Human language technology and communicative disabilities: requirements and possibilities for the future

For some years now, the Nederlandse Taalunie (Dutch Language Union) has been active in promoting the development of human language technology (HLT) applications for speakers of Dutch with communicative disabilities. The reason is that HLT products and services may enable them to improve their communication skills and verbal autonomy. We sought to identify a minimum common set of HLT resources that is required to develop tools for a wide range of communication disabilities. In order to reach this goal, we investigated the specific needs of communicatively disabled people and related these needs to the underlying HLT software components. By analysing the availability and quality of these essential HLT resources, we were able to identify which of the crucial elements need further research and development to become usable for developing applications for communicatively disabled speakers of Dutch. The results obtained in the current survey can be used to inform policy institutions on how they can stimulate the development of HLT resources for this target group. In the current survey results were obtained for Dutch, but a similar approach can also be applied to other languages.     

Energy Metabolites as Biomarkers in Ischemic and Dilated Cardiomyopathy

With more than 25 million people affected, heart failure (HF) is a global threat. As energy production pathways are known to play a pivotal role in HF, we sought here to identify key metabolic changes in ischemic- and non-ischemic HF by using a multi-OMICS approach. Serum metabolites and mRNAseq and epigenetic DNA methylation profiles were analyzed from blood and left ventricular heart biopsy specimens of the same individuals. In total we collected serum from n = 82 patients with Dilated Cardiomyopathy (DCM) and n = 51 controls in the screening stage. We identified several metabolites involved in glycolysis and citric acid cycle to be elevated up to 5.7-fold in DCM (p = 1.7 × 10⁻⁶). Interestingly, cardiac mRNA and epigenetic changes of genes encoding rate-limiting enzymes of these pathways could also be found and validated in our second stage of metabolite assessment in n = 52 DCM, n = 39 ischemic HF and n = 57 controls. In conclusion, we identified a new set of metabolomic biomarkers for HF. We were able to identify underlying biological cascades that potentially represent suitable intervention targets.     

The ChaLearn gesture dataset (CGD 2011)

This paper describes the data used in the ChaLearn gesture challenges that took place in 2011/2012, whose results were discussed at the CVPR 2012 and ICPR 2012 conferences. The task can be described as: user-dependent, small vocabulary, fixed camera, one-shot-learning. The data include 54,000 hand and arm gestures recorded with an RGB-D \(\hbox {Kinect}^\mathrm{TM}\) camera. The data are organized into batches of 100 gestures pertaining to a small gesture vocabulary of 8–12 gestures, recorded by the same user. Short continuous sequences of 1–5 randomly selected gestures are recorded. We provide man-made annotations (temporal segmentation into individual gestures, alignment of RGB and depth images, and body part location) and a library of function to preprocess and automatically annotate data. We also provide a subset of batches in which the user’s horizontal position is randomly shifted or scaled. We report on the results of the challenge and distribute sample code to facilitate developing new solutions. The data, datacollection software and the gesture vocabularies are downloadable from http://gesture.chalearn.org. We set up a forum for researchers working on these data http://groups.google.com/group/gesturechallenge.     

Efficient Binary Tomographic Reconstruction

Tomographic reconstruction of a binary image from few projections is considered. A novel heuristic algorithm is proposed, the central element of which is a nonlinear transformation ψ(p)=log(p/(1?p)) of the probability p that a pixel of the sought image be 1-valued. It consists of backprojections based on ψ(p) and iterative corrections. Application of this algorithm to a series of artificial test cases leads to exact binary reconstructions, (i.e., recovery of the binary image for each single pixel) from the knowledge of projection data over a few directions. Images up to 10⁶ pixels are reconstructed in a few seconds. A series of test cases is performed for comparison with previous methods, showing a better efficiency and reduced computation times.     

A web-based platform for biosignal visualization and annotation

With the advent of wearable sensing and mobile technologies, biosignals have seen an increasingly growing number of application areas, leading to the collection of large volumes of data. One of the difficulties in dealing with these data sets, and in the development of automated machine learning systems which use them as input, is the lack of reliable ground truth information. In this paper we present a new web-based platform for visualization, retrieval and annotation of biosignals by non-technical users, aimed at improving the process of ground truth collection for biomedical applications. Moreover, a novel extendable and scalable data representation model and persistency framework is presented. The results of the experimental evaluation with possible users has further confirmed the potential of the presented framework.     

Effect of operating conditions in removal of arsenic from water by nanofiltration membrane

The removal of arsenic from synthetic waters and surface water by nanofiltration (NF) membrane was investigated. In synthetic solutions, arsenic rejection experiments included variation of arsenic retentate concentration, transmembrane pressure, crossflow velocity and temperature. Arsenic rejection increased with arsenic retentate concentration. Arsenic was removed 93-99% from synthetic feed waters containing between 100 and 382 μg/L as V, resulting in permeate arsenic concentrations of about 5 μg/L. Under studied conditions, arsenic rejection was independent of transmembrane pressure, crossflow velocity and temperature. In surface water, the mean rejection of As V was 95% while the rejection of sulfate was 97%. The co-occurrence of dissolved inorganics does not significantly influence arsenic rejection. The mean concentration of As in collected permeated was 8 μg/L. The mean rejection of TDS, total hardness and conductivity were 75, 88 and 75% respectively.     

Einfluß von Lösungsmitteln auf den Partikeldurchmesser von Dispersionen anionischer Polyurethanionomerer

Aqueous dispersions of anionic polyurethanes were prepared by reaction of polyethers, 1,6-hexamethylene diisocyanate, 1,2,4-benzenetricarboxylic acid anhydride and triethyl amine. Formation of the dispersion was achieved by phase reversal or by precipitation. Phase reversal occurred when the solution or the melt of the polymer was treated with water, while precipitation took place when the solution was stirred into water. The amount of acetone used has an effect on the mean particle diameter, D?_T, obtained by turbidity measurements. There was an optimal acetone concentration at which D?_T reached a minimum. A similar effect was observed when tetrahydrofuran, 2-butanone or acetonitrile were used as solvents instead of acetone. When the dispersion was formed by precipitation, only adequately diluted acetonic solutions formed colloidal dispersions, while concentrated solutions gave dispersions with a broad particle size distribution.     

Practical validation of the two-fluid model applied to dense gas-solid flows in fluidized beds

This paper discusses the simulation of bubbling gas-solid flows by using the Eulerian two-fluid approach. Predictions of particle motion, bed expansion, bubble size and bubble velocity in bubbling beds containing Geldart B particles are compared with experimental results and correlations found in the literature. In addition, gas mixing in a bed of Geldart A particles is investigated.An in-house code has been developed based on the finite-volume method and the time-splitting approach using a staggered grid arrangement. The velocities in both phases are obtained by solving the 2D Reynolds-averaged Navier/Stokes equations using a partial elimination algorithm (PEA) and a coupled solver. The k-ε turbulence model is used to describe the turbulent quantities in the continuous phase.In general, the model predictions are in good agreement with experimental data found in the literature. Most important observations are: the level of the restitution coefficient was found to be crucial in order to obtain successful results from 2D axisymmetric simulations of a system containing Geldart B particles. Bubble size and bubble rise velocities are not as sensitive to the restitution coefficient. The turbulence model is of outmost importance concerning gas mixing in a fluidized bed of Geldart A particles.From these numerical analyzes an optimized granular flow two-fluid model can be designed for the purpose of simulating reactive systems in fluidized bed reactors.