Parallel Extreme Learning Machines Based on Frequency Multiplexing

In a recent work, we reported on an Extreme Learning Machine (ELM) implemented in a photonic system based on frequency multiplexing, where each wavelength of the light encodes a different neuron state. In the present work, we experimentally demonstrate the parallelization potentialities of this approach. We show that multiple frequency combs centered on different frequencies can copropagate in the same system, resulting in either multiple independent ELMs executed in parallel on the same substrate or a single ELM with an increased number of neurons. We experimentally tested the performances of both these operation modes on several classification tasks, employing up to three different light sources, each of which generates an independent frequency comb. We also numerically evaluated the performances of the system in configurations containing up to 15 different light sources.

Improved Efficiency of Data Transmission in Wireless Communication Systems with Orthogonal Frequency Multiplexing

The active introduction of Orthogonal Frequency Division Multiplexing (OFDM) technology is now beginning to be widely used in wireless transmission systems, television, radio communication, and radio broadcasting. The efficiency of using a dedicated frequency band at a constant high transmission rate allows you to combat interference arising from the transmission of a useful information on the radio channel. A method of improving quality of information transmission in communication systems with orthogonal frequency multiplexing is described. It is shown that with an increase in the number of receiving and transmitting antennas, the noise immunity increases significantly. An experiment was carried out to change the number of receiving-transmitting antennas and the signal-to-noise ratio, and the dependence of the appearance of an error on the number of transmitting antennas was obtained. The work investigated the software model of MIMO OFDM (modulators and demodulators). As a result of the analysis, the dependence of the appearance of the error frequency on the probability of the error was obtained. This showed that the use of OFDM and MIMO places increased demands on channel estimation.

The effect of the carrier frequency estimation erroron the quality of receiving signals with OFDM modulation.

The article discusses the features and main stages of the formation of OFDM signals. Analytical models of signals with orthogonal frequency multiplexing in the time and frequency domains are presented in the absence and presence of a mismatch in the carrier frequency of the transmitter and receiver. The analysis of the models allowed us to identify the parameters that affect the frequency and phase spectrum of signals. The study was carried out and the dependences of the reception quality of OFDM signals (the ratio of signal power to the power of equivalent noise) on the normalized error of the carrier frequency estimation were obtained.

A Multi-Image Encryption Based on Sinusoidal Coding Frequency Multiplexing and Deep Learning

Multi-image encryption technology is a vital branch of optical encryption technology. The traditional encryption method can only encrypt a small number of images, which greatly restricts its application in practice. In this paper, a new multi-image encryption method based on sinusoidal stripe coding frequency multiplexing and deep learning is proposed to realize the encryption of a greater number of images. In the process of encryption, several images are grouped, and each image in each group is first encoded with a random matrix and then modulated with a specific sinusoidal stripe; therefore, the dominant frequency of each group of images can be separated in the Fourier frequency domain. Each group is superimposed and scrambled to generate the final ciphertext. In the process of decryption, deep learning is used to improve the quality of decrypted image and the decryption speed. Specifically, the obtained ciphertext can be sent into the trained neural network and then the plaintext image can be reconstructed directly. Experimental analysis shows that when 32 images are encrypted, the CC of the decrypted result can reach more than 0.99. The efficiency of the proposed encryption method is proved in terms of histogram analysis, adjacent pixels correlation analysis, anti-noise attack analysis and resistance to occlusion attacks analysis. The encryption method has the advantages of large amount of information, good robustness and fast decryption speed.