Data mining approach for predicting the daily Internet data traffic of a smart university
Abstract Internet traffic measurement and analysis generate dataset that are indicators of usage trends, and such dataset can be used for traffic prediction via various statistical analyses. In this study, an extensive analysis was carried out on the daily internet traffic data generated from Januar...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2019-02-01
|
| Series: | Journal of Big Data |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s40537-019-0176-5 |
| _version_ | 1818041425482219520 |
|---|---|
| author | Aderibigbe Israel Adekitan Jeremiah Abolade Olamilekan Shobayo |
| author_facet | Aderibigbe Israel Adekitan Jeremiah Abolade Olamilekan Shobayo |
| author_sort | Aderibigbe Israel Adekitan |
| collection | DOAJ |
| description | Abstract Internet traffic measurement and analysis generate dataset that are indicators of usage trends, and such dataset can be used for traffic prediction via various statistical analyses. In this study, an extensive analysis was carried out on the daily internet traffic data generated from January to December, 2017 in a smart university in Nigeria. The dataset analysed contains seven key features: the month, the week, the day of the week, the daily IP traffic for the previous day, the average daily IP traffic for the two previous days, the traffic status classification (TSC) for the download and the TSC for the upload internet traffic data. The data mining analysis was performed using four learning algorithms: the Decision Tree, the Tree Ensemble, the Random Forest, and the Naïve Bayes Algorithm on KNIME (Konstanz Information Miner) data mining application and kNN, Neural Network, Random Forest, Naïve Bayes and CN2 Rule Inducer algorithms on the Orange platform. A comparative performance analysis for the models is presented using the confusion matrix, Cohen’s Kappa value, the accuracy of each model, Area under ROC Curve, etc. A minimum accuracy of 55.66% was observed for both the upload and the download IP data on the KNIME platform while minimum accuracies of 57.3% and 51.4% respectively were observed on the Orange platform. |
| first_indexed | 2024-12-10T08:30:13Z |
| format | Article |
| id | doaj.art-8dd978802c36423ab9c9b051d6d08312 |
| institution | Directory Open Access Journal |
| issn | 2196-1115 |
| language | English |
| last_indexed | 2024-12-10T08:30:13Z |
| publishDate | 2019-02-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Big Data |
| spelling | doaj.art-8dd978802c36423ab9c9b051d6d083122022-12-22T01:56:07ZengSpringerOpenJournal of Big Data2196-11152019-02-016112310.1186/s40537-019-0176-5Data mining approach for predicting the daily Internet data traffic of a smart universityAderibigbe Israel Adekitan0Jeremiah Abolade1Olamilekan Shobayo2Department of Electrical and Information Engineering, Covenant UniversityDepartment of Electrical and Information Engineering, Covenant UniversityDepartment of Electrical and Information Engineering, Covenant UniversityAbstract Internet traffic measurement and analysis generate dataset that are indicators of usage trends, and such dataset can be used for traffic prediction via various statistical analyses. In this study, an extensive analysis was carried out on the daily internet traffic data generated from January to December, 2017 in a smart university in Nigeria. The dataset analysed contains seven key features: the month, the week, the day of the week, the daily IP traffic for the previous day, the average daily IP traffic for the two previous days, the traffic status classification (TSC) for the download and the TSC for the upload internet traffic data. The data mining analysis was performed using four learning algorithms: the Decision Tree, the Tree Ensemble, the Random Forest, and the Naïve Bayes Algorithm on KNIME (Konstanz Information Miner) data mining application and kNN, Neural Network, Random Forest, Naïve Bayes and CN2 Rule Inducer algorithms on the Orange platform. A comparative performance analysis for the models is presented using the confusion matrix, Cohen’s Kappa value, the accuracy of each model, Area under ROC Curve, etc. A minimum accuracy of 55.66% was observed for both the upload and the download IP data on the KNIME platform while minimum accuracies of 57.3% and 51.4% respectively were observed on the Orange platform.http://link.springer.com/article/10.1186/s40537-019-0176-5Machine learningData miningNigerian universityInternet data trafficNetwork operations monitoringPattern recognition models |
| spellingShingle | Aderibigbe Israel Adekitan Jeremiah Abolade Olamilekan Shobayo Data mining approach for predicting the daily Internet data traffic of a smart university Journal of Big Data Machine learning Data mining Nigerian university Internet data traffic Network operations monitoring Pattern recognition models |
| title | Data mining approach for predicting the daily Internet data traffic of a smart university |
| title_full | Data mining approach for predicting the daily Internet data traffic of a smart university |
| title_fullStr | Data mining approach for predicting the daily Internet data traffic of a smart university |
| title_full_unstemmed | Data mining approach for predicting the daily Internet data traffic of a smart university |
| title_short | Data mining approach for predicting the daily Internet data traffic of a smart university |
| title_sort | data mining approach for predicting the daily internet data traffic of a smart university |
| topic | Machine learning Data mining Nigerian university Internet data traffic Network operations monitoring Pattern recognition models |
| url | http://link.springer.com/article/10.1186/s40537-019-0176-5 |
| work_keys_str_mv | AT aderibigbeisraeladekitan dataminingapproachforpredictingthedailyinternetdatatrafficofasmartuniversity AT jeremiahabolade dataminingapproachforpredictingthedailyinternetdatatrafficofasmartuniversity AT olamilekanshobayo dataminingapproachforpredictingthedailyinternetdatatrafficofasmartuniversity |