Semi-supervised SVM with Fuzzy Controlled Cooperation of Biology Related Algorithms

  title={Semi-supervised SVM with Fuzzy Controlled Cooperation of Biology Related Algorithms},
  author={Shakhnaz Akhmedova and Eugene Semenkin and Vladimir Stanovov},
Due to its wide applicability, the problem of semi-supervised classification is attracting increasing attention in machine learning. Semi-Supervised Support Vector Machines (SVM) are based on applying the margin maximization principle to both labelled and unlabelled examples. A new collective bionic algorithm, namely fuzzy controlled cooperation of biology related algorithms (COBRA-f), which solves constrained optimization problems, has been developed for semi-supervised SVM design. Firstly… 

Figures and Tables from this paper

Semi-supervised Data Mining Tool Design with Self-tuning Optimization Techniques
This article presented semi-supervised artificial neural network- (ANN) and support vector machine- (SVM) based classifiers designed by the self-configuring genetic algorithm (SelfCGA) and the fuzzy controlled meta-heuristic approach Co-operation of Biology Related Algorithms (COBRA) and their usefulness is demonstrated.
Success History-Based Position Adaptation in Fuzzy-Controlled Ensemble of Biology-Inspired Algorithms
It was concluded that the proposed modification of the meta-heuristic approach called Co-Operation of Biology-Related Algorithms (COBRA) outperformed other algorithms used in comparison and its usefulness and workability were demonstrated.
Success-History Based Position Adaptation in Co-operation of Biology Related Algorithms
It was established that the fuzzy-controlled COBRA with success-history based position adaptation allows better solutions with the same computational effort to be found.
Self-Training using Selection Network for Semi-supervised Learning
An SSL method called selective self-training (SST), which selectively decides whether to include each unlabeled sample in the training process, is proposed, which not only performs comparable to other conventional SSL algorithms but also can be combined with other SSL algorithms.


How good are fuzzy If-Then classifiers?
  • L. Kuncheva
  • Computer Science
    IEEE Trans. Syst. Man Cybern. Part B
  • 2000
It is shown that if the rule base consists of all possible rules, the fuzzy TSK model is a lookup classifier with hyperbox cells, regardless of the type (shape) of the membership functions used.
Semi-Supervised Support Vector Machines
A general S3VM model is proposed that minimizes both the misclassification error and the function capacity based on all the available data that can be converted to a mixed-integer program and then solved exactly using integer programming.
Semi-supervised Learning in Support Vector Machines 1
In traditional supervised classification, classifiers are trained using feature/label pairs and the classifier performance is measured on unseen test data. In the current Internet age, as the amount
Fuzzy Logic in Control Systems : Fuzzy Logic
  • Computer Science
Fuzzy implication functions, the sentence connectives and and also, compositional operators, inference mechanisms, and other concepts that are closely related to the decisionmaking logic of an FLC are investigated.
Transductive Inference for Text Classification using Support Vector Machines
An analysis of why Transductive Support Vector Machines are well suited for text classi cation is presented, and an algorithm for training TSVMs, handling 10,000 examples and more is proposed.
An Efficient Constraint Handling Method for Genetic Algorithms
A New Metaheuristic Bat-Inspired Algorithm
This paper proposes a new metaheuristic method, the Bat Algorithm, based on the echolocation behaviour of bats, and intends to combine the advantages of existing algorithms into the new bat algorithm.
Firefly Algorithms for Multimodal Optimization
Simulations and results indicate that the proposed firefly algorithm is superior to existing metaheuristic algorithms.
Introduction to Evolutionary Computation (lesson & activity)
Students learn about the field of evolutionary computation, which applies the principles of natural selection to solve engineering design problems, and use the digital evolution software, Avida-ED, to engineer digital organisms and evolve digital organisms with the goal of producing organism with the highest fitness values in a particular environment.
Building Better Test Functions
Basic guidelines for developing test suites for evolutionary algorithms and common test functions in terms of these guidelines are examined, which address speciic issues relevant to comparative studies of evolutionary algorithms.