Reduction Principal Component Analysis Research Articles

Machine Learning‐Based Clustering of Oceanic Lagrangian Particles: Identification of the Main Pathways of the Labrador Current

AbstractModeled geospatial Lagrangian trajectories are widely used in Earth Science, including in oceanography, atmospheric science and marine biology. The typically large size of these data sets makes them arduous to analyze, and their underlying pathways challenging to identify. Here, we show that we can use a machine learning unsupervised k‐means++ clustering method combined with expert aggregation of clusters to identify the pathways of the Labrador Current from a large set of modeled Lagrangian trajectories. The presented method requires simple pre‐processing of the data, including a Cartesian correction on longitudes and a principal component analysis reduction. The clustering is performed in a kernelized space and uses a larger number of clusters than the number of expected pathways. To identify the main pathways, similar clusters are grouped into pathway categories by experts in the circulation of the region of interest. We find that the Labrador Current mainly follows a westward‐flowing and an eastward retroflecting pathway (20% and 50% of the flow, respectively) that compensate each other through time in a see‐saw behavior. These pathways experience a strong variability (representing through time 4%–42% and 24%–73% of the flow, respectively). Two thirds of the retroflection occurs at the tip of the Grand Banks, and one quarter at Flemish Cap. The westward pathway is mostly fed by the on‐shelf branch of the Labrador Current, and the eastward pathway by the shelf‐break branch. Among the pathways of secondary importance, we identify a previously unreported one that feeds the subtropics across the Gulf Stream.

Nonlinear and nonstationary detection and quantification of multi-scale measured signals for bridge structure

The assessment of nonlinear and nonstationary levels in measured bridge signals is a vital step in system identification and long-term health monitoring for the bridge structure. The field-measured signals from the bridge structure are inherently weak and multiscale, so a specific adaptive variational mode decomposition (AVMD) is proposed to decompose them and extract their included multi-scale features. Combination the adaptability of empirical mode decomposition with the dimensionality reduction of principal component analysis, the number of inherent mode functions (IMFs) that need to be given in the conventional variational mode decomposition is adaptively determined in the proposed AVMD. The original measured signals from the bridge structure multiscale are subsequently decomposed by AVMD into the multiscale IMFs with the lowest cross-correlation. Then, the recurrence plot and recurrence quantification analysis are introduced into the detection and quantification of the measured signals, and the nonlinear and nonstationary quantification indexes are constructed to describe quantitatively the nonlinear and nonstationary levels. The stabilities and accuracies of three nonlinear and three nonstationary quantification indexes are comparatively discussed by the nonlinear and nonstationary detection and quantification of three well-defined simulated signals. The Shannon entropy and trapping time indexes are subsequently determined to quantify the nonlinear and nonstationary levels of the measured signals, respectively. Finally, the proposed algorithm and quantification indexes are applied to the nonlinear and nonstationary detection and quantification of the measured signals from the real-world bridge structures. It is shown from the validation and discussion that the proposed algorithm is available to detect and quantify the nonlinear and nonstationary levels of the measured multiscale signal from the real-world bridge structure.

The use of principal component analysis for reduction of training load data in professional soccer

The aim of this study was to explore the use of principal component analysis (PCA) in understanding multivariate relationships in soccer training load data. Training load data were collected from 20 professional male soccer players during a 28-week in-season period. Twelve training load variables (total distance, PlayerLoadTM, low-speed running distance, moderate-speed running distance, high-speed running distance, sprint distance, moderate-speed running efforts, high-speed running efforts, sprint efforts, accelerations, decelerations, and changes of direction) were collected during training sessions, with correlation analysis revealing high intercorrelation between most variables (r = 0.04-0.98). Principal component analysis was performed on datasets containing all players and on individual players. On the whole dataset, two principal components were retained explaining a total of 81% of data variance. The first component comprised variables associated with distances in speed zones and the second component changes of direction. Whilst some individual variation existed among players, distances in speed zones were loaded on the first component and inertial movement analysis variables, such as accelerations, decelerations, and changes of direction, were loaded on the second component. These findings evidence the strong relationships between several common training load variables and highlight the risk of data redundancy. By selecting variables from each component, practitioners can reduce the number of variables reported whilst retaining as much of the variation in data as possible.

