Biliana S. Paskaleva

Canonical Correlation Feature Selection for Sensors With Overlapping Bands: Theory and Application

The main focus of this paper is a rigorous development and validation of a novel canonical correlation feature- selection (CCFS) algorithm that is particularly well suited for spectral sensors with overlapping and noisy bands. The proposed approach combines a generalized canonical correlation analysis framework and a minimum mean-square-error criterion for the selection of feature subspaces. The latter induces ranking of the best linear combinations of the noisy overlapping bands and, in doing so, guarantees a minimal generalized distance between the centers of classes and their respective reconstructions in the space spanned by sensor bands. To demonstrate the efficacy and the scope of the proposed approach, two different applications are considered. The first one is separability and classification analysis of rock species using laboratory spectral data and a quantum-dot infrared photodetector (QDIP) sensor. The second application deals with supervised classification and spectral unmixing, and abundance estimation of hyperspectral imagery obtained from the Airborne Hyperspectral Imager sensor. Since QDIP bands exhibit significant spectral overlap, the first study validates the new algorithm in this important application context. The results demonstrate that proper postprocessing can facilitate the emergence of QDIP-based sensors as a promising technology for midwave- and longwave-infrared remote sensing and spectral imaging. In particular, the proposed CCFS algorithm makes it possible to exploit the unique advantage offered by QDIPs with a dot-in-a-well configuration, comprising their bias-dependent spectral response, which is attributable to the quantum Stark effect. The main objective of the second study is to assert that the scope of the new CCFS approach also extends to more traditional spectral sensors.

Dynamical discrete-time load balancing in distributed systems in the presence of time delays

The implementation of a load balancing policy on a continuous basis in a delay-limited distributed computing environment may not only drain the computational resources of each computational element (CE), but can also lead to an unnecessary exchange of loads between the CEs. This degrades the system performance, measured by the overall completion time of the total tasks in the system. Thus, for a given distribution of the load among the CEs, there has to be an optimal number and distribution of discrete balancing instants. This paper focuses on #xing the number of balancing instants and optimizing the completion time over the strength of load balancing, which is controlled by the so-called gain parameter, and the time when the balancing is executed. First, the case when the load balancing is implemented at a single instant per node is presented. Then, a strategy is considered where a second load balancing instant is allowed for each node. The simulations show that both strategies outperform the continuous balancing policy. Moreover, with the double load-balancing strategy the overall completion time is further reduced in comparison to the single load balancing case. It is also seen that the optimal choice of the gain parameter depends on the delay and this dependence becomes more significant as the delays increase. This interplay between the strength of load balancing and the magnitude delay has a direct effect on the performance of the policy and on the sensitivity to the selection of the balancing instants.

Multispectral Classification With Bias-Tunable Quantum Dots-in-a-Well Focal Plane Arrays

Mid-wave and long-wave infrared (IR) quantum-dots-in-a-well (DWELL) focal plane arrays (FPAs) are promising technology for multispectral (MS) imaging and sensing. The DWELL structure design provides the detector with a unique property that allows the spectral response of the detector to be continuously, albeit coarsely, tuned with the applied bias. In this paper, a MS classification capability of the DWELL FPA is demonstrated. The approach is based upon: 1) imaging an object repeatedly using a sequence of bias voltages in the tuning range of the FPA and then 2) applying a classification algorithm to the totality of readouts, over multiple biases, at each pixel to identify the “class” of the material. The approach is validated for two classification problems: separation among different combinations of three IR filters and discrimination between rocks. This work is the first demonstration of the MS classification capability of the DWELL FPA.

Feature selection for spectral sensors with overlapping noisy spectral bands

Quantum-dot infrared photodetectors (QDIPs) are emerging as a promising technology for midwave- and longwave-infrared remote sensing and spectral imaging. One of the key advantages that QDIPs offer is their bias-dependent spectral response, which is brought about by the asymmetric bandstructure of the dot-in-a-well (DWELL) configuration. Photocurrents of a single QDIP, driven by different operational biases can, therefore, be viewed as outputs of different bands. It has been shown that this property, combined with post-processing strategies (applied to the outputs of a single sensor operated at different biases), can be used to perform adaptive spectral tuning and matched filtering. However, unlike traditional sensors, bands of a QDIP exhibit significant spectral overlap, an attribute that calls for the development of novel methods for feature selection. Additionally, the presence of detector noise further complicates such feature selection. In this paper, the theoretical foundations for discriminant analysis, based on spectrally adaptive feature selection, are developed and applied to data obtained from QDIP sensors in the presence of noise. The approach is based on a generalized canonical-correlation-analysis framework that is used in conjunction with an optimization criterion for the selection of feature subspaces. The criterion ranks the best linear combinations of the overlapping bands, providing minimal energy norm (a generalized Euclidean norm) between the centers of classes and their respective reconstructions in the space spanned by sensor bands. Experiments using ASTER-based synthetic QDIP data are used to illustrate the performance of rock-type Bayesian classification according to the proposed feature-selection method.

Multispectral rock-type separation and classification

This paper shows the possibility of separating and classifying remotely-sensed multispectral data from rocks and minerals onto seven geological rock-type groups. These groups are extracted from the general categories of metamorphic, igneous and sedimentary rocks. This study is performed under ideal conditions for which the data is generated according to laboratory hyperspectral data for the members, which are, in turn, passed trough the Multispectral Thermal Imager (MTI) filters yielding 15 bands. The main challenge in separability is the small size of the training data sets, which initially did not permit the reliable estimation of the second-order statistics for every class. To enable Bayesian classification, the original training data is linearly perturbed with the addition of minerals, vegetation, soil, water and other valid impurities. As a result, the size of the training data is significantly increased and estimates of the covariance matrices are obtained. An eigenvalue analysis is used to generate a set of reduced (five) multispectral vectors, viz., feature vectors, providing principal information about the data. In addition, a nonlinear band-selection method is also employed, based on spectral indices, comprising a small subset of all possible ratios between bands. By applying three optimization strategies, optimal combinations of two and three ratios are found that provide reliable separability and classification between all seven groups. To set a benchmark to which the MTI capability in rock classification can be compared, an optimization strategy is performed for the selection of optimal multispectral filters, other than the MTI filters, and an improvement in classification is predicted when these filters are used.

Multispectral classification with bias-tunable quantum dots in a well focal plane array

The authors have demonstrated that the bias-tunability of quantum-dots-in-a-well photodetector (DWELL) FPA can be utilized for material classification. With the ongoing improvement and development of hardware and software for data acquisition and analysis, which allows for the increased bias-tunability and efficient data collection and processing, the DWELL FPA is expected to have a wide range of applications.

Remote sensing data exploiration for geologic characterization of difficult targets : Laboratory Directed Research and Development project 38703 final report.

Characterizing the geology, geotechnical aspects, and rock properties of deep underground facility sites can enhance targeting strategies for both nuclear and conventional weapons. This report describes the results of a study to investigate the utility of remote spectral sensing for augmenting the geological and geotechnical information provided by traditional methods. The project primarily considered novel exploitation methods for space-based sensors, which allow clandestine collection of data from denied sites. The investigation focused on developing and applying novel data analysis methods to estimate geologic and geotechnical characteristics in the vicinity of deep underground facilities. Two such methods, one for measuring thermal rock properties and one for classifying rock types, were explored in detail. Several other data exploitation techniques, developed under other projects, were also examined for their potential utility in geologic characterization.