Hand gesture recognition system based in computer vision and machine learning

"Lecture notes in computational vision and biomechanics series, ISSN 2212-9391, vol. 19"

Heliconia acuminata reproductive success is independent of local floral density

Reproductive plants in tropical forests are patchily distributed, with some in large aggregations of reproductive consepecifics while others are relatively isolated. This variation in floral density is hypothesized to have a major effect on plant reproductive success, since individuals in higher density neighborhoods can attract more or higher quality pollinators. We experimentally tested this hypothesis with populations of the understory herb Heliconia acuminata in central Amazonia. We created replicated plots in which reproductive plant density spanned the range of naturally occurring floral neighborhood size, then measured three surrogates of plant fitness in focal plants in each array. There was no significant difference between any of the three floral neighborhood treatments in total seed production, fruit set, or the number of seeds produced per fruit. Pollinator visitation rates to plants in all treatments were extremely low, with many plants not visited at all during the observation period. This could be because H. acuminata's hummingbird pollinators are unable to find the widely scattered reproductive plants, however this hypothesis appears unlikely. Instead, natural flowering plant densities may simply be below the threshold value at which neighborhood effects become important, even in "high-density" aggregations. Nutrient limitation, selective fruit abortion, and reproduction via male rather than female function may also be playing a role. We argue the absence of neighborhood effects may be a general phenomenon in central Amazonian forests, though additional experiments with other plant-pollinator systems are needed to determine the extent to which this hypothesis is supported.

Discrimination of Brazilian propolis according to the seasoning using chemometrics and machine learning based on UV-Vis scanning data

Propolis is a chemically complex biomass produced by honeybees (Apis mellifera) from plant resins added of salivary enzymes, beeswax, and pollen. The biological activities described for propolis were also identified for donor plants resin, but a big challenge for the standardization of the chemical composition and biological effects of propolis remains on a better understanding of the influence of seasonality on the chemical constituents of that raw material. Since propolis quality depends, among other variables, on the local flora which is strongly influenced by (a)biotic factors over the seasons, to unravel the harvest season effect on the propolis chemical profile is an issue of recognized importance. For that, fast, cheap, and robust analytical techniques seem to be the best choice for large scale quality control processes in the most demanding markets, e.g., human health applications. For that, UV-Visible (UV-Vis) scanning spectrophotometry of hydroalcoholic extracts (HE) of seventy-three propolis samples, collected over the seasons in 2014 (summer, spring, autumn, and winter) and 2015 (summer and autumn) in Southern Brazil was adopted. Further machine learning and chemometrics techniques were applied to the UV-Vis dataset aiming to gain insights as to the seasonality effect on the claimed chemical heterogeneity of propolis samples determined by changes in the flora of the geographic region under study. Descriptive and classification models were built following a chemometric approach, i.e. principal component analysis (PCA) and hierarchical clustering analysis (HCA) supported by scripts written in the R language. The UV-Vis profiles associated with chemometric analysis allowed identifying a typical pattern in propolis samples collected in the summer. Importantly, the discrimination based on PCA could be improved by using the dataset of the fingerprint region of phenolic compounds ( = 280-400m), suggesting that besides the biological activities of those secondary metabolites, they also play a relevant role for the discrimination and classification of that complex matrix through bioinformatics tools. Finally, a series of machine learning approaches, e.g., partial least square-discriminant analysis (PLS-DA), k-Nearest Neighbors (kNN), and Decision Trees showed to be complementary to PCA and HCA, allowing to obtain relevant information as to the sample discrimination.

