Event-related potential analyses via single-subject topographic classification.

Introduction: Responses to external stimuli are typically investigated by averaging peri-stimulus electroencephalography (EEG) epochs in order to derive event-related potentials (ERPs) across the electrode montage, under the assumption that signals that are related to the external stimulus are fixed in time across trials. We demonstrate the applicability of a single-trial model based on patterns of scalp topographies (De Lucia et al, 2007) that can be used for ERP analysis at the single-subject level. The model is able to classify new trials (or groups of trials) with minimal a priori hypotheses, using information derived from a training dataset. The features used for the classification (the topography of responses and their latency) can be neurophysiologically interpreted, because a difference in scalp topography indicates a different configuration of brain generators. An above chance classification accuracy on test datasets implicitly demonstrates the suitability of this model for EEG data. Methods: The data analyzed in this study were acquired from two separate visual evoked potential (VEP) experiments. The first entailed passive presentation of checkerboard stimuli to each of the four visual quadrants (hereafter, "Checkerboard Experiment") (Plomp et al, submitted). The second entailed active discrimination of novel versus repeated line drawings of common objects (hereafter, "Priming Experiment") (Murray et al, 2004). Four subjects per experiment were analyzed, using approx. 200 trials per experimental condition. These trials were randomly separated in training (90%) and testing (10%) datasets in 10 independent shuffles. In order to perform the ERP analysis we estimated the statistical distribution of voltage topographies by a Mixture of Gaussians (MofGs), which reduces our original dataset to a small number of representative voltage topographies. We then evaluated statistically the degree of presence of these template maps across trials and whether and when this was different across experimental conditions. Based on these differences, single-trials or sets of a few single-trials were classified as belonging to one or the other experimental condition. Classification performance was assessed using the Receiver Operating Characteristic (ROC) curve. Results: For the Checkerboard Experiment contrasts entailed left vs. right visual field presentations for upper and lower quadrants, separately. The average posterior probabilities, indicating the presence of the computed template maps in time and across trials revealed significant differences starting at ~60-70 ms post-stimulus. The average ROC curve area across all four subjects was 0.80 and 0.85 for upper and lower quadrants, respectively and was in all cases significantly higher than chance (unpaired t-test, p<0.0001). In the Priming Experiment, we contrasted initial versus repeated presentations of visual object stimuli. Their posterior probabilities revealed significant differences, which started at 250ms post-stimulus onset. The classification accuracy rates with single-trial test data were at chance level. We therefore considered sub-averages based on five single trials. We found that for three out of four subjects' classification rates were significantly above chance level (unpaired t-test, p<0.0001). Conclusions: The main advantage of the present approach is that it is based on topographic features that are readily interpretable along neurophysiologic lines. As these maps were previously normalized by the overall strength of the field potential on the scalp, a change in their presence across trials and between conditions forcibly reflects a change in the underlying generator configurations. The temporal periods of statistical difference between conditions were estimated for each training dataset for ten shuffles of the data. Across the ten shuffles and in both experiments, we observed a high level of consistency in the temporal periods over which the two conditions differed. With this method we are able to analyze ERPs at the single-subject level providing a novel tool to compare normal electrophysiological responses versus single cases that cannot be considered part of any cohort of subjects. This aspect promises to have a strong impact on both basic and clinical research.

