Local Tangent Space Alignment Research Articles

Application of multi-angle millimeter-wave radar detection in human motion behavior and micro-action recognition

Millimeter-wave radar is widely used in family safety, rehabilitation, and assisted living due to its ability to operate in all weathers and all day. To address the problem whereby the radar detection angle significantly impacts human behavior recognition, a recognition method based on multi-angle radar observation is adopted. We proposed a novel radar selection method called the energy domain ratio method to choose a radar with more sensitive features. Then, local tangent space alignment and an adaptive extreme learning machine (ELM) are presented to enhance the recognition rate of the model in a high-noise environment. A multi-angle entropy feature and an improved ELM are developed to identify human micro-motion in a low-noise indoor environment. The effect of observation distance on the recognition effect was also explored. The experimental results show that the proposed model has a more than 86% recognition rate for human behavior in outdoor scenes and a recognition accuracy of more than 98% for indoor micro-action.

Feature extraction and fault detection scheme via improved locality preserving projection and SVDD

Manifold learning is widely adopted for the fault detection of industrial processes. However, the quality of low-dimensional embedding coordinates can be adversely affected by ill-constructed graph Laplacian. An improved locality preserving projection (ILPP) scheme is proposed. ILPP is built on a geometrically inspired Laplacian, and the Riemannian metric is used to find the suitable bandwidth parameter. The proposed approach combines the advantages of ILPP in preserving manifold data structures and those of support vector data description (SVDD) in handling complex process data distributions. Case studies on helix data, hot strip mill, and Pensim benchmark processes demonstrate the utility and feasibility of the proposed approach. The average fault detection rate for proposed ILPP is 99%, which is higher than locality preserving projection (LPP; 87.8%), local tangent space alignment (LTSA; 74.9%), and principal component analysis (PCA; 90.6%).

Laser-Induced Breakdown Spectroscopy Combined with Nonlinear Manifold Learning for Improvement Aluminum Alloy Classification Accuracy.

Laser-induced breakdown spectroscopy (LIBS) spectra often include many intensity lines, and obtaining meaningful information from the input dataset and condensing the dimensions of the original data has become a significant challenge in LIBS applications. This study was conducted to classify five different types of aluminum alloys rapidly and noninvasively, utilizing the manifold dimensionality reduction technique and a support vector machine (SVM) classifier model integrated with LIBS technology. The augmented partial residual plot was used to determine the nonlinearity of the LIBS spectra dataset. To circumvent the curse of dimensionality, nonlinear manifold learning techniques, such as local tangent space alignment (LTSA), local linear embedding (LLE), isometric mapping (Isomap), and Laplacian eigenmaps (LE) were used. The performance of linear techniques, such as principal component analysis (PCA) and multidimensional scaling (MDS), was also investigated compared to nonlinear techniques. The reduced dimensions of the dataset were assigned as input datasets in the SVM classifier. The prediction labels indicated that the Isomap-SVM model had the best classification performance with the classification accuracy, the number of dimensions and the number of nearest neighbors being 96.67%, 11, and 18, respectively. These findings demonstrate that the combination of nonlinear manifold learning and multivariate analysis has the potential to classify the samples based on LIBS with reasonable accuracy.

Varying-parameter time-frequency manifold for gearbox fault diagnosis

Abstract The vibration signals of a faulty gearbox are non-stationary and contaminated by heavy background noise. Time-frequency transform is able to present the non-stationary fault impulsive features in the time-frequency distribution (TFD). However, the time-frequency fault information is still contaminated by the noise. This paper proposes a varying-parameter time-frequency manifold (VPTFM) method with the aim to remove the noise in the TFD for accurate identification of gearbox fault. First, a high-dimensional TFD is constructed by performing short- time Fourier transform (STFT) using some variable window lengths. Then, local tangent space alignment (LTSA) algorithm is carried out on the high-dimensional TFD to extract the manifold of the fault impulsive features with two dimensions, in which Rényi entropy is employed to select the proper neighborhood size for the LTSA by evaluating the first dimensional manifold. Afterwards, a threshold is designed by exploring the characteristics of the amplitudes of the manifold at two dimensions to adaptively remove the noise survived in the first dimensional manifold. Finally, the amplitudes at the frequency possessing the largest energy in the denoised manifold are taken out for spectrum analysis to identify the fault characteristic frequency. The enhanced performance of the proposed method in extraction of fault impulses and removal of background noise is validated by a gearbox experimental vibration signal measuring when the gear has a wearing fault.

