| dc.contributor.author | Bagheri, Ebrahim | |
| dc.date.accessioned | 2010-07-14T18:00:33Z | |
| dc.date.available | 2010-07-14T18:00:33Z | |
| dc.date.issued | 2010-07-14T18:00:33Z | |
| dc.identifier.uri | http://hdl.handle.net/2149/2653 | |
| dc.description | I attended the Canadian AI conference between May 30, 2010 – June 2, 2010. On May 30, 2010, I jointly with Marina Sokolova from the Children Hospital of Eastern Ontario, co-chaired the Canadian AI graduate students symposium. The symposium had originally attracted about 23 submissions and had an acceptance rate of around 25%. There were about 30 participants from around Canada along with 5 professor panelists and 2 researchers from industry. The organization of this symposium both from an academic perspective and also logistics was done by myself and Marina. The symposium was a great success in terms of both the number of attendance and the quality of the work presented at the symposium.
On the May 31, 2010, I presented my paper titled “Automatic Discovery of Network Applications: A hybrid Approach”. There were interesting issues raised during the Q&A period that can lead to the betterment of the work in the future including how the network packets were labeled before they were used in the classification algorithm and also about the possible applications of our work for network planning and alert correlation. | en |
| dc.description.abstract | Automatic discovery of network applications is a very challenging task which has received a lot of attentions due to its importance in many areas such as network security, QoS provisioning, and network management. In this paper, we propose an online hybrid mechanism for the classification of network
flows, in which we employ a signature-based classifier in the first level, and then using the weighted unigram model we improve the performance of the system by labeling the unknown portion. Our evaluation on two real networks shows between 5% and 9% performance improvement applying the genetic algorithm based scheme to find the appropriate weights for the unigram model. | en |
| dc.language.iso | en | en |
| dc.relation.ispartofseries | 92.927.G1196; | |
| dc.subject | Automatic Discover | en |
| dc.subject | Hybrid Mechanism | en |
| dc.subject | Network Security | en |
| dc.subject | Unigram Model | en |
| dc.title | Automatic Discovery of Network Applications: A hybrid Approach | en |
| dc.type | Presentation | en |
