Sparse Feature Extraction Research Articles

Audio Signal Recognition in Complex Environments Using Sparse Representation

Recognizing audio signals in complex environments is crucial for acquiring adequate information. This paper integrates the sparse expression algorithm with Mel-frequency cepstral coefficient (MFCC) features. The combined approach was applied in convolutional neural network classifiers to recognize acoustic scenes in audio signals within complex environments. The algorithm was then simulated and tested using the TUT Sound Events 2016 and TUT Acoustic Scenes 2016 datasets. In the experiments, the efficacy of the developed sparse feature extraction method was validated. Then, the appropriate sparse dictionary size was determined. The algorithm was subsequently compared with two recognition algorithms based on sparse and MFCC features, respectively. It was found that the extraction approach proposed in this paper had a higher signal-to-noise ratio. The results revealed variations in the required sparse dictionary size for different datasets: 75 for TUT Sound Events 2016 and 150 for TUT Acoustic Scenes 2016. The MFCC-combined recognition algorithm demonstrated the fastest convergence during training among the three audio scene recognition algorithms. For both the TUT Sound Events 2016 and TUT Acoustic Scenes 2016 datasets, the MFCC-combined recognition algorithm achieved the highest classification accuracy, and the recognition accuracy for the former dataset was higher.

A detection method of oil content for maize kernels based on CARS feature selection and deep sparse autoencoder feature extraction

To achieve accurate, rapid, and non-destructive oil content determination in maize, a neural fitting model that combines feature selection and feature extraction is proposed. Competitive adaptive re-weighted sampling (CARS) is used to choose features, while the deep sparse autoencoder (DSAE) network is utilized to extract features. The 160 spectral data from the near-infrared spectra public datasets of maize served as experimental samples. Several preprocessing approaches were tested, and the first-order derivatives fared the best. To capture the various degrees of abstract features in spectral data, SSAE networks with two or three hidden layers are developed. The number of nodes in the network's hidden layer (30, 50, 70, 100, 200, 300, respectively) and the network's sparsity parameter (0.001, 0.004, 0.007, 0.01, 0.04, 0.07, 0.1, 0.2, …, 1) are tuned to generate partial least squares regression (PLSR) models for testing the feature learning effect. The highest performance comes from a three-layer network with 200 hidden layer nodes and a sparsity parameter of 0.04. This network extracts three levels of features from the preprocessed spectral data: F1, F2, and F3. Full_cars, F1_cars, F2_cars, and F3_cars are obtained using the CARS algorithm for variable selection on the preprocessed spectral data, F1, F2, and F3, respectively. They are then integrated into a final feature set to build a neural-fitting network (FNN). After training and testing, the test set has a correlation coefficient of 0.964205 and an mean square error (MSE) of 0.00636809. Comparing this model to support vector machine regression (SVR), PLSR, and gaussian process regression (GPR), the findings demonstrate that the model described in this study outperforms the others in terms of fitting accuracy and generalization performance. To summarize, this paper introduces a new regression analysis method based on near-infrared spectra.

Permanent magnet synchronous motor inter-turn short circuit diagnosis based on physical-data dual model under oil-drilling environment

Inter-turn Short Circuit (ITSC) faults in Permanent Magnet Synchronous Motor (PMSM) have gained significant attention due to the growing demand for enhanced reliability and safety in actuation systems. This paper presents a adaptive fault diagnosis approach specifically designed for ITSC faults in PMSM used in oil-drilling applications, where sparse actual data and varying speed conditions pose considerable sparse training data and ITSC feature extraction challenges respectively. To address these challenges, we first construct a physical fault model of PMSM-ITSC and establish a simulation experiment platform to replicate downhole environments with high temperatures and rapidly changing PMSM speeds, ensuring a reliable data source for analysis. Subsequently, we propose a novel adaptive peak-to-peak self-finding method (APPS) that leverages frequency-domain prior knowledge to adaptively extract ITSC fault characteristics, even amidst drastic changes in PMSM speed. Furthermore, we introduce the time-sequence efficient moving window self-attention network (EMWSAN) data model for inferring the stator phase winding state, incorporating Half-sandwich and Cascaded windows group attention operations. This approach significantly reduces computational complexity and network parameters compared to traditional self-attention mechanisms. To expedite the fitting process, we apply transfer learning (TL) theory, transferring knowledge from the physical knowledge to the data model, enabling EMWSAN to be trained more efficiently. As a result, our proposed ITSC fault diagnosis scheme achieves an impressive 96.72% classification accuracy, achieving existing state-of-the-art methods.

