Seung-Yeon Hwang¹, Jeong-Joon Kim^2,*

CMC-Computers, Materials & Continua, Vol.75, No.2, pp. 3553-3569, 2023, DOI:10.32604/cmc.2023.037028

Abstract Recently, deep learning has achieved remarkable results in fields that require human cognitive ability, learning ability, and reasoning ability. Activation functions are very important because they provide the ability of artificial neural networks to learn complex patterns through nonlinearity. Various activation functions are being studied to solve problems such as vanishing gradients and dying nodes that may occur in the deep learning process. However, it takes a lot of time and effort for researchers to use the existing activation function in their research. Therefore, in this paper, we propose a universal activation function (UA) so that researchers can easily create… More >

Doaa Sami Khafaga¹, El-Sayed M. El-kenawy^2,3, Faten Khalid Karim^1,*, Mostafa Abotaleb⁴, Abdelhameed Ibrahim⁵, Abdelaziz A. Abdelhamid^6,7, D. L. Elsheweikh⁸

CMC-Computers, Materials & Continua, Vol.74, No.2, pp. 4531-4545, 2023, DOI:10.32604/cmc.2023.033042

Abstract Selecting the most relevant subset of features from a dataset is a vital step in data mining and machine learning. Each feature in a dataset has 2ⁿ possible subsets, making it challenging to select the optimum collection of features using typical methods. As a result, a new metaheuristics-based feature selection method based on the dipper-throated and grey-wolf optimization (DTO-GW) algorithms has been developed in this research. Instability can result when the selection of features is subject to metaheuristics, which can lead to a wide range of results. Thus, we adopted hybrid optimization in our method of optimizing, which allowed us… More >

Doaa Sami Khafaga¹, El-Sayed M. El-kenawy², Fadwa Alrowais^1,*, Sunil Kumar³, Abdelhameed Ibrahim⁴, Abdelaziz A. Abdelhamid^5,6

CMC-Computers, Materials & Continua, Vol.74, No.2, pp. 4027-4041, 2023, DOI:10.32604/cmc.2023.033039

Abstract In data mining and machine learning, feature selection is a critical part of the process of selecting the optimal subset of features based on the target data. There are 2ⁿ potential feature subsets for every n features in a dataset, making it difficult to pick the best set of features using standard approaches. Consequently, in this research, a new metaheuristics-based feature selection technique based on an adaptive squirrel search optimization algorithm (ASSOA) has been proposed. When using metaheuristics to pick features, it is common for the selection of features to vary across runs, which can lead to instability. Because of… More >