Sex differences: From mental rotation to object location memory, an ERP study

Sex differences in cognition have been largely investigated. The most consistent sex differences favoring females are observed in object location memory involving the left hemisphere whereas the most consistent sex differences favoring males are observed in tasks that require mental rotation involving the right hemisphere. Here we used a task involving these two abilities to see the impact of mental rotation on object location memory. To that end we used a combination of behavioral and event-related potential (ERP) electroencephalography (EEG) measures.A computer screen displayed a square frame of 4 pairs of images (a "teddy" bear, a shoe, an umbrella and a lamp) randomly arranged around a central fixation cross. After a 10-second interval for memorization, images disappeared and were replaced by a test frame with no image but a random pair of two locations marked in black. In addition, this test frame was randomly displayed either in the original orientation (0° rotation) or in the rotated one (90° clockwise - CW - or 90° counterclockwise - CCW). Preceding the test frame, an arrow indicating the presence or the absence of rotation of the frame was displayed on the screen. The task of the participants (15 females and 15 males) was to determine if two marked locations corresponded or not to a pair of identical images. Each response was followed by feedback.Findings showed no significant sex differences in the performance of the original orientation. In comparison with this position, the rotation of the frame produced an equal decrease of male and female performance. In addition, this decrease was significantly higher when the rotation of the frame was in a CCW direction. We further assessed the ERP when the arrow indicated the direction of rotation as stimulus-onset, during four time windows representing major components C1, P1, N1 and N2. Although no sex differences were observed in performance, brain activities differed according to sex. Enhanced amplitudes were found for the CCW compared to CW rotation over the right posterior areas for the P1, N1 and N2 components for men as well as for women. Major topographical differences related to sex were measured for the CW rotation condition as marked lateralized amplitude: left-hemisphere amplitude larger than right one was measured during P1 time range for men. These similar patterns prolonged from P1 to N1 for women. Early distinctions were found in interaction with sex between CCW and CW waveform amplitudes, expressing over anterior electrode sites during C1 time range (0-50 ms post-stimulus).In conclusion (i) women do not outperform men in object location memory in this study (absence of rotation condition); (ii) mental rotation, in particular the direction of rotation, influences performance on object location memory; (iii) CCW rotation is associated with activity in the right parietal hemisphere whereas the CW rotation involves the left parietal hemisphere; (iv) this last effect is less pronounced in males, which could explain why greater involvement of right parietal areas in men and of bilateral posterior areas in women is generally reported in mental rotation tasks; and (v) the early distinctions between both directions of rotation located over anterior sites could be related to sex differences in their respective involvement of control mechanisms.

Pliocene and Pleistocene diversification and multiple refugia in a Eurasian shrew (Crocidura suaveolens group).

We sequenced 998 base pairs (bp) of mitochondrial DNA cytochrome b and 799 bp of nuclear gene BRCA1 in the Lesser white-toothed shrew (Crocidura suaveolens group) over its geographic range from Portugal to Japan. The aims of the study were to identify the main clades within the group and respective refugia resulting from Pleistocene glaciations. Analyses revealed the Asian lesser white-toothed shrew (C. shantungensis) as the basal clade, followed by a major branch of C. suaveolens, subdivided sensu stricto into six clades, which split-up in the Upper Pliocene and Lower Pleistocene (1.9-0.9 Myr). The largest clade, occurring over a huge range from east Europe to Mongolia, shows evidence of population expansion after a bottleneck. West European clades originated from Iberian and Italo-Balkanic refugia. In the Near East, three clades evolved in an apparent hotspot of refugia (west Turkey, south-west and south-east of the Caucasus). Most clades include specimens of different morphotypes and the validity of many taxa in the C. suaveolens group has to be re-evaluated.

