Active Learning of Very-High Resolution Optical Imagery with SVM: Entropy vs Margin Sampling

An active learning method is proposed for the semi-automatic selection of training sets in remote sensing image classification. The method adds iteratively to the current training set the unlabeled pixels for which the prediction of an ensemble of classifiers based on bagged training sets show maximum entropy. This way, the algorithm selects the pixels that are the most uncertain and that will improve the model if added in the training set. The user is asked to label such pixels at each iteration. Experiments using support vector machines (SVM) on an 8 classes QuickBird image show the excellent performances of the methods, that equals accuracies of both a model trained with ten times more pixels and a model whose training set has been built using a state-of-the-art SVM specific active learning method

Serum uric acid and adiposity: deciphering causality using a bidirectional Mendelian randomization approach.

Although the relationship between serum uric acid (SUA) and adiposity is well established, the direction of the causality is still unclear in the presence of conflicting evidences. We used a bidirectional Mendelian randomization approach to explore the nature and direction of causality between SUA and adiposity in a population-based study of Caucasians aged 35 to 75 years. We used, as instrumental variables, rs6855911 within the SUA gene SLC2A9 in one direction, and combinations of SNPs within the adiposity genes FTO, MC4R and TMEM18 in the other direction. Adiposity markers included weight, body mass index, waist circumference and fat mass. We applied a two-stage least squares regression: a regression of SUA/adiposity markers on our instruments in the first stage and a regression of the response of interest on the fitted values from the first stage regression in the second stage. SUA explained by the SLC2A9 instrument was not associated to fat mass (regression coefficient [95% confidence interval]: 0.05 [-0.10, 0.19] for fat mass) contrasting with the ordinary least square estimate (0.37 [0.34, 0.40]). By contrast, fat mass explained by genetic variants of the FTO, MC4R and TMEM18 genes was positively and significantly associated to SUA (0.31 [0.01, 0.62]), similar to the ordinary least square estimate (0.27 [0.25, 0.29]). Results were similar for the other adiposity markers. Using a bidirectional Mendelian randomization approach in adult Caucasians, our findings suggest that elevated SUA is a consequence rather than a cause of adiposity.

Identification of pharmaceutical tablets by Raman spectroscopy and chemometrics

Raman spectroscopy has become an attractive tool for the analysis of pharmaceutical solid dosage forms. In the present study it is used to ensure the identity of tablets. The two main applications of this method are release of final products in quality control and detection of counterfeits. Twenty-five product families of tablets have been included in the spectral library and a non-linear classification method, the Support Vector Machines (SVMs), has been employed. Two calibrations have been developed in cascade: the first one identifies the product family while the second one specifies the formulation. A product family comprises different formulations that have the same active pharmaceutical ingredient (API) but in a different amount. Once the tablets have been classified by the SVM model, API peaks detection and correlation are applied in order to have a specific method for the identification and allow in the future to discriminate counterfeits from genuine products. This calibration strategy enables the identification of 25 product families without error and in the absence of prior information about the sample. Raman spectroscopy coupled with chemometrics is therefore a fast and accurate tool for the identification of pharmaceutical tablets.

Geographic distribution of phlebotomine sandfly species (Diptera: Psychodidae) in Central-West Brazil

This study updates the geographic distributions of phlebotomine species in Central-West Brazil and analyses the climatic factors associated with their occurrence. The data were obtained from the entomology services of the state departments of health in Central-West Brazil, scientific collections and a literature review of articles from 1962-2014. Ecological niche models were produced for sandfly species with more than 20 occurrences using the Maxent algorithm and eight climate variables. In all, 2,803 phlebotomine records for 127 species were analysed. Nyssomyia whitmani,Evandromyia lenti and Lutzomyia longipalpiswere the species with the greatest number of records and were present in all the biomes in Central-West Brazil. The models, which were produced for 34 species, indicated that the Cerrado areas in the central and western regions of Central-West Brazil were climatically more suitable to sandflies. The variables with the greatest influence on the models were the temperature in the coldest months and the temperature seasonality. The results show that phlebotomine species in Central-West Brazil have different geographical distribution patterns and that climate conditions in essentially the entire region favour the occurrence of at least one Leishmania vector species, highlighting the need to maintain or intensify vector control and surveillance strategies.

