A Survey of Active Learning Algorithms for Supervised Remote Sensing Image Classification

Defining an efficient training set is one of the most delicate phases for the success of remote sensing image classification routines. The complexity of the problem, the limited temporal and financial resources, as well as the high intraclass variance can make an algorithm fail if it is trained with a suboptimal dataset. Active learning aims at building efficient training sets by iteratively improving the model performance through sampling. A user-defined heuristic ranks the unlabeled pixels according to a function of the uncertainty of their class membership and then the user is asked to provide labels for the most uncertain pixels. This paper reviews and tests the main families of active learning algorithms: committee, large margin, and posterior probability-based. For each of them, the most recent advances in the remote sensing community are discussed and some heuristics are detailed and tested. Several challenging remote sensing scenarios are considered, including very high spatial resolution and hyperspectral image classification. Finally, guidelines for choosing the good architecture are provided for new and/or unexperienced user.

Bayesian classification criterion for forensic multivariate data

This study presents a classification criteria for two-class Cannabis seedlings. As the cultivation of drug type cannabis is forbidden in Switzerland, law enforcement authorities regularly ask laboratories to determine cannabis plant's chemotype from seized material in order to ascertain that the plantation is legal or not. In this study, the classification analysis is based on data obtained from the relative proportion of three major leaf compounds measured by gas-chromatography interfaced with mass spectrometry (GC-MS). The aim is to discriminate between drug type (illegal) and fiber type (legal) cannabis at an early stage of the growth. A Bayesian procedure is proposed: a Bayes factor is computed and classification is performed on the basis of the decision maker specifications (i.e. prior probability distributions on cannabis type and consequences of classification measured by losses). Classification rates are computed with two statistical models and results are compared. Sensitivity analysis is then performed to analyze the robustness of classification criteria.

Multi-stage oligopoly models with nested logit demand structures: A simplifying approach

Solving multi-stage oligopoly models by backward induction can easily become a com- plex task when rms are multi-product and demands are derived from a nested logit frame- work. This paper shows that under the assumption that within-segment rm shares are equal across segments, the analytical expression for equilibrium pro ts can be substantially simpli ed. The size of the error arising when this condition does not hold perfectly is also computed. Through numerical examples, it is shown that the error is rather small in general. Therefore, using this assumption allows to gain analytical tractability in a class of models that has been used to approach relevant policy questions, such as for example rm entry in an industry or the relation between competition and location. The simplifying approach proposed in this paper is aimed at helping improving these type of models for reaching more accurate recommendations.

Classification of human astrocytic gliomas on the basis of gene expression: a correlated group of genes with angiogenic activity emerges as a strong predictor of subtypes.

The development of targeted treatment strategies adapted to individual patients requires identification of the different tumor classes according to their biology and prognosis. We focus here on the molecular aspects underlying these differences, in terms of sets of genes that control pathogenesis of the different subtypes of astrocytic glioma. By performing cDNA-array analysis of 53 patient biopsies, comprising low-grade astrocytoma, secondary glioblastoma (respective recurrent high-grade tumors), and newly diagnosed primary glioblastoma, we demonstrate that human gliomas can be differentiated according to their gene expression. We found that low-grade astrocytoma have the most specific and similar expression profiles, whereas primary glioblastoma exhibit much larger variation between tumors. Secondary glioblastoma display features of both other groups. We identified several sets of genes with relatively highly correlated expression within groups that: (a). can be associated with specific biological functions; and (b). effectively differentiate tumor class. One prominent gene cluster discriminating primary versus nonprimary glioblastoma comprises mostly genes involved in angiogenesis, including VEGF fms-related tyrosine kinase 1 but also IGFBP2, that has not yet been directly linked to angiogenesis. In situ hybridization demonstrating coexpression of IGFBP2 and VEGF in pseudopalisading cells surrounding tumor necrosis provided further evidence for a possible involvement of IGFBP2 in angiogenesis. The separating groups of genes were found by the unsupervised coupled two-way clustering method, and their classification power was validated by a supervised construction of a nearly perfect glioma classifier.