Sex differences: From mental rotation to object location memory, an ERP study

Sex differences in cognition have been largely investigated. The most consistent sex differences favoring females are observed in object location memory involving the left hemisphere whereas the most consistent sex differences favoring males are observed in tasks that require mental rotation involving the right hemisphere. Here we used a task involving these two abilities to see the impact of mental rotation on object location memory. To that end we used a combination of behavioral and event-related potential (ERP) electroencephalography (EEG) measures.A computer screen displayed a square frame of 4 pairs of images (a "teddy" bear, a shoe, an umbrella and a lamp) randomly arranged around a central fixation cross. After a 10-second interval for memorization, images disappeared and were replaced by a test frame with no image but a random pair of two locations marked in black. In addition, this test frame was randomly displayed either in the original orientation (0° rotation) or in the rotated one (90° clockwise - CW - or 90° counterclockwise - CCW). Preceding the test frame, an arrow indicating the presence or the absence of rotation of the frame was displayed on the screen. The task of the participants (15 females and 15 males) was to determine if two marked locations corresponded or not to a pair of identical images. Each response was followed by feedback.Findings showed no significant sex differences in the performance of the original orientation. In comparison with this position, the rotation of the frame produced an equal decrease of male and female performance. In addition, this decrease was significantly higher when the rotation of the frame was in a CCW direction. We further assessed the ERP when the arrow indicated the direction of rotation as stimulus-onset, during four time windows representing major components C1, P1, N1 and N2. Although no sex differences were observed in performance, brain activities differed according to sex. Enhanced amplitudes were found for the CCW compared to CW rotation over the right posterior areas for the P1, N1 and N2 components for men as well as for women. Major topographical differences related to sex were measured for the CW rotation condition as marked lateralized amplitude: left-hemisphere amplitude larger than right one was measured during P1 time range for men. These similar patterns prolonged from P1 to N1 for women. Early distinctions were found in interaction with sex between CCW and CW waveform amplitudes, expressing over anterior electrode sites during C1 time range (0-50 ms post-stimulus).In conclusion (i) women do not outperform men in object location memory in this study (absence of rotation condition); (ii) mental rotation, in particular the direction of rotation, influences performance on object location memory; (iii) CCW rotation is associated with activity in the right parietal hemisphere whereas the CW rotation involves the left parietal hemisphere; (iv) this last effect is less pronounced in males, which could explain why greater involvement of right parietal areas in men and of bilateral posterior areas in women is generally reported in mental rotation tasks; and (v) the early distinctions between both directions of rotation located over anterior sites could be related to sex differences in their respective involvement of control mechanisms.

A species delimitation approach in the Trochulus sericeus/hispidus complex reveals two cryptic species within a sharp contact zone.

BACKGROUND: Mitochondrial DNA sequencing increasingly results in the recognition of genetically divergent, but morphologically cryptic lineages. Species delimitation approaches that rely on multiple lines of evidence in areas of co-occurrence are particularly powerful to infer their specific status. We investigated the species boundaries of two cryptic lineages of the land snail genus Trochulus in a contact zone, using mitochondrial and nuclear DNA marker as well as shell morphometrics. RESULTS: Both mitochondrial lineages have a distinct geographical distribution with a small zone of co-occurrence. In the same area, we detected two nuclear genotype clusters, each being highly significantly associated to one mitochondrial lineage. This association however had exceptions: a small number of individuals in the contact zone showed intermediate genotypes (4%) or cytonuclear disequilibrium (12%). Both mitochondrial lineage and nuclear cluster were statistically significant predictors for the shell shape indicating morphological divergence. Nevertheless, the lineage morphospaces largely overlapped (low posterior classification success rate of 69% and 78%, respectively): the two lineages are truly cryptic. CONCLUSION: The integrative approach using multiple lines of evidence supported the hypothesis that the investigated Trochulus lineages are reproductively isolated species. In the small contact area, however, the lineages hybridise to a limited extent. This detection of a hybrid zone adds an instance to the rare reported cases of hybridisation in land snails.

An intense form of homeostatic proliferation of naive CD8+ cells driven by IL-2.

In conditions of T lymphopenia, interleukin (IL) 7 levels rise and, via T cell receptor for antigen-self-major histocompatibility complex (MHC) interaction, induce residual naive T cells to proliferate. This pattern of lymphopenia-induced "homeostatic" proliferation is typically quite slow and causes a gradual increase in total T cell numbers and differentiation into cells with features of memory cells. In contrast, we describe a novel form of homeostatic proliferation that occurs when naive T cells encounter raised levels of IL-2 and IL-15 in vivo. In this situation, CD8(+) T cells undergo massive expansion and rapid differentiation into effector cells, thus closely resembling the T cell response to foreign antigens. However, the responses induced by IL-2/IL-15 are not seen in MHC-deficient hosts, implying that the responses are driven by self-ligands. Hence, homeostatic proliferation of naive T cells can be either slow or fast, with the quality of the response to self being dictated by the particular cytokine (IL-7 vs. IL-2/IL-15) concerned. The relevance of the data to the gradual transition of naive T cells into memory-phenotype (MP) cells with age is discussed.

