Accurate wave prediction can help avoid disasters. In this study, the significant height (SWH) performances of recurrent neural network (RNN), long short-term memory (LSTM), and gated unit (GRU) were compared. The 10 m u-component wind (U10), v-component (V10), SWH previous 24 h used as input parameters to predict SWHs future 1, 3, 6, 12, h. model was established at three different sites locate...

The leakage currents are appropriate for determining the contamination level of insulators in power distribution system, which efficiently cleaned or replaced during maintenance schedule. In this research, hybrid convolution neural network and gated recurrent unit model (CNN-GRU) developed to categorize current pulse 15 kV HDPE insulator transmission towers Taiwan. Many weather parameters accum...

A recurrent neural network (RNN) combines variable-length input data with a hidden state that depends on previous time steps to generate output data. RNNs have been widely used in time-series analysis, and various RNN algorithms proposed, such as the standard RNN, long short-term memory (LSTM), gated units (GRUs). In particular, it has experimentally proven LSTM GRU higher validation accuracy p...

For the concrete diaphragm wall (CDW) supported excavation, excessive deflection may pose a potential risk to adjacent structures and utilities in urban areas. Therefore, it is of significance predict CDW deformation with high accuracy efficiency. This paper investigates three machine learning algorithms, namely, back-propagation neural network (BPNN), long short-term memory (LSTM), gated recur...

This study aimed to analyze sentiment in office product reviews by using word embedding with three neural network modeling approaches: Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRU). Office review data is taken from Amazon's of products covering a wide range sentiments. Word converts text into numerical vector representation for processing. E...

Day-Ahead Market offers electricity market participants the opportunity to trade one day ahead of real-time. For each hour, a separate Clearing Price is created in Market. This study aims predict hourly using deep learning techniques. In this context, 24-hour Prices were forecasted with MLP, CNN, LSTM, and GRU. LSTM had best average forecasting performance an 8.15 MAPE value, according results ...

Significant wave height (SWH) prediction can effectively improve the safety of marine activities and reduce occurrence maritime accidents, which is great significance to national security development economy. In this study, we comprehensively analyzed SWH performance recurrent neural network (RNN), long short-term memory (LSTM), gated unit (GRU) by considering different input lengths, model com...