Decision fusion for the classification of hyperspectral data: Outcome of the 2008 GRS-S data fusion contest

The 2008 Data Fusion Contest organized by the IEEE Geoscience and Remote Sensing Data Fusion Technical Committee deals with the classification of high-resolution hyperspectral data from an urban area. Unlike in the previous issues of the contest, the goal was not only to identify the best algorithm but also to provide a collaborative effort: The decision fusion of the best individual algorithms was aiming at further improving the classification performances, and the best algorithms were ranked according to their relative contribution to the decision fusion. This paper presents the five awarded algorithms and the conclusions of the contest, stressing the importance of decision fusion, dimension reduction, and supervised classification methods, such as neural networks and support vector machines.

Inovatividade organizacional e seus antecedentes: um estudo aplicado às tecnologias para pecuária

Neste estudo, propõe-se um modelo para explicar a inovatividade dos pecuaristas de gado de corte sob a perspectiva organizacional. Segundo a teoria de difusão de inovações, a inovatividade organizacional é caracterizada como o grau em que uma organização inova relativamente mais cedo do que as demais. Para avaliar a inovatividade, quatro antecedentes foram considerados, sendo: as características percebidas da inovação compostas por vantagem relativa, compatibilidade, imagem, demonstração de resultado, visibilidade, experimentabilidade, voluntariedade e facilidade de uso; a participação dos pecuaristas em redes sociais, caracterizadas como redes de relacionamentos entre pares; as fontes de informação comercial, caracterizadas como informações obtidas por meio dos relacionamentos para reduzir os riscos; a psicografia organizacional, composta por direção, centralidade da decisão, abertura de comunicação e motivação para a conquista. Os quatro construtos possuem uma relação positiva com a inovatividade organizacional. Com amostragem não probabilística por conveniência, foram obtidos 205 questionários válidos. Na análise de componentes múltiplos, observou-se que o perfil dos respondentes se mostrou distinto quanto à inovatividade. Essa distinção motivou a geração de uma taxonomia com base no perfil de adoção de tecnologias com o objetivo de identificar as diferenças no comportamento inovativo, o que resultou em três grupos. Assim, três modelos foram analisados e comparados por meio da modelagem de equações estruturais, utilizando-se o método Partial Least Square (PLS). Os resultados mostraram que o grupo dos menos inovadores pauta suas decisões de adoção de novas tecnologias pelas redes sociais, pela compatibilidade da tecnologia com suas atividades organizacionais e pela imagem que ela tem perante os demais pecuaristas. Os intermediários têm uma psicografia organizacional voltada para a inovatividade, porém a adoção de novas tecnologias parece estar mais relacionada às imposições de mercado do que propriamente à percepção de suas características inovadoras. Os mais inovadores, como formadores de opinião, possuem uma inovatividade organizacional construída a partir de fontes de informação comerciais e avaliam o custo da tecnologia como um investimento positivo para o futuro de seu negócio.

Embedding Emotional Context in Recommender Systems

Emotions are crucial for user's decision making in recommendation processes. We first introduce ambient recommender systems, which arise from the analysis of new trends on the exploitation of the emotional context in the next generation of recommender systems. We then explain some results of these new trends in real-world applications through the smart prediction assistant (SPA) platform in an intelligent learning guide with more than three million users. While most approaches to recommending have focused on algorithm performance. SPA makes recommendations to users on the basis of emotional information acquired in an incremental way. This article provides a cross-disciplinary perspective to achieve this goal in such recommender systems through a SPA platform. The methodology applied in SPA is the result of a bunch of technology transfer projects for large real-world rccommender systems

