) rolling prediction generalization ability prediction accuracy 分类号 TV214...