scholarly journals Lightweight Neural Network-Based Viewport Prediction for Live VR Streaming in Wireless Video Sensor Network

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Xiaolei Chen ◽  
Baoning Cao ◽  
Ishfaq Ahmad
Keyword(s):  
Neural Network ◽  
Sensor Network ◽  
Prediction Accuracy ◽  
Prediction Method ◽  
Video Data ◽  
Wireless Video ◽  
Resource Saving ◽  
Movement Data ◽  
Unit Module ◽  
Video Sensor

Live virtual reality (VR) streaming (a.k.a., 360-degree video streaming) has become increasingly popular because of the rapid growth of head‐mounted displays and 5G networking deployment. However, the huge bandwidth and the energy required to deliver live VR frames in the wireless video sensor network (WVSN) become bottlenecks, making it impossible for the application to be deployed more widely. To solve the bandwidth and energy challenges, VR video viewport prediction has been proposed as a feasible solution. However, the existing works mainly focuses on the bandwidth usage and prediction accuracy and ignores the resource consumption of the server. In this study, we propose a lightweight neural network-based viewport prediction method for live VR streaming in WVSN to overcome these problems. In particular, we (1) use a compressed channel lightweight network (C-GhostNet) to reduce the parameters of the whole model and (2) use an improved gate recurrent unit module (GRU-ECA) and C-GhostNet to process the video data and head movement data separately to improve the prediction accuracy. To evaluate the performance of our method, we conducted extensive experiments using an open VR user dataset. The experiments results demonstrate that our method achieves significant server resource saving, real-time performance, and high prediction accuracy, while achieving low bandwidth usage and low energy consumption in WVSN, which meets the requirement of live VR streaming.

scholarly journals Traffic flow prediction method based on bidirectional linear recurrent neural network

2021 ◽  
Author(s):  
Ruizhi Xu ◽  
Zhou Shen
Keyword(s):  
Neural Network ◽  
Traffic Flow ◽  
Recurrent Neural Network ◽  
Prediction Accuracy ◽  
Prediction Method ◽  
Convergence Speed ◽  
Video Data ◽  
Particle Swarm Algorithm ◽  
Traffic Flow Prediction ◽  
Flow Prediction

Abstract In order to improve the rationality and effectiveness of intelligent traffic control and management on urban roads, a bidirectional linear recurrent neural network-based traffic flow prediction method is proposed from the perspective of spatial and temporal characteristics of traffic flow. The method effectively combines the characteristics of fast and accurate bilinear polynomial solution and dynamic calibration of recurrent neural network, and adopts particle swarm algorithm to realize the dynamic pruning process of redundant neurons and weights, which improves the convergence speed and prediction accuracy of the algorithm. The algorithm is trained and experimented with video data, and a comparative analysis is conducted. The results show that the method can achieve accurate prediction of road traffic flow, the traffic flow prediction accuracy reaches more than 90%, meeting the data accuracy requirements of actual traffic management and control, and the convergence speed of the algorithm has also been significantly improved.

Distortion optimized routing algorithm in wireless video sensor network

2013 ◽  
Vol 32 (5) ◽  
pp. 1232-1235
Author(s):  
Xu CHEN ◽  
Jun SHEN ◽  
Hu LUO ◽  
Xin-hua FU
Keyword(s):  
Sensor Network ◽  
Routing Algorithm ◽  
Wireless Video ◽  
Video Sensor

A Prediction Method of Power Energy Saving Potential Based on Rough Set Neural Network

2010 ◽  
Vol 44-47 ◽  
pp. 3795-3799
Author(s):  
Jin Ying Li ◽  
Ya Jun Wei ◽  
Jin Chao Li ◽  
Yu Zhi Zhao
Keyword(s):  
Neural Network ◽  
Energy Saving ◽  
Rough Set ◽  
Reduction Method ◽  
Prediction Method ◽  
Pollutant Emission ◽  
Resource Saving ◽  
Environment Friendly ◽  
Knowledge Reduction ◽  
Energy Saving Potential

Power industry is the key field of implementing energy saving and pollutant emission reduction in china, strengthen power energy saving is helpful to establish a resource-saving and environment-friendly society and promote a sustainable development of economic society. This paper synchronizes respective advantages of rough set and neural network, puts forward a prediction model-RSBPNN which uses rough set knowledge reduction method to prune the redundant and neural network to build a forecasting model.

A New Prediction Method for Chaotic Time Series

2013 ◽  
Vol 380-384 ◽  
pp. 1673-1676
Author(s):  
Juan Du
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Prediction Accuracy ◽  
Time Series Prediction ◽  
Prediction Method ◽  
Cumulative Effect ◽  
Training Data ◽  
Training Algorithm ◽  
Learning Speed ◽  
Sunspot Data

In order to show the time cumulative effect in the process for the time series prediction, the process neural network is taken. The training algorithm of modified particle swarm is used to the model for the learning speed. The training data is sunspot data from 1700 to 2007. Simulation result shows that the prediction model and algorithm has faster training speed and prediction accuracy than the artificial neural network.

scholarly journals Hybrid prediction method of ECG signals based on VMD, PSR, and RBF neural network

2020 ◽  
Author(s):  
Fuying Huang ◽  
Tuanfa Qin ◽  
Limei Wang ◽  
Haibin Wan
Keyword(s):  
Neural Network ◽  
Phase Space ◽  
Delay Time ◽  
Prediction Accuracy ◽  
Rbf Neural Network ◽  
Prediction Method ◽  
Prediction Methods ◽  
Embedding Dimension ◽  
Ecg Signals ◽  
Ecg Data

Abstract Background: It is significant for doctors and body area networks (BANs) to predict ECG signals accurately. At present, the prediction accuracy of many existing ECG prediction methods is generally low. In order to improve the prediction accuracy of ECG signals in BANs, a hybrid prediction method of ECG signals is proposed in this paper. Methods: The proposed prediction method combines variational mode decomposition (VMD), phase space reconstruction (PSR), and a radial basis function (RBF) neural network. First, the embedding dimension and delay time of PSR are calculated according to the trained set of ECG data. Second, the ECG data are decomposed into several intrinsic mode functions (IMFs). Third, the phase space of each IMF is reconstructed according to the embedding dimension and the delay time. Fourth, an RBF neural network is established and each IMF is predicted by the network. Finally, the prediction results of all IMFs are added to realize the final prediction result. Results: To evaluate the prediction performance of the proposed method, simulation experiments are carried out on ECG data from the MIT-BIH Arrhythmia Database. The experimental results show that the prediction index RMSE (root mean square error) of the proposed method is only 10-3 magnitude and that of some traditional prediction methods is 10-2 magnitude.Conclusions: Compared with some traditional prediction methods, the proposed method improves the prediction accuracy of ECG signals obviously.

Sign in / Sign up

Export Citation Format

Share Document