BEVEFNet: A Multiple Object Tracking Model Based on LiDAR-Camera Fusion

As a crucial task in the field of computer vision, object tracking models are widely used in various application domains, such as autonomous driving. However, existing multiple object tracking methods still face challenges in accurately and efficiently tracking moving multi-targets in real time. This paper presents BEVEFNet, a camera-LiDAR multi-target tracking model based on multistage fusion, which effectively utilizes the semantic information from optical images and the spatial and geometric information from LiDAR data to unify multi-modal features in a shared Bird’s Eye View(BEV) representation space. By leveraging LiDAR data to complement optical images, multi-level fusion is achieved at both the feature and decision levels. The proposed efficient sparse 3D feature extraction network significantly enhances the speed of multiple object tracking by incorporating sparse convolution. Experiments conducted on the nuSences dataset demonstrate that BEVEFNet achieves an AMOTA of 69.7, improving the accuracy of multiple object tracking.

An intelligent sparse feature extraction approach for music data component recognition and analysis of hybrid instruments

In this paper, a sparse feature extraction method is presented based on sparse decomposition and multiple musical instrument component dictionaries to address the challenges of existing methods in component-recognition and analysis of mixed musical instrument music data. These methods, which are often dependent on data labels, and rely primarily on frequency domain or physical features, can be improved significantly using this technique. Through the in-depth analysis of the sparse coefficient vectors, this method is capable of generating independent sparse music features that are highly interpretable and have been shown to intuitively express the composition of musical instruments, and capture the variations of emotion in the music. Consequently, this approach has great potential for application in the field of mixed musical instrument composition analysis and other time-varying signal analysis.

Jointly sparse fast hashing with orthogonal learning for large-scale image retrieval

Hash learning is a hot topic since it can save storage space and perform fast retrieval. One of the most representative hashing methods is Supervised Discrete Hashing (SDH). However, there exist several problems in SDH. First, the potential of sparse feature extraction has been overlooked in the SDH-based methods. Second, SDH is incapable of preventing large information loss between the binary codes and the features. Third, the discrete cyclic coordinate descent (DCC) method is time-consuming. To address the aforementioned issues, we propose a novel regression model for hash learning named Jointly Sparse Fast Hashing (JSFH). By designing an orthogonal transformation, we introduce the jointly sparse regression into hash learning. The proposed method successfully integrates the feature extraction and hash learning into a unified framework, the original data and the label information can be comprehensively utilized such that the binary code generated by our method can be more discriminative with less information loss. Furthermore, we adopt an iterative algorithm for optimization, the optimization problem has closed-form solutions for each variable such that the designed iterative algorithm is highly efficient compared to the classic supervised hashing methods. The experimental results on four large-scale datasets demonstrate its superior performance.

Exploring the Efficacy of Sparse Feature in Pavement Distress Image Classification: A Focus on Pavement-Specific Knowledge

Road surface deterioration, such as cracks and potholes, poses a significant threat to both road safety and infrastructure longevity. Swift and accurate detection of these issues is crucial for timely maintenance and user security. However, current techniques often overlook the unique characteristics of pavement images, where the small distressed areas are vastly outnumbered by the background. In response, we propose an innovative road distress classification model that capitalizes on sparse perception. Our method introduces a sparse feature extraction module using dilated convolution, tailored to capture and combine sparse features of different scales from the image. To further enhance our model, we design a specialized loss function rooted in domain-specific knowledge about pavement distress. This loss function enforces sparsity during feature extraction, guiding the model to align precisely with the sparse distribution of target features. We validate the strength and effectiveness of our model through comprehensive evaluations of a diverse dataset of road images containing various distress types and conditions. Our approach exhibits significant potential in advancing traffic safety by enabling more efficient and accurate detection and classification of road distress.

Constraint Linear Model for Period Estimation and Sparse Feature Extraction Based on Iterative Likelihood Ratio Test

This study proposes a constraint linear model (CLM) to represent periodic signals. Different from the conventional linear model, linear constraints are added to the proposed model to fulfill the continuity constraints of signals. To estimate the period of the signals, a hypothesis testing based on the generalized likelihood ratio is proposed to statistically compare misleading peaks exhibited in the likelihood function of CLM. The misleading peaks usually arise because the likelihood function has a similar value in the true period and its multiples, and this misleading effect obstructs the effectiveness of the conventional maximum likelihood estimation method. An iterative likelihood ratio test (ILRT) is proposed, in which hypothesis testing is iteratively conducted to test the significance of an identified period until no candidate period with significant evidence is found. After the period is estimated by ILRT, an L1 penalty is added to CLM to construct a sparse representation of the signals, and an augmented Lagrangian shrinkage algorithm is applied to extract sparse features from the signals. The effectiveness of the proposed method is verified through a simulation study on synthetic signals and a case study on real vibration signals.

