Human Gait Activity Recognition Using Multimodal Sensors.

Human activity recognition is an application of machine learning with the aim of identifying activities from the gathered activity raw data acquired by different sensors. In medicine, human gait is commonly analyzed by doctors to detect abnormalities and determine possible treatments for the patient. Monitoring the patient's activity is paramount in evaluating the treatment's evolution.

Small-Scale Urban Object Anomaly Detection Using Convolutional Neural Networks with Probability Estimation.

Anomaly detection in sequences is a complex problem in security and surveillance. With the exponential growth of surveillance cameras in urban roads, automating them to analyze the data and automatically identify anomalous events efficiently is essential. This paper presents a methodology to detect anomalous events in urban sequences using pre-trained convolutional neural networks (CNN) and super-resolution (SR) models.

Diabetic Wound Segmentation using Convolutional Neural Networks.

Image segmentation is a common goal in many medical applications, as its use can improve diagnostic capability and outcome prediction. In order to assess the wound healing rate in diabetic foot ulcers, some parameters from the wound area are measured. However, heterogeneity of diabetic skin lesions and the noise present in images captured by digital cameras make wound extraction a difficult task.

Foreground Detection by Competitive Learning for Varying Input Distributions.

One of the most important challenges in computer vision applications is the background modeling, especially when the background is dynamic and the input distribution might not be stationary, i.e. the distribution of the input data could change with time (e.

Bregman divergences for growing hierarchical self-organizing networks.

Growing hierarchical self-organizing models are characterized by the flexibility of their structure, which can easily accommodate for complex input datasets. However, most proposals use the Euclidean distance as the only error measure. Here we propose a way to introduce Bregman divergences in these models, which is based on stochastic approximation principles, so that more general distortion measures can be employed.

Comminuted radial head fractures treated with pyrocarbon prosthetic replacement.

Purpose: We had evaluated our experience in the treatment of displaced and comminuted radial head fractures with pyrocarbon radial head prosthesis.

Methods: From May 2003 to July 2008, radial head prostheses were performed in 47 patients. There were 29 female and 18 male with mean age 51 (34-70 years).

A comparative study of physical and chemical processes for removal of biomass in biofilters.

After 6 months of operation a long-term biofilter was stopped for two weeks and then it was started up again for a second experimental period of almost 1.3 years, with high toluene loads and submitted to several physical and chemical treatments in order to remove excess biomass that could affect the reactor's performance due to clogging, whose main effect is a high pressure drop. Elimination capacity and removal efficiency were determined after each treatment.

Foreground detection in video sequences with probabilistic self-organizing maps.

Background modeling and foreground detection are key parts of any computer vision system. These problems have been addressed in literature with several probabilistic approaches based on mixture models. Here we propose a new kind of probabilistic background models which is based on probabilistic self-organising maps.

Synthesis and pharmacological screening of several aroyl and heteroaroyl selenylacetic acid derivatives as cytotoxic and antiproliferative agents.

The synthesis and cytotoxic activity of a series of twenty six aroyl and heteroaroyl selenylacetic acid derivatives of general formula Ar-CO-Se-CH(2)-COOH or Heterar-CO-Se-CH(2)-COOH are reported. The synthesis was carried out by reaction of acyl chlorides with sodium hydrogen selenide, prepared in situ, and this led to the formation of sodium aroylselenides that subsequently reacted with alpha-bromoacetic acid to produce the corresponding selenylacetic acid derivatives. All of the compounds were tested against a prostate cancer cell line (PC-3) and some of the more active compounds were assessed against a panel of four human cancer cell lines (CCRF-CEM, HTB-54, HT-29, MCF-7) and one mammary gland-derived non-malignant cell line (184B5).