Active learning methods for remote sensing image classification

In this paper, we propose two active learning algorithms for semiautomatic definition of training samples in remote sensing image classification. Based on predefined heuristics, the classifier ranks the unlabeled pixels and automatically chooses those that are considered the most valuable for its improvement. Once the pixels have been selected, the analyst labels them manually and the process is iterated. Starting with a small and nonoptimal training set, the model itself builds the optimal set of samples which minimizes the classification error. We have applied the proposed algorithms to a variety of remote sensing data, including very high resolution and hyperspectral images, using support vector machines. Experimental results confirm the consistency of the methods. The required number of training samples can be reduced to 10% using the methods proposed, reaching the same level of accuracy as larger data sets. A comparison with a state-of-the-art active learning method, margin sampling, is provided, highlighting advantages of the methods proposed. The effect of spatial resolution and separability of the classes on the quality of the selection of pixels is also discussed.

Batch effect confounding leads to strong bias in performance estimates obtained by cross-validation.

BACKGROUND: With the large amount of biological data that is currently publicly available, many investigators combine multiple data sets to increase the sample size and potentially also the power of their analyses. However, technical differences ("batch effects") as well as differences in sample composition between the data sets may significantly affect the ability to draw generalizable conclusions from such studies. FOCUS: The current study focuses on the construction of classifiers, and the use of cross-validation to estimate their performance. In particular, we investigate the impact of batch effects and differences in sample composition between batches on the accuracy of the classification performance estimate obtained via cross-validation. The focus on estimation bias is a main difference compared to previous studies, which have mostly focused on the predictive performance and how it relates to the presence of batch effects. DATA: We work on simulated data sets. To have realistic intensity distributions, we use real gene expression data as the basis for our simulation. Random samples from this expression matrix are selected and assigned to group 1 (e.g., 'control') or group 2 (e.g., 'treated'). We introduce batch effects and select some features to be differentially expressed between the two groups. We consider several scenarios for our study, most importantly different levels of confounding between groups and batch effects. METHODS: We focus on well-known classifiers: logistic regression, Support Vector Machines (SVM), k-nearest neighbors (kNN) and Random Forests (RF). Feature selection is performed with the Wilcoxon test or the lasso. Parameter tuning and feature selection, as well as the estimation of the prediction performance of each classifier, is performed within a nested cross-validation scheme. The estimated classification performance is then compared to what is obtained when applying the classifier to independent data.

Using graphical probability analysis (Bayes Nets) to evaluate a conditional DNA inclusion

This paper discusses the analysis of cases in which the inclusion or exclusion of a particular suspect, as a possible contributor to a DNA mixture, depends on the value of a variable (the number of contributors) that cannot be determined with certainty. It offers alternative ways to deal with such cases, including sensitivity analysis and object-oriented Bayesian networks, that separate uncertainty about the inclusion of the suspect from uncertainty about other variables. The paper presents a case study in which the value of DNA evidence varies radically depending on the number of contributors to a DNA mixture: if there are two contributors, the suspect is excluded; if there are three or more, the suspect is included; but the number of contributors cannot be determined with certainty. It shows how an object-oriented Bayesian network can accommodate and integrate varying perspectives on the unknown variable and how it can reduce the potential for bias by directing attention to relevant considerations and distinguishing different sources of uncertainty. It also discusses the challenge of presenting such evidence to lay audiences.

