Improvement of the Handover Performance and Channel Allocation Scheme using Fuzzy Logic, Artificial Neural Network and Neuro-Fuzzy System to Reduce Call Drop in Cellular Network

Abstract

Due to handover failure, call drop occurs frequently. When a large number of incoming and handoff calls arrive at the same time, the performance of the conventional handoff algorithms may fall down. Moreover, multiple factors such as signal quality and available channels of cellular network can’t be evaluated in conventional algorithms. When mobile station (MS) moves, the connection of MS with nearby base station (BS) has to be switched from one to adjacent station. In this case, unnecessary handoffs will be occurred due to lack of proper decision of handoffs or lack of consideration about signal quality with available free channels. As a result call drop will occur frequently. For performing handoff efficiently, fuzzy logic based handoff decision algorithm, adaptive handoff threshold level using neural network and priority based dynamic channel allocation algorithm using neuro-fuzzy system has been proposed in this work. These algorithms will mainly focus on the proper decision of handoff based on evaluating signal strength, available free channels, spectrum efficiency, MS speed and distance from BS so that unnecessary and inefficient handoffs can’t be performed. Simulation revealed that using neuro-fuzzy system, the channel capacity, SIR and Handoff management were improved better than the others in terms of spectrum utilization efficiency, MS speed and SIR. The efficacy of the methodology has been proved by imitating the proposed model using MATLAB software.

Status of deep learning for EEG-based brain–computer interface applications

“…When no algorithmic solution can be found between the dependent and independent variables of the classification method, nonlinear classifiers are now used. Artificial neural networks (ANNs), k-nearest neighbor (KNN), and SVMs are some of these machine learning approaches (Lotte et al, 2018 ; Akhter et al, 2020 ; Islam et al, 2020 ).…”

Chronic kidney disease prediction based on machine learning algorithms

“… 1 , 16 Because there is such a wide diversity of health datasets, machine learning algorithms are the most appropriate method for enhancing the accuracy of diagnosis prediction. 17 , 19 The prevalence of machine learning algorithms in the healthcare industry is growing as a direct result of the rapid growth of electronic healthcare datasets. 9 …”

Brief Survey: Machine Learning in Handover Cellular Network

“…To mitigate call losses in cellular networks stemming from suboptimal HO performance or channel allocation, researchers have applied supervised algorithms, including neural networks. In one instance, an adaptive HO threshold, based on signal-to-interference ratio and available channels, was used in a decision matrix to label data and determine HO decisions [19].…”