Performance Comparison of Xgboost and Random Forest for The Prediction of Students Academic Performance (Published)
In educational data mining and learning analytics, predicting student academic performance is essential because it provides stakeholders with useful information to improve educational outcomes. In order to predict students’ academic results, this study assesses and contrasts the effectiveness of two popular machine learning algorithms: Random Forest (RF) and Extreme Gradient Boosting (XGBoost). Data preparation methods, such as principal component analysis (PCA) and feature normalization, were used to enhance a real-world dataset of 400 records gathered from six departments at Federal Polytechnic Ukana. Based on their Eigen values and explained variance, sixteen crucial input features were chosen for examination. Eighty percent (80%) of the dataset was used for training, and the remaining twenty percent (20%) was used for testing. To evaluate the performance of the models, evaluation metrics such as Mean Squared Error (MSE), Mean Absolute Error (MAE), R-Squared Score (R²), Explained Variance Score (EVS), and Median Absolute Error (MedAE) were used. The findings show that both models have strong predictive powers, with RF marginally outperforming XGBoost in important parameters. The results highlight the potential of data-driven tactics to enhance student outcomes and offer evidence-based suggestions for choosing machine learning models in educational predictive analytics.
Keywords: : Academic Performance, Performance, Prediction, Random Forest, Students, extreme gradient boosting
Operational approach to kernel system protection under Windows Server 2019: Optimization, QoS and Performance (Published)
Computer Sciences has become the culmination of all human activity these days, but it is also the worst fear that no epidemic has inspired today. And despite this, everyone concedes that the use of computers (especially through the Internet) now occupies the first place, even essential, in everyday life. Each of us uses a computer to work, to exchange information, to make purchases, etc. Unfortunately, malicious activity targeting computers is steadily increasing and trying to exploit vulnerabilities that are growing in number with ever-increasing complexity. In view of this, the present research has set itself the objective of mending the adequacy (optimization, dynamics and performance) of operating systems to their various deployment environments by emancipating a priori approaches, generally lacking in their capacity. to surpass future needs especially for the correction of security vulnerabilities, focusing on the functionalities of the hardware environment.
Keywords: Approach, Deployment, Dynamics, Performance, QOS, Security, System, kernel, operational, optimization, windows server 2019
Signal performance optimization in the local area network trafic management in the DRC : Models for transmission networks (Published)
The high availability of computer networks is a prerequisite in large companies and service providers. Thus, computer network administrators are called upon to face the various growing challenges related to unscheduled downtime of services; lack of expertise; lack of tools; the complexity of technologies; market consolidation and competition to provide better quality services. It should be remembered that the organization of the networks of telecommunication aims at giving control of the phenomena which occur there, during the treatment of the communications, and more generally of the services which they offer. These phenomena are governed by the randomness of the appearance of the requests, and are studied independently of the choices of technology implemented. They are amenable to the formalism of the calculation of probabilities, and give birth to the notion of traffic, which will play a central role in their apprehension, given that they condition for a large part the effective structure of modern networks. This research specifically examines the problems of optimization of signal performance in traffic management of local area networks of companies in the Democratic Republic of Congo, by presenting the different elements of network traffic theory and quality. Thus demonstrating their impact on the architectures of networks and computer systems, and at the same time introducing the major problems faced by IT network administrators on a daily basis; The main objective of this research is to evaluate the development performance of computer and telecommunications networks according to their applications in the areas of network design, equipment dimensioning, and characterization and quality measurement. Service, and network planning techniques.
Citation: RaphaeL Grevisse Yende ; Sr Tshiela Marie-Alice Nkuna ; Kazadi Pamphile Mulumba ; Ntumba Freddy Katayi ; Kaseka Viviane Katadi ; Musubao Patient Swambi ; Muamba Bernard. Tshiasuma (2022) Signal performance optimization in the local area network trafic management in the DRC : Models for transmission networks. European Journal of Computer Science and Information Technology, Vol.10, No.5, pp.1-23
Keywords: Administration, Entreprise, Modèle, Optimisation, Performance, QOS, RDC., Réseau local, Signal, Trafic, Transmission, Téléinformatique