Migration threshold tuning in the deterministic dendritic cell algorithm

Greensmith, Julie

Abstract

In this paper we explore the sensitivity of the migration threshold parameter in the Deterministic Dendritic Cell Algorithm (dDCA), one of the four main types of Artificial Immune System. This is with a view to the future construction of a DCA augmented with Deep Learning. Learning mechanisms are absent in the original DCA although tuneable parameters are identified which have the potential to be learned over time. Proposed in this paper is the necessary first step towards placing the dDCA within the context of Deep Learning by understanding the maximum migration threshold parameter. Tuning the maximum migration threshold determines the results of the signal processing within the algorithm, and here we explore a range of values. We use the previously explored Ping Scan Dataset to evaluate the influence of this key parameter. Results indicate a close relationship between the maximum migration threshold and the signal values of given datasets. We propose in future to ascertain an optimisation function which would learn the maximum migration threshold during run time. This work represents a necessary step towards producing a DCA which automatically interfaces with any given anomaly detection dataset.

Citation

Greensmith, J. (2019). Migration threshold tuning in the deterministic dendritic cell algorithm. In C. Martín-Vide, G. Pond, & M. A. Vega-Rodríguez (Eds.), Theory and Practice of Natural Computing: 8th International Conference, TPNC 2019, Kingston, ON, Canada, December 9–11, 2019: proceedings (122-133). Springer. https://doi.org/10.1007/978-3-030-34500-6_8

• Online Publication Date: Nov 22, 2019
• Publication Date: 2019
• Deposit Date: Nov 10, 2020
• Publicly Available Date: Nov 23, 2020
• Publisher: Springer
• Pages: 122-133
• Series Title: Lecture notes in computer science
• Series Number: 11934
• Series ISSN: 0302-9743
• Book Title: Theory and Practice of Natural Computing: 8th International Conference, TPNC 2019, Kingston, ON, Canada, December 9–11, 2019: proceedings
• ISBN: 9783030344993
• DOI: https://doi.org/10.1007/978-3-030-34500-6_8
• Public URL: https://nottingham-repository.worktribe.com/output/3610648
• Publisher URL: https://link.springer.com/chapter/10.1007/978-3-030-34500-6_8
• Additional Information: First Online: 22 November 2019; Conference Acronym: TPNC; Conference Name: International Conference on Theory and Practice of Natural Computing; Conference City: Kingston, ON; Conference Country: Canada; Conference Year: 2019; Conference Start Date: 9 December 2019; Conference End Date: 11 December 2019; Conference Number: 8; Conference ID: tpnc2019; Conference URL: https://tpnc2019.irdta.eu/; Type: Single-blind; Conference Management System: EasyChair; Number of Submissions Sent for Review: 38; Number of Full Papers Accepted: 15; Number of Short Papers Accepted: 2; Acceptance Rate of Full Papers: 39% - The value is computed by the equation "Number of Full Papers Accepted / Number of Submissions Sent for Review * 100" and then rounded to a whole number.; Average Number of Reviews per Paper: 3; Average Number of Papers per Reviewer: 2.1; External Reviewers Involved: Yes
• Contract Date: Sep 6, 2019