Detection of physical descaling damage in carp based on hyperspectral images and dimension reduction of principal component analysis combined with pixel values.

The surface of carp is easily damaged during the descaling process, which jeopardizes the quality and safety of carp products. Damage recognition realized by manual detection is an important factor restricting the automation in the pretreatment. For the commonly used methods of mechanical and water-jet descaling, damage area recognition according to the hyperspectral data was proposed. Two discrimination models, including decision tree (DT) and self-organizing feature mapping (SOM), were established to recognize the damaged and normal descaling area with the average spectral value. The damage-discrimination model based on DT was determined to be the optimal one, which possessed the best model performance (accuracy = 96.7%, sensitivity = 96.7%, specificity = 96.7%, F1-score = 96.7%). Considering the efficiency and precision of damage-area recognition and visualization, the principal component analysis (PCA) combined with pixel values statistical analysis was used to reduce the dimension of hyperspectral images at the image level. Through statistical analysis, the value 0 was used as the threshold to distinguish the normal area and the damaged area in the PC image to achieve preliminary segmentation. Then, the spectral values of the initially discriminated damage area were input into the DT discrimination model to realize the final discriminant of damaged area. On this basis, the position information of the damaged area could be used to realize the visualization. The final visualization maps for mechanical and water-jet descaling damage were obtained by image morphology processing. The average recognition accuracy can reach 94.9% and 90.3%, respectively. The results revealed that the hyperspectral imaging technique has great potential to recognize the carp damage area nondestructively and accurately under descaling processing. PRACTICAL APPLICATION: This study demonstrated that hyperspectral imaging technique can realize the carp damage area detection nondestructively and accurately under descaling processing. With the advantages of nondestructive and rapid, hyperspectral imaging system and the method can be widely expanded and applied to the quality detection of other freshwater fish pretreatment.

A Virtual Power Plant Load Curve Clustering Method Based on Improved K-means Algorithm and Its Application

In view of how virtual power plants can effectively participate in power grid operation, a method of load curve clustering of virtual power plants based on principal component analysis reduction and aggregation level clustering and k-means clustering is proposed, and the application of clustering results is studied. Firstly, combined with the data obtained from the information physical network, the principal component analysis method is adopted to analyze the characteristics of different loads participating in the virtual power plant aggregation, so as to standardize the data and reduce the dimension. Then, the algorithm combining aggregation hierarchical clustering and k-means clustering is used to cluster all load output curves participating in the aggregation, to obtain load curve clusters of the same class and find out the clustering center. Finally, the clustering results are analyzed, and the corresponding evaluation system is established. Through comprehensive evaluation, appropriate load combinations are selected to participate in the virtual power plant aggregation.

Detection and recognition of human body posture in motion based on sensor technology

The recognition of human motion posture is of great values in the field of sports. In this paper, inertial sensor technology is employed to recognize four postures including dribbling, passing, catching, and shooting in basketball. The data are collected by four nine‐axis inertial sensors worn on the arm. The time domain and frequency domain features are extracted after the process of smoothing and normalizing. Then 30 eigenvectors are obtained by dimensionality reduction of principal component analysis (PCA), and the support vector machine (SVM) method is used for posture recognition. The experimental results show that after PCA dimensionality reduction, the recognition accuracy of the features as the SVM input is significantly high. Compared with the recognition accuracy of back propagation neural network (BPNN) (85.4%), the average recognition accuracy of SVM is 96%, which verifies the reliability of the method proposed in this study. This research proves the effectiveness of sensor technology in basketball posture recognition, which can provide a reliable guidance for basketball training. © 2020 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

A Framework for Reduction of Principal Component Analysis based Algorithms using Residue Number System

A Framework for Reduction of Principal Component Analysis based Algorithms using Residue Number System

Comparison of Different Optimization Methods with Support Vecto Machine for Blast Furnace Multi-Fault Classification

Aiming at the complex and volatile conditions of the blast furnace, a support vector machine with multi-fault classification is proposed to solve the problem on blast furnace fault diagnosis. The normal or failure data is handled with a normalization and dimensionality reduction of principal component analysis (PCA). As a small amount of failure sample, a C-support vector classification (C-SVC) is applied in this filed. Different optimization methods have been performed for optimizing SVM parameters, including the grid-search method (GSM), the genetic algorithm (GA) and the particle swarm optimization (PSO). It compares these optimization algorithm strengths and limitations for multi-fault classification on classification ability and classification speed.