Improved Multi-Bandwidth Mode Manifold for Enhanced Bearing Fault Diagnosis

Variational mode decomposition (VMD) has been proved to be useful for extraction of fault-induced transients of rolling bearings. Multi-bandwidth mode manifold (Triple M, TM) is one variation of the VMD, which units multiple fault-related modes with different bandwidths by a nonlinear manifold learning algorithm named local tangent space alignment (LTSA). The merit of the TM method is that the bearing fault-induced transients extracted contain low level of in-band noise without optimization of the VMD parameters. However, the determination of the neighborhood size of the LTSA is time-consuming, and the extracted fault-induced transients may have the problem of asymmetry in the up-and-down direction. This paper aims to improve the efficiency and waveform symmetry of the TM method. Specifically, the multi-bandwidth modes consisting of the fault-related modes with different bandwidths are first obtained by repeating the recycling VMD (RVMD) method with different bandwidth balance parameters. Then, the LTSA algorithm is performed on the multi-bandwidth modes to extract their inherent manifold structure, in which the natural nearest neighbor (Triple N, TN) algorithm is adopted to efficiently and reasonably select the neighbors of each data point in the multi-bandwidth modes. Finally, a weight-based feature compensation strategy is designed to synthesize the low-dimensional manifold features to alleviate the asymmetry problem, resulting in a symmetric TM feature that can represent the real fault transient components. The major contribution of the improved TM method for bearing fault diagnosis is that the pure fault-induced transients are extracted efficiently and are symmetrical as the real. One simulation analysis and two experimental applications in bearing fault diagnosis validate the enhanced performance of the improved TM method over the traditional methods. This research proposes a bearing fault diagnosis method which has the advantages of high efficiency, good waveform symmetry and enhanced in-band noise removal capability.

Blind false data injection attacks in smart grids subject to measurement outliers

ABSTRACT False data injection attacks (FDIAs) can manipulate measurement data from Supervisory Control and Data Acquisition (SCADA) system and threat state estimation in smart grids. Blind FDIAs (BFDIAs) enhance traditional FDIAs, which eliminate the limitation of grasping measurement Jacobian matrix H in advance, but when there are outliers in measurement data, attack performance is degraded. In this paper, improved BFDIAs are proposed. In off-line phase, low-dimensional measurement matrix without outliers calculated by Linear Local Tangent Space Alignment algorithm (LLTSA) is sent into Continuous Deep Belief Network (CDBN) as training data to learn their probability distribution. In on-line phase, real-time low-dimensional measurement matrix with outliers are sent into the trained model as inputs, and outputs are reconstructed by the probability distribution in off-line phase, which eliminates the influence of outliers indirectly. Simulations are implemented on PJM 5-bus and IEEE 14-bus systems to verify the performance of proposed strategy compared with PCA-based BFDIAs.

Multifrequency Analysis via LTSA and Its Application on Carbonate Reservoir Delineation

Multi-frequency analysis is an effective tool for seismic data interpretation, such as fluvial channel characterization and sand bodies interpretation. Due to the broadband and non-stationary properties of seismic data, time-frequency transform is widely used for extracting multi-frequency components, e.g., S-transform and wavelet transform. However, how to fuse these extracted band-limited multi-frequency components for complex reservoir characterization is still a hot topic in exploration geophysics. In this study, we propose a multi-frequency analysis workflow for complex reservoir delineation based on the local tangent space alignment (LTSA). First, we utilize the generalized S-transform (GST) for extracting multi-frequency components, which is easy to implement and also a valid time-frequency analysis tool. Afterward, we adopt LTSA for blending the decomposed multi-frequency components. Finally, we apply the proposed workflow on a 3D post-stack field data for delineating complex carbonate reservoir. The results prove that the proposed workflow can effectively delineate carbonate reservoir, which is superior to the individual seismic attribute analysis and the contrastive blending method.

