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.

Hind limb ischemia in type 1 diabetic mice as useful tool to evaluate the neovascularization of tissue engineering constructs

Hind-limb ischemia has been used in type 1 diabetic mice to evaluate treatments for peripheral arterial disease or mechanisms of vascular impairment in diabetes [1]. Vascular deficiency is not only a pathophysiological condition, but also an obvious circumstance in tissue regeneration and in tissue engineering and regenerative medicine (TERM) strategies. We performed a pilot experiment of hind-limb ischemia in streptozotocin(STZ)-induced type 1 diabetic mice to hypothesise whether diabetes influences neovascularization induced by biomaterials. The dependent variables included blood flow and markers of arteriogenesis and angiogenesis. Type 1 diabetes was induced in 8-week-old C57BL/6 mice by an i.p. injection of STZ (50 mg/kg daily for 5 days). Hind-limb ischemia was created under deep anaesthesia and the left femoral artery and vein were isolated, ligated, and excised. The contralateral hind limb served as an internal control within each mouse. Non-diabetic ischaemic mice were used as experiment controls. At the hind-limb ischemia surgical procedure, different types of biomaterials were placed in the blood vessels gap. Blood flow was estimated by Laser Doppler perfusion imager, right after surgery and then weekly. After 28 days of implantation, surrounding muscle was excised and evaluated by histological analysis for arteriogenesis and angiogenesis. The results showed that implanted biomaterials were promote faster restoration of blood flow in the ischemic limbs and improved neovascularization in the diabetic mice. Therefore, we herein demonstrate that the combined model of hind-limb ischemia in type 1 diabetes mice is suitable to evaluate the neovascularization potential of biomaterials and eventually tissue engineering constructs.  

Methods to solve the equations of motion

"Series title: Springerbriefs in applied sciences and technology, ISSN 2191-530X"

Real-Time models to predict the use of vasopressors in monitored patients

The needs of reducing human error has been growing in every field of study, and medicine is one of those. Through the implementation of technologies is possible to help in the decision making process of clinics, therefore to reduce the difficulties that are typically faced. This study focuses on easing some of those difficulties by presenting real-time data mining models capable of predicting if a monitored patient, typically admitted in intensive care, will need to take vasopressors. Data Mining models were induced using clinical variables such as vital signs, laboratory analysis, among others. The best model presented a sensitivity of 94.94%. With this model it is possible reducing the misuse of vasopressors acting as prevention. At same time it is offered a better care to patients by anticipating their treatment with vasopressors.

Noise mapping for an urban area: study case: old city of Damascus, Syria

Dissertação de mestrado em Engenharia Urbana