A new kernel discriminant analysis framework for electronic nose recognition

Electronic nose (e-Nose) technology based on metal oxide semiconductor gas sensor array is widely studied for detection of gas components. This paper proposes a new discriminant analysis framework (NDA) for dimension reduction and e-Nose recognition. In a NDA, the between-class and the within-class Laplacian scatter matrix are designed from sample to sample, respectively, to characterize the between-class separability and the within-class compactness by seeking for discriminant matrix to simultaneously maximize the between-class Laplacian scatter and minimize the within-class Laplacian scatter. In terms of the linear separability in high dimensional kernel mapping space and the dimension reduction of principal component analysis (PCA), an effective kernel PCA plus NDA method (KNDA) is proposed for rapid detection of gas mixture components by an e-Nose. The NDA framework is derived in this paper as well as the specific implementations of the proposed KNDA method in training and recognition process. The KNDA is examined on the e-Nose datasets of six kinds of gas components, and compared with state of the art e-Nose classification methods. Experimental results demonstrate that the proposed KNDA method shows the best performance with average recognition rate and total recognition rate as 94.14% and 95.06% which leads to a promising feature extraction and multi-class recognition in e-Nose.

Recognition of spikes of Schizonepeta tenuifolia from different area based on backpropagation neural network coupled with dimension reduction of principal component analysis

The spikes of Schizonepeta tenuifolia from different habits were predicted by UV-Vis spectrum. The dimensions of spectrum data obtained from ten habits were reduced by principal component analysis, and the first six new variables with 99.82% of cumulative reliability were put into the backpropagation neural network for model building. The recognition rate of backpropagation neural network coupled with principal component analysis (PCA-BPNN) was 100%, and its mean square error was 0.001 0. PCA-BPNN can be used for the classifying of spikes of S. tenuifolia from different producing area, and this method is simple and fast.

Reducing microarray data via nonnegative matrix factorization for visualization and clustering analysis

In microarray data analysis, each gene expression sample has thousands of genes and reducing such high dimensionality is useful for both visualization and further clustering of samples. Traditional principal component analysis (PCA) is a commonly used method which has problems. Nonnegative Matrix Factorization (NMF) is a new dimension reduction method. In this paper we compare NMF and PCA for dimension reduction. The reduced data is used for visualization, and clustering analysis via k-means on 11 real gene expression datasets. Before the clustering analysis, we apply NMF and PCA for reduction in visualization. The results on one leukemia dataset show that NMF can discover natural clusters and clearly detect one mislabeled sample while PCA cannot. For clustering analysis via k-means, NMF most typically outperforms PCA. Our results demonstrate the superiority of NMF over PCA in reducing microarray data.

Principal component analysis for reduction of ocular artefacts in event-related potentials of normal and dyslexic children.

The aim of this study was to reduce ocular artefacts in single trial event-related potentials (ERPs) recorded in normal and in dyslexic children. ERPs were recorded during passive and active reading of centrally presented alphabetic letters and non alphabetic symbols. EEG was recorded from 10 EEG locations using the 10-20 system. Diagonal EOG from the right eye was also recorded. Principal component analysis (PCA) was applied in order to reduce ocular artefacts: the first or the second principal component (PC) was subtracted when the correlation coefficient between the component and EOG was greater or equal to 0.9 or 0.95, respectively. Performance of the method was tested on simulated and real data, on both single and averaged trials, varying EOG amplitude and artefact transmission characteristics. Applying the method to real recordings from normal and dyslexic children, we obtained a significant increase in the number of useful trials. In normal children we retrieved 41.0% of the rejected trials in passive and 39.1% in active reading. In dyslexic children 36.7 and 32.2% of the rejected trials in passive and active reading could be included in the respective averages. The method allows an increase in the number of trials suitable for averaging, a great improvement in ERP quality and a reduction in the recording time.