Optimal and Robust QoS-Aware Predictive Adaptive Video Streaming for Future Wireless Networks

Atawia, Ramy; Hassanein, Hossam S.; Noureldin, Aboelmagd

doi:10.1109/glocom.2017.8254134

Cited by 4 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we contrast our work with the state of the art in two categories: (1) We contrast our work with DL forecasting techniques as well as statistical models, none of which use feature selection. (2) We state the differences between our work and ML techniques that utilize feature selection. We subdivide this second category into two subcategories: (2.1) non-adaptive (i.e.…”

Section: Relationship To the State Of The Artmentioning

confidence: 99%

“…In the figure, s m t,l is the importance score for x t−l at iteration m; it measures the importance of x t−l in minimizing the forecasting error at the output of the FSF architecture. 2 Second, each of the features x t−l and the corresponding feature importance score s m t,l of that feature is passed onto the GG-FS module. The GG-FS module passes only the selected features {x m t−l } l∈{0,...L} to the Forecasting module, where the values of the features that have not been selected are set to zero.…”

Section: End-to-end Trainable Feature Selection-forecasting Architecturementioning

confidence: 99%

See 1 more Smart Citation

An End-to-End Trainable Feature Selection-Forecasting Architecture Targeted at the Internet of Things

et al. 2021

View full text Add to dashboard Cite

We develop a novel end-to-end trainable feature selection-forecasting (FSF) architecture for predictive networks targeted at the Internet of Things (IoT). In contrast with the existing filter-based, wrapper-based and embedded feature selection methods, our architecture enables the automatic selection of features dynamically based on feature importance score calculation and gamma-gated feature selection units that are trained jointly and end-to-end with the forecaster. We compare the performance of our FSF architecture on the problem of forecasting IoT device traffic against the following existing (feature selection, forecasting) technique pairs: Autocorrelation Function (ACF), Analysis of Variance (ANOVA), Recurrent Feature Elimination (RFE) and Ridge Regression methods for feature selection, and Linear Regression, Multi-Layer Perceptron (MLP), Long Short Term Memory (LSTM), 1 Dimensional Convolutional Neural Network (1D CNN), Autoregressive Integrated Moving Average (ARIMA), and Logistic Regression for forecasting. We show that our FSF architecture achieves either the best or close to the best performance among all of the competing techniques by virtue of its dynamic, automatic feature selection capability. In addition, we demonstrate that both the training time and the execution time of FSF are reasonable for IoT applications. This work represents a milestone for the development of predictive networks for IoT in smart cities of the near future.

show abstract

Section: Relationship To the State Of The Artmentioning

confidence: 99%

Section: End-to-end Trainable Feature Selection-forecasting Architecturementioning

confidence: 99%

An End-to-End Trainable Feature Selection-Forecasting Architecture Targeted at the Internet of Things

et al. 2021

View full text Add to dashboard Cite

show abstract

Predictability of Internet of Things Traffic at the Medium Access Control Layer Against Information-Theoretic Bounds

Nakıp

Gül

Rodoplu³

et al. 2022

IEEE Access

View full text Add to dashboard Cite

MOSAL: A Subspace-Based Forecasting Algorithm for Throughput Maximization in IoT Networks

Nakıp

Helva²,

Güzeliş³

et al. 2022

IEEE Sensors J.

View full text Add to dashboard Cite

Optimal and Robust QoS-Aware Predictive Adaptive Video Streaming for Future Wireless Networks

Cited by 4 publications

References 12 publications

An End-to-End Trainable Feature Selection-Forecasting Architecture Targeted at the Internet of Things

An End-to-End Trainable Feature Selection-Forecasting Architecture Targeted at the Internet of Things

Predictability of Internet of Things Traffic at the Medium Access Control Layer Against Information-Theoretic Bounds

MOSAL: A Subspace-Based Forecasting Algorithm for Throughput Maximization in IoT Networks

Contact Info

Product

Resources

About