Keratinocyte growth factor in acute lung injury to reduce pulmonary dysfunction--a randomised placebo-controlled trial (KARE):study protocol

Acute lung injury is a common, devastating clinical syndrome associated with substantial mortality and morbidity with currently no proven therapeutic interventional strategy to improve patient outcomes. The objectives of this study are to test the potential therapeutic effects of keratinocyte growth factor for patients with acute lung injury on oxygenation and biological indicators of acute inflammation, lung epithelial and endothelial function, protease:antiprotease balance, and lung extracellular matrix degradation and turnover.

Acute respiratory distress syndrome caused by Mycoplasma pneumoniae diagnosed by polymerase chain reaction

Mycoplasma pneumoniae (M. pneumoniae) is a common pathogen in cases of atypical pneumonia. Most individuals with Mycoplasma pneumonia run a benign course, with non-specific symptoms of malaise, fever and non-productive cough that usually resolve with no long-term sequelae. Acute lung injury is not commonly seen in Mycoplasma pneumonia. We report a case of acute respiratory distress syndrome cause by M. pneumoniae diagnosed by quantitative real-time polymerase chain reaction (RT-PCR).

Determining propeller induced erosion alongside quay walls in harbours using Artificial Neural Networks

In shallow waters, such as those found close to berth structures, the wash from a manoeuvring ship’s propeller can cause erosion of the seabed. This erosion can be increased if the wash intersects a berth structure. A number of researchers have undertaken model studies and used regression analysis to develop predictive relationships for the scouring action. This paper presents an experimental investigation with Artificial Neural Networks (ANN’s), used to analyse the results. The purpose of using ANN’s was to examine the prediction accuracy of the Networks in comparison with previous regression analysis methods. ANN’s were found to provide a more accurate method of predicting propeller wash scour than the equations presented by previous investigators.

Application of artificial neural network techniques to low bit-rate speech coding

Research has been undertaken to investigate the use of artificial neural network (ANN) techniques to improve the performance of a low bit-rate vector transform coder. Considerable improvements in the perceptual quality of the coded speech have been obtained. New ANN-based methods for vector quantiser (VQ) design and for the adaptive updating of VQ codebook are introduced for use in speech coding applications.

ARTIFICIAL SURFACES WITH INTERWOVEN AND TESSELLATED PATTERNED CONDUCTORS: PROPERTIES AND PHENOMENOLOGY

The features of artificial surfaces composed of doubly periodic patterns of interwoven planar conductors are discussed. The free-standing intertwined quadrifilar spirals and modified Brigid's crosses are presented as illustrative examples to demonstrate the highly stable angular reflection and transmittance response with low cross-polarisation and a broad fractional bandwidth. The main mechanisms contributing to the substantially sub-wavelength response of these arrays are discussed showing that interweaving their conductor patterns provides concurrent control of both the equivalent capacitance and inductance of the unit cell. The effects of dielectric substrate and conductor thickness on the properties of intertwined spiral and modified Brigid's cross arrays are discussed to provide insight in the effect of the structure parameters on array performance.

Evaluation of sampling methods for learning from imbalanced data

The problem of learning from imbalanced data is of critical importance in a large number of application domains and can be a bottleneck in the performance of various conventional learning methods that assume the data distribution to be balanced. The class imbalance problem corresponds to dealing with the situation where one class massively outnumbers the other. The imbalance between majority and minority would lead machine learning to be biased and produce unreliable outcomes if the imbalanced data is used directly. There has been increasing interest in this research area and a number of algorithms have been developed. However, independent evaluation of the algorithms is limited. This paper aims at evaluating the performance of five representative data sampling methods namely SMOTE, ADASYN, BorderlineSMOTE, SMOTETomek and RUSBoost that deal with class imbalance problems. A comparative study is conducted and the performance of each method is critically analysed in terms of assessment metrics. © 2013 Springer-Verlag.

Urethral atrophy after artificial urinary sphincter placement:Is cuff downsizing effective?

Purpose: We reviewed the outcome of cuff downsizing with an artificial urinary sphincter for treating recurrent incontinence due to urethral atrophy.

Materials and Methods: We analyzed the records of 17 patients in a 7-year period in whom clinical, radiological and urodynamic evidence of urethral atrophy was treated with cuff downsizing. Cuff downsizing was accomplished by removing the existing cuff and replacing it with a 4 cm. cuff within the established false capsule. Incontinence and satisfaction parameters before and after the procedure were assessed by a validated questionnaire.

Results: Mean patient age was 70 years (range 62 to 79). Average time to urethral atrophy was 31 months (range 5 to 96) after primary sphincter implantation. Mean followup after downsizing was 22 months (range 1 to 64). Cuff downsizing caused a mean decrease of 3.9 to 0.5 pads daily. The number of severe leakage episodes decreased from a mean of 5.4 to 2.1 The mean SEAPI (stress leakage, emptying, anatomy, protection, inhibition) score decreased from 8.2 to 2.4. Patient satisfaction increased from 15% to 80% after cuff downsizing. In 1 patient an infected cuff required complete removal of the device.