Promoting independent living and recreation in life through ambient assisted living technology

The increase in life expectancy with a decrease in birth rates is contributing to the ageing of the European population. This phenomenon, coupled with greater awareness of the quality of life, the need to have cost-efficient assistive care, the intention of people to live independently in their homes, and the technological developments in recent decades, have contributed to the emergence of the concept of ambient assisted living (AAL). AAL solutions aim to provide healthy and safe ageing to users through promoting independence in performing daily activities and interacting with technology, taking into consideration the deterioration of the users’ capabilities and the reduced costs of the solutions. In this chapter, AAL developments of monitoring activities of daily living (ADLs) and participation in a virtual community with the selected stakeholders are introduced, their roadmap with the expected technological developments are described, and the expected impact of these solutions on the end users of the developed solutions are discussed. This enables a real user guidance structure that represents the different needs and limitations of each user, presenting a highly structured project based on personas and possible solutions for them. The AAL4ALL Ambient Assisted Living for All (ALL4ALL) project is considered here as a case study to analyze and illustrate the ALL concepts discussed in this chapter.

Metabolic profiling and classification of propolis samples from Southern Brazil: an NMR-based platform coupled with machine learning

The chemical composition of propolis is affected by environmental factors and harvest season, making it difficult to standardize its extracts for medicinal usage. By detecting a typical chemical profile associated with propolis from a specific production region or season, certain types of propolis may be used to obtain a specific pharmacological activity. In this study, propolis from three agroecological regions (plain, plateau, and highlands) from southern Brazil, collected over the four seasons of 2010, were investigated through a novel NMR-based metabolomics data analysis workflow. Chemometrics and machine learning algorithms (PLS-DA and RF), including methods to estimate variable importance in classification, were used in this study. The machine learning and feature selection methods permitted construction of models for propolis sample classification with high accuracy (>75%, reaching 90% in the best case), better discriminating samples regarding their collection seasons comparatively to the harvest regions. PLS-DA and RF allowed the identification of biomarkers for sample discrimination, expanding the set of discriminating features and adding relevant information for the identification of the class-determining metabolites. The NMR-based metabolomics analytical platform, coupled to bioinformatic tools, allowed characterization and classification of Brazilian propolis samples regarding the metabolite signature of important compounds, i.e., chemical fingerprint, harvest seasons, and production regions.

Hand gesture recognition system based in computer vision and machine learning: Applications on human-machine interaction

Tese de Doutoramento em Engenharia de Eletrónica e de Computadores

Cathepsin D protects colorectal cancer cells from acetate-induced apoptosis through autophagy-independent degradation of damaged mitochondria

Acetate is a short-chain fatty acid secreted by Propionibacteria from the human intestine, known to induce mitochondrial apoptotic death in colorectal cancer (CRC) cells. We previously established that acetate also induces lysosome membrane permeabilization in CRC cells, associated with release of the lysosomal protease cathepsin D (CatD), which has a well-established role in the mitochondrial apoptotic cascade. Unexpectedly, we showed that CatD has an antiapoptotic role in this process, as pepstatin A (a CatD inhibitor) increased acetate-induced apoptosis. These results mimicked our previous data in the yeast system showing that acetic acid activates a mitochondria-dependent apoptosis process associated with vacuolar membrane permeabilization and release of the vacuolar protease Pep4p, ortholog of mammalian CatD. Indeed, this protease was required for cell survival in a manner dependent on its catalytic activity and for efficient mitochondrial degradation independently of autophagy. In this study, we therefore assessed the role of CatD in acetate-induced mitochondrial alterations. We found that, similar to acetic acid in yeast, acetate-induced apoptosis is not associated with autophagy induction in CRC cells. Moreover, inhibition of CatD with small interfering RNA or pepstatin A enhanced apoptosis associated with higher mitochondrial dysfunction and increased mitochondrial mass. This effect seems to be specific, as inhibition of CatB and CatL with E-64d had no effect, nor were these proteases significantly released to the cytosol during acetate-induced apoptosis. Using yeast cells, we further show that the role of Pep4p in mitochondrial degradation depends on its protease activity and is complemented by CatD, indicating that this mechanism is conserved. In summary, the clues provided by the yeast model unveiled a novel CatD function in the degradation of damaged mitochondria when autophagy is impaired, which protects CRC cells from acetate-induced apoptosis. CatD inhibitors could therefore enhance acetate-mediated cancer cell death, presenting a novel strategy for prevention or therapy of CRC.

