Enhancing Multicriteria-Based Recommendations by Alleviating Scalability and Sparsity Issues Using Collaborative Denoising Autoencoder

A Recommender System(RS)is a crucial part of several firms,particularly those involved in e-commerce.In conventional RS,a user may only offer a single rating for an item-that is insufficient to perceive consumer preferences.Nowadays,businesses in industries like e-learning and tourism enable customers to rate a product using a variety of factors to comprehend customers’preferences.On the other hand,the collaborative filtering(CF)algorithm utilizing AutoEncoder(AE)is seen to be effective in identifying user-interested items.However,the cost of these computations increases nonlinearly as the number of items and users increases.To triumph over the issues,a novel expanded stacked autoencoder(ESAE)with Kernel Fuzzy C-Means Clustering(KFCM)technique is proposed with two phases.In the first phase of offline,the sparse multicriteria rating matrix is smoothened to a complete matrix by predicting the users’intact rating by the ESAE approach and users are clustered using the KFCM approach.In the next phase of online,the top-N recommendation prediction is made by the ESAE approach involving only the most similar user from multiple clusters.Hence the ESAE_KFCM model upgrades the prediction accuracy of 98.2%in Top-N recommendation with a minimized recommendation generation time.An experimental check on the Yahoo!Movies(YM)movie dataset and TripAdvisor(TA)travel dataset confirmed that the ESAE_KFCM model constantly outperforms conventional RS algorithms on a variety of assessment measures.

Extension of sound field reconstruction based on element radiation superposition method in a sparsity framework

Nearfield acoustic holography(NAH)is a powerful tool for realizing source identification and sound field reconstruction.The wave superposition(WS)-based NAH is appropriate for the spatially extended sources and does not require the complex numerical integrals.Equivalent source method(ESM),as a classical WS approach,is widely used due to its simplicity and efficiency.In the ESM,a virtual source surface is introduced,on which the virtual point sources are taken as the assumed sources,and an optimal retreat distance needs to be considered.A newly proposed WS-based approach,the element radiation superposition method(ERSM),uses piston surface source as the assumed source with no need to choose a virtual source surface.To satisfy the application conditions of piston pressure formula,the sizes of pistons are assumed to be as small as possible,which results in a large number of pistons and sampling points.In this paper,transfer matrix modes(TMMs),which are composed of the singular vectors of the vibro-acoustic transfer matrix,are used as the sparse basis of piston normal velocities.Then,the compressive ERSM based on TMMs is proposed.Compared with the conventional ERSM,the proposed method maintains a good pressure reconstruction when the number of sampling points and pistons are both reduced.Besides,the proposed method is compared with the compressive ESM in a mathematical sense.Both simulations and experiments for a rectangular plate demonstrate the advantage of the proposed method over the existing methods.

Wind turbine clutter mitigation using morphological component analysis with group sparsity

To address the problem that dynamic wind turbine clutter(WTC)significantly degrades the performance of weather radar,a WTC mitigation algorithm using morphological component analysis(MCA)with group sparsity is studied in this paper.The ground clutter is suppressed firstly to reduce the morphological compositions of radar echo.After that,the MCA algorithm is applied and the window used in the short-time Fourier transform(STFT)is optimized to lessen the spectrum leakage of WTC.Finally,the group sparsity structure of WTC in the STFT domain can be utilized to decrease the degrees of freedom in the solution,thus contributing to better estimation performance of weather signals.The effectiveness and feasibility of the proposed method are demonstrated by numerical simulations.

Nonstationary sparsity-constrained seismic deconvolution

The Robinson convolution model is mainly restricted by three inappropriate assumptions, i.e., statistically white reflectivity, minimum-phase wavelet, and stationarity. Modern reflectivity inversion methods（e.g., sparsity-constrained deconvolution） generally attempt to suppress the problems associated with the first two assumptions but often ignore that seismic traces are nonstationary signals, which undermines the basic assumption of unchanging wavelet in reflectivity inversion. Through tests on reflectivity series, we confirm the effects of nonstationarity on reflectivity estimation and the loss of significant information, especially in deep layers. To overcome the problems caused by nonstationarity, we propose a nonstationary convolutional model, and then use the attenuation curve in log spectra to detect and correct the influences of nonstationarity. We use Gabor deconvolution to handle nonstationarity and sparsity-constrained deconvolution to separating reflectivity and wavelet. The combination of the two deconvolution methods effectively handles nonstationarity and greatly reduces the problems associated with the unreasonable assumptions regarding reflectivity and wavelet. Using marine seismic data, we show that correcting nonstationarity helps recover subtle reflectivity information and enhances the characterization of details with respect to the geological record.

