Hand gesture recognition for human computer interaction : a comparative study of different image features

Hand gesture recognition for human computer interaction, being a natural way of human computer interaction, is an area of active research in computer vision and machine learning. This is an area with many different possible applications, giving users a simpler and more natural way to communicate with robots/systems interfaces, without the need for extra devices. So, the primary goal of gesture recognition research is to create systems, which can identify specific human gestures and use them to convey information or for device control. For that, vision-based hand gesture interfaces require fast and extremely robust hand detection, and gesture recognition in real time. In this study we try to identify hand features that, isolated, respond better in various situations in human-computer interaction. The extracted features are used to train a set of classifiers with the help of RapidMiner in order to find the best learner. A dataset with our own gesture vocabulary consisted of 10 gestures, recorded from 20 users was created for later processing. Experimental results show that the radial signature and the centroid distance are the features that when used separately obtain better results, with an accuracy of 91% and 90,1% respectively obtained with a Neural Network classifier. These to methods have also the advantage of being simple in terms of computational complexity, which make them good candidates for real-time hand gesture recognition.

Generic system for human-computer gesture interaction: applications on sign language recognition and robotic soccer refereeing

Hand gestures are a powerful way for human communication, with lots of potential applications in the area of human computer interaction. Vision-based hand gesture recognition techniques have many proven advantages compared with traditional devices, giving users a simpler and more natural way to communicate with electronic devices. This work proposes a generic system architecture based in computer vision and machine learning, able to be used with any interface for human-computer interaction. The proposed solution is mainly composed of three modules: a pre-processing and hand segmentation module, a static gesture interface module and a dynamic gesture interface module. The experiments showed that the core of visionbased interaction systems could be the same for all applications and thus facilitate the implementation. For hand posture recognition, a SVM (Support Vector Machine) model was trained and used, able to achieve a final accuracy of 99.4%. For dynamic gestures, an HMM (Hidden Markov Model) model was trained for each gesture that the system could recognize with a final average accuracy of 93.7%. The proposed solution as the advantage of being generic enough with the trained models able to work in real-time, allowing its application in a wide range of human-machine applications. To validate the proposed framework two applications were implemented. The first one is a real-time system able to interpret the Portuguese Sign Language. The second one is an online system able to help a robotic soccer game referee judge a game in real time.

Generic system for human-computer gesture interaction

Hand gestures are a powerful way for human communication, with lots of potential applications in the area of human computer interaction. Vision-based hand gesture recognition techniques have many proven advantages compared with traditional devices, giving users a simpler and more natural way to communicate with electronic devices. This work proposes a generic system architecture based in computer vision and machine learning, able to be used with any interface for humancomputer interaction. The proposed solution is mainly composed of three modules: a pre-processing and hand segmentation module, a static gesture interface module and a dynamic gesture interface module. The experiments showed that the core of vision-based interaction systems can be the same for all applications and thus facilitate the implementation. In order to test the proposed solutions, three prototypes were implemented. For hand posture recognition, a SVM model was trained and used, able to achieve a final accuracy of 99.4%. For dynamic gestures, an HMM model was trained for each gesture that the system could recognize with a final average accuracy of 93.7%. The proposed solution as the advantage of being generic enough with the trained models able to work in real-time, allowing its application in a wide range of human-machine applications.

Looking for mechanisms regulating lung growth in CDH: rat and human studies

Tese de Doutoramento em Ciências da Saúde

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

Determination of the importance of iron acquisition for Staphylococcus epidermidis biofilm survival in human blood

Dissertação de mestrado em Bioengenharia

mRNA metabolism: nonsense mediated mRNA decay as a tool for gene therapy and the role of human DIS3L2 in transcript degradation

Tese de mestrado em Biologia Humana e Ambiente, apresentada à Universidade de Lisboa, através da Faculdade de Ciências, 2015

Human capital in export-based internationalisation. "Managerial determinants and their influence upon the export behaviour of the firm: four case-studies of catalan exporting SMEs"

Export activities are a major source of economic growth and are considered important both at the national level and for individual businesses. Moreover, in the case of SMEs, they gain particular relevance, exporting being the most common foreign market entry mode for these firms. The decision maker’s role in the export activity is crucial, particularly in the case of SMEs. However, the extant literature on internationalization is characterized by a lack of consensus among scholars as to what constitutes the managerial factor in determining exporting. Therefore, this study focuses on the following issue: Which are the decision maker’s characteristics and perceptions that may influence the export behaviour of Catalan SMEs? To address this question a multiple case study method is applied across four Catalan exporting SMEs. The methodology chosen for analysing the empirical data is relying on the proposition testing approach while the investigation is conducted including both within and cross-case analysis. The findings show that high educational level, language skills, high risk tolerance, innovativeness as well as strongly perceived export stimuli as compared to low and easy to overcome export barriers positively influence the export involvement and development of SMEs. The study provides further insights into the research topic by jointly studying managerial characteristics and perceptions. Additionally, the majority of research on exporting topics has been carried out in the USA, so there is a clear need of investigation in the field in other countries, moreover in Spain where the exporting activities have not been as widely studied.

