Improved Reptile Search Optimization Algorithm: Application on Regression and Classification Problems

Exciting news! Our team has just published a new article titled "Improved Reptile Search Optimization Algorithm: Application on Regression and Classification Problems" in the journal of Applied Sciences. I am grateful to all my co-authors for their incredible contributions!

• Khan, Muhammad Kamran, Muhammad Hamza Zafar, Saad Rashid, Majad Mansoor, Syed Kumayl Raza Moosavi, and Filippo Sanfilippo. "Improved Reptile Search Optimization Algorithm: Application on Regression and Classification Problems." Applied Sciences 13, no. 2 (2023): 945.

In this study, the authors propose an improved reptile search algorithm (IRSA) that solves the drawbacks of the original RSA, including sluggish convergence speed, high computational complexity, and local minima trapping. A number of test functions were used to evaluate the IRSA, and it was found to have quick convergence, low time complexity, and effective global search. Additionally, we used the IRSA to train hyperparameters for a multi-layer perceptron neural network and a radial basis function neural network and achieved superior classification and prediction capabilities. Do check it out: https://www.mdpi.com/2076-3417/13/2/945