Independent component analysis for the identification of sources of variation on an industrial nirs application

A Near Infrared Spectroscopy (NIRS) industrial application was developed by the LPF-Tagralia team, and transferred to a Spanish dehydrator company (Agrotécnica Extremeña S.L.) for the classification of dehydrator onion bulbs for breeding purposes. The automated operation of the system has allowed the classification of more than one million onion bulbs during seasons 2004 to 2008 (Table 1). The performance achieved by the original model (R2=0,65; SEC=2,28ºBrix) was enough for qualitative classification thanks to the broad range of variation of the initial population (18ºBrix). Nevertheless, a reduction of the classification performance of the model has been observed with the passing of seasons. One of the reasons put forward is the reduction of the range of variation that naturally occurs during a breeding process, the other is the variations in other parameters than the variable of interest but whose effects would probably be affecting the measurements [1]. This study points to the application of Independent Component Analysis (ICA) on this highly variable dataset coming from a NIRS industrial application for the identification of the different sources of variation present through seasons.

Automatic motion compensation of free breathing acquired myocardial perfusion data by using independent component analysis

Images acquired during free breathing using first-pass gadolinium-enhanced myocardial perfusion magnetic resonance imaging (MRI) exhibit a quasiperiodic motion pattern that needs to be compensated for if a further automatic analysis of the perfusion is to be executed. In this work, we present a method to compensate this movement by combining independent component analysis (ICA) and image registration: First, we use ICA and a time?frequency analysis to identify the motion and separate it from the intensity change induced by the contrast agent. Then, synthetic reference images are created by recombining all the independent components but the one related to the motion. Therefore, the resulting image series does not exhibit motion and its images have intensities similar to those of their original counterparts. Motion compensation is then achieved by using a multi-pass image registration procedure. We tested our method on 39 image series acquired from 13 patients, covering the basal, mid and apical areas of the left heart ventricle and consisting of 58 perfusion images each. We validated our method by comparing manually tracked intensity profiles of the myocardial sections to automatically generated ones before and after registration of 13 patient data sets (39 distinct slices). We compared linear, non-linear, and combined ICA based registration approaches and previously published motion compensation schemes. Considering run-time and accuracy, a two-step ICA based motion compensation scheme that first optimizes a translation and then for non-linear transformation performed best and achieves registration of the whole series in 32 ± 12 s on a recent workstation. The proposed scheme improves the Pearsons correlation coefficient between manually and automatically obtained time?intensity curves from .84 ± .19 before registration to .96 ± .06 after registration

Application of Independent Components Analysis with the JADE algorithm and NIR hyperspectral imaging for revealing food adulteration

In recent years, Independent Components Analysis (ICA) has proven itself to be a powerful signal-processing technique for solving the Blind-Source Separation (BSS) problems in different scientific domains. In the present work, an application of ICA for processing NIR hyperspectral images to detect traces of peanut in wheat flour is presented. Processing was performed without a priori knowledge of the chemical composition of the two food materials. The aim was to extract the source signals of the different chemical components from the initial data set and to use them in order to determine the distribution of peanut traces in the hyperspectral images. To determine the optimal number of independent component to be extracted, the Random ICA by blocks method was used. This method is based on the repeated calculation of several models using an increasing number of independent components after randomly segmenting the matrix data into two blocks and then calculating the correlations between the signals extracted from the two blocks. The extracted ICA signals were interpreted and their ability to classify peanut and wheat flour was studied. Finally, all the extracted ICs were used to construct a single synthetic signal that could be used directly with the hyperspectral images to enhance the contrast between the peanut and the wheat flours in a real multi-use industrial environment. Furthermore, feature extraction methods (connected components labelling algorithm followed by flood fill method to extract object contours) were applied in order to target the spatial location of the presence of peanut traces. A good visualization of the distributions of peanut traces was thus obtained

Two Novel Methods For The Determination Of The Number Of Components In Independent Components Analysis Models

Independent Components Analysis is a Blind Source Separation method that aims to find the pure source signals mixed together in unknown proportions in the observed signals under study. It does this by searching for factors which are mutually statistically independent. It can thus be classified among the latent-variable based methods. Like other methods based on latent variables, a careful investigation has to be carried out to find out which factors are significant and which are not. Therefore, it is important to dispose of a validation procedure to decide on the optimal number of independent components to include in the final model. This can be made complicated by the fact that two consecutive models may differ in the order and signs of similarly-indexed ICs. As well, the structure of the extracted sources can change as a function of the number of factors calculated. Two methods for determining the optimal number of ICs are proposed in this article and applied to simulated and real datasets to demonstrate their performance.