A Novel Volume-Age-KPS (VAK) Glioblastoma Classification Identifies a Prognostic Cognate microRNA-Gene Signature.

BACKGROUND: Several studies have established Glioblastoma Multiforme (GBM) prognostic and predictive models based on age and Karnofsky Performance Status (KPS), while very few studies evaluated the prognostic and predictive significance of preoperative MR-imaging. However, to date, there is no simple preoperative GBM classification that also correlates with a highly prognostic genomic signature. Thus, we present for the first time a biologically relevant, and clinically applicable tumor Volume, patient Age, and KPS (VAK) GBM classification that can easily and non-invasively be determined upon patient admission. METHODS: We quantitatively analyzed the volumes of 78 GBM patient MRIs present in The Cancer Imaging Archive (TCIA) corresponding to patients in The Cancer Genome Atlas (TCGA) with VAK annotation. The variables were then combined using a simple 3-point scoring system to form the VAK classification. A validation set (N = 64) from both the TCGA and Rembrandt databases was used to confirm the classification. Transcription factor and genomic correlations were performed using the gene pattern suite and Ingenuity Pathway Analysis. RESULTS: VAK-A and VAK-B classes showed significant median survival differences in discovery (P = 0.007) and validation sets (P = 0.008). VAK-A is significantly associated with P53 activation, while VAK-B shows significant P53 inhibition. Furthermore, a molecular gene signature comprised of a total of 25 genes and microRNAs was significantly associated with the classes and predicted survival in an independent validation set (P = 0.001). A favorable MGMT promoter methylation status resulted in a 10.5 months additional survival benefit for VAK-A compared to VAK-B patients. CONCLUSIONS: The non-invasively determined VAK classification with its implication of VAK-specific molecular regulatory networks, can serve as a very robust initial prognostic tool, clinical trial selection criteria, and important step toward the refinement of genomics-based personalized therapy for GBM patients.

Domain Adaptation in remote sensing: increasing the portability of land-cover classifiers

Among the types of remote sensing acquisitions, optical images are certainly one of the most widely relied upon data sources for Earth observation. They provide detailed measurements of the electromagnetic radiation reflected or emitted by each pixel in the scene. Through a process termed supervised land-cover classification, this allows to automatically yet accurately distinguish objects at the surface of our planet. In this respect, when producing a land-cover map of the surveyed area, the availability of training examples representative of each thematic class is crucial for the success of the classification procedure. However, in real applications, due to several constraints on the sample collection process, labeled pixels are usually scarce. When analyzing an image for which those key samples are unavailable, a viable solution consists in resorting to the ground truth data of other previously acquired images. This option is attractive but several factors such as atmospheric, ground and acquisition conditions can cause radiometric differences between the images, hindering therefore the transfer of knowledge from one image to another. The goal of this Thesis is to supply remote sensing image analysts with suitable processing techniques to ensure a robust portability of the classification models across different images. The ultimate purpose is to map the land-cover classes over large spatial and temporal extents with minimal ground information. To overcome, or simply quantify, the observed shifts in the statistical distribution of the spectra of the materials, we study four approaches issued from the field of machine learning. First, we propose a strategy to intelligently sample the image of interest to collect the labels only in correspondence of the most useful pixels. This iterative routine is based on a constant evaluation of the pertinence to the new image of the initial training data actually belonging to a different image. Second, an approach to reduce the radiometric differences among the images by projecting the respective pixels in a common new data space is presented. We analyze a kernel-based feature extraction framework suited for such problems, showing that, after this relative normalization, the cross-image generalization abilities of a classifier are highly increased. Third, we test a new data-driven measure of distance between probability distributions to assess the distortions caused by differences in the acquisition geometry affecting series of multi-angle images. Also, we gauge the portability of classification models through the sequences. In both exercises, the efficacy of classic physically- and statistically-based normalization methods is discussed. Finally, we explore a new family of approaches based on sparse representations of the samples to reciprocally convert the data space of two images. The projection function bridging the images allows a synthesis of new pixels with more similar characteristics ultimately facilitating the land-cover mapping across images.

