scholarly journals Blind separation of PCMA signals based on neural network

2018 ◽  
Vol 173 ◽  
pp. 03045 ◽  
Author(s):  
WEI Chi ◽  
PENG Hua ◽  
QIU Zeyu
Keyword(s):  
Neural Network ◽  
Frequency Spectrum ◽  
Multiple Access ◽  
Single Channel ◽  
Blind Separation ◽  
Output Data ◽  
Time Frequency ◽  
Characteristic Data ◽  
Lower Complexity ◽  
Separation Model

For paired carrier multiple access (PCMA) signals, a new single-channel blind separation on neural network was proposed. Firstly, the sample waveforms (three symbols) which contains different bit information are constructed, secondly, the time-frequency spectrum of each sample under the different influences of the trailing symbols is Intercepted, finally, the characteristic data of the spectrum as the input data, and the two-bit sequence in each sample as the output data to be trained, network trains these data repeatedly to complete the construction of separation model. The receiver carries on window truncation to the time-frequency spectrum of PCMA signal, neural network recognize the characteristic data of these spectrums to realizes the separation of bit sequences. Experimental results show that this algorithm has lower complexity than PSP algorithm, and the accuracy of it is close to PSP algorithm (L=5).

scholarly journals Blind separation of asymmetric signals based on Synchrosqueezing Wavelet Transform

2018 ◽  
Vol 232 ◽  
pp. 01050
Author(s):  
Chuang Peng ◽  
Xiaojing Yang ◽  
Yu Zhang
Keyword(s):  
Wavelet Transform ◽  
Single Channel ◽  
Satellite Communications ◽  
Signal Interference ◽  
Blind Separation ◽  
Mixed Signal ◽  
Time Frequency ◽  
Strong Signal ◽  
Signal Demodulation ◽  
Better Than

A blind separation algorithm based on synchronous squeezing wavelet transform is proposed to solve the blind separation problem of single channel asymmetric signals in satellite communications. First, the algorithm is used to synchronize the strong signal. Then, the signal time-frequency curve is extracted by synchronous extrusion wavelet transform. Finally, the weak signal interference is filtered out from the mixed signal except the noise and the main frequency of the strong signal. Therefore, the ber of the strong signal demodulation is reduced. The algorithm has the characteristics of blind separation of single channel asymmetric signals without prior information sequence sent by cooperative communicators. The simulation results show that the performance of strong signal demodulation error is better than that of mixed signal direct hard decision.

scholarly journals Enhanced NOMA System Using Adaptive Coding and Modulation Based on LSTM Neural Network Channel Estimation

2019 ◽  
Vol 9 (15) ◽  
pp. 3022 ◽  
Author(s):  
AbdelMoniem ◽  
Gasser ◽  
El-Mahallawy ◽  
Fakhr ◽  
Soliman
Keyword(s):  
Neural Network ◽  
Channel Estimation ◽  
Multiple Access ◽  
Short Term Memory ◽  
Power Coefficient ◽  
Modulation Scheme ◽  
Channel Fading ◽  
Adaptive Coding ◽  
Time Frequency ◽  
Shift Keying

Non-orthogonal multiple access (NOMA) is the technique proposed for multiple access in the fifth generation (5G) cellular network. In NOMA, different users are allocated different power levels and are served using the same time/frequency resource blocks (RBs). The main challenges in existing NOMA systems are the limited channel feedback and the difficulty of merging it with advanced adaptive coding and modulation schemes. Unlike formerly proposed solutions, in this paper, we propose an effective channel estimation (CE) algorithm based on the long-short term memory (LSTM) neural network. The LSTM has the advantage of adapting dynamically to the behavior of the fluctuating channel state. On average, the use of LSTM results in a 10% lower outage probability and a 37% increase in the user sum rate as well as a maximal reduction in the bit error rate (BER) of 50% in comparison to the conventional NOMA system. Furthermore, we propose a novel power coefficient allocation algorithm based on binomial distribution and Pascal’s triangle. This algorithm is used to divide power among N users according to each user’s channel condition. In addition, we introduce adaptive code rates and rotated constellations with cyclic Q-delay in the quadri-phase shift keying (QPSK) and quadrature amplitude modulation (QAM) modulators. This modified modulation scheme overcomes channel fading effects and helps to restore the transmitted sequences with fewer errors. In addition to the initial LSTM stage, the added adaptive coding and modulation stages result in a 73% improvement in the BER in comparison to the conventional NOMA system.

