Robust and sparse Dual Tree Complex Wavelet Transform-based Twin Support Vector regression for dense 5G InH  Communications

2021 ◽  
Author(s):  
anis charrada ◽  
Abdelaziz Samet
Keyword(s):  
Wavelet Transform ◽  
Discrete Wavelet Transform ◽  
Support Vector Regression ◽  
Path Loss ◽  
Series Data ◽  
Support Vector ◽  
Sensitivity Threshold ◽  
Discrete Wavelet ◽  
Twin Support Vector Regression ◽  
Receiver Sensitivity

Abstract A robust and sparse Twin Support Vector Regression based on Dual Tree Discrete Wavelet Transform algorithm is conceived in this paper and applied to 28, 38, 60 and 73-GHz LOS (Line-of-Sight) wireless multipath transmission system in 5G Indoor Hotspot (InH) settings (simple, semi-complex and complex conference rooms) under small receiver sensitivity threshold. The algorithm establishes a denoising process in the learning phase based on Dual Tree Discrete Wavelet Transform (DT-CWT) which is suitable for time-series data. Additionally, the Close-In (CI) free space reference distance path loss model is analyzed and the large-scale propagation and probability distribution functions are investigated by determining the PLE (Path Loss Exponent) and the standard deviation of Shadow Factor (SF) for each InH scenario under consideration. Performance are evaluated under twelve (12) configuration scenarios, according to three criteria: mobility (0/3mps), receiver sensitivity threshold (-80/-120 dBm) and type of the InH area (simple, semi-complex and complex conference room). Experimental results confirm the effectiveness of the proposed approach compared to other standard techniques.

scholarly journals A Hybrid Arima and Discrete Wavelet Transform Model for Predicting the Electricity Consumption of Punjab

2019 ◽  
Vol 8 (11) ◽  
pp. 1915-1919
Keyword(s):  
Wavelet Transform ◽  
Discrete Wavelet Transform ◽  
Arima Model ◽  
Electricity Consumption ◽  
Electricity Production ◽  
Series Data ◽  
Support Vector ◽  
Discrete Wavelet ◽  
World Population ◽  
Proposed Model

The significant increase in the world population increases the demand for energy which seems to be alarming for the electricity production boards in the existing time. In the last decade, there are various engineering, simulation tools, and artificial intelligence-based methods such as Support Vector Machine and Artificial Neural Network proposed in the literature to forecast the optimal electricity demand. But these models seldom to work with the linear data. In this paper, a reliable prediction model using the linear time series data of the previous years from January 2013 to December 2017 has been presented to forecast the electricity consumption in Punjab, India. Initially, Discrete Wavelet Transform (DWT) analysis presented to extract the upper and lower limit of the previous year dataand then AutoRegressive Integrated Moving Average (ARIMA) model has been applied to extract the forecast values. The experimental results compared the original and predicted value using the proposed model to evaluate the effectiveness of the proposed approach. The results show that the difference between the original and proposed modelis only 9% while that of ARIMA only it is 11%. Thus, the proposed model using ARIMA and DWT provides effective results in predicting the forecast value.

Sign in / Sign up

Export Citation Format

Share Document