The evolutionary host switches of Polychromophilus: a multi-gene phylogeny of the bat malaria genus suggests a second invasion of mammals by a haemosporidian parasite.

BACKGROUND: The majority of Haemosporida species infect birds or reptiles, but many important genera, including Plasmodium, infect mammals. Dipteran vectors shared by avian, reptilian and mammalian Haemosporida, suggest multiple invasions of Mammalia during haemosporidian evolution; yet, phylogenetic analyses have detected only a single invasion event. Until now, several important mammal-infecting genera have been absent in these analyses. This study focuses on the evolutionary origin of Polychromophilus, a unique malaria genus that only infects bats (Microchiroptera) and is transmitted by bat flies (Nycteribiidae). METHODS: Two species of Polychromophilus were obtained from wild bats caught in Switzerland. These were molecularly characterized using four genes (asl, clpc, coI, cytb) from the three different genomes (nucleus, apicoplast, mitochondrion). These data were then combined with data of 60 taxa of Haemosporida available in GenBank. Bayesian inference, maximum likelihood and a range of rooting methods were used to test specific hypotheses concerning the phylogenetic relationships between Polychromophilus and the other haemosporidian genera. RESULTS: The Polychromophilus melanipherus and Polychromophilus murinus samples show genetically distinct patterns and group according to species. The Bayesian tree topology suggests that the monophyletic clade of Polychromophilus falls within the avian/saurian clade of Plasmodium and directed hypothesis testing confirms the Plasmodium origin. CONCLUSION: Polychromophilus' ancestor was most likely a bird- or reptile-infecting Plasmodium before it switched to bats. The invasion of mammals as hosts has, therefore, not been a unique event in the evolutionary history of Haemosporida, despite the suspected costs of adapting to a new host. This was, moreover, accompanied by a switch in dipteran host.

Genetic caste determination in Pogonomyrmex harvester ants imposes costs during colony founding.

Some populations of Pogonomyrmex harvester ants comprise genetically differentiated pairs of interbreeding lineages. Queens mate with males of their own and of the alternate lineage and produce pure-lineage offspring which develop into queens and inter-lineage offspring which develop into workers. Here we tested whether such genetic caste determination is associated with costs in terms of the ability to optimally allocate resources to the production of queens and workers. During the stage of colony founding, when only workers are produced, queens laid a high proportion of pure-lineage eggs but the large majority of these eggs failed to develop. As a consequence, the number of offspring produced by incipient colonies decreased linearly with the proportion of pure-lineage eggs laid by queens. Moreover, queens of the lineage most commonly represented in a given mating flight produced more pure-lineage eggs, in line with the view that they mate randomly with the two types of males and indiscriminately use their sperm. Altogether these results predict frequency-dependent selection on pairs of lineages because queens of the more common lineage will produce more pure-lineage eggs and their colonies be less successful during the stage of colony founding, which may be an important force maintaining the coexistence of pairs of lineages within populations.

