Survey on Research of RNN-Based Spatio-Temporal Sequence Prediction  Algorithms

Fang, Wei; Chen, Yupeng; Xue, Qiongying

doi:10.32604/jbd.2021.016993

Cited by 58 publications

(21 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with CNN, the biggest feature of Recurrent Neural Network (RNN) and LSTM is that, by adding a connection between the current moment and the next moment in hidden layer, the output of current moment can affect the next moment. The RNN has been used by some method to analyze spatio-temporal sequence [27]. Thus, RNN and LSTM might be better at capturing the temporal characteristics of sequence data, which is more consistent with the PoI change prediction described in Section 2.…”

Section: Cnnmentioning

confidence: 69%

Interest Points Analysis for Internet Forum Based on Long-Short Windows Similarity

Ju¹,

Lu²,

Luo³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

For Internet forum Points of Interest (PoI), existing analysis methods are usually lack of usability analysis under different conditions and ignore the long-term variation, which lead to blindness in method selection. To address this problem, this paper proposed a PoI variation prediction framework based on similarity analysis between long and short windows. Based on the framework, this paper presented 5 PoI analysis algorithms which can be categorized into 2 types, i.e., the traditional sequence analysis methods such as autoregressive integrated moving average model (ARIMA), support vector regressor (SVR), and the deep learning methods such as convolutional neural network (CNN), long-short term memory network (LSTM), Transformer (TRM). Specifically, this paper firstly divides observed data into long and short windows, and extracts key words as PoI of each window. Then, the PoI similarities between long and short windows are calculated for training and prediction. Finally, series of experiments is conducted based on real Internet forum datasets. The results show that, all the 5 algorithms could predict PoI variations well, which indicate effectiveness of the proposed framework. When the length of long window is small, traditional methods perform better, and SVR is the best. On the contrary, the deep learning methods show superiority, and LSTM performs best. The results could provide beneficial references for PoI variation analysis and prediction algorithms selection under different parameter configurations.

show abstract

Section: Cnnmentioning

confidence: 69%

Interest Points Analysis for Internet Forum Based on Long-Short Windows Similarity

Ju¹,

Lu²,

Luo³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…In the last decade, Recurrent Neural Networks (RNNs) have gained widespread attention and developed rapidly due to their powerful and effective modeling capabilities [19]. However, traditional RNN suffers from short term memory and vanishing gradient problems [20,21,22] which makes it difficult to capture long term dependencies, an important factor to capture historical relevant data over long time series to accurately predict the future weather. In the world of RNN, the Long-Short Term Memory (LSTM) based RNN overcomes the drawbacks of traditional RNN and formulates long-term dependencies between training samples [2,23,24,25].…”

Section: Related Workmentioning

confidence: 99%

Short-Term Weather Forecasting Using Spatial Feature Attention Based LSTM Model

Suleman

Shridevi

2022

IEEE Access

View full text Add to dashboard Cite

Weather prediction and meteorological analysis contribute significantly towards sustainable development to reduce the damage from extreme events which could otherwise set-back the progress in development by years. The change in surface temperature is as one of the important indicators in detecting climate change. In this research, we propose a novel deep learning model named Spatial Feature Attention Long Short Term Memory (SFA-LSTM) model to capture accurate spatial and temporal relations of multiple meteorological features to forecast temperature. Significant spatial feature and temporal interpretations of historical data aligned directly to output feature helps the model to forecast data accurately. The spatial feature attention captures mutual influence of input features on the target feature. The model is built using encoder-decoder architecture, where the temporal dependencies in data are learnt using LSTM layers in the encoder phase and spatial feature relations in the decoder phase. SFA-LSTM forecasts temperature by simultaneously learning most important time steps and weather variables. When compared with baseline models, SFA-LSTM maintains the state-of the-art prediction accuracy while offering the benefit of appropriate spatial feature interpretability. The learned spatial feature attention weights are validated from magnitude of correlation with target feature obtained from the dataset.

show abstract

“…(1) Data sorting: After splitting the original video set into multiple frame level sequences {frame 1 , frame 2 , …, frame n }, the video frames in the frame level sequences [28] are unevenly partitioned to obtain multiple chunks of size x n Ã y n which are non-overlapping with each other (2) Motion feature extraction: As single optical flow feature extraction often suffers from information omission, the inter frame difference method is used to obtain difference images by subtracting the previous frame from the next frame, and then the obtained images are binarized to obtain the motion target positions. Similarly, the same location chunks corresponding to adjacent video frames are input into Flownet2 [29] to obtain the optical flow features of each chunk in the video frame.…”

Section: Overall Structure and Processing Flowmentioning

confidence: 99%

Multi Chunk Learning Based Auto Encoder for Video Anomaly Detection

Qi¹,

Ji²,

Zhang³

et al. 2022

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Video anomaly detection is essential to distinguish abnormal events in large volumes of surveillance video and can benefit many fields such as traffic management, public security and failure detection. However, traditional video anomaly detection methods are unable to accurately detect and locate abnormal events in real scenarios, while existing deep learning methods are likely to omit important information when extracting features. In order to avoid omitting important features and improve the accuracy of abnormal event detection and localization, this paper proposes a novel method called Multi Chunk Learning based Skip Connected Convolutional Auto Encoder (MCSCAE). The proposed method improves the accuracy of video anomaly detection by obtaining more vital information. In the data sorting phase, non-uniform chunking is proposed to divide the video frame into several chunks of different sizes to avoid obtaining unnecessary information and omitting crucial information. In order to well reflect the abnormal motion of objects in the video, a new feature, the inter frame flow feature, which is obtained by merging inter frame difference and optical flow features, is proposed to extract motion feature. Moreover, in this paper, skip connection in the auto encoder is utilized during the training phase to reduce the reconstruction error between the original frames and the reconstruction frames, so that the reconstruction error can be used to detect abnormal events during testing. Experience on three public datasets verifies the effectiveness and accuracy of our proposed method. Experimental results show that the proposed method can detect and locate abnormal events outperforms other recent methods significantly.

show abstract

Survey on Research of RNN-Based Spatio-Temporal Sequence Prediction Algorithms

Cited by 58 publications

References 22 publications

Interest Points Analysis for Internet Forum Based on Long-Short Windows Similarity

Interest Points Analysis for Internet Forum Based on Long-Short Windows Similarity

Short-Term Weather Forecasting Using Spatial Feature Attention Based LSTM Model

Multi Chunk Learning Based Auto Encoder for Video Anomaly Detection

Contact Info

Product

Resources

About