A robust procedure for damage detection from strain measurements based on principal component analysis

FBGs are excellent strain sensors, because of its low size and multiplexing capability. Tens to hundred of sensors may be embedded into a structure, as it has already been demonstrated. Nevertheless, they only afford strain measurements at local points, so unless the damage affects the strain readings in a distinguishable manner, damage will go undetected. This paper show the experimental results obtained on the wing of a UAV, instrumented with 32 FBGs, before and after small damages were introduced. The PCA algorithm was able to distinguish the damage cases, even for small cracks. Principal Component Analysis (PCA) is a technique of multivariable analysis to reduce a complex data set to a lower dimension and reveal some hidden patterns that underlie.

Detection and quantification of peanut traces in wheat flour by near infrared hyperspectral imaging spectroscopy using principal-component analysis

The use of a common environment for processing different powder foods in the industry has increased the risk of finding peanut traces in powder foods. The analytical methods commonly used for detection of peanut such as enzyme-linked immunosorbent assay (ELISA) and real-time polymerase chain reaction (RT-PCR) represent high specificity and sensitivity but are destructive and time-consuming, and require highly skilled experimenters. The feasibility of NIR hyperspectral imaging (HSI) is studied for the detection of peanut traces down to 0.01% by weight. A principal-component analysis (PCA) was carried out on a dataset of peanut and flour spectra. The obtained loadings were applied to the HSI images of adulterated wheat flour samples with peanut traces. As a result, HSI images were reduced to score images with enhanced contrast between peanut and flour particles. Finally, a threshold was fixed in score images to obtain a binary classification image, and the percentage of peanut adulteration was compared with the percentage of pixels identified as peanut particles. This study allowed the detection of traces of peanut down to 0.01% and quantification of peanut adulteration from 10% to 0.1% with a coefficient of determination (r2) of 0.946. These results show the feasibility of using HSI systems for the detection of peanut traces in conjunction with chemical procedures, such as RT-PCR and ELISA to facilitate enhanced quality-control surveillance on food-product processing lines.

Class-Conditional Probabilistic Principal Component Analysis: application to gender recognition

Este trabajo presenta una solución al problema del reconocimiento del género de un rostro humano a partir de una imagen. Adoptamos una aproximación que utiliza la cara completa a través de la textura de la cara normalizada y redimensionada como entrada a un clasificador Näive Bayes. Presentamos la técnica de Análisis de Componentes Principales Probabilístico Condicionado-a-la-Clase (CC-PPCA) para reducir la dimensionalidad de los vectores de características para la clasificación y asegurar la asunción de independencia para el clasificador. Esta nueva aproximación tiene la deseable propiedad de presentar un modelo paramétrico sencillo para las marginales. Además, este modelo puede estimarse con muy pocos datos. En los experimentos que hemos desarrollados mostramos que CC-PPCA obtiene un 90% de acierto en la clasificación, resultado muy similar al mejor presentado en la literatura---ABSTRACT---This paper presents a solution to the problem of recognizing the gender of a human face from an image. We adopt a holistic approach by using the cropped and normalized texture of the face as input to a Naïve Bayes classifier. First it is introduced the Class-Conditional Probabilistic Principal Component Analysis (CC-PPCA) technique to reduce the dimensionality of the classification attribute vector and enforce the independence assumption of the classifier. This new approach has the desirable property of a simple parametric model for the marginals. Moreover this model can be estimated with very few data. In the experiments conducted we show that using CCPPCA we get 90% classification accuracy, which is similar result to the best in the literature. The proposed method is very simple to train and implement.