Análise de fatores associados ao significado do trabalho

O trabalho tem sido visto não somente como forma de obter a renda, mas também como atividade que proporciona realização pessoal, status social e possibilidade de estabelecer e manter contatos interpessoais, entre outros. Nesta pesquisa, teve-se como objetivo investigar os fatores que influenciam e conferem sentido ao trabalho, como centralidade do trabalho, normas da sociedade e objetivos e resultados valorizados. Na centralidade do trabalho, procurou-se investigar o grau de importância do trabalho dentro do contexto das diversas áreas da vida das pessoas, como família, lazer, religião e vida comunitária. Em normas da sociedade, foram analisados os pontos mais significativos no tocante ao que a sociedade deveria proporcionar ao indivíduo, assim como o que o indivíduo deveria fazer em prol da sociedade. Nos objetivos e resultados valorizados, foi pesquisado o que as pessoas buscam com o trabalho. A partir da pesquisa na literatura, foi elaborado um modelo inicial que, não se mostrando satisfatório segundo critérios estatísticos, foi substituído por outro que apresentou significância estatística e boa aderência aos dados. O modelo escolhido foi o que melhor goodness-of-fit apresentou, quando se utilizou modelagem de equações estruturais pelo método partial least square. O estudo revelou que o significado do trabalho se reflete, na ordem, na centralidade do trabalho, nos objetivos e resultados valorizados e, por último, nas normas sociais.

O processo decisório em grupo: uma análise temporal-ambiental

Neste artigo, investiga-se a dinâmica do processo decisório conduzido por grupos de trabalho ao longo do tempo em ambientes com diferentes latitudes de ação (graus de liberdade para a atuação dos gestores distintos). O objetivo é verificar a influência do tempo e do ambiente nos processos decisórios em grupo. O tema é enfocado a partir de uma revisão teórica considerando três tópicos - o processo decisório conduzido por grupos, a influência do tempo nesses processos e a influência do ambiente nesses processos -, os quais dão origem às hipóteses a serem testadas. Na pesquisa de campo, de natureza quantitativa, utiliza-se o método survey e os dados foram coletados com 89 grupos da disciplina Jogos de Empresa, em um curso de graduação em Administração de Empresas. Para o tratamento dos dados, utilizou-se a modelagem por equações estruturais via partial least square para avaliação das relações entre os construtos. Como resultado, constatou-se influência temporal na associação entre qualidade do processo decisório e resultados organizacionais, reduzindo-se o efeito do perfil dos grupos. Já as relações interpessoais, independente do ambiente, influenciaram nos processos de planejamento e execução das decisões. Concluiu-se que diferentes relações entre perfil dos gestores, qualidade do processo e resultados são observadas pela incorporação simultânea das dimensões temporal e ambiental como contingências na análise do processo decisório em grupo.

The differentiation of fibre- and drug type Cannabis seedlings by gas chromatography/mass spectrometry and chemometric tools

Cannabis cultivation in order to produce drugs is forbidden in Switzerland. Thus, law enforcement authorities regularly ask forensic laboratories to determinate cannabis plant's chemotype from seized material in order to ascertain that the plantation is legal or not. As required by the EU official analysis protocol the THC rate of cannabis is measured from the flowers at maturity. When laboratories are confronted to seedlings, they have to lead the plant to maturity, meaning a time consuming and costly procedure. This study investigated the discrimination of fibre type from drug type Cannabis seedlings by analysing the compounds found in their leaves and using chemometrics tools. 11 legal varieties allowed by the Swiss Federal Office for Agriculture and 13 illegal ones were greenhouse grown and analysed using a gas chromatograph interfaced with a mass spectrometer. Compounds that show high discrimination capabilities in the seedlings have been identified and a support vector machines (SVMs) analysis was used to classify the cannabis samples. The overall set of samples shows a classification rate above 99% with false positive rates less than 2%. This model allows then discrimination between fibre and drug type Cannabis at an early stage of growth. Therefore it is not necessary to wait plants' maturity to quantify their amount of THC in order to determine their chemotype. This procedure could be used for the control of legal (fibre type) and illegal (drug type) Cannabis production.

Monitoring of posture allocations and activities by a shoe-based wearable sensor.

