Wavelet Principal Component Analysis Research Articles

A new quantitative evaluation method for fluid constituents with NMR T1-T2 spectra in shale reservoirs

Saturation estimation of different fluids is crucial for reserve calculation and perforation location selection in shale reservoirs. Due to the low resolution of different fluids on the inverted T1-T2 spectra, different fluid signatures overlap, making it difficult to quantitatively evaluate fluid constituents and accurately calculate the fluid saturations. In this paper, a new quantitative metric that integrates discrete wavelet principal component analysis (PCA) and two-dimensional (2D) PCA is proposed to determine the optimal number of fluid constituents, and a quantitative evaluation method consisting of geometry-based unmixing method and nonnegative matrix factorization (NMF) is proposed to obtain the T1-T2 signatures of different fluids. The geometry-based unmixing method is used to obtain approximate fluid signatures called pseudo-signatures, which are processed by NMF to obtain accurate fluid signatures at a low computational cost. Subsequently, the fluid saturations are obtained from the least-squares method with full constraints. Numerical simulations are used to process the T1-T2 data. The results show that the proposed quantitative metric effectively provides the optimal number of fluid constituents, and the quantitative evaluation method accurately predicts the T1-T2 signatures and saturations of different fluids. In addition, the quantitative evaluation method requires less time than comparable methods to obtain the T1-T2 signatures and saturations of different fluids.

Nonlinear Volatility Risk Prediction Algorithm of Financial Data Based on Improved Deep Learning

With the gradual integration of global economy and finance, the financial market presents many complex financial phenomena. To increase the prediction accuracy of financial data, a new nonlinear volatility risk prediction algorithm is proposed based on the improved deep learning algorithm. First, the financial data are taken as the research object and the closing price is set as the prediction target. Then, the nonlinear volatility risk prediction model of the financial data is established through the wavelet principal component analysis noise reduction module and the long and short‐term memory network (LSTM) module, and the nonlinear volatility trend is extracted from multiple financial data series to realize the nonlinear volatility risk prediction of the financial data. During the whole experiment, the time of the research method was less than 1.5 minutes. And for 1200 test samples, the average error of data risk prediction of the proposed method is 0.0217%. The average cost of the research method is 114.25 million yuan, which is significantly lower than other existing algorithms. Experimental results show that the research method can effectively predict the risk of financial data and is more suitable for the risk control early warning of Internet financial platform.

Classification of heavy metal Cd stress in lettuce leaves based on WPCA algorithm and fluorescence hyperspectral technology

The feasibility of fluorescence hyperspectral technology to classify lettuce leaves under different heavy metal pollutant cadmium stress was discussed and demonstrated, and the wavelet principal component analysis (WPCA) algorithm was proposed to effectively reduce the dimensionality of the data in this paper. The fluorescence hyperspectral images of 1250 lettuce leaves with 5 cadmium (Cd) stress categories (contrast check, low pollution, light pollution, medium pollution and severe pollution) were obtained by fluorescence hyperspectral imaging instrument. In addition, the results of atomic absorption spectrometry showed that the Cd content in lettuce leaves increased with the increase of Cd stress concentration. Taking the entire lettuce leaf as the region of interest, the ROI fluorescence hyperspectra of the lettuce leaf was obtained through mask processing. Then, WPCA was used to reduce the dimensionality of the fluorescence hyperspectral data with different wavelet basis function including db4, db5, db6, sym5 and sym7. Support vector machine (SVM) and cuckoo search optimization support vector machine (CS-SVM) models were set up based on WPCA dimensionality reduction data. Besides, the classification accuracy rate of WPCA-CS-SVM model for Cd stress lettuce leaves was higher than that of WPCA-SVM model. Among them, the WPCA-CS-SVM model based on the third layer decomposition of the sym7 wavelet basis function had the best performance, the accuracy of the calibration set and the prediction set were 99.79% and 94.19%, and the modeling time was only 465.32 s. WPCA algorithm combined with fluorescence hyperspectral technology could effectively realize the classification of lettuce leaves under different Cd concentration stress.

