Recognition of Signed Expressions in an Experimental System Supporting Deaf Clients in the City Office.

The paper addresses the recognition of dynamic Polish Sign Language expressions in an experimental system supporting deaf people in an office when applying for an ID card. A method of processing a continuous stream of RGB-D data and a feature vector are proposed. The classification is carried out using the k-nearest neighbors algorithm with dynamic time warping, hidden Markov models, and bidirectional long short-term memory. The leave-one-subject-out protocol is used for the dataset containing 121 Polish Sign Language sentences performed five times by four deaf people. A data augmentation method is also proposed and tested. Preliminary observations and conclusions from the use of the system in a laboratory, as well as in real conditions with an experimental installation in the Office of Civil Affairs are given.

Recognition of Human Activities Using Depth Maps and the Viewpoint Feature Histogram Descriptor.

In this paper we propose a way of using depth maps transformed into 3D point clouds to classify human activities. The activities are described as time sequences of feature vectors based on the Viewpoint Feature Histogram descriptor (VFH) computed using the Point Cloud Library. Recognition is performed by two types of classifiers: (i) k-NN nearest neighbors' classifier with Dynamic Time Warping measure, (ii) bidirectional long short-term memory (BiLSTM) deep learning networks. Reduction of classification time for the k-NN by introducing a two tier model and improvement of BiLSTM-based classification via transfer learning and combining multiple networks by fuzzy integral are discussed. Our classification results obtained on two representative datasets: University of Texas at Dallas Multimodal Human Action Dataset and Mining Software Repositories Action 3D Dataset are comparable or better than the current state of the art.

Recognition of Fingerspelling Sequences in Polish Sign Language Using Point Clouds Obtained from Depth Images.

The paper presents a method for recognizing sequences of static letters of the Polish finger alphabet using the point cloud descriptors: viewpoint feature histogram, eigenvalues-based descriptors, ensemble of shape functions, and global radius-based surface descriptor. Each sequence is understood as quick highly coarticulated motions, and the classification is performed by networks of hidden Markov models trained by transitions between postures corresponding to particular letters. Three kinds of the left-to-right Markov models of the transitions, two networks of the transition models-independent and dependent on a dictionary-as well as various combinations of point cloud descriptors are examined on a publicly available dataset of 4200 executions (registered as depth map sequences) prepared by the authors. The hand shape representation proposed in our method can also be applied for recognition of hand postures in single frames. We confirmed this using a known, challenging American finger alphabet dataset with about 60,000 depth images.

[Thermography in the early detection of breast cancer--our own experiences]. / Termografia we wczesnej diagnostyce raka piersi--wlasne doswiadczenia.

In combination with X-ray mammography and clinical examination thermography adds to the accuracy of breast cancer diagnosis. Thermographic examinations can be repeated at short intervals with no radiation hazard to the patient. However, performing and interpreting thermograms requires meticulous training. It was found that women with an abnormal thermogram are at a higher risk and have a poorer prognosis. A change in the thermal pattern is often the earliest sign of a cancer. The authors believe that the fault lies in misinterpretation of the thermogram, rather than the thermogram itself. Computer stimulations could be an adjunct tool to help the clinician in the interpretation.

Influence of AT1 receptor blockade on blood pressure, renal haemodynamics and hormonal responses to intravenous angiotensin II infusion in hypertensive patients.

The aim of this study was to investigate blood pressure, renal haemodynamics, hormone secretion and the responses to angiotensin II infusion during candesartan cilexetil (candesartan), losartan potassium (losartan) and valsartan treatment in patients with essential hypertension. In this double-blind, randomized, crossover study, 24 patients (mean blood pressure of 163/97 mmHg), received candesartan 16 mg, losartan 50 mg and valsartan 80 mg once daily (o.d.) for 4 weeks after a placebo run-in period. At the end of each period, angiotensin II (0.5, 1.0 and 1.5 ng/min/kg) was infused 24 h after the previous drug administration. Each dose of angiotensin II was infused for 45 min. Before infusion and at the end of each infusion step, blood pressure and renal haemodynamics were assessed and plasma renin activity and plasma concentrations of angiotensin II and aldosterone were measured. During treatment with candesartan, resting mean arterial pressure (mean +/- SEM, 106 +/- 2 mmHg) was significantly decreased compared with treatment with losartan (110 +/- 2 mmHg) and valsartan (109 +/- 2 mmHg). Candesartan inhibited the angiotensin II induced increase in filtration fraction (0.8 +/- 0.4%) significantly more than losartan (1.5 +/- 0.4%) and valsartan (1.6 +/- 0.4%) and reduced the increase in aldosterone secretion (17 +/- 5 pg/ml/) significantly more than losartan (74 +/- 17 pg/ml/) and valsartan (82 +/- 19 pg/ml/). In conclusion, candesartan 16 mg o.d. reduced resting blood pressure significantly more than losartan 50 mg o.d. and valsartan 80 mg o.d. Candesartan almost completely inhibited the exogenous angiotensin II induced renal vasoconstriction, effectively inhibited the increase in filtration fraction and significantly blunted aldosterone secretion compared with losartan and valsartan, indicating a more effective AT1 receptor blockade with candesartan.