Multi-Scenario Millimeter Wave Wireless Channel Measurements and Sparsity Analysis

Wireless channel characteristics have significant impacts on channel modeling,estimation,and communication performance.While the channel sparsity is an important characteristic of wireless channels.Utilizing the sparse nature of wireless channels can reduce the complexity of channel modeling and estimation,and improve system design and performance analysis.Compared with the traditional sub6 GHz channel,millimeter wave(mmWave)channel has been considered to be more sparse in existing researches.However,most research only assume that the mmWave channel is sparse,without providing quantitative analysis and evaluation.Therefore,this paper evaluates the sparsity of mmWave channels based on mmWave channel measurements.A vector network analyzer(VNA)-based mmWave channel sounder is developed to measure the channel at 28 GHz,and multi-scenario channel measurements are conducted.The Gini index,Rician𝐾factor and rootmean-square(RMS)delay spread are used to measure channel sparsity.Then,the key factors affecting mmWave channel sparsity are explored.It is found that antenna steering direction and scattering environment will affect the sparsity of mmWave channel.In addition,the impact of channel sparsity on channel eigenvalue and capacity is evaluated and analyzed.

An improved sparsity estimation variable step-size matching pursuit algorithm

To improve the reconstruction performance of the greedy algorithm for sparse signals, an improved greedy algorithm, called sparsity estimation variable step-size matching pursuit, is proposed. Compared with state-of-the-art greedy algorithms, the proposed algorithm incorporates the restricted isometry property and variable step-size, which is utilized for sparsity estimation and reduces the reconstruction time, respectively. Based on the sparsity estimation, the initial value including sparsity level and support set is computed at the beginning of the reconstruction, which provides preliminary sparsity information for signal reconstruction. Then, the residual and correlation are calculated according to the initial value and the support set is refined at the next iteration associated with variable step-size and backtracking. Finally, the correct support set is obtained when the halting condition is reached and the original signal is reconstructed accurately. The simulation results demonstrate that the proposed algorithm improves the recovery performance and considerably outperforms the existing algorithm in terms of the running time in sparse signal reconstruction.

DUAL-SPARSITY PRESERVING PROJECTION

Sparsity preserving projection（SPP） is a popular graph-based dimensionality reduction（DR） method, which has been successfully applied to solve face recognition recently. SPP contains natural discriminating information by preserving sparse reconstruction relationship of data sets. However, SPP suffers from the fact that every new feature learned from data sets is linear combinations of all the original features, which often makes it difficult to interpret the results. To address this issue, a novel DR method called dual-sparsity preserving projection （DSPP） is proposed to further impose sparsity constraints on the projection directions of SPP. Specifically, the proposed method casts the projection function learning of SPP into a regression-type optimization problem, and then the sparse projections can be efficiently computed by the related lasso algorithm. Experimental results from face databases demonstrate the effectiveness of the proposed algorithm.

Applying memetic algorithm-based clustering to recommender system with high sparsity problem

A new recommendation method was presented based on memetic algorithm-based clustering. The proposed method was tested on four highly sparse real-world datasets. Its recommendation performance is evaluated and compared with that of the frequency-based, user-based, item-based, k-means clustering-based, and genetic algorithm-based methods in terms of precision, recall, and F1 score. The results show that the proposed method yields better performance under the new user cold-start problem when each of new active users selects only one or two items into the basket. The average F1 scores on all four datasets are improved by 225.0%, 61.6%, 54.6%, 49.3%, 28.8%, and 6.3% over the frequency-based, user-based, item-based, k-means clustering-based, and two genetic algorithm-based methods, respectively.