Rainfall variation over Sinai Peninsula and its teleconnection to El Niño sea surface temperature

This study aims at investigating the spatial and temporal variability of the seasonal rainfall over Sinai Peninsula, Egypt, relying on rainfall data taken from gridded data of four gauge stations for 35 years. Moreover, this study determines the teleconnection between the seasonal rainfall and equatorial Pacific sea surface temperature (El Niño SST) over El Arish and Wadi Watir. Due to non-stationary characteristics of Sinai rainfall, this study employs the Wavelet Principal Component Analysis (WPCA) technique. According to the spatial characteristics of January, February and March (JFM), and October, November and December (OND) rainfall seasons, Sinai Peninsula can be divided into two zones: northern zone along the coastal area of the Mediterranean, and central-southern zone. The WPC signals showed that the dominant frequency period of Sinai rainfall ranged 2–8 years. Using Wavelet Coherence (WC), the study found a strong teleconnection between the seasonal rainfall over El Arish and Wadi Watir as well and El Niño SST at a 3-month lead time. The study results will improve the forecasting skills of flash water events over Sinai Peninsula, particularly, the northern zone in order to take suitable precautions to eliminate their impacts.

PC SWT A Hybrid Image Fusion Algorithm of Stationary Wavelet Transform and Principal Component Analysis

Image fusion is viewed as perhaps the best procedure to confine the level of uncertainty and convey a significant feeling of picture lucidity. It is a strategy of combining the appropriate information/data from a group of pictures into a solitary resultant (intertwined) picture that would render higher picture proficiency and clarity. Until now, the image fusion procedures looked like Discrete Wavelet Transform (DWT) or pixel-based methodologies. These already established methods have limited effectiveness. Also, they fail to deliver the typical outcomes like edge perseverance, spatial resolution, and shift-invariance. To get rid of these demerits, in this paper, we have proposed a hybrid approach called Principal Component Stationary Wavelet Transform (PC-SWT) that combines Principal Component Analysis (PCA) and Stationary Wavelet Transform. SWT is an algorithm that defines the wavelet transformation to compensate for the absence of translation invariance in DWT. PCA is a methodical approach that utilizes an orthogonal transformation in order to transform a group of perceptions of possibly correlated values into the principal components, which are linearly uncorrelated variables. When compared to conventional methods, PC-SWT intends to obtain a more efficient, clear, and superior quality image. This fused image is expected to have all of its preserved edges as well as its spatial resolution. In addition to this, it can also be used to deal with shift-invariance.

Biomass Estimation for Semiarid Vegetation and Mine Rehabilitation Using Worldview-3 and Sentinel-1 SAR Imagery

The surface mining activities in grassland and rangeland zones directly affect the livestock production, forage quality, and regional grassland resources. Mine rehabilitation is necessary for accelerating the recovery of the grassland ecosystem. In this work, we investigate the integration of data obtained via a synthetic aperture radar (Sentinel-1 SAR) with data obtained by optical remote sensing (Worldview-3, WV-3) in order to monitor the conditions of a vegetation area rehabilitated after coal mining in North China. The above-ground biomass (AGB) is used as an indicator of the rehabilitated vegetation conditions and the success of mine rehabilitation. The wavelet principal component analysis is used for the fusion of the WV-3 and Sentinel-1 SAR images. Furthermore, a multiple linear regression model is applied based on the relationship between the remote sensing features and the AGB field measurements. Our results show that WV-3 enhanced vegetation indices (EVI), mean texture from band8 (near infrared band2, NIR2), the SAR vertical and horizon (VH) polarization, and band 8 (NIR2) from the fused image have higher correlation coefficient value with the field-measured AGB. The proposed AGB estimation model combining WV-3 and Sentinel 1A SAR imagery yields higher model accuracy (R2 = 0.79 and RMSE = 22.82 g/m2) compared to that obtained with any of the two datasets only. Besides improving AGB estimation, the proposed model can also reduce the uncertainty range by 7 g m−2 on average. These results demonstrate the potential of new multispectral high-resolution datasets, such as Sentinel-1 SAR and Worldview-3, in providing timely and accurate AGB estimation for mine rehabilitation planning and management.

Image Fusion of SAR and Optical Images for Identifying Antarctic Ice Features

Remote sensing data plays an important role in extracting thematic information from various sensors having different spectral, spatial and temporal resolutions. The present study aims at fusion of Radar Imaging Satellite-1 Fine Resolution Stripmap-1 and ResourceSAT-2 Linear Imaging Self Scanning Scanner-4 (LISS-4) images over Indian Antarctic Research Station Maitri and its surroundings to generate a better product which contains the characteristics of both the spectral information from LISS-4 and the spatial details of SAR. Different pixel-based fusion techniques such as Brovey Transform, Principal Component Analysis (PCA), Intensity Hue Saturation and Wavelet Principal Component Analysis (W-PCA) have been used in the present study. These image fusion techniques have been applied for the whole scene as well as for individual surface features like melt ponds, crevasses, freshwater lake, blue ice, oasis and lake ice for better discrimination of features. Quality assessment is performed by evaluating the performance of these algorithms using visual, spatial (High Pass Correlation Coefficient and Entropy) and spectral (Root Mean Square Error, Correlation Coefficient, ERGAS and Universal Quality Index) parameters. It is found that the identification of certain features such as crevasses, blue ice, melt ponds and lake ice has been improved with fused images compared to the original multi-spectral and SAR images. PCA and W-PCA fusion techniques offer better performance as compared to the rest of the techniques.