Which Target to Focus on: Class-Perception for Semantic Segmentation of Remote Sensing

Deep Learning-based (DL) methods have dominated the task of semantic segmentation of remote sensing images. However, the sizes of different objects vary widely, and there is a great deal of label-noise due to the inevitable shadows. Therefore, there is an urgent need for a method that can precisely handle complex ground data. In this paper, we propose an Inter-Class Enhanced Network (ICEN) for representing features of varying sizes. It comprises two branches: Sparse Representation Network (SPN) and Feature Extraction Network (FEN). Then, a Class-Perception Block is inserted between the two branches to instruct the SPN’s low-level semantic features to be merged into the deeper network. Such a block can reduce label-noise in remote sensing image segmentation. In addition, the proposed EIRI provides a more precise classification process for target edges containing many misclassified points without requiring excessive computational overhead. The experimental results of our proposed Class-Perception Network (C-PNet) achieve competitive performance on the Vaihingen, Potsdam, LoveDA, and UAVid datasets.

Group-Sparse Feature Extraction via Ensemble Generalized Minimax-Concave Penalty for Wind-Turbine-Fault Diagnosis

Extracting weak fault features from noisy measured signals is critical for the diagnosis of wind turbine faults. In this paper, a novel group-sparse feature extraction method via an ensemble generalized minimax-concave (GMC) penalty is proposed for machinery health monitoring. Specifically, the proposed method tackles the problem of formulating large useful magnitude values as isolated features in the original GMC-based sparse feature extraction method. To accurately estimate group-sparse fault features, the proposed method formulates an effective unconstrained optimization problem wherein the group-sparse structure is incorporated into non-convex regularization. Moreover, the convex condition is proved to maintain the convexity of the whole formulated cost function. In addition, the setting criteria of the regularization parameter are investigated. A simulated signal is presented to verify the performance of the proposed method for group-sparse feature extraction. Finally, the effectiveness of the proposed group-sparse feature extraction method is further validated by experimental fault diagnosis cases.

Bearing Fault Diagnosis for Time-Varying System Using Vibration–Speed Fusion Network Based on Self-Attention and Sparse Feature Extraction

Nowadays, most deep-learning-based bearing fault diagnosis methods are studied under the condition of steady speed, while the performance of these models cannot be fully played under time-varying conditions. Therefore, in order to facilitate the practical application of a deep learning model in bearing fault diagnosis, a vibration–speed fusion network is proposed, which utilizes a transformer with a self-attention module to extract vibration features and utilizes a sparse autoencoder (SAE) network to extract sparse features from speed pulse signal. The vibration–speed fusion network enables the efficient fusion of different signals in a high-dimensional vector space with a high degree of model interpretability, without additional signal processing steps. After tuning the hyperparameters of the network, the key segments of the bearing’s time-domain vibration signals can be optimally extracted, the network performance is much better than traditional deep learning methods, and the classification accuracy can reach 95.18% and 99.85% on the two public bearing datasets from the Xi’an Jiaotong University and the University of Ottawa.

Sparse 3D Point Cloud Parallel Multi-Scale Feature Extraction and Dense Reconstruction with Multi-Headed Attentional Upsampling

Three-dimensional (3D) point clouds have a wide range of applications in the field of 3D vision. The quality of the acquired point cloud data considerably impacts the subsequent work of point cloud processing. Due to the sparsity and irregularity of point cloud data, processing point cloud data has always been challenging. However, existing deep learning-based point cloud dense reconstruction methods suffer from excessive smoothing of reconstruction results and too many outliers. The reason for this is that it is not possible to extract features for local and global features at different scales and provide different levels of attention to different regions in order to obtain long-distance dependence for dense reconstruction. In this paper, we use a parallel multi-scale feature extraction module based on graph convolution and an upsampling method with an added multi-head attention mechanism to process sparse and irregular point cloud data to obtain extended point clouds. Specifically, a point cloud training patch with 256 points is inputted. The PMS module uses three residual connections in the multi-scale feature extraction stage. Each PMS module consists of three parallel DenseGCN modules with different size convolution kernels and different averaging pooling sizes. The local and global feature information of the augmented receptive field is extracted efficiently. The scale information is obtained by averaging the different pooled augmented receptive fields. The scale information was obtained using the different average pooled augmented receptive fields. The upsampling stage uses an upsampling rate of r=4, The self-attentive features with a different focus on different point cloud data regions obtained by fusing different weights make the feature representation more diverse. This operation avoids the bias of one attention, and each focuses on extracting valuable fine-grained feature information. Finally, the coordinate reconstruction module obtains 1024 dense point cloud data. Experiments show that the proposed method demonstrates good evaluation metrics and performance and is able to obtain better visual quality. The problems of over-smoothing and excessive outliers are effectively mitigated, and the obtained sparse point cloud is more dense.

