Unmixing hyperspectral data: independent and dependent component analysis

The development of high spatial resolution airborne and spaceborne sensors has improved the capability of ground-based data collection in the fields of agriculture, geography, geology, mineral identification, detection [2, 3], and classification [4–8]. The signal read by the sensor from a given spatial element of resolution and at a given spectral band is a mixing of components originated by the constituent substances, termed endmembers, located at that element of resolution. This chapter addresses hyperspectral unmixing, which is the decomposition of the pixel spectra into a collection of constituent spectra, or spectral signatures, and their corresponding fractional abundances indicating the proportion of each endmember present in the pixel [9, 10]. Depending on the mixing scales at each pixel, the observed mixture is either linear or nonlinear [11, 12]. The linear mixing model holds when the mixing scale is macroscopic [13]. The nonlinear model holds when the mixing scale is microscopic (i.e., intimate mixtures) [14, 15]. The linear model assumes negligible interaction among distinct endmembers [16, 17]. The nonlinear model assumes that incident solar radiation is scattered by the scene through multiple bounces involving several endmembers [18]. Under the linear mixing model and assuming that the number of endmembers and their spectral signatures are known, hyperspectral unmixing is a linear problem, which can be addressed, for example, under the maximum likelihood setup [19], the constrained least-squares approach [20], the spectral signature matching [21], the spectral angle mapper [22], and the subspace projection methods [20, 23, 24]. Orthogonal subspace projection [23] reduces the data dimensionality, suppresses undesired spectral signatures, and detects the presence of a spectral signature of interest. The basic concept is to project each pixel onto a subspace that is orthogonal to the undesired signatures. As shown in Settle [19], the orthogonal subspace projection technique is equivalent to the maximum likelihood estimator. This projection technique was extended by three unconstrained least-squares approaches [24] (signature space orthogonal projection, oblique subspace projection, target signature space orthogonal projection). Other works using maximum a posteriori probability (MAP) framework [25] and projection pursuit [26, 27] have also been applied to hyperspectral data. In most cases the number of endmembers and their signatures are not known. Independent component analysis (ICA) is an unsupervised source separation process that has been applied with success to blind source separation, to feature extraction, and to unsupervised recognition [28, 29]. ICA consists in finding a linear decomposition of observed data yielding statistically independent components. Given that hyperspectral data are, in given circumstances, linear mixtures, ICA comes to mind as a possible tool to unmix this class of data. In fact, the application of ICA to hyperspectral data has been proposed in reference 30, where endmember signatures are treated as sources and the mixing matrix is composed by the abundance fractions, and in references 9, 25, and 31–38, where sources are the abundance fractions of each endmember. In the first approach, we face two problems: (1) The number of samples are limited to the number of channels and (2) the process of pixel selection, playing the role of mixed sources, is not straightforward. In the second approach, ICA is based on the assumption of mutually independent sources, which is not the case of hyperspectral data, since the sum of the abundance fractions is constant, implying dependence among abundances. This dependence compromises ICA applicability to hyperspectral images. In addition, hyperspectral data are immersed in noise, which degrades the ICA performance. IFA [39] was introduced as a method for recovering independent hidden sources from their observed noisy mixtures. IFA implements two steps. First, source densities and noise covariance are estimated from the observed data by maximum likelihood. Second, sources are reconstructed by an optimal nonlinear estimator. Although IFA is a well-suited technique to unmix independent sources under noisy observations, the dependence among