26 research outputs found
Ensemble to Improve Gesture Recognition
No full textAutomatic hand gesture recognition plays a fundamental role in current research with the aim of empowering a natural communication between users and virtual reality systems. Starting from an existing work, based on the extraction of two different descriptors from the depth maps followed by their classification with a stand-alone multi SVM classifier, in this paper we improve the gesture recognition system performances and reliability and we evaluate different classification approaches.
To this purpose, we first compare the performance of different descriptors and analyze their correlation for assessing their complementarity, and then we demonstrate the advantage gained by their fusion by the Wilcoxon Signed-Rank test.
In particular, the novelties of this paper are a new method for extracting features from the curvature image and the design of a very effective ensemble of classifiers to solve the problem
Combination of Depth and Texture Descriptors for Gesture Recognition
No full textAutomatic hand gesture recognition is a challenging problem that is attaining a growing interest due to its applications in natural interfaces for human-machine interaction, automatic sign-language recognition, computer gaming, robotics and healthcare. This chapter briefly reviews existing approaches for automatic hand gesture recognition and proposes a novel system exploiting together color and depth data. The proposed approach is based on a set of four descriptors extracted from the depth map and three texture descriptors extracted from the 2D image, while the classification is performed by an ensemble of support vector machines and decision trees. A main novelty for feature extraction is a method based on the histogram of gradients used for describing the curvature image obtained from the depth map.
Another novelty is the evaluation of different colorimetric spaces for improving the recognition performance of the texture descriptors: the best performance is obtained using the lightness band of the L*c*h* color space.
In the experimental Section the performances of different "stand-alone" descriptors are firstly compared and their correlation is analyzed for assessing their complementarity, and eventually the advantage gained by their fusion is demonstrated by the Wilcoxon Signed-Rank test
Palm area detection for reliable hand gesture recognition
No full textAbstract—Hand gesture recognition applications require as a first step a reliable identification of the hand region and its subdivision into fingers and palm areas. In this work the hand is firstly extracted from the depth data acquired by a depth sensor (e.g., Microsoft Kinect). Then the center of the palm and the hand orientation are identified. Finally circular and elliptical shapes are fitted on the extracted samples in order to reliably identify the palm and fingers area. The proposed approach has been tested inside a simple gesture recognition scheme and preliminary results show its reliability. I
Holt-Oram syndrome: cardiological, radiological and genetic evaluation
No full textA case of a 63-year-old woman with Holt-Oram syndrome is presented. The patient, operated at 38 years for correction of an interatrial defect of the ostium secundum type presented with upper extremity skeletal abnormalities, in particular on the left, and a severe mitral insufficiency with ruptured chordae tendinae of the posterior leaflet. Mitral valve reconstruction was followed by an unusual severe hemolytic anemia and acute secondary renal insufficiency. Valve replacement was therefore necessary. At present, the patient, whose karyotype is normal, is in NYHA functional class I
Effectiveness and safety of intravenous valproate in agitation: a systematic review
No full textRationale: The use of intravenous valproate is not approved for clinical practice in psychiatry. Literature data pointed out for a potential usefulness of this route of administration for valproate, but there is no actual consensus. Objectives: The aim of the present systematic review is to assess the effectiveness of intravenous valproate in agitation as well as general safety. Methods: A systematic review of studies evaluating the use of intravenous valproate in agitation was conducted. Additionally, safety was evaluated in all randomized trials involving the use of intravenous valproate in all medical conditions (epilepsy, migraine and psychiatric conditions). Results: For the systematic review on effectiveness in agitation, the search yielded 965 articles overall. After removing duplicates, 9411 articles were screened by title and abstract, and 39 of these were evaluated at a full-text level. Six studies were considered eligible for qualitative synthesis: one RCT and case report (n = 3), followed by cohort studies (n = 2). For the systematic review on safety, twenty-two RCTs were considered eligible for quantitative synthesis. Conclusion: Intravenous valproate seems efficacious in reducing agitation in psychiatric patients; it generally appears safe compared to other neuroleptics or antiepileptics. However, the evidence is still not strong as it relies mainly on open-label studies or case series
INDAGINE SULLA PRESENZA DI SALMONELLA SPP IN ALIMENTI PREPARATI PRESSO INSEDIAMENTI TURISTICI RIVIERASCHI DELLA REGIONE PUGLIA
No full textUpstream building effects on urban wind energy: a study of the University of Alberta North Campus
No full textAbstract: This paper assesses the effects of upstream buildings on the wind energy available on the tallest building of the University of Alberta, the Donadeo Innovation Centre for Engineering (DICE). CFD simulations with ? ? ? SST turbulence model were performed to compare the removal of upstream buildings using the same inlet boundary layer profile, which was obtained using a periodic boundary condition to ensure horizontal homogeneity through all the cases. The results show the importance of contextualization for CFD simulations and how the upstream obstacles could significantly affect wind prediction for energy assessments. One particular building, which is 2 rows upstream but only 10 meters lower in height, has a significant effect on the approaching wind on the target location. Nevertheless, its effects are diminished by the presence of further upstream buildings. In general, the effects of the upfront buildings are perceived up to 20-30% of the height of the building from its top without an evident correlation to the number of buildings included upstream. The notable exception of the case of the tallest upstream building highlights the necessity of a framework to segregate the computational domain into building groups, reducing the computational cost of a single-building assessment and the risk of omitting relevant upstream obstacles from the simulation.Communication présentée lors du congrès international tenu conjointement par Canadian Society for Mechanical Engineering (CSME) et Computational Fluid Dynamics Society of Canada (CFD Canada), à l’Université de Sherbrooke (Québec), du 28 au 31 mai 2023
