logo

Novel applications of Machine Learning to Network Traffic Analysis

PDF Publication Title:

Novel applications of Machine Learning to Network Traffic Analysis ( novel-applications-machine-learning-network-traffic-analysis )

Previous Page View | Next Page View | Return to Search List

Text from PDF Page: 064

In relation with the results reported by the papers, we have presented separate results for all the models investigated in the study. A detailed comparison between the proposed and alternative models is always provided in all papers. Fig. 17. Model of relationships between the main “points of interests” for the papers. All the papers that make up this thesis employ the workflow shown in Fig. 17. Similarly, all papers follow the schema of datasets management presented in Fig. 18. It is very important to mention that all reported results, in all papers, are provided in accordance with Fig. 18, therefore, all results are obtained using a separate test dataset that was never used in the training phase of any of the models that have been part of this research. In Fig. 18 is observed how the original data is split between training and test subsets. The training subset can be further split in a training part and a validation part. This latter division of the training dataset is used when the successive parameters tuning of the model can affect the generalization results if all the validation would be done on the test dataset. This good practice has some limitations, mainly due to the large volume of data required to have the three separated datasets. For this reason, we have not employed a validation dataset. In addition, the validation dataset is mandatory when the parameters tuning is thoroughly done, trying a substantial number of parameter values. In our case, we have done a basic parameter tuning of the algorithms, since we have not had the intention of providing the best possible result, but to make clear the applicability, the possibilities and the good behaviour of the proposed models, and not fitting a final model to be used in an industrial setting. Doctoral Thesis: Novel applications of Machine Learning to NTAP - 62

PDF Image | Novel applications of Machine Learning to Network Traffic Analysis

novel-applications-machine-learning-network-traffic-analysis-064

PDF Search Title:

Novel applications of Machine Learning to Network Traffic Analysis

Original File Name Searched:

456453_1175348.pdf

DIY PDF Search: Google It | Yahoo | Bing

Cruise Ship Reviews | Luxury Resort | Jet | Yacht | and Travel Tech More Info

Cruising Review Topics and Articles More Info

Software based on Filemaker for the travel industry More Info

The Burgenstock Resort: Reviews on CruisingReview website... More Info

Resort Reviews: World Class resorts... More Info

The Riffelalp Resort: Reviews on CruisingReview website... More Info

CONTACT TEL: 608-238-6001 Email: greg@cruisingreview.com | RSS | AMP