Photodynamic therapy with mTHPC and polyethylene glycol-derived mTHPC: a comparative study on human tumour xenografts.

The photosensitizing properties of m-tetrahydroxyphenylchlorin (mTHPC) and polyethylene glycol-derivatized mTHPC (pegylated mTHPC) were compared in nude mice bearing human malignant mesothelioma, squamous cell carcinoma and adenocarcinoma xenografts. Laser light (20 J/cm2) at 652 nm was delivered to the tumour (surface irradiance) and to an equal-sized area of the hind leg of the animals after i.p. administration of 0.1 mg/kg body weight mTHPC and an equimolar dose of pegylated mTHPC, respectively. The extent of tumour necrosis and normal tissue injury was assessed by histology. Both mTHPC and pegylated mTHPC catalyse photosensitized necrosis in mesothelioma xenografts at drug-light intervals of 1-4 days. The onset of action of pegylated mTHPC seemed slower but significantly exceeds that of mTHPC by days 3 and 4 with the greatest difference being noted at day 4. Pegylated mTHPC also induced significantly larger photonecrosis than mTHPC in squamous cell xenografts but not in adenocarcinoma at day 4, where mTHPC showed greatest activity. The degree of necrosis induced by pegylated mTHPC was the same for all three xenografts. mTHPC led to necrosis of skin and underlying muscle at a drug-light interval of 1 day but minor histological changes only at drug-light intervals from 2-4 days. In contrast, pegylated mTHPC did not result in histologically detectable changes in normal tissues under the same treatment conditions at any drug-light interval assessed. In this study, pegylated mTHPC had advantages as a photosensitizer compared to mTHPC. Tissue concentrations of mTHPC and pegylated mTHPC were measured by high-performance liquid chromatography in non-irradiated animals 4 days after administration. There was no significant difference in tumour uptake between the two sensitizers in mesothelioma, adenocarcinoma and squamous cell carcinoma xenografts. Tissue concentration measurements were of limited use for predicting photosensitization in this model.

In vitro engineering of human stratified urothelium: analysis of its morphology and function.

PURPOSE: Gastric or intestinal patches, commonly used for reconstructive cystoplasty, may induce severe metabolic complications. The use of bladder tissues reconstructed in vitro could avoid these complications. We compared cellular differentiation and permeability characteristics of human native with in vitro cultured stratified urothelium. MATERIALS AND METHODS: Human stratified urothelium was induced in vitro. Morphology was studied with light and electron microscopy and expression of key cellular proteins was assessed using immunohistochemistry. Permeability coefficients were determined by measuring water, urea, ammonia and proton fluxes across the urothelium. RESULTS: As in native urothelium the stratified urothelial construct consisted of basal membrane and basal, intermediate and superficial cell layers. The apical membrane of superficial cells formed villi and glycocalices, and tight junctions and desmosomes were developed. Immunohistochemistry showed similarities and differences in the expression of cytokeratins, integrin and cellular adhesion proteins. In the cultured urothelium cytokeratin 20 and integrin subunits alpha6 and beta4 were absent, and symplekin was expressed diffusely in all layers. Uroplakins were clearly expressed in the superficial umbrella cells of the urothelial constructs, however, they were also present in intermediate and basal cells. Symplekin and uroplakins were expressed only in the superficial cells of native bladder tissue. The urothelial constructs showed excellent viability, and functionally their permeabilities for water, urea and ammonia were no different from those measured in native human urothelium. Proton permeability was even lower in the constructs compared to that of native urothelium. CONCLUSIONS: Although the in vitro cultured human stratified urothelium did not show complete terminal differentiation of its superficial cells, it retained the same barrier characteristics against the principal urine components. These results indicate that such in vitro cultured urothelium, after being grown on a compliant degradable support or in coculture with smooth muscle cells, is suitable for reconstructive cystoplasty.

Transfer of ultrasmall iron oxide nanoparticles from human brain-derived endothelial cells to human glioblastoma cells.

