The research presented in this manuscript proposes a novel Harris Hawks optimization algorithm with practical application for evolving convolutional neural network architecture to classify various grades of brain tumor using magnetic resonance imaging. The proposed improved Harris Hawks optimization method, which belongs to the group of swarm intelligence metaheuristics, further improves the exploration and exploitation abilities of the basic algorithm by incorporating a chaotic population initialization and local search, along with a replacement strategy based on the quasi-reflection-based learning procedure. The proposed method was first evaluated on 10 recent CEC2019 benchmarks and the achieved results are compared with the ones generated by the basic algorithm, as well as with results of other state-of-the-art approaches that were tested under the same experimental conditions. In subsequent empirical research, the proposed method was adapted and applied for a practical challenge of convolutional neural network design. The evolved network structures were validated against two datasets that contain images of a healthy brain and brain with tumors. The first dataset comprises well-known IXI and cancer imagining archive images, while the second dataset consists of axial T1-weighted brain tumor images, as proposed in one recently published study in the Q1 journal. After performing data augmentation, the first dataset encompasses 8.000 healthy and 8.000 brain tumor images with grades I, II, III, and IV and the second dataset includes 4.908 images with Glioma, Meningioma, and Pituitary, with 1.636 images belonging to each tumor class. The swarm intelligence-driven convolutional neural network approach was evaluated and compared to other, similar methods and achieved a superior performance. The obtained accuracy was over 95% in all conducted experiments. Based on the established results, it is reasonable to conclude that the proposed approach could be used to develop networks that can assist doctors in diagnostics and help in the early detection of brain tumors.

The learning process is one of the most difficult problems in artificial neural networks. This process goal is to find the appropriate values for connection weights and biases and has a direct influence on the neural network classification and prediction accuracy. Since the search space is huge, traditional optimization techniques are not suitable as they are prone to slow convergence and getting trapped in the local optima. In this paper, an enhanced harris hawks optimization algorithm is proposed to address the task of neural networks training. Conducted experiments include 2 well-known classification benchmark datasets to evaluate the performance of the proposed method. The obtained results indicate that the devised algorithm has promising performance, as that it is able to achieve better overall results than other state-of-the-art metaheuristics that were taken into account in comparative analysis, in terms of classification accuracy and converging speed.

The learning process is one of the most difficult problems in the artificial neural networks. This task refers to the challenge of finding the appropriate values for connection weights and biases and directly influences the neural network classification accuracy. Since the search space is enormous, traditional optimization techniques are not suitable as they are prone to slow converging speed and getting trapped to the local optima. In this paper, an enhanced seagull optimization algorithm was proposed to address the task of neural networks training. Conducted experiments included ten binary classification benchmark datasets to evaluate the performance of proposed enhanced seagull optimization algorithm. The obtained results indicate that the proposed method has promising performance, as it was able to achieve better overall results than other state-of-the-art algorithms that were included in the comparative analysis, in terms of classification accuracy and converging speed.

No abstract

No abstract