Conclusions: Patient satisfaction and continence parameters improved after cuff downsizing. We believe that this technique is a simple and effective method of restoring continence after urethral atrophy.

Artificial urinary sphincter implantation in the irradiated patient:safety, efficacy and satisfaction

Objective To compare the long-term outcome of artificial urinary sphincter (AUS) implantation in patients after prostatectomy, with and with no history of previous irradiation.

Patients and methods The study included 98 men (mean age 68 years) with urinary incontinence after prostatectomy for prostate cancer (85 radical, 13 transurethral resection) who had an AUS implanted. Twenty-two of the patients had received adjuvant external beam irradiation before AUS implantation. Over a mean (range) follow-up of 46 (5-118) months, the complication and surgical revision rates were recorded and compared between irradiated and unirradiated patients. The two groups were also compared for the resolution of incontinence and satisfaction, assessed using a questionnaire.

Results Overall, surgical revision was equally common in irradiated (36%) and unirradiated (24%) patients. After activating the AUS, urethral atrophy, infection and erosion requiring surgical revision were more common in irradiated patients (41% vs 11%; P <0.05); 70% of patients reported a significant improvement in continence, regardless of previous irradiation. Patient satisfaction remained high, with >80% of patients stating that they would undergo surgery again and/or recommend it to others, despite previous Irradiation and/or the need for surgical revision.

Conclusions Despite higher complication and surgical revision rates in patients who have an AUS implanted and have a history of previous Irradiation, the long-term continence and patient satisfaction appear not to be adversely affected.

Predicting forest attributes In southeast Alaska using artificial neural networks

Artificial neural network (ANN) methods are used to predict forest characteristics. The data source is the Southeast Alaska (SEAK) Grid Inventory, a ground survey compiled by the USDA Forest Service at several thousand sites. The main objective of this article is to predict characteristics at unsurveyed locations between grid sites. A secondary objective is to evaluate the relative performance of different ANNs. Data from the grid sites are used to train six ANNs: multilayer perceptron, fuzzy ARTMAP, probabilistic, generalized regression, radial basis function, and learning vector quantization. A classification and regression tree method is used for comparison. Topographic variables are used to construct models: latitude and longitude coordinates, elevation, slope, and aspect. The models classify three forest characteristics: crown closure, species land cover, and tree size/structure. Models are constructed using n-fold cross-validation. Predictive accuracy is calculated using a method that accounts for the influence of misclassification as well as measuring correct classifications. The probabilistic and generalized regression networks are found to be the most accurate. The predictions of the ANN models are compared with a classification of the Tongass national forest in southeast Alaska based on the interpretation of satellite imagery and are found to be of similar accuracy.

Modeling of titanium alloys by using artificial neural networks

Titanium alloy exhibits an excellent combination of bio-compatibility, corrosion resistance, strength and toughness. The microstructure of an alloy influences the properties. The microstructures depend mainly on alloying elements, method of production, mechanical, and thermal treatments. The relationships between these variables and final properties of the alloy are complex, non-linear in nature, which is the biggest hurdle in developing proper correlations between them by conventional methods. So, we developed artificial neural networks (ANN) models for solving these complex phenomena in titanium alloys.

In the present work, ANN models were used for the analysis and prediction of the correlation between the process parameters, the alloying elements, microstructural features, beta transus temperature and mechanical properties in titanium alloys. Sensitivity analysis of trained neural network models were studied which resulted a better understanding of relationships between inputs and outputs. The model predictions and the analysis are well in agreement with the experimental results. The simulation results show that the average output-prediction error by models are less than 5% of the prediction range in more than 95% of the cases, which is quite acceptable for all metallurgical purposes.

Two-Stage Orthogonal Least Squares Methods for Neural Network Construction

A number of neural networks can be formulated as the linear-in-the-parameters models. Training such networks can be transformed to a model selection problem where a compact model is selected from all the candidates using subset selection algorithms. Forward selection methods are popular fast subset selection approaches. However, they may only produce suboptimal models and can be trapped into a local minimum. More recently, a two-stage fast recursive algorithm (TSFRA) combining forward selection and backward model refinement has been proposed to improve the compactness and generalization performance of the model. This paper proposes unified two-stage orthogonal least squares methods instead of the fast recursive-based methods. In contrast to the TSFRA, this paper derives a new simplified relationship between the forward and the backward stages to avoid repetitive computations using the inherent orthogonal properties of the least squares methods. Furthermore, a new term exchanging scheme for backward model refinement is introduced to reduce computational demand. Finally, given the error reduction ratio criterion, effective and efficient forward and backward subset selection procedures are proposed. Extensive examples are presented to demonstrate the improved model compactness constructed by the proposed technique in comparison with some popular methods.