Prediction of Call Drops in GSM Network using Artificial Neural Network

Erunkulu, Olaonipekun Oluwafemi; Onwuka, Elizabeth Nnonye; Ugweje, Okechukwu C.; Ajao, Lukman Adewale

doi:10.14710/jtsiskom.7.1.2019.38-46

Cited by 11 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, one of the objectives of the study was to determine the call-drop probability distribution of the wireless cellular network. The result has indicated that the call-drop rates of the four major networks (MTN, Vodafone, Airtel-Tigo, and Glo) in the country have different probability distributions, confirming the findings of other authors that call-drops have different probability distributions (Aalo & Efthymoglou, 2010;Boggia et al, 2005;Boggia et al,2007;Fang et al, 1997;Pattaramalai et al, 2007;Erunkulu et al,2019;Ojuh & Isabona, 2021;Patil, 2016), and that the probability distribution of call-drop is inconclusive (Erunkulu et al, 2019;Tarkaa & Mom, 2018).…”

Section: Discussionsupporting

confidence: 77%

Estimating Call-Drop Probability Rates among Wireless Cellular Networks in Ghana

Agbesi¹,

Louis²

2021

ijird

View full text Add to dashboard Cite

The increasing rate of call-drop among wireless cellular networks has become a headache for subscribers of mobile voice networks in Ghana. Despite the many studies that have been carried out on call-drop, most of them have failed to examine call-drop probability rates, a key metric of tackling the issue of call-drop. This study combines the probability distribution function of call-drop and maximum likelihood estimator to estimate call-drop probability rates among the wireless cellular networks in Ghana. The call-drop of the networks was, first of all, fitted to a probability distribution. The call-drop probability rate was then estimated using the maximum likelihood estimator of the fitted distribution. The call-drop probability distribution of Airtel-Tigo, Vodafone, and Glo follow the Geometric probability distribution, while that of MNT follows the Negative Binomial probability distribution. The call-drop probability rate of MTN is 7.6%, Vodafone is 3.3%, Airtel-Tigo, and Glo is 3.0%. These call-drop rates are found to be outside the prescribed NCA's acceptable limit of less than 3 %.

show abstract

Section: Discussionsupporting

confidence: 77%

Estimating Call-Drop Probability Rates among Wireless Cellular Networks in Ghana

Agbesi¹,

Louis²

2021

ijird

View full text Add to dashboard Cite

show abstract

“…The ordinary least squares model is used to lessen the loss of factor for the provided set of training samples: as shown in ( 8): (8) where pi represents the training set, qi is the vector, and denotes the variance of estimate. The following model is used to illustrate the reduction in cost consumption and squared error values through ridge regression as shown in ( 9): (9) where  represents the regularization parameter,  indicates the regularization parameter, which is used to reduce the estimate variance by balancing the tradeoff among the bias and variance. To find the best parameters for lowering the error values, cross validation is also carried out in this model.…”

Section: Linear Kernel Regression Model (Lkrm)mentioning

confidence: 99%

“…networks are a technique that makes complex networks simpler and guarantees better service. A major factor in it is Machine Learning (ML) [9], which is a subset of artificial intelligence that helps to comprehend actions and see patterns beyond human recognition, repairs the holes left by human limitations. ML allows technologies to improve the learning capacity without having to be explicitly programmed for performing particular tasks [10], [11].…”

Section: Introductionmentioning

confidence: 99%

A Novel Chimp Optimized Linear Kernel Regression (COLKR) Model for Call Drop Prediction in Mobile Networks

G V,

Kumari P.

2023

IJRITCC

View full text Add to dashboard Cite

Call failure can be caused by a variety of factors, including inadequate cellular infrastructure, undesirable system structuring, busy mobile phone towers, changing between towers, and many more. Outdated equipment and networks worsen call failure, and installing more towers to improve coverage might harm the regional ecosystems. In the existing studies, a variety of machine learning algorithms are implemented for call drop prediction in the mobile networks. But it facing problems in terms of high error rate, low prediction accuracy, system complexity, and more training time. Therefore, the proposed work intends to develop a new and sophisticated framework, named as, Chimp Optimized Linear Kernel Regression (COLKR) for predicting call drops in the mobile networks. For the analysis, the Call Detail Record (CDR) has been collected and used in this framework. By preprocessing the attributes, the normalized dataset is constructed using the median regression-based filtering technique. To extract the most significant features for training the classifier with minimum processing complexity, a sophisticated Chimp Optimization Algorithm (COA) is applied. Then, a new machine learning model known as the Linear Kernel Regression Model (LKRM) has been deployed to predict call drops with greater accuracy and less error. For the performance assessment of COLKR, several machine learning classifiers are compared with the proposed model using a variety of measures. By using the proposed COLKR mechanism, the call drop detection accuracy is improved to 99.4%, and the error rate is reduced to 0.098%, which determines the efficiency and superiority of the proposed system.

show abstract

“…Call drop occurs when a call is terminated before the speaking parties have ended their conversational tone and one of them has hung up. The percentage of total calls is a common way to describe this (Tarkaa & Mom, 2018;Erunkulu et al, 2019). A telephone conversation may be cancelled before the parties who initiated the call choose to do so because of a technical issue.…”

Section: Call-drop In Mobile Cellular Networkmentioning

confidence: 99%

An Investigation of Factors Influencing Call-Drop among Wireless Cellular Network Users in Ghana

Agbesi¹,

Louis²

2022

theijst

View full text Add to dashboard Cite

The aim of the study was to examine the factors influencing call-drops among wireless cellular network users in Ghana. A total of 1109 wireless cellular network users participated in the study. Exploratory and confirmatory factor analyses were used to find out the latent factors influencing the call-drops among wireless cellular network users in Ghana. The results of the exploratory and confirmatory factor analyses revealed eight-factor constructs. Among these factors, limited cell towers, cell tower overload, and general power problems were found to be the highest contributory factors. The combined three factors accounted for almost 57% of the total variance. The study's results reveal that network factors play a major role among the factors influencing call-drops in Ghana. This implies that in dealing with call-drop problems in Ghana, policymakers, regulators, and stakeholders should pay attention to the network factors of wireless cellular networks.

show abstract

Prediction of Call Drops in GSM Network using Artificial Neural Network

Cited by 11 publications

References 6 publications

Estimating Call-Drop Probability Rates among Wireless Cellular Networks in Ghana

Estimating Call-Drop Probability Rates among Wireless Cellular Networks in Ghana

A Novel Chimp Optimized Linear Kernel Regression (COLKR) Model for Call Drop Prediction in Mobile Networks

An Investigation of Factors Influencing Call-Drop among Wireless Cellular Network Users in Ghana

Contact Info

Product

Resources

About