Training artificial neural networks using self-organizing migrating algorithm for skin segmentation.

This study presents an application of the self-organizing migrating algorithm (SOMA) to train artificial neural networks for skin segmentation tasks. We compare the performance of SOMA with popular gradient-based optimization methods such as ADAM and SGDM, as well as with another evolutionary algorithm, differential evolution (DE). Experiments are conducted on the skin dataset, which consists of 245,057 samples with skin and non-skin labels.

Crossmixed convolutional neural network for digital speech recognition.

Digital speech recognition is a challenging problem that requires the ability to learn complex signal characteristics such as frequency, pitch, intensity, timbre, and melody, which traditional methods often face issues in recognizing. This article introduces three solutions based on convolutional neural networks (CNN) to solve the problem: 1D-CNN is designed to learn directly from digital data; 2DS-CNN and 2DM-CNN have a more complex architecture, transferring raw waveform into transformed images using Fourier transform to learn essential features. Experimental results on four large data sets, containing 30,000 samples for each, show that the three proposed models achieve superior performance compared to well-known models such as GoogLeNet and AlexNet, with the best accuracy of 95.

Secrecy Outage Probability of a NOMA Scheme and Impact Imperfect Channel State Information in Underlay Cooperative Cognitive Networks.

Security performance and the impact of imperfect channel state information (CSI) in underlay cooperative cognitive networks (UCCN) is investigated in this paper. In the proposed scheme, relay R uses non-orthogonal multiple access (NOMA) technology to transfer messages e 1 , e 2 from the source node S to User 1 (U 1 ) and User 2 (U 2 ), respectively. An eavesdropper (E) is also proposed to wiretap the messages of U 1 and U 2 .