Nonrigid Motion Compensation of Free Breathing Acquired Myocardial Perfusion Data

In this work, we present a novel method to compensate the movement in images acquired during free breathing using first-pass gadolinium enhanced, myocardial perfusion magnetic resonance imaging (MRI). First, we use independent component analysis (ICA) to identify the optimal number of independent components (ICs) that separate the breathing motion from the intensity change induced by the contrast agent. Then, synthetic images are created by recombining the ICs, but other then in previously published work (Milles et al. 2008), we omit the component related to motion, and therefore, the resulting reference image series is free of motion. Motion compensation is then achieved by using a multi-pass non-rigid image registration scheme. We tested our method on 15 distinct image series (5 patients) consisting of 58 images each and we validated our method by comparing manually tracked intensity profiles of the myocardial sections to automatically generated ones before and after registration. The average correlation to the manually obtained curves before registration 0:89 0:11 was increased to 0:98 0:02

Two way clustering of Microarray Data using a Hybrid Approach

The Microarray technique is rather powerful, as it allows to test up thousands of genes at a time, but this produces an overwhelming set of data files containing huge amounts of data, which is quite difficult to pre-process, separate, classify and correlate for interesting conclusions to be extracted. Modern machine learning, data mining and clustering techniques based on information theory, are needed to read and interpret the information contents buried in those large data sets. Independent Component Analysis method can be used to correct the data affected by corruption processes or to filter the uncorrectable one and then clustering methods can group similar genes or classify samples. In this paper a hybrid approach is used to obtain a two way unsupervised clustering for a corrected microarray data.

Changes in resting-state functionally connected parieto-frontal networks after videogame practice

Neuroimaging studies provide evidence for organized intrinsic activity under task-free conditions. This activity serves functionally relevant brain systems supporting cognition. Here, we analyze changes in resting-state functional connectivity after videogame practice applying a test–retest design. Twenty young females were selected from a group of 100 participants tested on four standardized cognitive ability tests. The practice and control groups were carefully matched on their ability scores. The practice group played during two sessions per week across 4 weeks (16 h total) under strict supervision in the laboratory, showing systematic performance improvements in the game. A group independent component analysis (GICA) applying multisession temporal concatenation on test–retest resting-state fMRI, jointly with a dual-regression approach, was computed. Supporting the main hypothesis, the key finding reveals an increased correlated activity during rest in certain predefined resting state networks (albeit using uncorrected statistics) attributable to practice with the cognitively demanding tasks of the videogame. Observed changes were mainly concentrated on parietofrontal networks involved in heterogeneous cognitive functions.

Signal-to-noise ratio of the MEG signal after preprocessing

Background Magnetoencephalography (MEG) provides a direct measure of brain activity with high combined spatiotemporal resolution. Preprocessing is necessary to reduce contributions from environmental interference and biological noise. New method The effect on the signal-to-noise ratio of different preprocessing techniques is evaluated. The signal-to-noise ratio (SNR) was defined as the ratio between the mean signal amplitude (evoked field) and the standard error of the mean over trials. Results Recordings from 26 subjects obtained during and event-related visual paradigm with an Elekta MEG scanner were employed. Two methods were considered as first-step noise reduction: Signal Space Separation and temporal Signal Space Separation, which decompose the signal into components with origin inside and outside the head. Both algorithm increased the SNR by approximately 100%. Epoch-based methods, aimed at identifying and rejecting epochs containing eye blinks, muscular artifacts and sensor jumps provided an SNR improvement of 5–10%. Decomposition methods evaluated were independent component analysis (ICA) and second-order blind identification (SOBI). The increase in SNR was of about 36% with ICA and 33% with SOBI. Comparison with existing methods No previous systematic evaluation of the effect of the typical preprocessing steps in the SNR of the MEG signal has been performed. Conclusions The application of either SSS or tSSS is mandatory in Elekta systems. No significant differences were found between the two. While epoch-based methods have been routinely applied the less often considered decomposition methods were clearly superior and therefore their use seems advisable.

Comparison of linear and non-linear 2D+T registration methods for DE-MRI cardiac perfusion studies

A series of motion compensation algorithms is run on the challenge data including methods that optimize only a linear transformation, or a non-linear transformation, or both – first a linear and then a non-linear transformation. Methods that optimize a linear transformation run an initial segmentation of the area of interest around the left myocardium by means of an independent component analysis (ICA) (ICA-*). Methods that optimize non-linear transformations may run directly on the full images, or after linear registration. Non-linear motion compensation approaches applied include one method that only registers pairs of images in temporal succession (SERIAL), one method that registers all image to one common reference (AllToOne), one method that was designed to exploit quasi-periodicity in free breathing acquired image data and was adapted to also be usable to image data acquired with initial breath-hold (QUASI-P), a method that uses ICA to identify the motion and eliminate it (ICA-SP), and a method that relies on the estimation of a pseudo ground truth (PG) to guide the motion compensation.