Nanoparticles (NPs) are being used or explored for the development of biomedical applications in diagnosis and therapy, including imaging and drug delivery. Therefore, reliable tools are needed to study the behavior of NPs in biological environment, in particular the transport of NPs across biological barriers, including the blood-brain tumor barrier (BBTB), a challenging question. Previous studies have addressed the translocation of NPs of various compositions across cell layers, mostly using only one type of cells. Using a coculture model of the human BBTB, consisting in human cerebral endothelial cells preloaded with ultrasmall superparamagnetic iron oxide nanoparticles (USPIO NPs) and unloaded human glioblastoma cells grown on each side of newly developed ultrathin permeable silicon nitride supports as a model of the human BBTB, we demonstrate for the first time the transfer of USPIO NPs from human brain-derived endothelial cells to glioblastoma cells. The reduced thickness of the permeable mechanical support compares better than commercially available polymeric supports to the thickness of the basement membrane of the cerebral vascular system. These results are the first report supporting the possibility that USPIO NPs could be directly transferred from endothelial cells to glioblastoma cells across a BBTB. Thus, the use of such ultrathin porous supports provides a new in vitro approach to study the delivery of nanotherapeutics to brain cancers. Our results also suggest a novel possibility for nanoparticles to deliver therapeutics to the brain using endothelial to neural cells transfer.

Patterns of serologic response to human immunodeficiency virus type 1 (HIV-1) in brazilians with different clinical forms of HIV infection

In order to investigate the IgG HIV-1 antibodies rectivity to structural components of the virus, 85 sera from infected Brazilians, comprising the total spectrum of HIV infection, were analysed by Western blot assay. The sera were confirmed as being positive to HIV with enzyme linked immuno assay (ELISA) and indirect immunofluorescence (IIF). Although the sera from patients reacted less intensively to the gag polypeptide of 55KDa, no distinctive antigen reaction patterns were observed between sera patients with different clinical forms. Because of the higher frequency of reactivity to the gag p24 in AIDS patients, the patterns of anti-HIV IgG responses are similar to those observed in their African counterparts.

Evidence for transcript networks composed of chimeric RNAs in human cells.

The classic organization of a gene structure has followed the Jacob and Monod bacterial gene model proposed more than 50 years ago. Since then, empirical determinations of the complexity of the transcriptomes found in yeast to human has blurred the definition and physical boundaries of genes. Using multiple analysis approaches we have characterized individual gene boundaries mapping on human chromosomes 21 and 22. Analyses of the locations of the 5' and 3' transcriptional termini of 492 protein coding genes revealed that for 85% of these genes the boundaries extend beyond the current annotated termini, most often connecting with exons of transcripts from other well annotated genes. The biological and evolutionary importance of these chimeric transcripts is underscored by (1) the non-random interconnections of genes involved, (2) the greater phylogenetic depth of the genes involved in many chimeric interactions, (3) the coordination of the expression of connected genes and (4) the close in vivo and three dimensional proximity of the genomic regions being transcribed and contributing to parts of the chimeric RNAs. The non-random nature of the connection of the genes involved suggest that chimeric transcripts should not be studied in isolation, but together, as an RNA network.

A new chemical tool (C0036E08) supports the role of adenosine A(2B) receptors in mediating human mast cell activation.

Asthma is a chronic inflammatory disease of the airways that involves many cell types, amongst which mast cells are known to be important. Adenosine, a potent bronchoconstricting agent, exerts its ability to modulate adenosine receptors of mast cells thereby potentiating derived mediator release, histamine being one of the first mediators to be released. The heterogeneity of sources of mast cells and the lack of highly potent ligands selective for the different adenosine receptor subtypes have been important hurdles in this area of research. In the present study we describe compound C0036E08, a novel ligand that has high affinity (pK(i) 8.46) for adenosine A(2B) receptors, being 9 times, 1412 times and 3090 times more selective for A(2B) receptors than for A(1), A(2A) and A(3) receptors, respectively. Compound C0036E08 showed antagonist activity at recombinant and native adenosine receptors, and it was able to fully block NECA-induced histamine release in freshly isolated mast cells from human bronchoalveolar fluid. C0036E08 has been shown to be a valuable tool for the identification of adenosine A(2B) receptors as the adenosine receptors responsible for the NECA-induced response in human mast cells. Considering the increasing interest of A(2B) receptors as a therapeutic target in asthma, this chemical tool might provide a base for the development of new anti-asthmatic drugs.

Genuine savings and future well-being in Germany, 1850-2000

Genuine Savings (GS), also known as ‘net adjusted savings’, is a composite indicator of the sustainability of economic development. Genuine Savings reflects year-on-year changes in the total wealth or capital of a country, including net investment in produced capita, investment in human capital, depletion of natural resources, and damage caused by pollution. A negative Genuine Savings rate suggests that the stock of national wealth is declining and that future utility must be less than current utility, indicating that economic development is non-sustainable (Hamilton and Clemens, 1999). We make use of data over a 150 year period to examine the relationship between Genuine Savings and a number of indicators of well-being over time, and compare the relative changes in human, produced, and components of natural capital over the period. Overall, we find that the magnitude of genuine savings is positively related to changes in future consumption, with some evidence of a cointegrating relationship. However, the relationships between genuine savings and infant mortality or average heights are less clear.