abundance fractions in hyperspectral imagery compromises, as in the ICA case, the IFA performance. Considering the linear mixing model, hyperspectral observations are in a simplex whose vertices correspond to the endmembers. Several approaches [40–43] have exploited this geometric feature of hyperspectral mixtures [42]. Minimum volume transform (MVT) algorithm [43] determines the simplex of minimum volume containing the data. The MVT-type approaches are complex from the computational point of view. Usually, these algorithms first find the convex hull defined by the observed data and then fit a minimum volume simplex to it. Aiming at a lower computational complexity, some algorithms such as the vertex component analysis (VCA) [44], the pixel purity index (PPI) [42], and the N-FINDR [45] still find the minimum volume simplex containing the data cloud, but they assume the presence in the data of at least one pure pixel of each endmember. This is a strong requisite that may not hold in some data sets. In any case, these algorithms find the set of most pure pixels in the data. Hyperspectral sensors collects spatial images over many narrow contiguous bands, yielding large amounts of data. For this reason, very often, the processing of hyperspectral data, included unmixing, is preceded by a dimensionality reduction step to reduce computational complexity and to improve the signal-to-noise ratio (SNR). Principal component analysis (PCA) [46], maximum noise fraction (MNF) [47], and singular value decomposition (SVD) [48] are three well-known projection techniques widely used in remote sensing in general and in unmixing in particular. The newly introduced method [49] exploits the structure of hyperspectral mixtures, namely the fact that spectral vectors are nonnegative. The computational complexity associated with these techniques is an obstacle to real-time implementations. To overcome this problem, band selection [50] and non-statistical [51] algorithms have been introduced. This chapter addresses hyperspectral data source dependence and its impact on ICA and IFA performances. The study consider simulated and real data and is based on mutual information minimization. Hyperspectral observations are described by a generative model. This model takes into account the degradation mechanisms normally found in hyperspectral applications—namely, signature variability [52–54], abundance constraints, topography modulation, and system noise. The computation of mutual information is based on fitting mixtures of Gaussians (MOG) to data. The MOG parameters (number of components, means, covariances, and weights) are inferred using the minimum description length (MDL) based algorithm [55]. We study the behavior of the mutual information as a function of the unmixing matrix. The conclusion is that the unmixing matrix minimizing the mutual information might be very far from the true one. Nevertheless, some abundance fractions might be well separated, mainly in the presence of strong signature variability, a large number of endmembers, and high SNR. We end this chapter by sketching a new methodology to blindly unmix hyperspectral data, where abundance fractions are modeled as a mixture of Dirichlet sources. This model enforces positivity and constant sum sources (full additivity) constraints. The mixing matrix is inferred by an expectation-maximization (EM)-type algorithm. This approach is in the vein of references 39 and 56, replacing independent sources represented by MOG with mixture of Dirichlet sources. Compared with the geometric-based approaches, the advantage of this model is that there is no need to have pure pixels in the observations. The chapter is organized as follows. Section 6.2 presents a spectral radiance model and formulates the spectral unmixing as a linear problem accounting for abundance constraints, signature variability, topography modulation, and system noise. Section 6.3 presents a brief resume of ICA and IFA algorithms. Section 6.4 illustrates the performance of IFA and of some well-known ICA algorithms with experimental data. Section 6.5 studies the ICA and IFA limitations in unmixing hyperspectral data. Section 6.6 presents results of ICA based on real data. Section 6.7 describes the new blind unmixing scheme and some illustrative examples. Section 6.8 concludes with some remarks.

