Pablo Rivas-Perea

A Low-Complexity Geometric Bilateration Method for Localization in Wireless Sensor Networks and Its Comparison with Least-Squares Methods

This research presents a distributed and formula-based bilateration algorithm that can be used to provide initial set of locations. In this scheme each node uses distance estimates to anchors to solve a set of circle-circle intersection (CCI) problems, solved through a purely geometric formulation. The resulting CCIs are processed to pick those that cluster together and then take the average to produce an initial node location. The algorithm is compared in terms of accuracy and computational complexity with a Least-Squares localization algorithm, based on the Levenberg–Marquardt methodology. Results in accuracy vs. computational performance show that the bilateration algorithm is competitive compared with well known optimized localization algorithms.

A Distributed Localization Algorithm for Wireless Sensor Networks Based on the Solutions of Spatially-Constrained Local Problems

We present a distributed localization algorithm for wireless sensor networks. Each sensor estimates its position by iteratively solving a set of local spatially-constrained programs. The constraints allow sensors to update their positions simultaneously and collaboratively using range and position estimates to those neighbors within their communications range. Moreover, the algorithm is designed for implementation with resource-limited devices. Since the exchange of information among sensors is a key component for this method, we introduce a stopping criterion to monitor the wireless transmissions for the whole network in order to significantly reduce energy consumption with minimal impact on localization accuracy. Experimental results show that we can determine the best tradeoff between wireless transmissions and accuracy. The performance of the proposed scheme is very competitive when compared with similar and more computationally demanding schemes.

An algorithm for training a large scale support vector machine for regression based on linear programming and decomposition methods

This paper presents a method to train a Support Vector Regression (SVR) model for the large-scale case where the number of training samples supersedes the computational resources. The proposed scheme consists of posing the SVR problem entirely as a Linear Programming (LP) problem and on the development of a sequential optimization method based on variables decomposition, constraints decomposition, and the use of primal-dual interior point methods. Experimental results demonstrate that the proposed approach has comparable performance with other SV-based classifiers. Particularly, experiments demonstrate that as the problem size increases, the sparser the solution becomes, and more computational efficiency can be gained in comparison with other methods. This demonstrates that the proposed learning scheme and the LP-SVR model are robust and efficient when compared with other methodologies for large-scale problems.

Automatic Dust Storm Detection Based on Supervised Classification of Multispectral Data

This paper address the detection of dust storms based on a probabilistic analysis of multispectral images. We develop a feature set based on the analysis of spectral bands reported in the literature. These studies have focused on the visual identification of the image channels that reflect the presence of dust storms through correlation with meteorological reports. Using this feature set we develop a Maximum Likelihood classifier and a Probabilistic Neural Network (PNN) to automate the dust storm detection process. The data sets are MODIS multispectral bands from NASA Terra satellite. Findings indicate that the PNN provides improved classification performance with reference to the ML classifier. Furthermore, the proposed schemes allow real-time processing of satellite data at 1 km resolutions which is an improvement compared to the 10 km resolution currently provided by other detection methods.

A Recursive Shortest Path Routing Algorithm With Application for Wireless Sensor Network Localization

In this paper, we present a routing algorithm useful in the realm of centralized range-based localization schemes. The proposed method is capable of estimating the distance between two non-neighboring sensors in multi-hop wireless sensor networks. Our method employs a global table search of sensor edges and recursive functions to find all possible paths between a source sensor and a destination sensor with the minimum number of hops. Using a distance matrix, the algorithm evaluates and averages all paths to estimate a measure of distance between both sensors. Our algorithm is then analyzed and compared with classical and novel approaches, and the results indicate that the proposed approach outperforms the other methods in distance estimate accuracy when used in random and uniform placement of nodes for large-scale wireless networks. Furthermore, the proposed methodology is suitable for the implementation in centralized localization schemes, such as multi-dimensional scaling, least squares, and maximum likelihood to mention a few.

