University of Kent - Home

• Contact
• Maps
• Departments

Navigation menu

School of Computing

• Home
• Teaching
• Research

Studying

• Undergraduate courses
• Postgraduate courses

Activities

• News
• National & International services
• Seminars
• Schools Liaison
• Outreach
• Kent IT Clinic
• Kent enterprise

Local users

• For current students and staff
• Systems Support

About us

• Contacts - How to find us
• People
  • Staff
  • Research Students
  • Undergraduate (local)
  • Taught Postgraduate (local)
  • Former Staff
  • Former Research Students
  • Student portal (univ)

Search

School of Computing

Search:

Publications

My publications are available from the Computer Science department publications repository.

Research Interests

I belong to the following research groups:

• Computational Intelligence Group

My main research interests involve bio-inspired algorithms, bioinformatics, and data mining and knowledge discovery. I am interested in the creation of new ant colony optimisation algorithms for data mining. I am also working on combining ideas from software engineering with automatic programming techniques, more specifically genetic programming.

I am currently working in the EPSRC-funded project 'Refactoring and Neutrality in Genetic Programming'. The main goal of the project is to introduce refactoring techniques commonly applied in software engineering to genetic programming methods.

Software

I have implemented a modular open-source ant colony optimisation framework to facilitate the implementation of ant colony classification algorithms, called Myra (hosted at sourceforge). It provides an intuitive GUI and command-line interface, and also the implementation of Ant-Miner, cAnt-Miner, hAnt-Miner, hmAnt-Miner and cAnt-Miner_PB algorithms. Below is a list of publications related to these algorithms.

cAnt-Miner_PB

The cAnt-Miner_PB implements a new sequential covering strategy, where the order of rules is implicitly encoded as pheromone values and the search is guided by the quality of a candidate list of rules, to mitigate the problem of rule interaction.

• F.E.B. Otero, A.A. Freitas and C.G. Johnson. A New Sequential Covering Strategy for Inducing Classification Rules with Ant Colony Algorithms. To appear in IEEE Transactions on Evolutionary Computation, 2012. DOI: 10.1109/TEVC.2012.2185846 (pre-print pdf) © IEEE

hmAnt-Miner

The hmAnt-Miner is an ACO classification algorithm tailored for the hierarchical multi-label problem of protein function prediction, but can also be applied to other hierarchical multi-label problems.

• F.E.B. Otero, A.A. Freitas and C.G. Johnson. A hierarchical multi-label classification ant colony algorithm for protein function prediction. In: Memetic Computing, Volume 2, Number 3, pp. 165-181, DOI: 10.1007/s12293-010-0045-4. Springer, 2010. (pre-print pdf)

hAnt-Miner

The hAnt-Miner is a hierarchical classification ACO algorithm, which employs two colonies: one to create the antecedent of a rule and the other to create the consequent of the rule.

• F.E.B. Otero, A.A. Freitas and C.G. Johnson. A hierarchical classification ant colony algorithm for predicting gene ontology terms. In: Proceedings of the 7th European Conference on Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics (EvoBio 2009), Lecture Notes in Computer Science 5483, pp. 339-357. Springer, 2009. (pre-print pdf)

cAnt-Miner

The cAnt-Miner is an extension of the Ant-Miner algorithm that copes with continuous attributes directly, which incorporates an entropy-based discretization method in order to cope with continuous attributes during the rule construction process.

• F.E.B. Otero, A.A. Freitas and C.G. Johnson. Handling continuous attributes in ant colony classification algorithms. In: Proceedings of the 2009 IEEE Symposium on Computational Intelligence in Data Mining (CIDM 2009), pp. 225-231. IEEE, 2009. (pre-print pdf)


• F.E.B. Otero, A.A. Freitas and C.G. Johnson. cAnt-Miner: an ant colony classification algorithm to cope with continuous attributes. In: Ant Colony Optimization and Swarm Intelligence (Proc. ANTS 2008), Lecture Notes in Computer Science 5217, pp. 48-59. Springer, 2008. (pre-print pdf)

Background

I got my PhD in Computer Science from the University of Kent in 2010, doing research on ant colony optimisation (ACO) algorithms for data mining, in particular the creation of ACO algorithms for the bioinformatics problem of predicting protein functions.