A Face Recognition System Based on Principal Component Analysis-Wavelet and Support Vector Machines

Face recognition can represent a key requirement in various types of applications such as human-computer interface, monitoring systems, as well as personal identification. In this paper, design and implement of face recognition system are introduced. In this system, a combination of principal component analysis (PCA) and wavelet feature extraction algorithms with support vector machine (SVM) and K-nearest neighborhood classifier is used. PCA and wavelet transform methods are used to extract features from face image using and identify the image of the face using SVMs classifier as well as the neural network are used as a classifier to compare its results with the proposed system. For a more comprehensive comparison, two face image databases (Yale and ORL) are used to test the performance of the system. Finally, the experimental results show the efficiency and reliability of face recognition system, and the results demonstrate accuracy on two databases indicated that the results enhancement 5% using the SVM classifier with polynomial Kernel function compared to use feedforward neural network classifier.

Insight into Polycyclic Aromatic Hydrocarbons in Unconventional Oil via Concentration-Resolved Fluorescence Spectroscopy Coupled with Data Mining Techniques

The exploration, production, and transportation of unconventional oils have attracted increasing attention for their economic value and environmental pressure. However, the previous analytical techniques of conventional oils encounter bottlenecks because of the separation difficulties of the unresolved complex mixtures. It is of great value to develop new methods to pursue a more detailed investigation of the chemical compositions of unconventional oil. Concentration-resolved fluorescence spectroscopy (CRFS) was developed to characterize the multi-dimensional fluorescence features of polycyclic aromatic hydrocarbons in unconventional oil samples. Laboratory simulation experiments of thermal evolution and biodegradation were designed to verify the effectiveness of CRFS compared to gas chromatography–flame ionization detector and gas chromatography–mass spectrometry. Dual-tree complex wavelet analysis and principal component analysis were used to remove redundant information and extract more detailed and effective information on CRFS spectra, and then a generalized regression neural network was used to classify and identify crude oil samples of different heavy oil species. With 100% accuracy, this computer data processing combined CRFS method is proven to be fast, accurate, and economical and is expected to be an effective method to solve the present problem of unconventional oil analysis.

Depth Profiling of Organic Light-Emitting Diodes by ToF-SIMS Coupled with Wavelet–Principal Component Analysis

The investigation of interface effects in hybrid organic/inorganic electronic and photonic devices is a key step for improving their performance and operation stability. Depth profile analysis by t...

A new wavelet conjunction approach for estimation of relative humidity: wavelet principal component analysis combined with ANN

Relative humidity (RH) has an important effect on precipitation, especially in arid and semiarid regions. Prediction of RH has been the focus of attention of climate change researchers as well. In this investigation, the accuracy of six intelligent models, including an artificial neural network (ANN), a co-active neuro-fuzzy inference system (CANFIS), principal component analysis (PCA) combined with ANN (PCA–ANN) and three hybrid wavelet-artificial intelligence models, including WANN, WCANFIS and WPCA–ANN, was evaluated in daily RH prediction. Thirty weather stations located in different climates in Iran for the period 2000–2010 were selected for the evaluation and comparison of these models. The performance of each model was evaluated using correlation coefficient (r) and normal root mean square error (NRMSE). Based on the statistical evaluation criteria, the accuracy ranks of the six models were: WPCA–ANN, WCANFIS, WANN, PCA–ANN, ANN and CANFIS. The results indicated that the WPCA–ANN model was the optimal model for estimation of RH, and the range of NRMSE and r values were from 0.009 to 0.080 and from 0.996 to 0.999, respectively. Overall, WPCA–ANN is a new approach that can be successfully applied to predict RH with a high accuracy.