Linear Local Tangent Space Alignment with Autoencoder

Linear Local Tangent Space Alignment with Autoencoder

Multi-Stage Feature Extraction and Classification for Ship-Radiated Noise.

Due to the complexity and unique features of the hydroacoustic channel, ship-radiated noise (SRN) detected using a passive sonar tends mostly to distort. SRN feature extraction has been proposed to improve the detected passive sonar signal. Unfortunately, the current methods used in SRN feature extraction have many shortcomings. Considering this, in this paper we propose a new multi-stage feature extraction approach to enhance the current SRN feature extractions based on enhanced variational mode decomposition (EVMD), weighted permutation entropy (WPE), local tangent space alignment (LTSA), and particle swarm optimization-based support vector machine (PSO-SVM). In the proposed method, first, we enhance the decomposition operation of the conventional VMD by decomposing the SRN signal into a finite group of intrinsic mode functions (IMFs) and then calculate the WPE of each IMF. Then, the high-dimensional features obtained are reduced to two-dimensional ones by using the LTSA method. Finally, the feature vectors are fed into the PSO-SVM multi-class classifier to realize the classification of different types of SRN sample. The simulation and experimental results demonstrate that the recognition rate of the proposed method overcomes the conventional SRN feature extraction methods, and it has a recognition rate of up to 96.6667%.

EEG fading data classification based on improved manifold learning with adaptive neighborhood selection

In electroencephalogram (EEG) signal analysis, data fading problem exists from signal production to collection by brain-computer interface (BCI) device, which can be raised by BCI device deficiency, dynamic network limitation and subject issue. EEG data fading problem changes the distribution of data, which results in the movement of the cluster center and fuzzy class boundary after feature extraction with negative effects in EEG classification results. To decrease the adverse influence of data fading, a novel fading data classification method based on manifold learning and adaptive neighborhood selection is proposed in this paper to mitigate this adverse effect of data fading. In the proposed method, after neighborhood selection according to local linearity, data are mapped into manifold space through local tangent space alignment (LTSA) for dimensionality reduction. The method is carried out on BCI Competition 2008 – Graz data set A of four-class EEG data of motor imagery (MI) experiments. The experimental results are compared with conventional LTSA and indicate that the proposed method effectively improves the classification accuracy of fading data.

Application of a whale optimized variational mode decomposition method based on envelope sample entropy in the fault diagnosis of rotating machinery

In recent years, the variational mode decomposition (VMD) method has been introduced for rotating machinery fault diagnosis. However, the results largely depend on its parameters. When an optimization algorithm is employed to optimize these parameters, the fitness function is critical. In this paper, a new fitness function, envelope sample entropy, is constructed. Based on this, a whale optimized VMD method is proposed for rotating machinery fault diagnosis. First, the vibration signals were decomposed by the optimized VMD method to obtain a series of intrinsic mode functions (IMFs), from which the IMFs containing the main information were selected. Then, features were extracted from the selected IMFs and their dimensions were reduced using the local tangent space alignment method. Finally, support vector machine was adopted for fault identification. Compared with related methods, the experiment results show that the proposed method obtains a higher fault recognition accuracy.