Monitoring of posture allocations and activities enables accurate estimation of energy expenditure and may aid in obesity prevention and treatment. At present, accurate devices rely on multiple sensors distributed on the body and thus may be too obtrusive for everyday use. This paper presents a novel wearable sensor, which is capable of very accurate recognition of common postures and activities. The patterns of heel acceleration and plantar pressure uniquely characterize postures and typical activities while requiring minimal preprocessing and no feature extraction. The shoe sensor was tested in nine adults performing sitting and standing postures and while walking, running, stair ascent/descent and cycling. Support vector machines (SVMs) were used for classification. A fourfold validation of a six-class subject-independent group model showed 95.2% average accuracy of posture/activity classification on full sensor set and over 98% on optimized sensor set. Using a combination of acceleration/pressure also enabled a pronounced reduction of the sampling frequency (25 to 1 Hz) without significant loss of accuracy (98% versus 93%). Subjects had shoe sizes (US) M9.5-11 and W7-9 and body mass index from 18.1 to 39.4 kg/m2 and thus suggesting that the device can be used by individuals with varying anthropometric characteristics.

Efficacy and Safety of Canakinumab Vs Triamcinolone Acetonide in Patients with Gouty Arthritis Unable to Use Nonsteroidal Anti-Inflammatory Drugs and Colchicine, and On Stable Urate Lowering Therapy (ULT) or Unable to Use ULT

Background/Purpose: The primary treatment goals for gouty arthritis (GA) are rapid relief of pain and inflammation during acute attacks, and long-term hyperuricemia management. A post-hoc analysis of 2 pivotal trials was performed to assess efficacy and safety of canakinumab (CAN), a fully human monoclonal anti-IL-1_ antibody, vs triamcinolone acetonide (TA) in GA patients unable to use NSAIDs and colchicine, and who were on stable urate lowering therapy (ULT) or unable to use ULT. Methods: In these 12-week, randomized, multicenter, double-blind, double-dummy, active-controlled studies (_-RELIEVED and _-RELIEVED II), patients had to have frequent attacks (_3 attacks in previous year) meeting preliminary GA ACR 1977 criteria, and were unresponsive, intolerant, or contraindicated to NSAIDs and/or colchicine, and if on ULT, ULT was stable. Patients were randomized during an acute attack to single dose CAN 150 mg s.c. or TA 40 mg i.m. and were redosed "on demand" for each new attack. Patients completing the core studies were enrolled into blinded 12-week extension studies to further investigate on-demand use of CAN vs TA for new attacks. The subpopulation selected for this post-hoc analysis was (a) unable to use NSAIDs and colchicine due to contraindication, intolerance or lack of efficacy for these drugs, and (b) currently on ULT, or contraindication or previous failure of ULT, as determined by investigators. Subpopulation comprised 101 patients (51 CAN; 50 TA) out of 454 total. Results: Several co-morbidities, including hypertension (56%), obesity (56%), diabetes (18%), and ischemic heart disease (13%) were reported in 90% of this subpopulation. Pain intensity (VAS 100 mm scale) was comparable between CAN and TA treatment groups at baseline (least-square [LS] mean 74.6 and 74.4 mm, respectively). A significantly lower pain score was reported with CAN vs TA at 72 hours post dose (1st co-primary endpoint on baseline flare; LS mean, 23.5 vs 33.6 mm; difference _10.2 mm; 95% CI, _19.9, _0.4; P_0.0208 [1-sided]). CAN significantly reduced risk for their first new attacks by 61% vs TA (HR 0.39; 95% CI, 0.17-0.91, P_0.0151 [1-sided]) for the first 12 weeks (2nd co-primary endpoint), and by 61% vs TA (HR 0.39; 95% CI, 0.19-0.79, P_0.0047 [1-sided]) over 24 weeks. Serum urate levels increased for CAN vs TA with mean change from baseline reaching a maximum of _0.7 _ 2.0 vs _0.1 _ 1.8 mg/dL at 8 weeks, and _0.3 _ 2.0 vs _0.2 _ 1.4 mg/dL at end of study (all had GA attack at baseline). Adverse Events (AEs) were reported in 33 (66%) CAN and 24 (47.1%) TA patients. Infections and infestations were the most common AEs, reported in 10 (20%) and 5 (10%) patients treated with CAN and TA respectively. Incidence of SAEs was comparable between CAN (gastritis, gastroenteritis, chronic renal failure) and TA (aortic valve incompetence, cardiomyopathy, aortic stenosis, diarrohea, nausea, vomiting, bicuspid aortic valve) groups (2 [4.0%] vs 2 [3.9%]). Conclusion: CAN provided superior pain relief and reduced risk of new attack in highly-comorbid GA patients unable to use NSAIDs and colchicine, and who were currently on stable ULT or unable to use ULT. The safety profile in this post-hoc subpopulation was consistent with the overall _-RELIEVED and _-RELIEVED II population.