Blind hyperspectral unmixing

This paper introduces a new hyperspectral unmixing method called Dependent Component Analysis (DECA). This method decomposes a hyperspectral image into a collection of reflectance (or radiance) spectra of the materials present in the scene (endmember signatures) and the corresponding abundance fractions at each pixel. DECA models the abundance fractions as mixtures of Dirichlet densities, thus enforcing the constraints on abundance fractions imposed by the acquisition process, namely non-negativity and constant sum. The mixing matrix is inferred by a generalized expectation-maximization (GEM) type algorithm. This method overcomes the limitations of unmixing methods based on Independent Component Analysis (ICA) and on geometrical based approaches. DECA performance is illustrated using simulated and real data.

Development of a system to monitor surfer’s balance and plantar pressure and surfboard’s movement

O uso da tecnologia tem crescido nas últimas décadas nas mais diversas áreas, seja na indústria ou no dia-a-dia, e é cada vez mais evidente os benefícios que traz. No desporto não é diferente. Cada dia surgem novos desenvolvimentos objetivando a melhoria do desempenho dos praticantes de atividades físicas, possibilitando atingir resultados nunca antes pensados. Além disto, a utilização da tecnologia no desporto permite a obtenção de dados biomecânicos que podem ser utilizados tanto no treinamento quando na melhoria da qualidade de vida dos atletas auxiliando na prevenção de lesões, por exemplo. Deste modo, o presente projeto se aplica na área do desporto, nomeadamente, na modalidade do surfe, onde a ausência de trabalhos científicos ainda é elevada, aliando a tecnologia eletrônica ao desporto para quantificar informações até então desconhecidas. Três fatores básicos de desempenho foram levantados, sendo eles: equilíbrio, posicionamento dos pés e movimentação da prancha de surfe. Estes fatores levaram ao desenvolvimento de um sistema capaz de medi-los dinamicamente através da medição das forças plantares e da rotação da prancha de surfe. Além da medição dos fatores, o sistema é capaz de armazenar os dados adquiridos localmente através de um cartão de memória, para posterior análise; e também enviá-los através de uma comunicação sem fio, permitindo a visualização do centro de pressões plantares; dos ângulos de rotação da prancha de surfe; e da ativação dos sensores; em tempo real. O dispositivo consiste em um sistema eletrônico embarcado composto por um microcontrolador ATMEGA1280; um circuito de aquisição e condicionamento de sinal analógico; uma central inercial; um módulo de comunicação sem fio RN131; e um conjunto de sensores de força Flexiforce. O firmware embarcado foi desenvolvido em linguagem C. O software Matlab foi utilizado para receção de dados e visualização em tempo real. Os testes realizados demostraram que o funcionamento do sistema atende aos requisitos propostos, fornecendo informação acerca do equilíbrio, através do centro de pressões; do posicionamento dos pés, através da distribuição das pressões plantares; e do movimento da prancha nos eixos pitch e roll, através da central inercial. O erro médio de medição de força verificado foi de -0.0012 ± 0.0064 N, enquanto a mínima distância alcançada na transmissão sem fios foi de 100 m. A potência medida do sistema foi de 330 mW.

New analytical methodologies for doping control – detection of anabolic androgenic steroids in human urine

Dissertation submitted to Faculdade de Ciências e Tecnologia - Universidade Nova de Lisboa in fulfilment of the requirements for the degree of Doctor of Philosophy (Biochemistry - Biotechnology)

Using data mining techniques to support breast cancer diagnosis

More than ever, there is an increase of the number of decision support methods and computer aided diagnostic systems applied to various areas of medicine. In breast cancer research, many works have been done in order to reduce false-positives when used as a double reading method. In this study, we aimed to present a set of data mining techniques that were applied to approach a decision support system in the area of breast cancer diagnosis. This method is geared to assist clinical practice in identifying mammographic findings such as microcalcifications, masses and even normal tissues, in order to avoid misdiagnosis. In this work a reliable database was used, with 410 images from about 115 patients, containing previous reviews performed by radiologists as microcalcifications, masses and also normal tissue findings. Throughout this work, two feature extraction techniques were used: the gray level co-occurrence matrix and the gray level run length matrix. For classification purposes, we considered various scenarios according to different distinct patterns of injuries and several classifiers in order to distinguish the best performance in each case described. The many classifiers used were Naïve Bayes, Support Vector Machines, k-nearest Neighbors and Decision Trees (J48 and Random Forests). The results in distinguishing mammographic findings revealed great percentages of PPV and very good accuracy values. Furthermore, it also presented other related results of classification of breast density and BI-RADS® scale. The best predictive method found for all tested groups was the Random Forest classifier, and the best performance has been achieved through the distinction of microcalcifications. The conclusions based on the several tested scenarios represent a new perspective in breast cancer diagnosis using data mining techniques.