Multi Focus Image Fusion using Combined Median and Average Filter based Hybrid Stationary Wavelet Transform and Principal Component Analysis

Poor illumination, less background contrast and blurring effects makes the medical, satellite and camera images difficult to visualize. Image fusion plays the vital role to enhance image quality by resolving the above issues and reducing the image quantity. The combination of spatial and spectral technique Discrete Wavelet Transform and Principal Component Analysis (DWT-PCA) decrease processing time and reduce number of dimensions but down sampling causes lack of shift invariance that results in poor quality final fused image. At first this work uses combined median and average filter that eliminates noise in the image which is caused by illumination, camera circuitry and sensor at preprocessing stage. Then, hybrid Stationary Wavelet Transform and Principal Component Analysis (SWT-PCA) technique is implemented to increase output image accuracy by eliminating down sampling and is not influenced by artifacts and blurring effects. Further, it can overcome the trade-off of Heisenberg’s uncertainty principle by improving accuracy in both domains, time (spatial) as well as frequency (spectral). The proposed combined median and average filter with hybrid SWT-PCA algorithm measures quality parameters, such as peak signal to noise ratio (PSNR), mean squared error (MSE) and normalized cross correlation (NCC) and improved results depict the superiority of the algorithm than existing techniques.

Face Recognition Based on Dwt and PCA Feature Extraction Using Artificial neural network Classifier

Face Recognition is a prototype with stirring functions in the direction of facial features for consent and validation. In this approach, a particular type of face recognition systems is bond different feature extraction approaches to conquer the image entity configuration. To solve face recognition under unreliable pose is rigorous pose invariant features with effective approach. In this work, an algorithm is implemented in MATLAB and performance evaluation of achievement rate with existing techniques is proposed. Also, the performance of the face recognition system is based on feature extractions using wavelet transform and demonstrates the improved quality image. This work provides Artificial Neural Network (ANN) for face recognition and using a combination of Discrete Wavelet Transform (DWT) and Principal Component Analysis (PCA) algorithm for feature extraction and acquires a transformed face image to raise the features. The results demonstrated that the proposed system has higher accuracy, precision and sensitivity than face recognition using different feature extractors.

HYPERSPECTRAL IMAGE SHARPENING BASED ON EHLERS FUSION

Abstract. As the application of hyperspectral images is increasing, many researchers attempt to extend existing pansharpening techniques to hyperspectral images. This paper focuses on the application of Ehlers fusion to hyperspectral image sharpening. Ehlers fusion involves two crucial algorithms: filter technique in the frequency domain and intensity transform. In this study, different filter types and intensity transform methods were analysed separately. With a combination of filter types and intensity transforms, the fusion procedure was implemented to test data sets. The spectral profiles of the pixels of the images were then used as a tool to control the quality of the fused image. Finally, the performance of Ehlers fusion is compared with Principle Component (PC) analysis, Gram-Schmidt transform (Gram-Schmidt), High-Pass Filtering in the spatial domain (HPF), and Wavelet Principal Component (Wavelet-PC) analysis using the same input data. The comparison shows that Ehlers high-pass filter fusion shows outstanding performance both on spatial enhancement and colour preservation.

Classification of Motor Imagery EEG Using Combined Feature Vectors Based on Wavelet Transform and Principal Component Analysis

Classification of Motor Imagery EEG Using Combined Feature Vectors Based on Wavelet Transform and Principal Component Analysis

Comparison of various pan-sharpening methods using Quickbird-2 and Landsat-8 imagery

Pan-sharpening is the process of transferring the spatial resolution of panchromatic (PAN) image to a multispectral (MS) image for producing a single image with high spatial detail and rich spectral information. In this study, PAN and MS imagery of Quickbird-2 and Landsat-8 are fused separately, using ten different pan-sharpening methods such as principal component analysis (PCA), modified-intensity hue saturation (M-IHS), multiplicative, brovey transform (BT), wavelet-principal component analysis (W-PCA), hyperspectral color space (HCS), high-pass filter (HPF), Gram-Schmidt (GS), Fuze Go, and non-subsampled contourlet transform (NSCT). The effectiveness of these techniques is assessed and compared by qualitative analysis and 14 quantitative analysis methods including bias, correlation coefficient (CC), difference in variance (DIV), relative dimensionless global error in synthesis (ERGAS), universal image quality index (Q), relative average spectral error (RASE), root mean square error (RMSE), structural similarity index method (SSIM), signal-to-noise ratio (SNR), peak SNR (PSNR), spatial correlation coefficient (SCC), image entropy (E), and gradient and quality with no reference image (QNR). The results of both analysis types show that the Fuze Go and NSCT produced the best fused image with high spatial detail and rich spectral information followed by the HPF and GS.