Galanin-mediated behavioural hyperalgesia from the dorsomedial nucleus of the hypothalamus involves two independent descending pronociceptive pathways

Activation of the dorsomedial nucleus of the hypothalamus (DMH) by galanin (GAL) induces behavioural hyperalgesia. Since DMH neurones do not project directly to the spinal cord, we hypothesized that the medullary dorsal reticular nucleus (DRt), a pronociceptive region projecting to the spinal dorsal horn (SDH) and/or the serotoninergic raphe-spinal pathway acting on the spinal 5-HT3 receptor (5HT3R) could relay descending nociceptive facilitation induced by GAL in the DMH. Heat-evoked paw-withdrawal latency (PWL) and activity of SDH neurones were assessed in monoarthritic (ARTH) and control (SHAM) animals after pharmacological manipulations of the DMH, DRt and spinal cord. The results showed that GAL in the DMH and glutamate in the DRt lead to behavioural hyperalgesia in both SHAM and ARTH animals, which is accompanied particularly by an increase in heat-evoked responses of wide-dynamic range neurons, a group of nociceptive SDH neurones. Facilitation of pain behaviour induced by GAL in the DMH was reversed by lidocaine in the DRt and by ondansetron, a 5HT3R antagonist, in the spinal cord. However, the hyperalgesia induced by glutamate in the DRt was not blocked by spinal ondansetron. In addition, in ARTH but not SHAM animals PWL was increased after lidocaine in the DRt and ondansetron in the spinal cord. Our data demonstrate that GAL in the DMH activates two independent descending facilitatory pathways: (i) one relays in the DRt and (ii) the other one involves 5-HT neurones acting on spinal 5HT3Rs. In experimental ARTH, the tonic pain-facilitatory action is increased in both of these descending pathways.

Is female sex an independent predictor of in-hospital mortality in acute myocardial infarction?

OBJECTIVE: To assess whether female sex is a factor independently related to in-hospital mortality in acute myocardial infarction. METHODS: Of 600 consecutive patients (435 males and 165 females) with acute myocardial infarction, we studied 13 demographic and clinical variables obtained at the time of hospital admission through uni- and multivariate analysis, and analyzed their relation to in-hospital death. RESULTS: Females were older (p<0.001) and had a higher incidence of hypertension (p<0.001). Males were more frequently smokers (p<0.001). The remaining risk factors had a similar incidence among both sexes. All variables underwent uni- and multivariate analysis. Through univariate analysis, the following variables were found to be associated with in-hospital death: female sex (p<0.001), age >70 years (p<0.001), the presence of previous coronary artery disease (p=0.0004), previous myocardial infarction (p<0.001), infarction in the anterior wall (p=0.007), presence of left ventricular dysfunction (p<0.001), and the absence of thrombolytic therapy (p=0.04). Through the multivariate analysis of logistic regression, the following variables were associated with in-hospital mortality: female sex (p=0.001), age (p=0.008), the presence of previous myocardial infarction (p=0.02), and left ventricular dysfunction (p<0.001). CONCLUSION: After adjusting for all risk variables, female sex proved to be a variable independently related to in-hospital mortality in acute myocardial infarction.

Analysis of functional magnetic resonance imaging time series by independent component analysis

Independent Component Analysis, Time Series Analysis, Functional Magnetic Resonance Imaging

Robust learning in safety-related domains : machine learning methods for solving safety-related application problems

Magdeburg, Univ., Fak. für Informatik, Diss., 2009

Machine learning with Lipschitz classifiers

Magdeburg, Univ., Fak. für Elektrotechnik und Informationstechnik, Diss., 2010

Multimodal automatic user disposition recognition in human-machine interaction

Magdeburg, Univ., Fak. für Elektrotechnik und Informationstechnik, Diss., 2013

Citation-based Plagiarism Detection : applying citation pattern analysis to identify currently non-machine-detectible disguised plagiarism in scientific publications

Magdeburg, Univ., Fak. für Informatik, Diss., 2013