Low-field NMR inversion based on low-rank and sparsity restraint of relaxation spectra

In this paper,we proposed a novel method for low-field nuclear magnetic resonance(NMR)inversion based on low-rank and sparsity restraint(LRSR)of relaxation spectra,with which high quality construction is made possible for one-and two-dimensional low-field and low signal to noise ratio NMR data.In this method,the low-rank and sparsity restraints are introduced into the objective function instead of the smoothing term.The low-rank features in relaxation spectra are extracted to ensure the local characteristics and morphology of spectra.The sparsity and residual term are contributed to the resolution and precision of spectra,with the elimination of the redundant relaxation components.Optimization process of the objective function is designed with alternating direction method of multiples,in which the objective function is decomposed into three subproblems to be independently solved.The optimum solution can be obtained by alternating iteration and updating process.At first,numerical simulations are conducted on synthetic echo data with different signal-to-noise ratios,to optimize the desirable regularization parameters and verify the feasibility and effectiveness of proposed method.Then,NMR experiments on solutions and artificial sandstone samples are conducted and analyzed,which validates the robustness and reliability of the proposed method.The results from simulations and experiments have demonstrated that the suggested method has unique advantages for improving the resolution of relaxation spectra and enhancing the ability of fluid quantitative identification.

AN IMPROVED SPARSITY ADAPTIVE MATCHING PURSUIT ALGORITHM FOR COMPRESSIVE SENSING BASED ON REGULARIZED BACKTRACKING

Sparsity Adaptive Matching Pursuit (SAMP) algorithm is a widely used reconstruction algorithm for compressive sensing in the case that the sparsity is unknown. In order to match the sparsity more accurately, we presented an improved SAMP algorithm based on Regularized Backtracking (SAMP-RB). By adapting a regularized backtracking step to SAMP algorithm in each iteration stage, the proposed algorithm can flexibly remove the inappropriate atoms. The experimental results show that SAMP-RB reconstruction algorithm greatly improves SAMP algorithm both in reconstruction quality and computational time. It has better reconstruction efficiency than most of the available matching pursuit algorithms.

Multi-narrowband signals receiving method based on analog-to-information convertor and block sparsity

The analog-to-information convertor (AIC) is a successful practice of compressive sensing (CS) theory in the analog signal acquisition. This paper presents a multi-narrowband signals sampling and reconstruction model based on AIC and block sparsity. To overcome the practical problems, the block sparsity is divided into uniform block and non-uniform block situations, and the block restricted isometry property and sub-sampling limit in different situations are analyzed respectively in detail. Theoretical analysis proves that using the block sparsity in AIC can reduce the restricted isometric constant, increase the reconstruction probability and reduce the sub -sampling rate. Simulation results show that the proposed model can complete sub -sampling and reconstruction for multi-narrowband signals. This paper extends the application range of AIC from the finite information rate signal to the multi-narrowband signals by using the potential relevance of support sets. The proposed receiving model has low complexity and is easy to implement, which can promote the application of CS theory in the radar receiver to reduce the burden of analog-to digital convertor (ADC) and solve bandwidth limitations of ADC.

Research on Efficient Seismic Data Acquisition Methods Based on Sparsity Constraint

In actual exploration,the demand for 3D seismic data collection is increasing,and the requirements for data are becoming higher and higher.Accordingly,the collection cost and data volume also increase.Aiming at this problem,we make use of the nature of data sparse expression,based on the theory of compressed sensing,to carry out the research on the efficient collection method of seismic data.It combines the collection of seismic data and the compression in data processing in practical work,breaking through the limitation of the traditional sampling frequency,and the sparse characteristics of the seismic signal are utilized to reconstruct the missing data.We focus on the key elements of the sampling matrix in the theory of compressed sensing,and study the methods of seismic data acquisition.According to the conditions that the compressed sensing sampling matrix needs to meet,we introduce a new random acquisition scheme,which introduces the widely used Low-density Parity-check(LDPC)sampling matrix in image processing into seismic exploration acquisition.Firstly,its properties are discussed and its conditions for satisfying the sampling matrix in compressed sensing are verified.Then the LDPC sampling method and the conventional data acquisition method are used to synthesize seismic data reconstruction experiments.The reconstruction results,signal-to-noise ratio and reconstruction error are compared to verify the seismic data based on sparse constraints.The LDPC sampling method improves the current seismic data reconstruction efficiency,reduces the exploration cost and the effectiveness and feasibility of the method.