Efficient K-Nearest Neighbor Searches for Multiple-Face Recognition in the Classroom based on Three Levels DWT-PCA

The main weakness of the k-Nearest Neighbor algorithm in face recognition is calculating the distance and sort all training data on each prediction which can be slow if there are a large number of training instances. This problem can be solved by utilizing the priority k-d tree search to speed up the process of k-NN classification. This paper proposes a method for student attendance systems in the classroom using facial recognition techniques by combining three levels of Discrete Wavelet Transforms (DWT) and Principal Component Analysis (PCA) to extract facial features followed by applying the priority of k-d tree search to speed up the process of facial classification using k-Nearest Neighbor. The proposed algorithm is tested on two datasets that are Honda/UCSD video dataset and our dataset (AtmafaceDB dataset). This research looks for the best value of k to get the right facial recognition using k-fold cross-validation. 10-fold cross-validation at level 3 DWT-PCA shows that face recognition using k-Nearest Neighbor on our dataset is 95.56% with k = 5, whereas in the Honda / UCSD dataset it is only 82% with k = 3. The proposed method gives computational recognition time on our dataset 40 milliseconds.

Evaluation of pan-sharpening methods for spatial and spectral quality

Many pan-sharpening methods have been proposed to fuse the high spectral and low spatial resolution of multispectral (MS) image with the high spatial resolution of panchromatic (PAN) image to produce a multispectral image with improved spatial resolution. In this study, the effectiveness of pan-sharpening methods such as principal component analysis (PCA), brovey transform (BT), modified intensity hue saturation (M-IHS), multiplicative, wavelet-intensity-hue-saturation (W-IHS), wavelet principal component analysis (W-PCA), hyperspectral colour space (HCS), high-pass filter (HPF), gram-schmidt (GS), subtractive resolution merge (SRM), Fuze Go and Ehlers was assessed and compared by fusing the PAN and MS imagery of Quickbird-2. The qualities of the pan-sharpening methods were evaluated by both visual and quantitative analyses with respect to spatial and spectral fidelity. In quantitative analysis, the spectral indices such as spectral angle mapper (SAM), relative dimensionless global error in synthesis (ERGAS), structural similarity index method (SSIM), relative average spectral error (RASE), correlation coefficient (CC) and universal image quality index (Q) were used. The spatial indices such as spatial correlation coefficient (SCC), gradient and image entropy (E) were used. The result of both analyses revealed that the Ehlers and Fuze Go methods performed better than the other methods. The Ehlers method was superior by retaining the colour information, and Fuze Go best enhanced the spatial details in the fused image.

Multi-variable process data compression and defect isolation using wavelet PCA and genetic algorithm

This paper characterizes an approach to data compression and defect isolation for the multi-variable process by introducing the wavelet principal component analysis (PCA) and the genetic algorithms. In the defect analysis process, data compression is a critical phase. In our case of study, this can be achieved through the wavelet PCA. We can, through the use of such a technique, filter the data noise and the measurement errors by combining the PCA and the wavelet analysis. The genetic algorithm optimization feature is then employed in structuring the residues of the defect isolation. We present the principle of the PCA as well as the wavelet compression property. Then, we describe both the defect isolation classical method by structuring the residues and the principle of optimizing a problem by the genetic algorithms. The proposed approach is implemented on a statistic system and the Tennessee Eastman process. In comparison with other previous methods, the obtained results mirror the performance of the approach to defect isolation.

Adjustment and Assessment of the Measurements of Low and High Sampling Frequencies of GPS Real-Time Monitoring of Structural Movement

Global Positioning System (GPS) structural health monitoring data collection is one of the important systems in structure movement monitoring. However, GPS measurement error and noise limit the application of such systems. Many attempts have been made to adjust GPS measurements and eliminate their errors. Comparing common nonlinear methods used in the adjustment of GPS positioning for the monitoring of structures is the main objective of this study. Nonlinear Adaptive-Recursive Least Square (RLS), extended Kalman filter (EKF), and wavelet principal component analysis (WPCA) are presented and applied to improve the quality of GPS time series observations. Two real monitoring observation systems for the Mansoura railway and long-span Yonghe bridges are utilized to examine suitable methods used to assess bridge behavior under different load conditions. From the analysis of the results, it is concluded that the wavelet principal component is the best method to smooth low and high GPS sampling frequency observations. The evaluation of the bridges reveals the ability of the GPS systems to detect the behavior and damage of structures in both the time and frequency domains.