Adaptive sliding window LSTM NN based RUL prediction for lithium-ion batteries integrating LTSA feature reconstruction

The extraction and prediction of health indicators (HIs) are two vital aspects in remaining useful life (RUL) prediction of lithium-ion batteries (LIBs). Aiming to estimate the RUL precisely, a novel integrated prediction method is proposed for LIBs on the basis of local tangent space alignment (LTSA) feature extraction and adaptive sliding window long short-term memory neural networks (ASW LSTM NN). In the proposed method, the indirect HI is first extracted by LTSA automatically to replace the unmeasurable capacity, and a strong correlation between them is verified by the Spearman correlation coefficient. Following that, with the extracted HI, an adaptive sliding window LSTM is constructed to conduct the RUL estimation of LIBs in routine environment. For the structured neural network, corresponding inputs are dynamically selected by the sliding window, while a varying length window mechanism is devised to update the window data along with the predicting cycle. Hence, the designed predicting method can learn the long-term dependencies by means of the inherent nature of LSTM and simultaneously capture the local fluctuations via the adaptive sliding window. Eventually, extensive experiments are conducted and corresponding results are compared with those obtained by existed approaches. The effectiveness of the integrated prediction method is validated, and our proposed model is proved to be more accurate in predicting the RUL compared with existed approaches.

A novel AdaBoost ensemble model based on the reconstruction of local tangent space alignment and its application to multiple faults recognition

In order to recognize the coupling faults of complex industrial processes effectively, this paper proposed an AdaBoost ensemble (AdBE) model based on the reconstruction of local tangent space alignment (RLTSA). First, to obtain the low-dimensional manifold structure embedded in original data space, RLTSA algorithm is designed by constructing the tangent space in the neighborhood of each data point to represent the local geometry and then aligning them to obtain the embedding coordinates. Secondly, to solve the loss of global feature information, an affine matrix is used to inversely map the low-dimensional coordinates to restore the global structure information. Thirdly, based on the above reconstruction of local tangent space alignment, an AdaBoost ensemble (AdBE) classifier is constructed for multiple faults recognition in which the AdaBoost algorithm is used to improve the performance of Decision Tree (DT), and One vs. Rest (OvR) ensemble strategy is introduced to establish the RLTSA-AdBE model. Case studies are conducted using a three-dimensional S_curve data set and the Tennessee Eastman process (TEP) to respectively verify the performance of the RLTSA algorithm and the proposed RLTSA-AdBE model. The simulation results indicate that the proposed method guarantees high diagnosis accuracy and macro_F1 Score of coupling faults recognition.

Visible-NIR spectral characterization and grade inversion modelling study of the Derni copper deposit

At present, chemical analysis is the main method for copper ore grade verification. Because of its long test cycle and lag effect relative to mining and ore blending processes, this approach cannot effectively reduce losses in mineral resource mining. An effective way to solve this problem is to conduct research on in situ grade determination methods for ore bodies based on visible-near-infrared hyperspectral grade modelling techniques. However, the accuracy of the modelling is seriously reduced by the large redundancy of hyperspectral data and the self-limiting nature of some machine learning methods. Therefore, the accurate selection of dimensionality reduction algorithms and machine learning algorithms determines the accuracy of the inverse model, and the setting of parameters such as dimensionality reduction, number of nearest neighbour points and number of hidden layers in neural networks is crucial. In this paper, 190 ore samples were collected from the open pit of the Derni copper deposit in Dawu town, Guoluo Tibetan Autonomous Prefecture, Qinghai Province, China. First, the visible-near-infrared spectral data for the sample set were obtained with an SVC HR-1024 spectrometer. The copper grade of the sample set was verified by chemical analysis. Three algorithms—the Laplacian eigenmap (LE), local tangent space alignment (LTSA) and local linear embedding (LLE)—were used to reduce the dimensionality of the original hyperspectral data. The original data and the three hyperspectral datasets after dimensionality reduction were used as data sources. Several Derni copper grade inversion models based on two machine learning algorithms, the backpropagation neural network and radial basis function (RBF) neural network, were developed. Finally, the coefficient of determination (R2), mean absolute error (MAE) and root mean square error (RMSE) were used to evaluate the accuracy of each model. The results show that the accuracy of the model built with spectral data processed by the dimension reduction algorithm is higher than that of the model constructed with the original spectral data. Among the above combined models, the LLE-RBF model has the highest inversion accuracy. The MAE of the model is 0.117%, the RMSE is 0.136, and R2 is 0.934.

