The invention discloses a signal detection and estimation method based on a multi-dimensional characteristic neural network, and relates to the technical fields of artificial neural networks and direct sequence spread spectrum (DSSS) communication. According to the method, the presence of a DSSS signal is detected by using a correlation function accumulation method, and the estimation of a PN (Pseudo-Noise) code is finished, namely, a direct spread signal spread spectrum code is detected under the situation of low signal-to-noise ratio based on a multi-dimensional characteristic neural network method. The method comprises the following steps: extracting the multi-dimensional characteristics of a signal (comprising the period of the PN code, the width of a code element, the starting and stopping moments of the synchronization of the PN code and an information code, and the like); periodically segmenting the signal; inputting the segmented signals into the neural network in batches for training; and training and converging the segmented signals through the neural network to detect a spread spectrum sequence. Through adoption of the method, a signal can be detected from noise and a PN sequence of the signal can be estimated in non-cooperative communication through an artificial neural network; and moreover, the network can quickly converge to a sequence or a reverse sequence thereof under the situation of low signal-to-noise ratio.

Signal detection and estimation method based on multi-dimensional characteristic neural network

The invention discloses a high-speed wavelet multi-carrier spread-spectrum communication system and method suitable for a 5G network. The system comprises a plurality of communication devices which are in mutual communication and are arranged in a wireless network. The communication devices comprise the signal emission device and the signal receiving device. The signal emission device comprises a coding unit, a spread-spectrum unit, a carrier modulation unit and a parallel-serial conversion unit which are sequentially connected. The signal receiving device comprises a series-parallel conversion unit, a wavelet filtering unit, a dispreading unit, a data demodulation unit and a decoding unit which are sequentially connected. High adaptability is achieved to a time-frequency selectivity wireless channel. Meanwhile, due to the facts that spreading codes with different lengths are used for corresponding to various wavelet subcarriers with different bandwidths, and the spreading codes with the same length are further arranged, so that multiple choices are achieved, the high-speed wavelet multi-carrier spread-spectrum communication system can obtain more higher data rates than that of a conventional multi-carrier spread-spectrum communication system in which fast Fourier transformation is used, and thus the high-speed wavelet multi-carrier spread-spectrum communication system and method are suitable for the high-speed 5G network.

High-speed wavelet multi-carrier spread-spectrum communication system and method suitable for 5G network

The invention discloses a visible light channel joint balance method based on orthogonal mapping and a probabilistic neural network. The method comprises a transmitting end and a receiving end. Signals are transmitted from the transmitting end to the receiving end through visible light MIMO (Multiple Input Multiple Output) channels. The visible light MIMO channels are multiple input multiple output channels. According to joint balance, preposition balance and postposition balance are combined. According to the method, a joint balance scheme combing a preposition balance technology and a postposition balance technology is employed, namely, the visible light multiple input multiple output channel joint balance method based on the orthogonal mapping and the probabilistic neural network is employed. The interference between the channels of a visible light MIMO communication system can be effectively suppressed and the data transmission reliability is improved.

Visible light channel joint balance method based on orthogonal mapping and probabilistic neural network

The present invention discloses a channel environment adaptive OFDM receiving method based on a neural network. The method comprises the steps of: selecting a plurality of different channel environments to obtain each trained deep neural network; inputting reception frequency domain pilot frequency and local frequency domain pilot frequency for estimation to obtain a noisy channel estimation result, inputting the noisy channel estimation result into a trained main Wiener filtering deep neural network, outputting the main channel estimation result, obtaining each slave channel estimation result, and adding the slave channel estimation results after the slave channel estimation results multiply by a weight to obtain a final channel estimation result; and inputting the final channel estimation result and received frequency domain data to obtain a zero-forcing balance result, inputting the zero-forcing balance result into the trained main and slave balance deep neural networks to obtain the output result of each network and add the output results after the output results multiply by a weight coefficient, and outputting an estimated bit stream after hard decision. The known frequency domain pilot frequency or channel parameters are collected in real time in the actual transmission, and the weight coefficient is dynamically regulated. The channel environment adaptive OFDM receiving method based on the neural network is few in parameter, high in working efficiency and flexible and rapid in online switching.

Channel environment adaptive OFDM receiving method based on neural network

The invention discloses a multiplexer, a de-multiplexer, a multiplexing method and a de-multiplexing method for use in an optical fiber communication system. The multiplex comprises a plurality of orthogonal signal generators which are configured to modulate a plurality of user signals onto a plurality of pairwise orthogonal digital waveform signals generated on the basis of wavelet transform respectively in order to generate a plurality of pairwise orthogonal digital modulation signals, a plurality of digital-to-analog converters which are configured to convert the plurality of digital modulation signals into a plurality of analog signals respectively, and a combiner which is configured to mix the plurality of analog signals into a single signal. Through the equipment and the methods, multiplexing of the plurality of user signals can be realized; each user can use a whole time interval and share a laser of one wavelength without occupying a large quantity of optical fiber frequency resources.

Multiplexer, de-multiplexer, multiplexing method and de-multiplexing method

This invention discloses a small wave packet multi-carrier amplifying-frequency system based on neural net balancer and its controlling method. The system comprises a transmitting end composed of a quad-rature modulator, a copier, an inverse small wave packet conversion with an amplifying frequency code inserted before; a receiving end composed of multi-radial neural net balance, discrete small wave packet conversion, summer, a maximum likelihood tester and quad-rature modulator; after the conversion, inserting amplifying frequency code WH and sub-belt gain factor. The system owes a control switch to control its dislocation to realize using LMS method to renewing weight of multiradial neural net balancer and the communication of the sender and receiver, including channel balance, amplifying frequency, small wave packet multi-carrier adjusting, modulation and ML testing decision.

Xiaodong Zhou

Papers

Wavelet packet multi-carrier spread-spectrum system and control method based on neural net equalizer