Self-adjusting binary search trees
Journal of the ACM (JACM)
C4.5: programs for machine learning
C4.5: programs for machine learning
Data mining: practical machine learning tools and techniques with Java implementations
Data mining: practical machine learning tools and techniques with Java implementations
Data Mining, Cookbook: Modeling Data for Marketing, Risk and Customer Relationship Management
Data Mining, Cookbook: Modeling Data for Marketing, Risk and Customer Relationship Management
Machine Learning
Data Mining: Concepts and Techniques
Data Mining: Concepts and Techniques
| Hi-index | 0.00 |
The paper addresses the problem of minimizing response times for an e-Learning platform. The activities that are performed within Tesys [1] e-Learning platform require sometimes heavy data traffic between platform itself and users. That is why, within the platform there was implemented a data traffic monitoring mechanism at byte level. The levels of data traffic are monitored and constitute the raw data within the analysis process. The analysis process uses state of the art machine learning algorithms in order to produce knowledge. This expertise is further used within the platform to cache recently used data, using the principle of temporal locality of data. Experiments showed the factors that influence the response times are: granularity of traffic monitoring, employed learning algorithm and the data structure used for caching. The results are promising in the way that after prototype implementation of analysis process in the form of an Expertise Module, the response time decreased. The main advantage of Expertise Module is that it virtually introduces insignificant delays since all analysis is performed off-line.