Micro-Structural Brain Alterations in Aviremic HIV+ Patients with Minor Neurocognitive Disorders: A Multi-Contrast Study at High Field.

OBJECTIVE: Mild neurocognitive disorders (MND) affect a subset of HIV+ patients under effective combination antiretroviral therapy (cART). In this study, we used an innovative multi-contrast magnetic resonance imaging (MRI) approach at high-field to assess the presence of micro-structural brain alterations in MND+ patients. METHODS: We enrolled 17 MND+ and 19 MND- patients with undetectable HIV-1 RNA and 19 healthy controls (HC). MRI acquisitions at 3T included: MP2RAGE for T1 relaxation times, Magnetization Transfer (MT), T2* and Susceptibility Weighted Imaging (SWI) to probe micro-structural integrity and iron deposition in the brain. Statistical analysis used permutation-based tests and correction for family-wise error rate. Multiple regression analysis was performed between MRI data and (i) neuropsychological results (ii) HIV infection characteristics. A linear discriminant analysis (LDA) based on MRI data was performed between MND+ and MND- patients and cross-validated with a leave-one-out test. RESULTS: Our data revealed loss of structural integrity and micro-oedema in MND+ compared to HC in the global white and cortical gray matter, as well as in the thalamus and basal ganglia. Multiple regression analysis showed a significant influence of sub-cortical nuclei alterations on the executive index of MND+ patients (p = 0.04 he and R(2) = 95.2). The LDA distinguished MND+ and MND- patients with a classification quality of 73% after cross-validation. CONCLUSION: Our study shows micro-structural brain tissue alterations in MND+ patients under effective therapy and suggests that multi-contrast MRI at high field is a powerful approach to discriminate between HIV+ patients on cART with and without mild neurocognitive deficits.

Classification of sags according to their origin based on the waveform similarity

A statistical method for classification of sags their origin downstream or upstream from the recording point is proposed in this work. The goal is to obtain a statistical model using the sag waveforms useful to characterise one type of sags and to discriminate them from the other type. This model is built on the basis of multi-way principal component analysis an later used to project the available registers in a new space with lower dimension. Thus, a case base of diagnosed sags is built in the projection space. Finally classification is done by comparing new sags against the existing in the case base. Similarity is defined in the projection space using a combination of distances to recover the nearest neighbours to the new sag. Finally the method assigns the origin of the new sag according to the origin of their neighbours

Social meets molecular: Combining phylogenetic and latent class analyses to understand HIV-1 transmission in Switzerland.

Switzerland has a complex human immunodeficiency virus (HIV) epidemic involving several populations. We examined transmission of HIV type 1 (HIV-1) in a national cohort study. Latent class analysis was used to identify socioeconomic and behavioral groups among 6,027 patients enrolled in the Swiss HIV Cohort Study between 2000 and 2011. Phylogenetic analysis of sequence data, available for 4,013 patients, was used to identify transmission clusters. Concordance between sociobehavioral groups and transmission clusters was assessed in correlation and multiple correspondence analyses. A total of 2,696 patients were infected with subtype B, 203 with subtype C, 196 with subtype A, and 733 with recombinant subtypes (mainly CRF02_AG and CRF01_AE). Latent class analysis identified 8 patient groups. Most transmission clusters of subtype B were shared between groups of gay men (groups 1-3) or between the heterosexual groups "heterosexual people of lower socioeconomic position" (group 4) and "injection drug users" (group 8). Clusters linking homosexual and heterosexual groups were associated with "older heterosexual and gay people on welfare" (group 5). "Migrant women in heterosexual partnerships" (group 6) and "heterosexual migrants on welfare" (group 7) shared non-B clusters with groups 4 and 5. Combining approaches from social and molecular epidemiology can provide insights into HIV-1 transmission and inform the design of prevention strategies.