MCDA applied to performance appraisal of short-haul truck drivers: a case study in a portuguese trucking company

Performance appraisal increasingly assumes a more important role in any organizational environment. In the trucking industry, drivers are the company's image and for this reason it is important to develop and increase their performance and commitment to the company's goals. This paper aims to create a performance appraisal model for trucking drivers, based on a multi-criteria decision aid methodology. The PROMETHEE and MMASSI methodologies were adapted using the criteria used for performance appraisal by the trucking company studied. The appraisal involved all the truck drivers, their supervisors and the company's Managing Director. The final output is a ranking of the drivers, based on their performance, for each one of the scenarios used. The results are to be used as a decision-making tool to allocate drivers to the domestic haul service.

Life-cycle performance of structures: combining expert judgment and results of inspection

Life-Cycle Civil Engineering – Biondini & Frangopol

Consumers Performance Evaluation of the Participation in Demand Response Programs Using Baseline Methods

Demand response has gain increasing importance in the context of competitive electricity markets environment. The use of demand resources is also advantageous in the context of smart grid operation. In addition to the need of new business models for integrating demand response, adequate methods are necessary for an accurate determination of the consumers’ performance evaluation after the participation in a demand response event. The present paper makes a comparison between some of the existing baseline methods related to the consumers’ performance evaluation, comparing the results obtained with these methods and also with a method proposed by the authors of the paper. A case study demonstrates the application of the referred methods to real consumption data belonging to a consumer connected to a distribution network.

Developing and implementing an environmental performance index for the Portuguese military

Business Strategy and the Environment nº 15, p. 71–86

The state of environmental performance evaluation in the public sector: the case of the Portuguese defence sector

Journal of Cleaner Production, nº 17, p. 36-52

Analysis of Consumption Data to Detect Commercial Losses Using Performance Evaluation Methods in a Smart Grid

Electric power networks, namely distribution networks, have been suffering several changes during the last years due to changes in the power systems operation, towards the implementation of smart grids. Several approaches to the operation of the resources have been introduced, as the case of demand response, making use of the new capabilities of the smart grids. In the initial levels of the smart grids implementation reduced amounts of data are generated, namely consumption data. The methodology proposed in the present paper makes use of demand response consumers’ performance evaluation methods to determine the expected consumption for a given consumer. Then, potential commercial losses are identified using monthly historic consumption data. Real consumption data is used in the case study to demonstrate the application of the proposed method.

Environmental performance policy indicators for the public sector: The case of the defence sector

Journal of Environmental Management, nº 82 p. 410–432

RepComp - replicated software components for improved performance

Trabalho apresentado no âmbito do Mestrado em Engenharia Informática, como requisito parcial para obtenção do grau de Mestre em Engenharia Informática

Cochineal, a precious source of red: cochineal dyes characterization by high performance liquid chromatography with diode array detection and principal component analysis

Presented at Faculdade de Ciências e Tecnologias, Universidade de Lisboa, to obtain the Master Degree in Conservation and Restoration of Textiles

Safety climate and its relationship with furniture companies’ safety performance and workers’ risk acceptance

This study aims to analyse the relationship between safety climate and the level of risk acceptance, as well as its relationship with workplace safety performance. The sample includes 14 companies and 403 workers. The safety climate assessment was performed by the application of a Safety Climate in Wood Industries questionnaire and safety performance was assessed with a checklist. Judgements about risk acceptance were measured through questionnaires together with four other variables: trust, risk perception, benefit perception and emotion. Safety climate was found to be correlated with workgroup safety performance, and it also plays an important role in workers’ risk acceptance levels. Risk acceptance tends to be lower when safety climate scores of workgroups are high, and subsequently, their safety performance is better. These findings seem to be relevant, as they provide Occupational, Safety and Health practitioners with a better understanding of workers’ risk acceptance levels and of the differences among workgroups.