Artikel,
MULTI-CHANNELS DEEP CONVOLUTION NEURAL NETWORK FOR EARLY CLASSIFICATION OF MULTIVARIATE TIME SERIES
CENTRAL ASIAN JOURNAL OF MATHEMATICAL THEORY AND COMPUTER SCIENCES, 4 (8): 1-11 (August 2023)
Zusammenfassung
Today, many time series forecasting approaches require data pre-processing and analysis to make accurate predictions. This study uses Deep Neural Networks to examine the performance of the most popular Time Series estimators on a variety of EEG sensing field series (DNN). All DNN models have automated hyper-parameter search. So it may be used on the EEG dataset without understanding the model. These advertisements were automatically launched using internal feature extraction and benchmarking of 61 EEG features. Deep learning-based DNN model that refined data engineering with 97.00% accuracy performed well in the research. The thesis evaluates two shallow networks, one DNN and one LSTM, to overcome this limitation and better explain DNN outcomes in time series classification. We broaden the few experimental parallels to include a baseline study of the two categorization fields for time series, where studies are scarce. We designed an extensible experiment structure and cross validated our models on three datasets to do this. Engine-operating depressives are classified. The method tested DNN and LSTM independently for each dataset and is generalizable to other neural network models for comparison research. Basic DNN performs like LSTM and trains faster. When DNN uses more workouts, we notice a balance in seconds and repeats. DNNs are better than LSTM for time series classification due to their efficiency and faster preparation.