Evolutionary patterns of MHC class II B in owls and their implications for the understanding of avian MHC evolution

Owing to its special mode of evolution and central role in the adaptive immune system, the major histocompatibility complex (MHC) has become the focus of diverse disciplines such as immunology, evolutionary ecology, and molecular evolution. MHC evolution has been studied extensively in diverse vertebrate lineages over the last few decades, and it has been suggested that birds differ from the established mammalian norm. Mammalian MHC genes evolve independently, and duplication history (i.e., orthology) can usually be traced back within lineages. In birds, this has been observed in only 3 pairs of closely related species. Here we report strong evidence for the persistence of orthology of MHC genes throughout an entire avian order. Phylogenetic reconstructions of MHC class II B genes in 14 species of owls trace back orthology over tens of thousands of years in exon 3. Moreover, exon 2 sequences from several species show closer relationships than sequences within species, resembling transspecies evolution typically observed in mammals. Thus, although previous studies suggested that long-term evolutionary dynamics of the avian MHC was characterized by high rates of concerted evolution, resulting in rapid masking of orthology, our results question the generality of this conclusion. The owl MHC thus opens new perspectives for a more comprehensive understanding of avian MHC evolution.

Multi-scale label interaction to improve object detection and segmentation

The project aims at advancing the state of the art in the use of context information for classification of image and video data. The use of context in the classification of images has been showed of great importance to improve the performance of actual object recognition systems. In our project we proposed the concept of Multi-scale Feature Labels as a general and compact method to exploit the local and global context. The feature extraction from the discriminative probability or classification confidence label field is of great novelty. Moreover the use of a multi-scale representation of the feature labels lead to a compact and efficient description of the context. The goal of the project has been also to provide a general-purpose method and prove its suitability in different image/video analysis problem. The two-year project generated 5 journal publications (plus 2 under submission), 10 conference publications (plus 2 under submission) and one patent (plus 1 pending). Of these publications, a relevant number make use of the main result of this project to improve the results in detection and/or segmentation of objects.

Automatic Lexical Semantic Classification of Nouns

The work we present here addresses cue-based noun classification in English and Spanish. Its main objective is to automatically acquire lexical semantic information by classifying nouns into previously known noun lexical classes. This is achieved by using particular aspects of linguistic contexts as cues that identify a specific lexical class. Here we concentrate on the task of identifying such cues and the theoretical background that allows for an assessment of the complexity of the task. The results show that, despite of the a-priori complexity of the task, cue-based classification is a useful tool in the automatic acquisition of lexical semantic classes.

An Automatic Approach for Learning and Tuning Gaussian Interval Type-2 Fuzzy Membership Functions Applied to Lung CAD Classification System

The potential of type-2 fuzzy sets for managing high levels of uncertainty in the subjective knowledge of experts or of numerical information has focused on control and pattern classification systems in recent years. One of the main challenges in designing a type-2 fuzzy logic system is how to estimate the parameters of type-2 fuzzy membership function (T2MF) and the Footprint of Uncertainty (FOU) from imperfect and noisy datasets. This paper presents an automatic approach for learning and tuning Gaussian interval type-2 membership functions (IT2MFs) with application to multi-dimensional pattern classification problems. T2MFs and their FOUs are tuned according to the uncertainties in the training dataset by a combination of genetic algorithm (GA) and crossvalidation techniques. In our GA-based approach, the structure of the chromosome has fewer genes than other GA methods and chromosome initialization is more precise. The proposed approach addresses the application of the interval type-2 fuzzy logic system (IT2FLS) for the problem of nodule classification in a lung Computer Aided Detection (CAD) system. The designed IT2FLS is compared with its type-1 fuzzy logic system (T1FLS) counterpart. The results demonstrate that the IT2FLS outperforms the T1FLS by more than 30% in terms of classification accuracy.

Non-monophyly of the woody bamboos (Bambuseae; Poaceae): a multi-gene region phylogenetic analysis of Bambusoideae s.s.

