Synthetic Aperture Radar Cold Regions Hazard and Surveillance Monitoring
Abstract not provided.
Publications
Optimization framework for wireless unattended ground sensor (UGS) networks
Abstract not provided.
Least Squares Support Vector Machines for Direction of Arrival Estimation with Error Control and Validation
GLOBECOM - IEEE Global Telecommunications Conference
This paper presents a multiclass, multilabel implementation of Least Squares Support Vector Machines (LS-SVM) for direction of arrival (DOA) estimation in a CDMA system. For any estimation or classification system the algorithm's capabilities and performance must be evaluated. Specifically, for classification algorithms a high confidence level must exist along with a technique to automatically tag misclassifications. The learning algorithm presented in this paper includes error control and validation steps for generating statistics on the multiclass evaluation path and the signal subspace dimension. The error statistics provide a confidence level of the classification accuracy.
Least squares support vector machines for DOA estimation with classification error control
Proposed for presentation at the IEEE Transactions on Antennas and Propagation.
Abstract not provided.
Least squares support vector machines for direction of arrival estimation
IEEE Antennas and Propagation Society, AP-S International Symposium (Digest)
A multiclass LS-SVM architecture for DOA estimation as applied to a CDMA cellular system is presented. As such, simulation results showed a high degree of accuracy, as related to the DOA classes and proved that the LS-SVM DDAG system has a wide range of performance capabilities. The broad range of the research in machine learning based DOA estimation includes multilabel and multiclass classification, classification accuracy, error control and validation, kernel selection, estimation of signal subspace dimension, and overall performance characterization of the LS-SVM DDAG DOA estimation algorithm.
Least squares support vector machines for fixed step/set CDMA power control
Abstract not provided.
Open-loop adaptive filtering for speckle reduction in synthetic aperture radar images
Conference Record of the Asilomar Conference on Signals, Systems and Computers
The Two-Dimensional Adaptive Correlation Enhancer Algorithm (2DACE) is an open-loop adaptive filtering technique that can be applied to Synthetic Aperture Radar (SAR) images for the purpose of reducing speckle. This paper includes the development of the 2DACE algorithm and the optimum filter parameters for this specific task. The unique implementation of 2DACE with a data amplitude pre-compression operation was proven to effectively reduce speckle, enhance fine features, and maintain image resolution.
Open-Loop Adaptive Filtering for Speckle Reduction in Synthetic Aperture Radar Images
Abstract not provided.
8 Results