O
Omid Tarkhaneh
Researcher at University of Tabriz
Publications - 10
Citations - 218
Omid Tarkhaneh is an academic researcher from University of Tabriz. The author has contributed to research in topics: Evolutionary algorithm & Cluster analysis. The author has an hindex of 5, co-authored 9 publications receiving 89 citations. Previous affiliations of Omid Tarkhaneh include Azarbaijan Shahid Madani University.
Papers
More filters
Journal ArticleDOI
An adaptive differential evolution algorithm to optimal multi-level thresholding for MRI brain image segmentation
Omid Tarkhaneh,Haifeng Shen +1 more
TL;DR: This paper proposes a DE solution that achieves a good balance between exploration and exploitation through a new adaptive approach and new mutation strategies, and experimentally compares the proposed DE algorithm, referred to as Adaptive Differential Evolution with Levy Distribution (ALDE), against three DE benchmark algorithms on T2 weighted MRI brain images.
Journal ArticleDOI
A novel wrapper-based feature subset selection method using modified binary differential evolution algorithm
TL;DR: A Modified Differential Evolution approach to Feature Selection (MDEFS) is proposed by utilizing two new mutation strategies to create a feasible balance between exploration and exploitation and maintain the classification performance in an acceptable range concerning both the number of features and accuracy.
Journal ArticleDOI
Training of feedforward neural networks for data classification using hybrid particle swarm optimization, Mantegna Lévy flight and neighborhood search
Omid Tarkhaneh,Haifeng Shen +1 more
TL;DR: A new evolutionary training algorithm referred to as LPSONS is proposed, which combines the velocity operators in Particle Swarm Optimization (PSO) with Mantegna Lévy distribution to produce more diverse solutions by dividing the population and generation between different sections of the algorithm.
Journal ArticleDOI
An Efficient Hybrid Algorithm using Cuckoo Search and Differential Evolution for Data Clustering
TL;DR: This paper proposes hybrid approach for data clustering using cuckoo search and differential evolution algorithms and shows that the proposed algorithm has ability in obtaining better results in terms of Convergence Speed, Accuracy, and also reducing number of functional evaluation.
Proceedings ArticleDOI
Flower Image Classification Using Deep Convolutional Neural Network
TL;DR: In this article, the authors used the transfer learning approach employing DenseNet121 architecture to classify various species of oxford-102 flowers dataset and achieved an accuracy of 98.6% for 50 epochs.