Ontology-based representation and generation of workflows for micro-task human-machine computation

Doctoral Program in Computer Science

The human eye as human-machine interface

Eye tracking as an interface to operate a computer is under research for a while and new systems are still being developed nowadays that provide some encouragement to those bound to illnesses that incapacitates them to use any other form of interaction with a computer. Although using computer vision processing and a camera, these systems are usually based on head mount technology being considered a contact type system. This paper describes the implementation of a human-computer interface based on a fully non-contact eye tracking vision system in order to allow people with tetraplegia to interface with a computer. As an assistive technology, a graphical user interface with special features was developed including a virtual keyboard to allow user communication, fast access to pre-stored phrases and multimedia and even internet browsing. This system was developed with the focus on low cost, user friendly functionality and user independency and autonomy.

Vision-based hand Wheel-chair control

Several studies have shown that people with disabilities benefit substantially from access to a means of independent mobility and assistive technology. Researchers are using technology originally developed for mobile robots to create easier to use wheelchairs. With this kind of technology people with disabilities can gain a degree of independence in performing daily life activities. In this work a computer vision system is presented, able to drive a wheelchair with a minimum number of finger commands. The user hand is detected and segmented with the use of a kinect camera, and fingertips are extracted from depth information, and used as wheelchair commands.

Hand gesture recognition system based in computer vision and machine learning

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

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.