Comparing Machine Learning Algorithms for Improving the Maintenance of LTE Networks Based on Alarms Analysis

Mobile network operators are facing many challenges to satisfy their subscribers in terms of quality of service and quality of experience provided. To achieve this goal, technological progress and scientific advances offer good opportunities for efficiency in the management of faults occurring in a mobile network. Machine learning techniques allow systems to learn from past experiences and can predict, solutions to be applied to correct the root cause of a failure. This paper evaluates machine learning techniques and identifies the decision tree as a learning model that provides the most optimal error rate in predicting outages that may occur in a mobile network. Three machine learning techniques are presented in this study and compared with regard to accuracy. This study demonstrates that the appropriate machine learning technique improves the accuracy of the model. By using the decision tree as a machine learning model, it was possible to predict solutions to network failures, with an error rate less than 2%. In addition, the use of Machine Learning makes it possible to eliminate steps in the network failure processing chain;resulting in reduced service disruption time and improved the network availability which is a key network performance index.

SISDH: A Model Based on SMAs and SIRs for the Simulation of the Evolution of COVID-19 in Cameroon

This paper presents a model to simulate the evolution of COVID-19 in the Cameroonian context. The presented model SISDH stands for Susceptible, Infected, Severe, Died, and Healed is made up of the mixture of a Multi-Agent System (SMA) and a SIR (Susceptible, Infected, Recovered)-based model, and mainly addresses the problem of modelling the evolution of pandemics with a high transmission rate. Multi-agent systems are used to design the SIR model’s entities, namely the habitants of the region subject to the study. The experimentation carried out showed that the combination of the two concepts favours rapid decision-making. For example, the requirement to wear a mask or strict adherence to social distancing reduces the risk of spread. The application of these tough measures had theoretically leveled down the spreading of the epidemic. Besides the lowering of the number of cases when strict measures were applied, we also highlighted a significant reduction of deaths and severe illness which is a concomitant result of the lockdown. On the other hand, our experiments revealed a peak of infections a few steps after the beginning when no restrictions are made for barrier measures. The peak is followed by a sudden decrease in infection which might convey immunity of the population.