Enhanced Sparse Low-Rank Representation via Nonconvex Regularization for Rotating Machinery Early Fault Feature Extraction

The weak fault feature extraction is key to early fault diagnosis of rotary machinery. However, the existing sparse low-rank fault feature extraction methods have the deficiency of underestimation and low peak signal-to-noise ratio. To solve these problems, this article presents an enhanced sparse low-rank (ESL) representation approach for weak fault feature extraction. Considering the periodic self-similarity and shift invariance of fault feature, a weighted dual approximation regularization is proposed for noise and fault irrelevant harmonic suppression, which provides a cornerstone for rotating machinery weak fault feature extraction. To be specific, the truncated nuclear norm (TNN) and weighted generalized minimax-concave (WGMC) penalty are leveraged to form the weighted dual approximation regularization so that it can inherit their superior properties. The TNN can capture the periodic self-similarity and shift-invariance structure of fault impulses while restraining the noise; the WGMC penalty can enhance the sparsity, restrain the fault irrelevant harmonics, and overcome the deficiency of underestimating the large amplitude components. Therefore, the proposed model can effectively extract the weak fault feature. The proposed approach is applied to bearing and planet gear fault diagnosis to evaluate its effectiveness. Comparison results show the significant improvements of the proposed ESL method, indicating that it has great potentials in fault diagnosis of rotating machinery.

A sparse feature extraction method based on the shiftinvariable dictionary applied in the diagnosis of gearbox with multiple faults

Abstract The vibration signals of gearbox often contain complex components, such as the gear engagement, shafts rotation, bearings, and vibration of the box, and they brings a big challenge to fault diagnosis of gearbox. Furthermore, there are many fault types of gearbox, and the fault characteristics of them are possibly the same. For example, the pass frequency of the missing tooth or root crack in the gear on the input shaft are both equal to the rotation frequency of input shaft. In thus circumstance, traditional diagnosis methods are inapplicable, because we can’t determine which type of faults. In this paper, we proposed a dictionary learning with the shift-invariant dictionary to extract the fault features in a sparse way, and afterwards hidden Markov model (HMM) is utilized to identify the fault type from extractive features. We used the proposed method to diagnose the experimental data from a benchmark two-stage gearbox and there are nine different health conditions introduced to the pinion on the input shaft, and the diagnosis result verifies the good performance of the novel scheme in the fault diagnosis of gearbox.

Adaptive nearest neighbor reconstruction with deep contractive sparse filtering for fault diagnosis of roller bearings

Case-based intelligent fault diagnosis has had some notable successes in recent years. However, compared with parameter-based methods, they pay less attention to automatic and powerful feature extraction. Meanwhile, most approaches use k-nearest neighbor (KNN) algorithms or related variants, which fail in adaptive nearest neighbor location. To deal with these shortcomings, an algorithm called adaptive nearest neighbor reconstruction (ANNR) is proposed, which can take advantage of both parameter- and case-based diagnosis methods. Firstly, ANNR offers sparse and robust feature extraction by designed deep contractive sparse filtering (DCSF), which fuses a local contractive term to learn robust feature manifolds. Secondly, to locate the nearest neighbors for diverse testing samples adaptively, a case-based reconstruction algorithm is developed to obtain correlation vectors between training and testing samples. Finally, according to correlation vector of each testing sample, its optimized nearest neighbors are located, enabling precise feature classification. Extensive experiments were conducted on two roller bearing vibration signal datasets and verified its effectiveness.