The taxonomy of Bambusoideae is in a state of flux and phylogenetic studies are required to help resolve systematic issues. Over 60 taxa, representing all subtribes of Bambuseae and related non-bambusoid grasses were sampled. A combined analysis of five plastid DNA regions, trnL intron, trnL-F intergenic spacer, atpB-rbcL intergenic spacer, rps16 intron, and matK, was used to study the phylogenetic relationships among the bamboos in general and the woody bamboos in particular. Within the BEP clade (Bambusoideae s.s., Ehrhartoideae, Pooideae), Pooideae were resolved as sister to Bambusoideae s.s. Tribe Bambuseae, the woody bamboos, as currently recognized were not monophyletic because Olyreae, the herbaceous bamboos, were sister to tropical Bambuseae. Temperate Bambuseae were sister to the group consisting of tropical Bambuseae and Olyreae. Thus, the temperate Bambuseae would be better treated as their own tribe Arundinarieae than as a subgroup of Bambuseae. Within the tropical Bambuseae, neotropical Bambuseae were sister to the palaeotropical and Austral Bambuseae. In addition, Melocanninae were found to be sister to the remaining palaeotropical and Austral Bambuseae. We discuss phylogenetic and morphological patterns of diversification and interpret them in a biogeographic context.

A data-dependent skeleton estimate and a scale-sensitive dimension for classification

The classical binary classification problem is investigatedwhen it is known in advance that the posterior probability function(or regression function) belongs to some class of functions. We introduceand analyze a method which effectively exploits this knowledge. The methodis based on minimizing the empirical risk over a carefully selected``skeleton'' of the class of regression functions. The skeleton is acovering of the class based on a data--dependent metric, especiallyfitted for classification. A new scale--sensitive dimension isintroduced which is more useful for the studied classification problemthan other, previously defined, dimension measures. This fact isdemonstrated by performance bounds for the skeleton estimate in termsof the new dimension.

AWSum-Combining Classification with Knowledge Aquisition

Many classifiers achieve high levels of accuracy but have limited applicability in real world situations because they do not lead to a greater understanding or insight into the^way features influence the classification. In areas such as health informatics a classifier that clearly identifies the influences on classification can be used to direct research and formulate interventions. This research investigates the practical applications of Automated Weighted Sum, (AWSum), a classifier that provides accuracy comparable to other techniques whilst providing insight into the data. This is achieved by calculating a weight for each feature value that represents its influence on the class value. The merits of this approach in classification and insight are evaluated on a Cystic Fibrosis and Diabetes datasets with positive results.

Mutational analysis of class A and class B penicillin-binding proteins in Streptococcus gordonii.

High-molecular-weight (HMW) penicillin-binding proteins (PBPs) are divided into class A and class B PBPs, which are bifunctional transpeptidases/transglycosylases and monofunctional transpeptidases, respectively. We determined the sequences for the HMW PBP genes of Streptococcus gordonii, a gingivo-dental commensal related to Streptococcus pneumoniae. Five HMW PBPs were identified, including three class A (PBPs 1A, 1B, and 2A) and two class B (PBPs 2B and 2X) PBPs, by homology with those of S. pneumoniae and by radiolabeling with [3H]penicillin. Single and double deletions of each of them were achieved by allelic replacement. All could be deleted, except for PBP 2X, which was essential. Morphological alterations occurred after deletion of PBP 1A (lozenge shape), PBP 2A (separation defect and chaining), and PBP 2B (aberrant septation and premature lysis) but not PBP 1B. The muropeptide cross-link patterns remained similar in all strains, indicating that cross-linkage for one missing PBP could be replaced by others. However, PBP 1A mutants presented shorter glycan chains (by 30%) and a relative decrease (25%) in one monomer stem peptide. Growth rate and viability under aeration, hyperosmolarity, and penicillin exposure were affected primarily in PBP 2B-deleted mutants. In contrast, chain-forming PBP 2A-deleted mutants withstood better aeration, probably because they formed clusters that impaired oxygen diffusion. Double deletion could be generated with any PBP combination and resulted in more-altered mutants. Thus, single deletion of four of the five HMW genes had a detectable effect on the bacterial morphology and/or physiology, and only PBP 1B seemed redundant a priori.