학술논문

Utilizing LCR of Wireless System with SC Receiver Weakened by Beaulieu-Xie Fading and κ-¼ Interference for Machine Learning-Based QoS Prediction
Document Type
Conference
Source
2023 IEEE 21st Jubilee International Symposium on Intelligent Systems and Informatics (SISY) Intelligent Systems and Informatics (SISY), 2023 IEEE 21st Jubilee International Symposium on. :000079-000084 Sep, 2023
Subject
Communication, Networking and Broadcast Technologies
Computing and Processing
Engineering Profession
General Topics for Engineers
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Fading channels
Wireless communication
Input variables
System performance
Diversity reception
Quality of service
Receivers
Beaulieu-Xie fading
κ-¼ CCI
Level crossing rate (LCR)
SC combining
Machine learning
Quality of Service (QoS)
Weka
Language
ISSN
1949-0488
Abstract
For applications in wireless systems, accurate channel modeling is necessary. Since there were no precise distributions for modeling channels consisting of more line-of-sight (LOS) likewise non-LOS signals components, many theoretical investigations based on practical measurements in wireless channels were done in last years. Because of that, a new Beaulieu-Xie (BX) distribution for modeling wireless systems that contain more than one dominant specular component was defined. Beside new BX fading, the co-channel interference (CCI) also disturbs observed wireless system. The CCI in this system is κ-¼ distributed. The most efficient tools to mitigate the impact of these disturbances are diversity combining schemes. Here, the selection combining is used as inexpensive and good enough way for improving system performance. In this place, we derived the expression for the signal to interference ratio (SIR) based level crossing rate (LCR) for such configuration. We ploted some figures of the LCR versus SIR and analyzed how the parameters of BX fading and κ-¼ CCI affect the displayed LCR. Additionally, the calculated LCR is utilized as one of input variables within classification model for Quality of Service (QoS) degree prediction implemented using Weka library in Java.