Aplicació de predicció del risc d'una cartera

L'objectiu principal del projecte és la creació d'una aplicació per a telèfons intel·ligents que intenti predir la volatilitat no atribuïble al mercat per tal de permetre a l'usuari crear portfolios òptims utilitzant tècniques d'intel·ligència artificial com són les Support Vector Machines (SVM). Una vegada s'hagi predit aquesta volatilitat es crearà un portfolio òptim amb el pes adequat de cada un dels valors, per tal d'obtenir una inversió amb el mínim risc possible.

Statistical learning theory for geospatial data. Case study: Aral sea

In recent years there has been an explosive growth in the development of adaptive and data driven methods. One of the efficient and data-driven approaches is based on statistical learning theory (Vapnik 1998). The theory is based on Structural Risk Minimisation (SRM) principle and has a solid statistical background. When applying SRM we are trying not only to reduce training error ? to fit the available data with a model, but also to reduce the complexity of the model and to reduce generalisation error. Many nonlinear learning procedures recently developed in neural networks and statistics can be understood and interpreted in terms of the structural risk minimisation inductive principle. A recent methodology based on SRM is called Support Vector Machines (SVM). At present SLT is still under intensive development and SVM find new areas of application (www.kernel-machines.org). SVM develop robust and non linear data models with excellent generalisation abilities that is very important both for monitoring and forecasting. SVM are extremely good when input space is high dimensional and training data set i not big enough to develop corresponding nonlinear model. Moreover, SVM use only support vectors to derive decision boundaries. It opens a way to sampling optimization, estimation of noise in data, quantification of data redundancy etc. Presentation of SVM for spatially distributed data is given in (Kanevski and Maignan 2004).

A behavioral ecology of shermen: hidden stories from trajectory data in the Northern Humboldt Current System

This work proposes an original contribution to the understanding of shermen spatial behavior, based on the behavioral ecology and movement ecology paradigms. Through the analysis of Vessel Monitoring System (VMS) data, we characterized the spatial behavior of Peruvian anchovy shermen at di erent scales: (1) the behavioral modes within shing trips (i.e., searching, shing and cruising); (2) the behavioral patterns among shing trips; (3) the behavioral patterns by shing season conditioned by ecosystem scenarios; and (4) the computation of maps of anchovy presence proxy from the spatial patterns of behavioral mode positions. At the rst scale considered, we compared several Markovian (hidden Markov and semi-Markov models) and discriminative models (random forests, support vector machines and arti cial neural networks) for inferring the behavioral modes associated with VMS tracks. The models were trained under a supervised setting and validated using tracks for which behavioral modes were known (from on-board observers records). Hidden semi-Markov models performed better, and were retained for inferring the behavioral modes on the entire VMS dataset. At the second scale considered, each shing trip was characterized by several features, including the time spent within each behavioral mode. Using a clustering analysis, shing trip patterns were classi ed into groups associated to management zones, eet segments and skippers' personalities. At the third scale considered, we analyzed how ecological conditions shaped shermen behavior. By means of co-inertia analyses, we found signi cant associations between shermen, anchovy and environmental spatial dynamics, and shermen behavioral responses were characterized according to contrasted environmental scenarios. At the fourth scale considered, we investigated whether the spatial behavior of shermen re ected to some extent the spatial distribution of anchovy. Finally, this work provides a wider view of shermen behavior: shermen are not only economic agents, but they are also foragers, constrained by ecosystem variability. To conclude, we discuss how these ndings may be of importance for sheries management, collective behavior analyses and end-to-end models.