Climate change technology transfer to developing countries: evidence analysis and policy recommendations

Developing countries are experiencing unprecedented levels of economic growth. As a result, they will be responsible for most of the future growth in energy demand and greenhouse gas (GHG) emissions. Curbing GHG emissions in developing countries has become one of the cornerstones of a future international agreement under the United Nations Framework Convention for Climate Change (UNFCCC). However, setting caps for developing countries’ GHG emissions has encountered strong resistance in the current round of negotiations. Continued economic growth that allows poverty eradication is still the main priority for most developing countries, and caps are perceived as a constraint to future growth prospects. The development, transfer and use of low-carbon technologies have more positive connotations, and are seen as the potential path towards low-carbon development. So far, the success of the UNFCCC process in improving the levels of technology transfer (TT) to developing countries has been limited. This thesis analyses the causes for such limited success and seeks to improve on the understanding about what constitutes TT in the field of climate change, establish the factors that enable them in developing countries and determine which policies could be implemented to reinforce these factors. Despite the wide recognition of the importance of technology and knowledge transfer to developing countries in the climate change mitigation policy agenda, this issue has not received sufficient attention in academic research. Current definitions of climate change TT barely take into account the perspective of actors involved in actual climate change TT activities, while respective measurements do not bear in mind the diversity of channels through which these happen and the outputs and effects that they convey. Furthermore, the enabling factors for TT in non-BRIC (Brazil, Russia, India, China) developing countries have been seldom investigated, and policy recommendations to improve the level and quality of TTs to developing countries have not been adapted to the specific needs of highly heterogeneous countries, commonly denominated as “developing countries”. This thesis contributes to enriching the climate change TT debate from the perspective of a smaller emerging economy (Chile) and by undertaking a quantitative analysis of enabling factors for TT in a large sample of developing countries. Two methodological approaches are used to study climate change TT: comparative case study analysis and quantitative analysis. Comparative case studies analyse TT processes in ten cases based in Chile, all of which share the same economic, technological and policy frameworks, thus enabling us to draw conclusions on the enabling factors and obstacles operating in TT processes. The quantitative analysis uses three methodologies – principal component analysis, multiple regression analysis and cluster analysis – to assess the performance of developing countries in a number of enabling factors and the relationship between these factors and indicators of TT, as well as to create groups of developing countries with similar performances. The findings of this thesis are structured to provide responses to four main research questions: What constitutes technology transfer and how does it happen? Is it possible to measure technology transfer, and what are the main challenges in doing so? Which factors enable climate change technology transfer to developing countries? And how do different developing countries perform in these enabling factors, and how can differentiated policy priorities be defined accordingly? vi Resumen Los paises en desarrollo estan experimentando niveles de crecimiento economico sin precedentes. Como consecuencia, se espera que sean responsables de la mayor parte del futuro crecimiento global en demanda energetica y emisiones de Gases de Efecto de Invernadero (GEI). Reducir las emisiones de GEI en los paises en desarrollo es por tanto uno de los pilares de un futuro acuerdo internacional en el marco de la Convencion Marco de las Naciones Unidas para el Cambio Climatico (UNFCCC). La posibilidad de compromisos vinculantes de reduccion de emisiones de GEI ha sido rechazada por los paises en desarrollo, que perciben estos limites como frenos a su desarrollo economico y a su prioridad principal de erradicacion de la pobreza. El desarrollo, transferencia y uso de tecnologias bajas en carbono tiene connotaciones mas positivas y se percibe como la via hacia un crecimiento bajo en carbono. Hasta el momento, la UNFCCC ha tenido un exito limitado en la promocion de transferencias de tecnologia (TT) a paises en desarrollo. Esta tesis analiza las causas de este resultado y busca mejorar la comprension sobre que constituye transferencia de tecnologia en el area de cambio climatico, cuales son los factores que la facilitan en paises en desarrollo y que politicas podrian implementarse para reforzar dichos factores. A pesar del extendido reconocimiento sobre la importancia de la transferencia de tecnologia a paises en desarrollo en la agenda politica de cambio climatico, esta cuestion no ha sido suficientemente atendida por la investigacion existente. Las definiciones actuales de transferencia de tecnologia relacionada con la mitigacion del cambio climatico no tienen en cuenta la diversidad de canales por las que se manifiestan o los efectos que consiguen. Los factores facilitadores de TT en paises en desarrollo no BRIC (Brasil, Rusia, India y China) apenas han sido investigados, y las recomendaciones politicas para aumentar el nivel y la calidad de la TT no se han adaptado a las necesidades especificas de paises muy heterogeneos aglutinados bajo el denominado grupo de "paises en desarrollo". Esta tesis contribuye a enriquecer el debate sobre la TT de cambio climatico con la perspectiva de una economia emergente de pequeno tamano (Chile) y el analisis cuantitativo de factores que facilitan la TT en una amplia muestra de paises en desarrollo. Se utilizan dos metodologias para el estudio de la TT a paises en desarrollo: analisis comparativo de casos de estudio y analisis cuantitativo basado en metodos multivariantes. Los casos de estudio analizan procesos de TT en diez casos basados en Chile, para derivar conclusiones sobre los factores que facilitan u obstaculizan el proceso de transferencia. El analisis cuantitativo multivariante utiliza tres metodologias: regresion multiple, analisis de componentes principales y analisis cluster. Con dichas metodologias se busca analizar el posicionamiento de diversos paises en cuanto a factores que facilitan la TT; las relaciones entre dichos factores e indicadores de transferencia tecnologica; y crear grupos de paises con caracteristicas similares que podrian beneficiarse de politicas similares para la promocion de la transferencia de tecnologia. Los resultados de la tesis se estructuran en torno a cuatro preguntas de investigacion: .Que es la transferencia de tecnologia y como ocurre?; .Es posible medir la transferencia de tecnologias de bajo carbono?; .Que factores facilitan la transferencia de tecnologias de bajo carbono a paises en desarrollo? y .Como se puede agrupar a los paises en desarrollo en funcion de sus necesidades politicas para la promocion de la transferencia de tecnologias de bajo carbono?

