The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper we present a new method which allows us to detect the most informative features out of all data extracted from a certain data corpus. Widely used Pearson's coefficient is not reliable if the dependency between extracted features (input variables) and the objective function (output) is not linear. This approach is based on a modified random balance method (RBM) combined with non-parametric...
Solving function approximation problem is to appropriately find the relationship between dependent variable and independent variable(s). Function approximation algorithms normally require sufficient amount of samples to approximate a function. However, insufficient samples may result in unsatisfactory prediction to any function approximation algorithms. It is due to the failure of the function approximation...
Estimation of forest stand parameters from airborne laser scanning data relies on the selection of laser metrics sets and numerous field plots for model calibration. In mountainous areas, forest is highly heterogeneous and field data collection labour-intensive hence the need for robust prediction methods. The aim of this paper is to compare stand parameters prediction accuracies of support vector...
We develop a particle swarm optimisation (PSO) aided orthogonal forward regression (OFR) approach for constructing radial basis function (RBF) classifiers with tunable nodes. At each stage of the OFR construction process, the centre vector and diagonal covariance matrix of one RBF node is determined efficiently by minimising the leave-one-out (LOO) misclassification rate (MR) using a PSO algorithm...
This paper presents a novel feature selection approach (KP-SVR) that determines a non-linear regression function with minimal error and simultaneously minimizes the number of features by penalizing their use in the dual formulation of SVR. The approach optimizes the width of an anisotropic RBF Kernel using an iterative algorithm based on the gradient descent method, eliminating features that have...
A multi-kernel Support Vector Machine model, called Hierarchical Support Vector Regression (HSVR), is proposed here. This is a self-organizing (by growing) multiscale version of a Support Vector Regression (SVR) model. It is constituted of hierarchical layers, each containing a standard SVR with Gaussian kernel, at decreasing scales. HSVR have been applied to a noisy synthetic dataset. The results...
Next-generation ultrasound contrast agents, in the form of tiny gas bubbles, can be targeted to selectively adhere to cancer cells. The number of attached microbubbles could be correlated with the status of the cancer. Consequently, the estimation of bubble concentration can provide useful medical information in addition to ultrasound molecular imaging. In this paper, a method to obtain the ultrasound...
This paper introduces a new supervised Bayesian approach to hyper-spectral image segmentation. The algorithm mainly consists of two steps: (a) learning, for each class label, the posterior probability distributions, based on a multinomial logistic regression model; (b) segmenting the hyperspectral image, based on the posterior probability distribution of the image of class labels built on the learned...
We present a new semi-supervised segmentation algorithm suited to hyperspectral images, which takes full advantage of the spectral and spatial information available in the scenes. We mainly focus on problems involving very few labeled samples and a larger set of unlabeled samples. A multinomial logistic regression (MLR) is used to model the posterior class probability distributions, whereas a multilevel...
This research visualizes the spatial patterns of diagnosed colon and lung cancer mortalities across the New York State. Kernel density analysis was applied to visualize the spatial patterns of old industrial sites across the state. Geographically Weighted Regression (GWR) was applied to model the possible pollution impact of old industrial sites on colon and lung cancer incidents. GWR is a local spatial...
Prognosis of traffic flow is a basic part of intelligent transportation research. Due to the extremely complexity of vehicular traffic, efficient models should be constructed to do accurate simulation and prediction of real traffic, such as locally kernel models. However, locally kernel regression fails when the traffic data points are sparse, and the data distribution should be considered seriously...
In order to simulate human behavior to achieve intelligent control, in this paper a mathematical modeling method is presented based on Kernel Principal Component Analysis (KPCA) and Support Sector Machine. Sample data from the input space are mapped to high-dimensional feature space by non-linear transformation, then their features are extracted by PCA to decrease dimension of input vector and then...
Background estimation is the first step of background suppression in many infrared (IR) target detection algorithms. One sort of these algorithms consider background estimation as a supervised learning problem. On this point of view, it is necessary to search sparse solutions to control the complexity of the learned function to achieve good generalization. On the other hand, the more effective nonlinear...
Nitrogen oxide (NOx) is one of main pollutants emitted from coal fired power plants and is a significant pollutant source in the environment. Therefore, the monitoring or prediction of NOx emissions is an indispensable process in coal-fired power plant so as to control NOx emissions. In this paper, NOx emissions modeling for real-time operation and control of a 300MWe coal-fired power generation plant...
Gait is a well recognized biometric feature that is used to identify a human at a distance. However, in real environment, appearance changes of individuals due to viewing angle changes cause many difficulties for gait recognition. This paper re-formulates this problem as a regression problem. A novel solution is proposed to create a View Transformation Model (VTM) from the different point of view...
In image categorization the goal is to decide if an image belongs to a certain category or not. A binary classifier can be learned from manually labeled images; while using more labeled examples improves performance, obtaining the image labels is a time consuming process. We are interested in how other sources of information can aid the learning process given a fixed amount of labeled images. In particular,...
Non-negative matrix factorization (NMF) is an excellent tool for unsupervised parts-based learning, but proves to be ineffective when parts of a whole follow a specific pattern. Analyzing such local changes is particularly important when studying anatomical transformations. We propose a supervised method that incorporates a regression constraint into the NMF framework and learns maximally changing...
Spectrometric oil analysis technology is an important method in condition monitoring. This method has been applied to study the state of Power-shift Steering Transmission (PSST) in this paper. But, how to predict the future state of the PSST using existing data is a difficult work. In order to solve this problem, a support vector regression method is applied. The building process of this method is...
Long memory processes are widely used in many scientific fields, such as bioinformatics, economics and engineering. In this paper, we use the multivariate local linear estimator to predict the ARFIMA(p,d,q) processes. Using the C-C method to choose the appropriate delay time and the embedding dimension, we reconstruct the time series and use multivariate local linear estimator to directly predict...
We present an improved online learning algorithm for sparse kernel partial least squares, this algorithm improves current methods to kernel-based regression in two aspects. First, it operates online at each time step when it acquires a new input support vector, performs an update and drop out the old data to adapted process changes. Second, it effectively reduces the dimension of feature space and...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.