Advanced Kernel Methods For Remote Sensing Image Classification

Résumé Suite aux recentes avancées technologiques, les archives d'images digitales ont connu une croissance qualitative et quantitative sans précédent. Malgré les énormes possibilités qu'elles offrent, ces avancées posent de nouvelles questions quant au traitement des masses de données saisies. Cette question est à la base de cette Thèse: les problèmes de traitement d'information digitale à très haute résolution spatiale et/ou spectrale y sont considérés en recourant à des approches d'apprentissage statistique, les méthodes à noyau. Cette Thèse étudie des problèmes de classification d'images, c'est à dire de catégorisation de pixels en un nombre réduit de classes refletant les propriétés spectrales et contextuelles des objets qu'elles représentent. L'accent est mis sur l'efficience des algorithmes, ainsi que sur leur simplicité, de manière à augmenter leur potentiel d'implementation pour les utilisateurs. De plus, le défi de cette Thèse est de rester proche des problèmes concrets des utilisateurs d'images satellite sans pour autant perdre de vue l'intéret des méthodes proposées pour le milieu du machine learning dont elles sont issues. En ce sens, ce travail joue la carte de la transdisciplinarité en maintenant un lien fort entre les deux sciences dans tous les développements proposés. Quatre modèles sont proposés: le premier répond au problème de la haute dimensionalité et de la redondance des données par un modèle optimisant les performances en classification en s'adaptant aux particularités de l'image. Ceci est rendu possible par un système de ranking des variables (les bandes) qui est optimisé en même temps que le modèle de base: ce faisant, seules les variables importantes pour résoudre le problème sont utilisées par le classifieur. Le manque d'information étiquétée et l'incertitude quant à sa pertinence pour le problème sont à la source des deux modèles suivants, basés respectivement sur l'apprentissage actif et les méthodes semi-supervisées: le premier permet d'améliorer la qualité d'un ensemble d'entraînement par interaction directe entre l'utilisateur et la machine, alors que le deuxième utilise les pixels non étiquetés pour améliorer la description des données disponibles et la robustesse du modèle. Enfin, le dernier modèle proposé considère la question plus théorique de la structure entre les outputs: l'intègration de cette source d'information, jusqu'à présent jamais considérée en télédétection, ouvre des nouveaux défis de recherche. Advanced kernel methods for remote sensing image classification Devis Tuia Institut de Géomatique et d'Analyse du Risque September 2009 Abstract The technical developments in recent years have brought the quantity and quality of digital information to an unprecedented level, as enormous archives of satellite images are available to the users. However, even if these advances open more and more possibilities in the use of digital imagery, they also rise several problems of storage and treatment. The latter is considered in this Thesis: the processing of very high spatial and spectral resolution images is treated with approaches based on data-driven algorithms relying on kernel methods. In particular, the problem of image classification, i.e. the categorization of the image's pixels into a reduced number of classes reflecting spectral and contextual properties, is studied through the different models presented. The accent is put on algorithmic efficiency and the simplicity of the approaches proposed, to avoid too complex models that would not be used by users. The major challenge of the Thesis is to remain close to concrete remote sensing problems, without losing the methodological interest from the machine learning viewpoint: in this sense, this work aims at building a bridge between the machine learning and remote sensing communities and all the models proposed have been developed keeping in mind the need for such a synergy. Four models are proposed: first, an adaptive model learning the relevant image features has been proposed to solve the problem of high dimensionality and collinearity of the image features. This model provides automatically an accurate classifier and a ranking of the relevance of the single features. The scarcity and unreliability of labeled. information were the common root of the second and third models proposed: when confronted to such problems, the user can either construct the labeled set iteratively by direct interaction with the machine or use the unlabeled data to increase robustness and quality of the description of data. Both solutions have been explored resulting into two methodological contributions, based respectively on active learning and semisupervised learning. Finally, the more theoretical issue of structured outputs has been considered in the last model, which, by integrating outputs similarity into a model, opens new challenges and opportunities for remote sensing image processing.

Bayes factor for investigative assessment of selected handwriting features

This paper extends previous research [1] on the use of multivariate continuous data in comparative handwriting examinations, notably for gender classification. A database has been constructed by analyzing the contour shape of loop characters of type a and d by means of Fourier analysis, which allows characters to be described in a global way by a set of variables (e.g., Fourier descriptors). Sample handwritings were collected from right- and left-handed female and male writers. The results reported in this paper provide further arguments in support of the view that investigative settings in forensic science represent an area of application for which the Bayesian approach offers a logical framework. In particular, the Bayes factor is computed for settings that focus on inference of gender and handedness of the author of an incriminated handwritten text. An emphasis is placed on comparing the efficiency for investigative purposes of characters a and d.