Fully Connected Feedforward Neural Networks Based CSI Feedback Algorithm

In modern wireless communication systems,the accurate acquisition of channel state information(CSI)is critical to the performance of beamforming,non-orthogonal multiple access(NOMA),etc.However,with the application of massive MIMO in 5G,the number of antennas increases by hundreds or even thousands times,which leads to excessive feedback overhead and poses a huge challenge to the conventional channel state information feedback scheme.In this paper,by using deep learning technology,we develop a system framework for CSI feedback based on fully connected feedforward neural networks(FCFNN),named CF-FCFNN.Through learning the training set composed of CSI,CF-FCFNN is able to recover the original CSI from the compressed CSI more accurately compared with the existing method based on deep learning without increasing the algorithm complexity.

Interpretation and characterization of rate of penetration intelligent prediction model

Accurate prediction of the rate of penetration(ROP)is significant for drilling optimization.While the intelligent ROP prediction model based on fully connected neural networks(FNN)outperforms traditional ROP equations and machine learning algorithms,its lack of interpretability undermines its credibility.This study proposes a novel interpretation and characterization method for the FNN ROP prediction model using the Rectified Linear Unit(ReLU)activation function.By leveraging the derivative of the ReLU function,the FNN function calculation process is transformed into vector operations.The FNN model is linearly characterized through further simplification,enabling its interpretation and analysis.The proposed method is applied in ROP prediction scenarios using drilling data from three vertical wells in the Tarim Oilfield.The results demonstrate that the FNN ROP prediction model with ReLU as the activation function performs exceptionally well.The relative activation frequency curve of hidden layer neurons aids in analyzing the overfitting of the FNN ROP model and determining drilling data similarity.In the well sections with similar drilling data,averaging the weight parameters enables linear characterization of the FNN ROP prediction model,leading to the establishment of a corresponding linear representation equation.Furthermore,the quantitative analysis of each feature's influence on ROP facilitates the proposal of drilling parameter optimization schemes for the current well section.The established linear characterization equation exhibits high precision,strong stability,and adaptability through the application and validation across multiple well sections.

Artificial neural network-based subgrid-scale models for LES of compressible turbulent channel flow

Fully connected neural networks(FCNNs)have been developed for the closure of subgrid-scale(SGS)stress and SGS heat flux in large-eddy simulations of compressible turbulent channel flow.The FCNNbased SGS model trained using data with Mach number Ma=3.0 and Reynolds number Re=3000 was applied to situations with different Mach numbers and Reynolds numbers.The input variables of the neural network model were the filtered velocity gradients and temperature gradients at a single spatial grid point.The a priori test showed that the FCNN model had a correlation coefficient larger than 0.91 and a relative error smaller than 0.43,with much better reconstructions of SGS unclosed terms than the dynamic Smagorinsky model(DSM).In a posteriori test,the behavior of the FCNN model was marginally better than that of the DSM in predicting the mean velocity profiles,mean temperature profiles,turbulent intensities,total Reynolds stress,total Reynolds heat flux,and mean SGS flux of kinetic energy,and outperformed the Smagorinsky model.

Annual Frequency of Tropical Cyclones Directly Affecting Guangdong Province:Prediction Based on LSTM-FC

Tropical cyclone(TC)annual frequency forecasting is significant for disaster prevention and mitigation in Guangdong Province.Based on the NCEP-NCAR reanalysis and NOAA Extended Reconstructed global sea surface temperature(SST)V5 data in winter,the TC frequency climatic features and prediction models have been studied.During 1951-2019,353 TCs directly affected Guangdong with an annual average of about 5.1.TCs have experienced an abrupt change from abundance to deficiency in the mid to late 1980 with a slightly decreasing trend and a normal distribution.338 primary precursors are obtained from statistically significant correlation regions of SST,sea level pressure,1000hPa air temperature,850hPa specific humidity,500hPa geopotential height and zonal wind shear in winter.Then those 338 primary factors are reduced into 19 independent predictors by principal component analysis(PCA).Furthermore,the Multiple Linear Regression(MLR),the Gaussian Process Regression(GPR)and the Long Short-term Memory Networks and Fully Connected Layers(LSTM-FC)models are constructed relying on the above 19 factors.For three different kinds of test sets from 2010 to 2019,2011 to 2019 and 2010 to 2019,the root mean square errors(RMSEs)of MLR,GPR and LSTM-FC between prediction and observations fluctuate within the range of 1.05-2.45,1.00-1.93 and 0.71-0.95 as well as the average absolute errors(AAEs)0.88-1.0,0.75-1.36 and 0.50-0.70,respectively.As for the 2010-2019 experiment,the mean deviations of the three model outputs from the observation are 0.89,0.78 and 0.56,together with the average evaluation scores 82.22,84.44 and 88.89,separately.The prediction skill comparisons unveil that LSTM-FC model has a better performance than MLR and GPR.In conclusion,the deep learning model of LSTM-FC may shed light on improving the accuracy of short-term climate prediction about TC frequency.The current research can provide experience on the development of deep learning in this field and help to achieve further progress of TC disaster prevention and mitigation in Guangdong Province.