Single Channel EEG signal for Automatic Detection of Absence Seizure using Convolutional Neural Network

2019 ◽  
Vol 13 ◽  
Author(s):  
Niha Kamal Basha ◽  
Aisha Banu Wahab
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Convolutional Neural Network ◽  
Monitoring System ◽  
Single Channel ◽  
Confusion Matrix ◽  
Sudden Change ◽  
Automatic Detection ◽  
Support Vector ◽  
Absence Seizure

: Absence seizure is a type of brain disorder in which subject get into sudden lapses in attention. Which means sudden change in brain stimulation. Most of this type of disorder is widely found in children’s (5-18 years). These Electroencephalogram (EEG) signals are captured with long term monitoring system and are analyzed individually. In this paper, a Convolutional Neural Network to extract single channel EEG seizure features like Power, log sum of wavelet transform, cross correlation, and mean phase variance of each frame in a windows are extracted after pre-processing and classify them into normal or absence seizure class, is proposed as an empowerment of monitoring system by automatic detection of absence seizure. The training data is collected from the normal and absence seizure subjects in the form of Electroencephalogram. The objective is to perform automatic detection of absence seizure using single channel electroencephalogram signal as input. Here the data is used to train the proposed Convolutional Neural Network to extract and classify absence seizure. The Convolutional Neural Network consist of three layers 1] convolutional layer – which extract the features in the form of vector 2] Pooling layer – the dimensionality of output from convolutional layer is reduced and 3] Fully connected layer–the activation function called soft-max is used to find the probability distribution of output class. This paper goes through the automatic detection of absence seizure in detail and provide the comparative analysis of classification between Support Vector Machine and Convolutional Neural Network. The proposed approach outperforms the performance of Support Vector Machine by 80% in automatic detection of absence seizure and validated using confusion matrix.

Arrhythmia Classification on Electrocardiogram Signal Using Convolution Neural Network Based on Frequency Spectrum

2020 ◽  
Author(s):  
Arief Kurniawan ◽  
Ananda ◽  
Firdaus Nanda Pradanggapasti ◽  
Reza Fuad Rachmadi ◽  
Eko Setijadi ◽  
...  
Keyword(s):  
Neural Network ◽  
Frequency Spectrum ◽  
Convolution Neural Network ◽  
Electrocardiogram Signal

scholarly journals Bearing Fault Classification Using Ensemble Empirical Mode Decomposition and Convolutional Neural Network

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1248
Author(s):  
Rafia Nishat Toma ◽  
Cheol-Hong Kim ◽  
Jong-Myon Kim
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Empirical Mode Decomposition ◽  
Vibration Signal ◽  
Ensemble Empirical Mode Decomposition ◽  
Fault Classification ◽  
Original Signal ◽  
Time Frequency ◽  
Mode Decomposition ◽  
Reconstructed Signal

Condition monitoring is used to track the unavoidable phases of rolling element bearings in an induction motor (IM) to ensure reliable operation in domestic and industrial machinery. The convolutional neural network (CNN) has been used as an effective tool to recognize and classify multiple rolling bearing faults in recent times. Due to the nonlinear and nonstationary nature of vibration signals, it is quite difficult to achieve high classification accuracy when directly using the original signal as the input of a convolution neural network. To evaluate the fault characteristics, ensemble empirical mode decomposition (EEMD) is implemented to decompose the signal into multiple intrinsic mode functions (IMFs) in this work. Then, based on the kurtosis value, insignificant IMFs are filtered out and the original signal is reconstructed with the rest of the IMFs so that the reconstructed signal contains the fault characteristics. After that, the 1-D reconstructed vibration signal is converted into a 2-D image using a continuous wavelet transform with information from the damage frequency band. This also transfers the signal into a time-frequency domain and reduces the nonstationary effects of the vibration signal. Finally, the generated images of various fault conditions, which possess a discriminative pattern relative to the types of faults, are used to train an appropriate CNN model. Additionally, with the reconstructed signal, two different methods are used to create an image to compare with our proposed image creation approach. The vibration signal is collected from a self-designed testbed containing multiple bearings of different fault conditions. Two other conventional CNN architectures are compared with our proposed model. Based on the results obtained, it can be concluded that the image generated with fault signatures not only accurately classifies multiple faults with CNN but can also be considered as a reliable and stable method for the diagnosis of fault bearings.

scholarly journals A compact and interpretable convolutional neural network for cross-subject driver drowsiness detection from single-channel EEG

Methods ◽  
2021 ◽  
Author(s):  
Jian Cui ◽  
Zirui Lan ◽  
Yisi Liu ◽  
Ruilin Li ◽  
Fan Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Single Channel ◽  
Drowsiness Detection ◽  
Driver Drowsiness
Sign in / Sign up

Export Citation Format

Share Document