SEMI-SUPERVISED RADIO TRANSMITTER CLASSIFICATION BASED ON ELASTIC SPARSITY REGULARIZED SVM

Non-collaborative radio transmitter recognition is a significant but challenging issue, since it is hard or costly to obtain labeled training data samples. In order to make effective use of the unlabeled samples which can be obtained much easier, a novel semi-supervised classification method named Elastic Sparsity Regularized Support Vector Machine (ESRSVM) is proposed for radio transmitter classification. ESRSVM first constructs an elastic-net graph over data samples to capture the robust and natural discriminating information and then incorporate the information into the manifold learning framework by an elastic sparsity regularization term. Experimental results on 10 GMSK modulated Automatic Identification System radios and 15 FM walkie-talkie radios show that ESRSVM achieves obviously better performance than KNN and SVM, which use only labeled samples for classification, and also outperforms semi-supervised classifier LapSVM based on manifold regularization.

A sparsity adaptive compressed signal reconstruction based on sensing dictionary

Signal reconstruction is a significantly important theoretical issue for compressed sensing.Considering the situation of signal reconstruction with unknown sparsity,the conventional signal reconstruction algorithms usually perform low accuracy.In this work,a sparsity adaptive signal reconstruction algorithm using sensing dictionary is proposed to achieve a lower reconstruction error.The sparsity estimation method is combined with the construction of the support set based on sensing dictionary.Using the adaptive sparsity method,an iterative signal reconstruction algorithm is proposed.The sufficient conditions for the exact signal reconstruction of the algorithm also is proved by theory.According to a series of simulations,the results show that the proposed method has higher precision compared with other state-of-the-art signal reconstruction algorithms especially in a high compression ratio scenarios.

COMPRESSED SPEECH SIGNAL SENSING BASED ON THE STRUCTURED BLOCK SPARSITY WITH PARTIAL KNOWLEDGE OF SUPPORT

Structural and statistical characteristics of signals can improve the performance of Compressed Sensing (CS). Two kinds of features of Discrete Cosine Transform (DCT) coefficients of voiced speech signals are discussed in this paper. The first one is the block sparsity of DCT coefficients of voiced speech formulated from two different aspects which are the distribution of the DCT coefficients of voiced speech and the comparison of reconstruction performance between the mixed program and Basis Pursuit (BP). The block sparsity of DCT coefficients of voiced speech means that some algorithms of block-sparse CS can be used to improve the recovery performance of speech signals. It is proved by the simulation results of the mixed program which is an improved version of the mixed program. The second one is the well known large DCT coefficients of voiced speech focus on low frequency. In line with this feature, a special Gaussian and Partial Identity Joint (GPIJ) matrix is constructed as the sensing matrix for voiced speech signals. Simulation results show that the GPIJ matrix outperforms the classical Gaussian matrix for speech signals of male and female adults.

A SPARSITY AND COMPRESSION RATIO JOINT ADJUSTMENT METHOD FOR COLLABORATIVE SPECTRUM SENSING

Spectrum sensing is the fundamental task for Cognitive Radio (CR). To overcome the challenge of high sampling rate in traditional spectral estimation methods, Compressed Sensing (CS) theory is developed. A sparsity and compression ratio joint adjustment algorithm for compressed spectrum sensing in CR network is investigated, with the hypothesis that the sparsity level is unknown as priori knowledge at CR terminals. As perfect spectrum reconstruction is not necessarily required during spectrum detection process, the proposed algorithm only performs a rough estimate of sparsity level. Meanwhile, in order to further reduce the sensing measurement, different compression ratios for CR terminals with varying Signal-to-Noise Ratio (SNR) are considered. The proposed algorithm, which optimizes the compression ratio as well as the estimated sparsity level, can greatly reduce the sensing measurement without degrading the detection performance. It also requires less steps of iteration for convergence. Corroborating simulation results are presented to testify the effectiveness of the proposed algorithm for collaborative spectrum sensing.

