Khunkitti, Akharin

Loading...
Thumbnail Image
Preferred name
Khunkitti, Akharin
Alternative Name
Khunkitti, A.
Main Affiliation
Email
akharin.kh@kmitl.ac.th

Settings

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    A packet classification's algorithm: Bitmap intersection lookup using cache
    (2010-05-28)
    Choorat, Thapana
    ;
    Khunkitti, Akharin
    Now, internet is a very large size network. The internet is a packet switched network offers best-effort service, not guarantee packet that was sent. That has not enough for user's requirements. Router provide different qualities of service to different application such Visual Private Network (VPN), Quality of Service (QOS), Distribute Firewall. Each service needs router to determine packet belonging to different flows. Thus router needs mechanisms for that. Example admission control, resource reservation, per-flow queuing, all of mechanisms needs tool to distinguish packet belong to different flows, so packet classification become a very importance tool. Therefore, researchers have proposed variety of algorithms each type suitable for different application and have different advantage and disadvantage. In this paper propose packet classification's algorithm, algorithm uses cache concept to increase performance, called "Bitmap Intersection Lookup Using Cache". ©2010 IEEE.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    A rule-based training for artificial neural network packet filtering firewall
    (2019-11-01)
    Khunkitti, Akharin
    ;
    Chongsujjatham, Ponsuda
    The Artificial Neural Network has been used in many network applications, including firewalls. Training process of neural network is very important to define the intelligence of the systems. Many artificial neural network firewalls used direct network packets for training process, which may be difficult to get training samples and may not follow their firewall's policies. This research work proposes a rule-based training for artificial neural network packet filtering firewall. The developed neural network model is trained by generating samples from legacy firewall ruleset. Each rule has been converted to random training samples. All firewall's rules are used to generate the training sample data, rule by rule. The accuracy results show high accuracy with some behavior studies. The number of samples per rule, number of rules and rule style, including default rule and rule-scope effects, have been studied for the best accuracy results. This study also concludes the styles of firewall ruleset for the best accuracy of the proposed system.