DFFIR-net: Infrared Dim Small Object Detection Network Constrained by Gray-level Distribution Model

A new deep learning method based on the target gray-level distribution constraint mechanism model is proposed to solve the infrared dim small target detection problem in the complex environment. First, to solve the uneven distribution of positive and negative samples, the designed smoothness operator is used to suppress the background and enhancement target by measuring the difference in their features in 1D and 2D gradient. Second, an infrared dim small target detection network based on dense feature fusion, namely the DFFIR-net network, is proposed. The DFFIR-net enhances the feature expression of dim small targets by integrating the original features and the smoothness features of gray-level gradient. Also, the DFFIR-net alleviates the problem of sparse feature extraction. Finally, a multiscale 2D Gaussian label generation strategy is proposed. This strategy is critical in supervising the training of DFFIR-net in multi-dimensional Gaussian space, improving the feature exploration ability of the network and detection performance under small training samples. The experimental results show that compared with the existing advanced detection methods, the proposed method has higher accuracy and lower false alarm rates in various complex scenes.

Sparse autoencoder-based feature extraction from TOF-SIMS image data of human skin structures.

Time-of-flight secondary ion mass spectrometry (TOF-SIMS) is a useful and versatile tool for surface analysis, enabling detailed compositional information to be obtained for the surfaces of diverse samples. Furthermore, in the case of two- or three-dimensional imaging, the measurement sensitivity in the higher molecular weight range can be improved by using a cluster ion source, thus further enriching the TOF-SIMS information. Therefore, appropriate analytical methods are required to interpret this TOF-SIMS data. This study explored the capabilities of a sparse autoencoder, a feature extraction method based on artificial neural networks, to process TOF-SIMS image data. The sparse autoencoder was applied to TOF-SIMS images of human skin keratinocytes to extract the distribution of endogenous intercellular lipids and externally penetrated drugs. The results were compared with those obtained using principal component analysis (PCA) and multivariate curve resolution (MCR), which are conventionally used for extracting features from TOF-SIMS data. This confirmed that the sparse autoencoder matches, and often betters, the feature extraction performance of conventional methods, while also offering greater flexibility.

Parallel sparse filtering for intelligent fault diagnosis using acoustic signal processing

Acoustic signals have attracted considerable attention in mechanical fault diagnosis because of their advantages in non-invasive technique, instant measurement and low cost. However, traditional fault diagnosis methods could not achieve accurate feature extraction because of the strong noise environment of acoustic signals. In view of this, this study aims to provide a method that could accurately extract effectiveness features under noisy environment. Sparse representation is a research hotspot in intelligent fault diagnosis and has shown great power in feature extraction. In this paper, a novel fault diagnosis method based on parallel sparse filtering is presented to achieve sparse feature extraction from acoustic signals. Specially, parallel sparse filtering achieves sparse feature exaction by adding another normalization direction based on sparse filtering, and the derivation of parallel sparse filtering is also presented in detail. Then Z-score normalization is used to activate the training and testing data in fault classification process. The superiority of the proposed method is validated by simulated and experimental data. The results show that PSF is a promising sparse feature extraction method that can be used for mechanical fault diagnosis under acoustic signals.

An intelligent fault diagnosis method for an electromechanical actuator based on sparse feature and long short-term network

Electromechanical actuators (EMAs), as the new generation of actuators, have an important impact on the safety of aircraft. With the development of measurement technology, a large amount of data provides a broad prospect for the data-based fault diagnosis method. However, the existence of redundant data increases the burden of software and hardware. Therefore, a semi-supervised sparse auto-encoder (SSAE) is employed to prune observed data based on sparsity analysis. Moreover, temporal and spatial relationships are explored by a multi-channel long short-term network to build a time series model, so as to perform fault detection and isolation based on the difference between its estimated and observed values. Due to its sparse feature extraction capability, the SSAE can improve the fault isolation accuracy while pruning observed data. Verification results confirm that the proposed method can effectively diagnose EMA faults.

Lifting Scheme-Based Sparse Density Feature Extraction for Remote Sensing Target Detection

The design of backbones is of great significance for enhancing the location and classification precision in the remote sensing target detection task. Recently, various approaches have been proposed on altering the feature extraction density in the backbones to enlarge the receptive field, make features prominent, and reduce computational complexity, such as dilated convolution and deformable convolution. Among them, one of the most widely used methods is strided convolution, but it loses the information about adjacent feature points which leads to the omission of some useful features and the decrease of detection precision. This paper proposes a novel sparse density feature extraction method based on the relationship between the lifting scheme and convolution, which improves the detection precision while keeping the computational complexity almost the same as the strided convolution. Experimental results on remote sensing target detection indicate that our proposed method improves both detection performance and network efficiency.