NRIC: A Noise Removal Approach for Nonlinear Isomap Method

Nonlinear manifold learning is a popular dimension reduction method that determines large and high dimensional datasets’ structures. However, these nonlinear manifold learning methods, including isomap and locally linear embedding, are sensitive to noise. In this paper, we focus on the noisy nonlinear manifold learning method, such as Isomap. The main problem of the Isomap is sensitivity to noise. Our proposed new method noise removal isomap with a classification (NRIC), is based on the local tangent space alignment (LTSA) algorithm with classification techniques to remove noises and optimize neighborhood structure Isomap. The primary purpose of the NRIC is to increase efficiency, reduce noise, and improve the performance of the graph. Experiments on the real-world datasets have shown that the NRIC method outperforms efficiently and maintains an accurate low dimensional representation of the noisy nonlinear manifold learning data. The results show that LTSA with classification techniques provides high accuracy, mean-precision, mean-recall, and areas under the (ROC) curve (AUC) of the high dimensional datasets and optimizes the graphs.

Modified Deep Autoencoder Driven by Multisource Parameters for Fault Transfer Prognosis of Aeroengine

The existing fault prognosis techniques of aeroengine mostly focus on a single monitoring parameter under stable condition, and have low adaptability to new prognosis scenes. To boost the fault prognosis capability cross aeroengines, modified deep autoencoder (MDAE) driven by multi-source parameters is proposed in this article. First, the sensitive multi-source parameters are selected and fused using linear local tangent space alignment to define a fused health index (FHI) to characterize performance degradation of aeroengine. Second, MDAE model is constructed with adaptive Morlet wavelet to flexibly establish accurate mapping hidden in the FHI under analysis. Third, parameter transfer learning is used to provide good initial parameters for enabling the constructed MDAE to have cross-domain fault prognosis capability. The proposed method is used to analyze both the simulation multisource performance degradation parameters of aeroengines (system level) and experiment run-to-failure bearing datasets (component level). The results confirm the feasibility of the proposed method in cross-domain fault prognosis of aeroengines, which outperforms the existing methods.

Optimal Deep Belief Network with Opposition based Pity Beetle Algorithm for Lung Cancer Classification: A DBNOPBA Approach

Background and ObjectiveThis research proposes a successful method of extracting Gray-Level Co-occurrence Matrix (GLCM) picture handling models to classify low-and high-metastatic cancer organisms with five prevalent cancer cell line pairs, coupled with the scanning laser picture projection technique and the typical textural function, i.e. contrast, correlation, power, temperature and homogeneity. The most significant level of disease for highly metastatic cancer cells are the degree of disturbance, contrast as well as entropy refers to the energy and homogeneity. A texture classification scheme to quantify the emphysema in Computed Tomography (CT) pictures is performed. Local binary models (LBP) are used to characterize areas of concern as texture characteristics and intensity histograms. A wavelet filter is used to acquire the informative matrix of each picture and decrease the dimensionality of the function space in the suggested method. A four-layer profound creed network is also used to obtain characteristics of elevated stage. Local Tangent Space Alignment (LTSA) is then used to compress the multi-domain defect characteristics into low dimensional vectors as a dimension reduction method. An unmonitored deep-belief network (DBN) is intended for the second phase to learn the unmarked characteristics. The strategy suggested uses Opposition Based Teaching (OBL), Position Clamping (PC) and the Cauchy Mutation (CM) to improve the fundamental PBA efficiency. MethodsThis research presents a fresh meta-heuristic algorithm called Opposition-Based Pity Beetle Algorithm (OPBA), which assesses effectiveness against state-of-the-art algorithms. OBL speeds up the convergence of the technique as both PC and CM assist OPBA with escaping local optima. The suggested algorithm was motivated by the behaviour of the beetle, which had been named six-toothed spruce bark beetle to aggregate nests and meals. This beetle can be found and harvested from weakened trees ' bark in a forest, while its populace can also infest healthy and robust trees when it exceeds the specified threshold. Results & ConclusionThe methodology has been evaluated on CT imagery from the Lung Image Database Consortium and Image Resources Initiative (LIDC-IDRI), with a maximum sensitivity of 96.86%, precision of 97.24%, and an accuracy of 97.92%.