Computer vision-based six layered ConvNeural network to recognize sign language for both numeral and alphabet signs

People who have trouble communicating verbally are often dependent on sign language,which can be difficult for most people to understand,making interaction with them a difficult endeavor.The Sign Language Recognition(SLR)system takes an input expression from a hearing or speaking-impaired person and outputs it in the form of text or voice to a normal person.The existing study related to the Sign Language Recognition system has some drawbacks,such as a lack of large datasets and datasets with a range of backgrounds,skin tones,and ages.This research efficiently focuses on Sign Language Recognition to overcome previous limitations.Most importantly,we use our proposed Convolutional Neural Network(CNN)model,“ConvNeural”,in order to train our dataset.Additionally,we develop our own datasets,“BdSL_OPSA22_STATIC1”and“BdSL_OPSA22_STATIC2”,both of which have ambiguous backgrounds.“BdSL_OPSA22_STATIC1”and“BdSL_OPSA22_STATIC2”both include images of Bangla characters and numerals,a total of 24,615 and 8437 images,respectively.The“ConvNeural”model outperforms the pre-trained models with accuracy of 98.38%for“BdSL_OPSA22_STATIC1”and 92.78%for“BdSL_OPSA22_STATIC2”.For“BdSL_OPSA22_STATIC1”dataset,we get precision,recall,F1-score,sensitivity and specificity of 96%,95%,95%,99.31%,and 95.78%respectively.Moreover,in case of“BdSL_OPSA22_STATIC2”dataset,we achieve precision,recall,F1-score,sensitivity and specificity of 90%,88%,88%,100%,and 100%respectively.

Applying Big Data Based Deep Learning System to Intrusion Detection

With vast amounts of data being generated daily and the ever increasing interconnectivity of the world’s internet infrastructures,a machine learning based Intrusion Detection Systems(IDS)has become a vital component to protect our economic and national security.Previous shallow learning and deep learning strategies adopt the single learning model approach for intrusion detection.The single learning model approach may experience problems to understand increasingly complicated data distribution of intrusion patterns.Particularly,the single deep learning model may not be effective to capture unique patterns from intrusive attacks having a small number of samples.In order to further enhance the performance of machine learning based IDS,we propose the Big Data based Hierarchical Deep Learning System(BDHDLS).BDHDLS utilizes behavioral features and content features to understand both network traffic characteristics and information stored in the payload.Each deep learning model in the BDHDLS concentrates its efforts to learn the unique data distribution in one cluster.This strategy can increase the detection rate of intrusive attacks as compared to the previous single learning model approaches.Based on parallel training strategy and big data techniques,the model construction time of BDHDLS is reduced substantially when multiple machines are deployed.

Hybrid beamforming with discrete phase shifters for millimeter wave backhaul networks

Hybrid beamforming（ HBF） technology becomes one of the key technologies in the millimeter wave（ mm Wave）mobile backhaul systems,for its lower complexity and low power consumption compared to full digital beamforming（ DBF）. Two structures of HBF exist in the mm Wave mobile backhaul system,namely,the fully connected structures（ FCS） and partially connected structures（ PCS）. However,the existing methods cannot be applied to both structures. Moreover,the ideal phase shifter is considered in some current HBF methods,which is not realistic. In this paper,a HBF algorithm for both structures based on the discrete phase shifters is proposed in the mm Wave mobile backhaul systems. By using the principle of alternating minimization,the optimization problem of HBF is decomposed into a DBF optimization problem and an analog beamforming（ ABF） optimization problem.Then the least square（ LS） method is enabled to solve the optimization model of DBF. In addition,the achievable data rate for both structures with closed-form expression which can be used to convert the optimization model into a single-stream beamforming optimization model with per antenna power constraint is derived. Therefore,the ABF is easily solved. Simulation results show that the performance of the proposed HBF method can approach the full DBF by using a lower resolution phase shifter.

High accuracy offering attention mechanisms based deep learning approach using CNN/bi-LSTM for sentiment analysis

Purpose-Neural network(NN)-based deep learning(DL)approach is considered for sentiment analysis(SA)by incorporating convolutional neural network(CNN),bi-directional long short-term memory(Bi-LSTM)and attention methods.Unlike the conventional supervised machine learning natural language processing algorithms,the authors have used unsupervised deep learning algorithms.Design/methodology/approach-The method presented for sentiment analysis is designed using CNN,Bi-LSTM and the attention mechanism.Word2vec word embedding is used for natural language processing(NLP).The discussed approach is designed for sentence-level SA which consists of one embedding layer,two convolutional layers with max-pooling,oneLSTMlayer and two fully connected(FC)layers.Overall the system training time is 30 min.Findings-The method performance is analyzed using metrics like precision,recall,F1 score,and accuracy.CNN is helped to reduce the complexity and Bi-LSTM is helped to process the long sequence input text.Originality/value-The attention mechanism is adopted to decide the significance of every hidden state and give a weighted sum of all the features fed as input.