Parallel spatio-temporal attention-based TCN for multivariate time series prediction

Fan, Jin; Zhang, Ke; Huang, Yipan; Zhu, Yi-hua; Chen, Baiping

doi:10.1007/s00521-021-05958-z

Cited by 96 publications

(38 citation statements)

References 36 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the prediction performance of the proposed model MLGCN, we use the following metrics: Root Mean‐Squared Error (RMSE) 56 : RMSE is the root mean‐squared error on the test set.

RMSE=\sum _{i=1}^{m}\sum _{t=1}^{T}{p}_{i}^{t}-{p}_{i}^{t}.

Precision@ n (abbreviated as P@n): In the predicted n topic words, the correct probability of prediction.…”

Section: Experiments and Results Analysismentioning

confidence: 99%

See 1 more Smart Citation

A scientific research topic trend prediction model based on multi‐LSTM and graph convolutional network

Xue

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

In recent years, with the increase of social investment in scientific research, the number of research results in various fields has increased significantly. Accurately and effectively predicting the trends of future research topics can help researchers discover future research hotspots.However, due to the increasingly close correlation between various research themes, there is a certain dependency relationship between a large number of research themes. Viewing a single research theme in isolation and using traditional sequence problem processing methods cannot effectively explore the spatial dependencies between these research themes. To simultaneously capture the spatial dependencies and temporal changes between research topics, we propose a deep neural network-based research topic hotness prediction algorithm, a spatiotemporal convolutional network model. Our model combines a graph convolutional neural network (GCN) and Temporal Convolutional Network (TCN), specifically, GCNs are used to learn the spatial dependencies of research topics a and use space dependence to strengthen spatial characteristics. TCN is used to learn the dynamics of research topics' trends. Optimization is based on the calculation of weighted losses based on time distance. Compared with the current mainstream sequence prediction models and similar spatiotemporal models on the paper datasets, experiments show that, in research topic prediction tasks, our model can effectively capture spatiotemporal relationships and the predictions outperform state-of-art baselines.

show abstract

“…To evaluate the prediction performance of the proposed model MLGCN, we use the following metrics: Root Mean‐Squared Error (RMSE) 56 : RMSE is the root mean‐squared error on the test set.

RMSE=\sum _{i=1}^{m}\sum _{t=1}^{T}{p}_{i}^{t}-{p}_{i}^{t}.

Precision@ n (abbreviated as P@n): In the predicted n topic words, the correct probability of prediction.…”

Section: Experiments and Results Analysismentioning

confidence: 99%

“…Root Mean‐Squared Error (RMSE) 56 : RMSE is the root mean‐squared error on the test set.

RMSE=\sum _{i=1}^{m}\sum _{t=1}^{T}{p}_{i}^{t}-{p}_{i}^{t}.

…”

Section: Experiments and Results Analysismentioning

confidence: 99%

A scientific research topic trend prediction model based on multi‐LSTM and graph convolutional network

Xue

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

show abstract

“…To show the superiority of our proposed model, we apply comparative studies with other state-of-the-art machine learning, deep learning, and attention models, including the support vector regression (SVR), decision tree regression (DTR), random forest regression (RFR), deep belief network (DBN), multilayer perception (MLP), single GRU, simpleRNN, LSTM, Dual-stage attention [39], PSTA-TCN [40] and Graph attention LSTM [41] models on NO.8 dataset. Table . 3 presents the RMSE, MAPE, MAE, and R 2 score of these models in our experiments, which demonstrates that our proposed model significantly outperforms the others in R 2 .…”

Section: Methodsmentioning

confidence: 99%

Saturation Line Forecasting via a Channel and Temporal Attention-Based Network

Wang

Li²,

Wang

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Tailings ponds are places for storing industrial waste. The saturation line is the crucial factor in quantifying the safety of tailings ponds. Existing saturation line time-series prediction methods are mainly based on statistical models or shallow machine learning models. Although these models aim to capture the time dependence of the sequence data, the channel and temporal are even unavailable in principle. To mitigate this problem, in this paper, we present a two-stage forecasting method, which embeds the channel and temporal attention into a hybrid CNN-LSTM model to predict the saturation line. The channel and temporal attention are utilized to capture subtle high-dimensional time-series dependence. In the first stage, the discrete wavelet transform (DWT) is applied to capture the refined sequence information. In the second stage, the CNN-LSTM model is utilized to learn the basic spatial and temporal features in the time series. Furthermore, the channel and temporal attention model are embedded into the CNN-LSTM model to enhance the feature-extracting ability in the channel and temporal dimensions. Consequently, our proposed model is shown to outperform classic models on multiple real-world datasets in terms of RMSE, MAPE, R 2 and MAE, respectively.

show abstract

“…Time-series prediction methods have evolved from traditional parametric modeling prediction and time regression prediction to ML and DL. However, most traditional methods have simple models and cannot balance spatial and temporal correlation [20]. At this stage, timeseries prediction methods mainly focus on ML and DL.…”

Section: Related Workmentioning

confidence: 99%

A Network Security Situation Prediction Method through the Use of Improved TCN and BiDLSTM

Yao¹,

Yang²,

Yang³

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The rapid development of information technology has brought much convenience to human life, but more network threats have also come one after another. Network security situation prediction technology is an effective means to protect against network threats. Currently, the network environment is characterized by high data traffic and complex features, making it difficult to maintain the accuracy of the situation prediction. In this study, a network security situation prediction model based on attention mechanism (AM) improved temporal convolutional network (ATCN) combined with bidirectional long short-term memory (BiDLSTM) network is proposed. The TCN is improved by AM to extract the input temporal features, which has a more stable feature extraction capability compared with the traditional TCN and BiDLSTM, which is more capable of processing temporal data, and is used to perform the situation prediction. Finally, by validating on a real network traffic dataset, the proposed method has better performance on multiple loss functions and has more accurate and stable prediction results than TCN, BiDLSTM, TCN-LSTM, and other time-series prediction methods.

show abstract

Parallel spatio-temporal attention-based TCN for multivariate time series prediction

Cited by 96 publications

References 36 publications

A scientific research topic trend prediction model based on multi‐LSTM and graph convolutional network

A scientific research topic trend prediction model based on multi‐LSTM and graph convolutional network

Saturation Line Forecasting via a Channel and Temporal Attention-Based Network

A Network Security Situation Prediction Method through the Use of Improved TCN and BiDLSTM

Contact Info

Product

Resources

About