Optimal deep belief network with opposition‐based hybrid grasshopper and honeybee optimization algorithm for lung cancer classification: A DBNGHHB approach

AbstractIn this manuscript, a new approach using deep belief network (DBN) along opposition‐based hybrid grasshopper and honey bee optimization algorithm for lung cancer classification is proposed. Chest computed tomography (CT) is commonly used to diagnosis the lung tumors. Initially, the image quality is improved by preprocessing techniques, and then the features like texture, color and shape are extracted. Several functions have been originating from the second order first gray level statistics like modified angles, high‐order algebraic time invariant, Gaussian defining properties and new spectral power metrics. Recently, a local binary pattern geometric characteristic descriptor has been demonstrated in the extraction and classification of pulmonary nodules. Furthermore, some functionality is stripped away for comparison purposes. Dimension reduction is significant for the implementation of algorithms in machine learning. The other special approaches can be implemented to determine the functionalities due to vast set of features. To remove the unused and obsolete features between the feature selection approaches, the multivariate approach like local tangent space alignment is used. Finally, DBN is used to categorize pulmonary CT images as malignant or benign, and is calibrated to the detection of lung cancer classification by the opposition‐based hybrid grasshopper and honey bee optimization algorithm. The Lung Image Database Consortium including Image Resources Initiative database are analyzed the network services, and the experimental results shows that the DBN network represents 97.52% accuracy, 96% sensitivity and 94.58% specificity.

Local coordinate weight reconstruction for rolling bearing fault diagnosis

The high dimensionality data originating from rolling bearing measuring signals with non-linearity and low signal to noise ratio often contains too much disturbance like interference and redundancy for accurate condition identification. A novel manifold learning named Local coordinate weight reconstruction (LCWR) is proposed to remove such disturbance. Due to the different contribution of samples to their manifold structure, weight value is used for the contribution difference. By reconstructing local low-dimensional coordinates according to its weight function about geodesic distance in neighborhood, LCWR targets to reduce reconstruction error, preserve intrinsic structure of the high dimensionality data, eradicate disturbance and extract sensitive features as global low-dimensional coordinates. The experimental results show that the intraclass aggregation and interclass differences of global low-dimensional coordinates extracted via LCWR are better than those of local tangent space alignment (LTSA), locally linear embedding (LLE) and principal component analysis (PCA). The accuracy reaches the highest 96.43 % using SVM to identify LCWR based global low-dimensional coordinates, and its effectiveness is testified in diagnosis of rolling bearing fault.

Nonlinear Feature Extraction Through Manifold Learning in an Electronic Tongue Classification Task.

A nonlinear feature extraction-based approach using manifold learning algorithms is developed in order to improve the classification accuracy in an electronic tongue sensor array. The developed signal processing methodology is composed of four stages: data unfolding, scaling, feature extraction, and classification. This study aims to compare seven manifold learning algorithms: Isomap, Laplacian Eigenmaps, Locally Linear Embedding (LLE), modified LLE, Hessian LLE, Local Tangent Space Alignment (LTSA), and t-Distributed Stochastic Neighbor Embedding (t-SNE) to find the best classification accuracy in a multifrequency large-amplitude pulse voltammetry electronic tongue. A sensitivity study of the parameters of each manifold learning algorithm is also included. A data set of seven different aqueous matrices is used to validate the proposed data processing methodology. A leave-one-out cross validation was employed in 63 samples. The best accuracy () was obtained when the methodology uses Mean-Centered Group Scaling (MCGS) for data normalization, the t-SNE algorithm for feature extraction, and k-nearest neighbors (kNN) as classifier.