Ant Based Semi-supervised Classification

Self-Trained LMT for Semisupervised Learning

“…Subsequently, we compared the proposed method with other state-of-the-art algorithms into the KEEL tool [39] such as self-training (C45) [7], self-training (SMO) [40], self-training (NN) [32], SETRED [13], cotraining (C45) [14], cotraining (SMO) [41], democratic-co [27], tri-training (C45) [41], tri-training (SMO) [25], tri-training (NN) [41], DE-tri-training (C45), DE-tri-training (SMO) [42], Co-Forest [6], Rasco (C45) [23], CLCC [29], APSSC [30], SNNRCE [31], Rel-Rasco (NB) [24], ADE-Co-Forest [43], cobagging (C45) [22], and cobagging (SMO) [44]. For all tested algorithms, the default parameters of KEEL were used.…”

“…This algorithm tries to resolve problems that occur when the provided datasets consist of a few labeled training data and facilitates situations in which the labeling process may lead to misclassified instances. Another algorithm which uses self-training scheme is aggregation pheromone density based semisupervised classification (APSSC) algorithm [30]. In this work, the corresponding property was used, as the name of algorithm defines, found in natural behavior of real ants.…”

Modeling biometric template update with Ant Colony Optimization

“…Each a i j ∈ C i emits pheromones at its neighborhood, and its intensity decreases with the distance. This is modeled -see [13,5] -by a Gaussian distribution: The effect of pheromone density on a k , -located atx k -at iteration t + 1 due to a i j ∈ C i -located atx i j is given by…”

“…When new input data is captured -a new ant in our representation -it will be influenced by the deposited phermonones related to the population of both "genuine" and "impostor" colonies. A membership coefficient is then computed [5] for the new ant to join the colony with the highest attraction potential, thus contributing with its pheromones to attract other new ants. As for the biometrics template update process, if the captured data is classified as belonging to a genuine user, the corresponding template will be updated accordingly.…”

“…In this paper, we present a novel template update algorithm based on Aggregation Pheromone Density Based Semi-Supervised Classification (APSSC), recently proposed by Halder et al [5]. APSSC is a semi-supervised classification algorithm based on Aggregation Pheromone Systems (APS) [13] -an extension of Ant Colony Optimization (ACO) [3] -a computational algorithm modeled on the behavior of social insects colonies, e.g., ants.…”