tionalneuralnetworksorlongshort-termmemorynetworksalone,thecombinedmodelwithat- tentionmechanismhashigherpredictionaccuracyandbetterfittingeffectonmultipleevaluation indicators.Inaddition,thispaperintroducestheisolationforestalgorithmforoutlierdetectionof thepredictionerrorsandcarriesoutadetailedclassificationanalysiscombinedwithth...
As Europe integrates more renewable energy resources, notably offshore wind power, into its super meshed grid, the demand for reliable long-distance High Voltage Direct Current (HVDC) transmission systems has surged. This paper addresses the intricacies
（Beijing Institute of Astronautical Systems Engineering, Beijing 100076, China）Abstract: For rocket structural health monitoring, this paper proposes a damage detection method based on deep learning. This method directly takes the vibration data of multiple channels as input, and performs damage ...
Fig. 1. Diagram of the proposed method. 2.1. EEG data This study used publicly available EEG data from the National Database for Autism Research (NDAR). The project name was Multimodal Developmental Neurogenetics of Females with ASD [29], [30], [31]. This project recruited a sex-balanced...
This paper compares its forecasted value with SVR, CNN, LSTM, GRU-LSTM, CNN-LSTM, and CNN-LSTM-AM to verify the forecasting effect of the CNN-STLSTM-AM. The experiments use root mean squared error (RMSE), R-squared (R2), mean absolute error (MAE), and training time to evaluate and...
Error backpropagation: The obtained error is updated with weights and biases for each layer of the model by the backpropagation algorithm. Fig. 9 Activity diagram of CNN-Bi-LSTM training process Full size image The prediction process of CNN-Bi-LSTM is shown in Fig.10. The main steps are ...
As the main goal of the paper, we present a novel hardware architecture and provide implementation details. We perform a throughput scalability analysis to identify a configuration with the highest throughput that is used for comparison to the state-of-the-art with respect to accuracy, achieved ...
different states. The influence of unit state, wake and space-time characteristics on wind power prediction cannot be ignored. Based on long short-term memory-temporal convolutional network (LSTM-TCN), an ultra-short-term power prediction method for offshore wind power was proposed in this paper...
TLSTM-Attention), which consists of a time delay neural network (TDNN) em-bedded by attention mechanism layer (Attention) and a long and short time memory (LSTM) recurrent neural network, is proposed in this paper. This model can effectively fuse the coarse and fine particle features with ...
The primary motivation of this paper is to develop a modified version of a deep learning model for precise intrusion detection in IoT systems with limited processing time. The contributions of this paper are illustrated below: This paper is prepared in this manner: A literature review related to...