RESUMO
Recently, orbital angular momentum (OAM) rays passing through free space have attracted the attention of researchers in the field of free-space optical communication systems. Throughout free space, the OAM states are subject to atmospheric turbulence (AT) distortion leading to crosstalk and power discrepancies between states. In this paper, a novel chaotic interleaver is used with low-density parity-check coded OAM-shift keying through an AT channel. Moreover, a convolutional neural network (CNN) is used as an adaptive demodulator to enhance the performance of the wireless optical communication system. The detection process with the conjugate light field method in the presence of chaotic interleaving has a better performance compared to that without chaotic interleaving for different values of propagation distance. Also, the viability of the proposed system is verified by conveying a digital image in the presence of distinctive turbulence conditions with different error correction codes. The impacts of turbulence strength, transmission distance, signal-to-noise ratio (SNR), and CNN parameters and hyperparameters are investigated and taken into consideration. The proposed CNN is chosen with the optimal parameter and hyperparameter values that yield the highest accuracy, utmost mean average precision (MAP), and the largest value of area under curve (AUC) for the different optimizers. The simulation results affirm that the proposed system can achieve better peak SNR values and lower mean square error values in the presence of different AT conditions. By computing accuracy, MAP, and AUC of the proposed system, we realize that the stochastic gradient descent with momentum and the adaptive moment estimation optimizers have better performance compared to the root mean square propagation optimizer.
RESUMO
For high accuracy classification of DNA sequences through Convolutional Neural Networks (CNNs), it is essential to use an efficient sequence representation that can accelerate similarity comparison between DNA sequences. In addition, CNN networks can be improved by avoiding the dimensionality problem associated with multi-layer CNN features. This paper presents a new approach for classification of bacterial DNA sequences based on a custom layer. A CNN is used with Frequency Chaos Game Representation (FCGR) of DNA. The FCGR is adopted as a sequence representation method with a suitable choice of the frequency k-lengthen words occurrence in DNA sequences. The DNA sequence is mapped using FCGR that produces an image of a gene sequence. This sequence displays both local and global patterns. A pre-trained CNN is built for image classification. First, the image is converted to feature maps through convolutional layers. This is sometimes followed by a down-sampling operation that reduces the spatial size of the feature map and removes redundant spatial information using the pooling layers. The Random Projection (RP) with an activation function, which carries data with a decent variety with some randomness, is suggested instead of the pooling layers. The feature reduction is achieved while keeping the high accuracy for classifying bacteria into taxonomic levels. The simulation results show that the proposed CNN based on RP has a trade-off between accuracy score and processing time.
