Tag: LSTM

Three tiny neural networks, each under 50,000 parameters, cut prediction error by more than half and reached up to 95 ...

A deep learning framework that fuses construction schedules with wall-deflection monitoring data cut long-term prediction errors for diaphragm walls at ...

A graph convolutional network with incremental learning improves network anomaly detection across three benchmark datasets by adapting to evolving attack ...

A new open-access framework combines graph neural networks, LSTM models, large language models and federated learning to detect money laundering ...

A hybrid VMD-CBiLSTM model optimized by the shuffled frog-leaping algorithm achieved an average R2 of 0.981 when predicting PM2.5 concentrations ...

A hybrid LSTM-ARO-VMD framework that jointly tunes signal decomposition and neural network hyperparameters cut forecasting errors across seven international stocks, ...

A new deep learning model combining wavelet decomposition, a CNN and LSTM layers achieved an RMSE of 0.09 in forecasting ...

A new two-layer hypergraph model simulates opinion change and workplace switching, with LSTM and XGBoost performing best at estimating its ...

A landmark head-to-head study finds that a YOLOv3 image detector outperforms point-cloud-native and modular machine learning methods for detecting moving ...

A new open access study proposes a four-layer framework combining machine learning forecasting, uncertainty-aware optimization, and automated fault redispatch for ...