Optimization-based image reconstruction in x-ray computed tomography by sparsity exploitation of local continuity and nonlocal spatial self-similarity

The additional sparse prior of images has been the subject of much research in problems of sparse-view computed tomography（CT） reconstruction. A method employing the image gradient sparsity is often used to reduce the sampling rate and is shown to remove the unwanted artifacts while preserve sharp edges, but may cause blocky or patchy artifacts.To eliminate this drawback, we propose a novel sparsity exploitation-based model for CT image reconstruction. In the presented model, the sparse representation and sparsity exploitation of both gradient and nonlocal gradient are investigated.The new model is shown to offer the potential for better results by introducing a similarity prior information of the image structure. Then, an effective alternating direction minimization algorithm is developed to optimize the objective function with a robust convergence result. Qualitative and quantitative evaluations have been carried out both on the simulation and real data in terms of accuracy and resolution properties. The results indicate that the proposed method can be applied for achieving better image-quality potential with the theoretically expected detailed feature preservation.

Three-Dimensional Interferometric ISAR Sensors Imaging for the Ship Target with Two-Dimensional Sparsity

There are great challenges for traditional three-dimensional( 3-D) interferometric inverse synthetic aperture radar( In ISAR) imaging algorithms of ship targets w ith 2-D sparsity in actual radar imaging system. To deal w ith this problem,a novel 3-D In ISAR imaging method is proposed in this paper.First,the high-precision gradient adaptive algorithm w as adopted to reconstruct the echoes in range dimension. Then the method of minimizing the entropy of the average range profile w as applied to estimate the parameters w hich are used to compensate translation components of the received echoes. Besides,the phase adjustment and image coregistration of the sparse echoes w ere achieved at the same time through the approach of the joint phase autofocus. Finally,the 3-D geometry coordinates of the ship target w ith 2-D sparsity w ere reconstructed by combining the range measurement and interferometric processing of the ISAR images. Simulation experiments w ere carried out to verify the practicability and effectiveness of the algorithm in the case that the received echoes are in 2-D sparsity.

Multiple wave prediction and suppression based on LO-norm sparsity constraint

Multiple wave is one of the important factors affecting the signal-to-noise ratio of marine seismic data.The model-driven-method(MDM)can effectively predict and suppress water-related multiple waves,while the quality of the multiple wave contribution gathers(MCG)can affect the prediction accuracy of multiple waves.Based on the compressed sensing framework,this study used the sparse constraint under LO norm to optimize MCG,which can not only reduce the false in the prediction and improve the image accuracy,but also saves computing time.At the same time,the MDM-type method for multiple wave suppression can be improved.The unified prediction of multiple types of water-related multiple waves weakens the dependence of conventional MDM on the adaptive subtraction process in suppressing water-related multiple waves,improves the stability of the method,and simultaneously,reduces the computational load.Finally,both theoretical model and practical data prove the effectiveness of the present method.

Simultaneous receiver-side deghosting and denoising method based on the sparsity constraint

In marine seismic exploration,the sea surface ghost causes frequency notches and low-frequency loss,which aff ects the signal-to-noise ratio(SNR)and resolution of seismic records.This paper presents a simultaneous receiver-side deghosting and denoising method based on the sparsity constraint.First,considering the influence of propagation direction and sea surface reflection coefficient,the ghost time delay is calculated accurately,and then the accurate ghost operator is constructed in the frequency–slowness domain.Finally,the ghost-free data are obtained using the sparse constraint algorithm that can effectively suppress the ghost along with the noise energy.This method can remove the ghost and noise simultaneously,achieving quick convergence and with few iterations.It is applied to synthetic data and actual streamer fi eld data.Test results prove that the ghost and notches are suppressed eff ectively,the SNR is improved,and the band is well broadened.