A practical approach to the global analysis of CLP programs

This paper presents and illustrates with an example a practical approach to the dataflow analysis of programs written in constraint logic programming (CLP) languages using abstract interpretation. It is first argued that, from the framework point of view, it sufnces to propose relatively simple extensions of traditional analysis methods which have already been proved useful and practical and for which efncient fixpoint algorithms have been developed. This is shown by proposing a simple but quite general extensión of Bruynooghe's traditional framework to the analysis of CLP programs. In this extensión constraints are viewed not as "suspended goals" but rather as new information in the store, following the traditional view of CLP. Using this approach, and as an example of its use, a complete, constraint system independent, abstract analysis is presented for approximating definiteness information. The analysis is in fact of quite general applicability. It has been implemented and used in the analysis of CLP(R) and Prolog-III applications. Results from the implementation of this analysis are also presented.

Latest developments in data analysis tools for disruption prediction and for the exploration of multimachine operational spaces.

In the last years significant efforts have been devoted to the development of advanced data analysis tools to both predict the occurrence of disruptions and to investigate the operational spaces of devices, with the long term goal of advancing the understanding of the physics of these events and to prepare for ITER. On JET the latest generation of the disruption predictor called APODIS has been deployed in the real time network during the last campaigns with the new metallic wall. Even if it was trained only with discharges with the carbon wall, it has reached very good performance, with both missed alarms and false alarms in the order of a few percent (and strategies to improve the performance have already been identified). Since for the optimisation of the mitigation measures, predicting also the type of disruption is considered to be also very important, a new clustering method, based on the geodesic distance on a probabilistic manifold, has been developed. This technique allows automatic classification of an incoming disruption with a success rate of better than 85%. Various other manifold learning tools, particularly Principal Component Analysis and Self Organised Maps, are also producing very interesting results in the comparative analysis of JET and ASDEX Upgrade (AUG) operational spaces, on the route to developing predictors capable of extrapolating from one device to another.