A nonlinear least squares quasi-Newton strategy for LP-SVR hyper-parameters selection

This paper studies the problem of hyper-parameters selection for a linear programming-based support vector machine for regression (LP-SVR). The proposed model is a generalized method that minimizes a linear-least squares problem using a globalization strategy, inexact computation of first order information, and an existing analytical method for estimating the initial point in the hyper-parameters space. The minimization problem consists of finding the set of hyper-parameters that minimizes any generalization error function for different problems. Particularly, this research explores the case of two-class, multi-class, and regression problems. Simulation results among standard data sets suggest that the algorithm achieves statistically insignificant variability when measuring the residual error; and when compared to other methods for hyper-parameters search, the proposed method produces the lowest root mean squared error in most cases. Experimental analysis suggests that the proposed approach is better suited for large-scale applications for the particular case of an LP-SVR. Moreover, due to its mathematical formulation, the proposed method can be extended in order to estimate any number of hyper-parameters.

Performance Analysis of the Feedforward and SOM Neural Networks in the Face Recognition Problem

This paper presents a comparative study between a feedforward neural network and a SOM network. The paper also proposes the incorporation of a new spatial feature, face feature lines, FFL, to represent the faces. FFL are considered as new features based on previous studies related to face recognition tasks on newborns. Besides the face feature lines, the feature vector incorporates eigenvectors of the face image obtained with the Karhunen-Loeve transformation. A face recognition system is based on a feedforward neural network, FFBP, method. The second classification scheme uses a self organized map, SOM, architecture combined with the k-means clustering algorithm. Experiments comparing both architectures show no significant differences for the ORL database, 92% for the FFBP and 90% for the SOM. However results obtained for the Yale database, 60% for the FFBP network and 70% for the SOM, indicate a better performance with the SOM architecture

Dust storm detection using a neural network with uncertainty and ambiguity output analysis

Dust storms are meteorological phenomena that may affect human life. Therefore, it is of great interest to work towards the development of a stand-alone dust storm detection system that may help to prevent and/or counteract its negative effects. This work proposes a dust storm detection system based on an Artificial Neural Network, ANN. The ANN is designed to identify not just dust storm areas but also vegetation and soil. The proposed ANN works on information obtained from multispectral images acquired with the Moderate Resolution Imaging Spectroradiometer (MODIS) instrument. Before the multispectral information is fed to the ANN a process to remove cloud regions from images is performed in order to reduce the computational burden. A method to manage undefined and ambiguous ANN outputs is also proposed in the paper which significantly reduces the false positives rate. Results of this research present a suitable performance at detecting the dust storm events.

Traditional and neural probabilistic multispectral image processing for the dust aerosol detection problem

This paper address the dust aerosol detection problem based on a probabilistic multispectral image analysis. Two classifiers are designed. First the Maximum Likelihood classifier is adapted to mode different types of atmospheric components. The second is a Probabilistic Neural Network (PNN) model. The data sets are MODIS multispectral bands from NASA Terra satellite. Findings indicate that the PNN presents a better classification performance than the ML classifier using manual segmentations as ground truth. The proposed algorithm is capable of real-time processing at 1 km resolutions which is an improvement compared to the 10 km resolution currently provided by other approaches.

Detection of leukocoria using a soft fusion of expert classifiers under non-clinical settings

BackgroundLeukocoria is defined as a white reflection and its manifestation is symptomatic of several ocular pathologies, including retinoblastoma (Rb). Early detection of recurrent leukocoria is critical for improved patient outcomes and can be accomplished via the examination of recreational photography. To date, there exists a paucity of methods to automate leukocoria detection within such a dataset.MethodsThis research explores a novel classification scheme that uses fuzzy logic theory to combine a number of classifiers that are experts in performing multichannel detection of leukocoria from recreational photography. The proposed scheme extracts features aided by the discrete cosine transform and the Karhunen-Loeve transformation.ResultsThe soft fusion of classifiers is significantly better than other methods of combining classifiers with p = 1.12 × 10-5. The proposed methodology performs at a 92% accuracy rate, with an 89% true positive rate, and an 11% false positive rate. Furthermore, the results produced by our methodology exhibit the lowest average variance.ConclusionsThe proposed methodology overcomes non-ideal conditions of image acquisition, presenting a competent approach for the detection of leukocoria. Results suggest that recreational photography can be used in combination with the fusion of individual experts in multichannel classification and preprocessing tools such as the discrete cosine transform and the Karhunen-Loeve transformation.