Papers by Keyword: Dimensionality Reduction

Abstract: The study investigated the structure of the integrated solar and hydraulic jump enhanced waste stabilization pond (ISHJEWSP) variables. Also, to determine the cluster of the most important variables that account for the performance of the ISHJEWSP using principal component analysis (PCA). Three sets of experimental ponds were constructed with varying locations of point of initiation of hydraulic jump. Wastewater samples collected from the inlet and outlet for varying inlet velocities were examined for physicochemical and bacteriological characteristics for a period of nine months. The Pearson’s R-matrix and KMO statistic were used in evaluating the structure of the variables. Consequently, the variables of temperature, pH, algae concentration, solar radiation, and locations of the point of initiation of hydraulic jump were subjected to PCA. Two components had eigenvalues above the Jolliffe’s criterion and in combination explained 90.66% of the total variance. The inflexion of the scree plot justified the retained components. The analysis after rotation revealed that the parameters of pH, temperature, solar radiation, and algal concentration loaded highly to component 1. This underscores the precedence of ambient climatic conditions, alongside the state of the wastewater in general, to the inlet velocity and location of point of initiation of hydraulic jump.

Abstract: A gait recognition method based on wavelet packet decomposition (WPD) and Locality preserving projections (LPP) is proposed in this paper. The method includes the following steps, pretreatment, feature extraction by WPD and dimensionality reduction by LPP and classification of the test samples to a corresponding class according to the nearest neighbor classifier. The experiment results on the public gait database show the effectiveness of the proposed method.

Abstract: Unsupervised Discriminant Projection (UDP) is a typical manifold-based dimensionality reduction method, and has been successfully applied in face recognition. However, UDP suffers from the small sample size problem and usually deteriorates because the basis vectors of UDP are statistically correlated. In order to resolve these problems, we propose an Optimal Uncorrelated Unsupervised Discriminant Projection (OUUDP).The aim of OUUDP is to seek a feature submanifold such that the local scatter is minimized and non-local scatter scatter is maximized simultaneously in the embedding space by using a difference-based optimization objective function. Moreover, we impose an appropriate constraint to make the extracted features statistically uncorrelated. As a result, OUUDP can solve the small sample size problem and exploit statistically uncorrelated features. Experimental results on ORL databases demonstrate the effectiveness of the proposed algorithm.

Abstract: We collected fatigue stress concentration factor and used Support Vector Machines (SVM) by linear kernel to reduce dimension processing. In order to research the way of dimensionality reduction for data, we also processed the sample of stress fatigue concentration factor to compare with Principal Component Analysis(PCA). The results showed that the sample is processed by linear kernel could improve efficiency to train by SVM again.

Abstract: Locally linear embedding is based on the assumption that the whole data manifolds are evenly distributed so that they determine the neighborhood for all points with the same neighborhood size. Accordingly, they fail to nicely deal with most real problems that are unevenly distributed. This paper presents a new approach that takes the general conceptual framework of Hessian locally linear embedding so as to guarantee its correctness in the setting of local isometry to an open connected subset but dynamically determines the local neighborhood size for each point. This approach estimates the approximate geodesic distance between any two points by the shortest path in the local neighborhood graph, and then determines the neighborhood size for each point by using the relationship between its local estimated geodesic distance matrix and local Euclidean distance matrix. This approach has clear geometry intuition as well as the better performance and stability to deal with the sparsely sampled or noise contaminated data sets that are often unevenly distributed. The conducted experiments on benchmark data sets validate the proposed approach.

Abstract: In recent years, a variety of manifold-based learning dimensionality reduction techniques have been proposed, which attempt to project the original data into a lower dimensional feature space by preserving the local neighborhood structure. Among them, marginal fisher analysis (MFA) achieved high performance for face recognition. However, the optimal basis vectors obtained by MFA are non-orthogonal and MFA usually deteriorates when labeled information is insufficient. In order to resolve these problems, we present a new method called orthogonal semi-supervised marginal fisher analysis (OSMFA), which not only extracts all the orthogonal discriminant vectors but also preserves the global structure of labeled and unlabeled samples to learn a better subspace for classification. Experimental results on ORL database demonstrate the effectiveness of the proposed algorithm.

Abstract: Overlap information usually exits in the high-dimensional data. Misclassified points may be more when affinity propagation clustering is applied to these data. Concerning this problem, a new method combining principal components analysis and affinity propagation clustering is proposed. In this method, dimensionality of the original data is reduced on the premise of reserving most information of the variables. Then, affinity propagation clustering is implemented in the low-dimensional space. Thus, because the redundant information is deleted, the classification is accurate. Experiment is done by using this new method, the results of the experiment explain that this method is effective.

Abstract: A novel three-dimensional (3D) convex hull method is proposed, which is called dimensionality reduction convex hull method (DRCH).Through having 3d point set map to 2d plane, most initial 3D points in the convex hull are removed. Then, the remaining points are to generate 3D convex hull using any convex hull algorithm. The experiment demonstrates 3D DRCH is faster than general 3D convex hull algorithms. Its time complexity is O(r log r), where r is the number of points not in the hull. And DRCH can be generalized to higher-dimensional problems.

Abstract: Manifold learning has made many successful applications in the fields of dimensionality reduction, pattern recognition, and data visualization. In this paper we proposed hierarchical macro manifold (HMM) for the purpose of supervised classification. We construct hierarchical macro manifold based on the given training sets. The generalized regression neural network is employed to solve the out-of-sample problem. Experimental results demonstrate the feasibility and effectiveness of our proposed approach.

Abstract: Manifold learning has made many successful applications in the fields of dimensionality reduction and pattern recognition. However, when it is used for supervised classification, the result is still unsatisfactory. To address this challenge, a novel supervised approach, namely macro manifold learning (MML) is proposed. Based on the proposed approach, the low-dimensional embeddings of the testing samples is more favorable for classification tasks. Experimental results demonstrate the feasibility and effectiveness of our proposed approach.