A conditional classification recurrent RBM for improved series mid-term forecasting

In the context of human-robot and robot-robot interactions, the better cooperation can be achieved by predicting the other party’s subsequent actions based on the current action of the other party. The time duration for adjustment is not sufficient provided by short term forecasting models to robots. A longer duration can by achieved by mid-term forecasting. But the mid-term forecasting models introduce the previous errors into the follow-up forecasting and amplified gradually, eventually invalidating the forecasting. A new mid-term forecasting with error suppression based on restricted Boltzmann machine(RBM) is proposed in this paper. The proposed model can suppress the error amplification by replacing the previous inputs with their features, which are retrieved by a deep belief network(DBN). Furthermore, a new mechanism is proposed to decide whether the forecasting result is accepted or not. The model is evaluated with several datasets. The reported experiments demonstrate the superior performance of the proposed model compared to the state-of-the-art approaches.

[1]  Wanqing Li,et al.  Action recognition based on a bag of 3D points , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[2]  Yong Du,et al.  Hierarchical recurrent neural network for skeleton based action recognition , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Cordelia Schmid,et al.  Action recognition by dense trajectories , 2011, CVPR 2011.

[4]  Athanasios V. Vasilakos,et al.  Temporal difference method-based multi-step ahead prediction of long term deep fading in mobile networks , 2002, Comput. Commun..

[5]  Liang Wang,et al.  Beyond Joints: Learning Representations From Primitive Geometries for Skeleton-Based Action Recognition and Detection , 2018, IEEE Transactions on Image Processing.

[6]  Chunheng Wang,et al.  Cross-View Action Recognition via a Continuous Virtual Path , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Xiaohui Xie,et al.  Co-Occurrence Feature Learning for Skeleton Based Action Recognition Using Regularized Deep LSTM Networks , 2016, AAAI.

[8]  Gautier Marti,et al.  Autoregressive Convolutional Neural Networks for Asynchronous Time Series , 2017, ICML.

[9]  Binlong Li,et al.  Cross-view activity recognition using Hankelets , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Daniela Fischer,et al.  Digital Design And Computer Architecture , 2016 .

[11]  Ramakrishnan Srikant,et al.  Mining Sequential Patterns: Generalizations and Performance Improvements , 1996, EDBT.

[12]  Toby Sharp,et al.  Real-time human pose recognition in parts from single depth images , 2011, CVPR.

[13]  Roni Mittelman,et al.  Time-series modeling with undecimated fully convolutional neural networks , 2015, ArXiv.

[14]  Geoffrey E. Hinton,et al.  The Recurrent Temporal Restricted Boltzmann Machine , 2008, NIPS.

[15]  Yong Du,et al.  Skeleton based action recognition with convolutional neural network , 2015, 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR).

[16]  Tej Singh,et al.  A Hybrid Framework for Action Recognition in Low-Quality Video Sequences , 2019, ArXiv.

[17]  Jin Liu,et al.  Improved human action recognition approach based on two-stream convolutional neural network model , 2020, The Visual Computer.

[18]  Yun Yang,et al.  Time Series Clustering Via RPCL Network Ensemble With Different Representations , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[19]  Andrew Zisserman,et al.  Two-Stream Convolutional Networks for Action Recognition in Videos , 2014, NIPS.

[20]  Indranil Ghosh,et al.  Artificial Neural Network and Time Series Modeling Based Approach to Forecasting the Exchange Rate in a Multivariate Framework , 2016, ArXiv.

[21]  Geoffrey E. Hinton,et al.  Two Distributed-State Models For Generating High-Dimensional Time Series , 2011, J. Mach. Learn. Res..

[22]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[23]  Meinard Müller,et al.  Motion templates for automatic classification and retrieval of motion capture data , 2006, SCA '06.

[24]  Tim Oates,et al.  Time series classification from scratch with deep neural networks: A strong baseline , 2016, 2017 International Joint Conference on Neural Networks (IJCNN).

[25]  Daniel Hsu,et al.  Time Series Forecasting Based on Augmented Long Short-Term Memory , 2017, ArXiv.

[26]  Shaun S. Wulff,et al.  Time Series Analysis: Forecasting and Control, 5th edition , 2017 .

[27]  C. F. Stevens,et al.  A Bayesian Approach to Short-term Forecasting , 1971 .

[28]  Michalis E. Zervakis,et al.  A Long Short-Term Memory deep learning network for the prediction of epileptic seizures using EEG signals , 2018, Comput. Biol. Medicine.

[29]  D. J. Bartholomew,et al.  Time Series Analysis Forecasting and Control , 1971 .

[30]  Ruonan Li,et al.  Discriminative virtual views for cross-view action recognition , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[31]  Geoffrey E. Hinton,et al.  Learning Multilevel Distributed Representations for High-Dimensional Sequences , 2007, AISTATS.

[32]  Sarah L. Harris,et al.  Chapter 6 – Architecture , 2007 .

[33]  Aparecido Nilceu Marana,et al.  Human action recognition in videos based on spatiotemporal features and bag-of-poses , 2020, Appl. Soft Comput..

[34]  Mubarak Shah,et al.  Learning a Deep Model for Human Action Recognition from Novel Viewpoints , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[35]  Zhang Yi,et al.  A Local Non-Negative Pursuit Method for Intrinsic Manifold Structure Preservation , 2014, AAAI.