A hybrid breast cancer detection system via neural network and feature selection based on SBS, SFS and PCA

Two hybrid feature selection methods (SFSP and SBSP) which are composed by combining the sequential forward selection and the sequential backward selection together with the principal component analysis developed by utilizing quadratic discriminant analysis classification algorithmic criteria so as to utilize in the diagnosis of breast cancer fast and effectively are presented in this study. The tenfold cross-validation method has been applied in the algorithm, which is utilized as criteria during the selection of the features. The dimension of the feature space for input has been decreased from 9 to 4 thanks to the selection of these two hybrid features. The Artificial Neural Networks have been used as classifier. The cross-validation method has been preferred also in the phase of this classification as in the case of the selection of the feature in order to increase the reliability of the result. The Wisconsin Breast Cancer Database obtained from the UCI has been utilized so as to determine the correctness of the system suggested. The values of the average correctness of the classification obtained by utilizing a tenfold cross-validation of the two hybrid systems developed earlier are found, respectively, as follows: for SFSP + NN, 97.57 % and for SBSP + NN, 98.57 %. SBSP + NN system has been observed that, among the studies carried out by implementing the cross-validation method for the breast cancer, the result appears to be very promising. The acquired results have revealed that this hybrid system applied by means of reducing dimension is an utilizable system in order to diagnose the diseases faster and more successfully.     

High performance concrete compressive strength forecasting using ensemble models based on discrete wavelet transform

This paper investigates the use of wavelet ensemble models for high performance concrete (HPC) compressive strength forecasting. More specifically, we incorporate bagging and gradient boosting methods in building artificial neural networks (ANN) ensembles (bagged artificial neural networks (BANN) and gradient boosted artificial neural networks (GBANN)), first. Coefficient of determination (R²), mean absolute error (MAE) and the root mean squared error (RMSE) statics are used for performance evaluation of proposed predictive models. Empirical results show that ensemble models (R²_BANN=0.9278, R²_GBANN=0.9270) are superior to a conventional ANN model (R²_ANN=0.9088). Then, we use the coupling of discrete wavelet transform (DWT) and ANN ensembles for enhancing the prediction accuracy. The study concludes that DWT is an effective tool for increasing the accuracy of the ANN ensembles (R²_WBANN=0.9397, R²_WGBANN=0.9528).     

Thermal and mechanical properties of polypropylene nanocomposite materials reinforced with cellulose nano whiskers

We use polypropylene (PP, an apolar polymer) and cellulose nano whiskers (CNW, a polar material) to produce nano polymer composites with enhanced mechanical and thermal properties. To improve compatibility, maleic anhydride grafted PP has also been used as a coupling agent. To enhance the uniform distribution of CNW in the composite, the matrix polymer is dissolved in toluene, and sonification and magnetic stirring are applied. Good film transparency indicates uniform CNW dispersion, but CNW domains in the composite film observed under an scanning electron microscope may indicate slight agglomeration of CNW in the composite film. The tensile strength of the composite compared with neat PP improves by 70–80% with the addition of CNW. The crystallinity has also been improved by about 50% in the CNW reinforced samples. As the content of CNW increases, the composite exhibits higher thermal degradation temperature, higher hydrophilicity, and higher thermal conductivity. © 2012 Wiley Periodicals, Inc. J Appl Polym Sci, 2012     

Synthesis, contact printing, and device characterization of Ni-catalyzed, crystalline InAs nanowires

InAs nanowires have been actively explored as the channel material for high performance transistors owing to their high electron mobility and ease of ohmic metal contact formation. The catalytic growth of nonepitaxial InAs nanowires, however, has often relied on the use of Au colloids which is non-CMOS compatible. Here, we demonstrate the successful synthesis of crystalline InAs nanowires with high yield and tunable diameters by using Ni nanoparticles as the catalyst material on amorphous SiO2 substrates. The nanowires show superb electrical properties with field-effect electron mobility ~2700 cm2/Vs and ION/IOFF >103. The uniformity and purity of the grown InAs nanowires are further demonstrated by large-scale assembly of parallel arrays of nanowires on substrates via the contact printing process that enables high performance, “printable” transistors, capable of delivering 5 10 mA ON currents (~400 nanowires).     

Analysis of Target Detection Probability in Randomly Deployed Sensor Networks

The main functionality of a surveillance wireless sensor network is to detect unauthorized traversals in a field. In this paper, we develop a formulation to determine the probability of detecting a randomly positioned target by a set of binary sensors to serve as the deployment quality measure. This formulation leads to a recipe to determine the number of sensors required to deliver a certain deployment quality level. The sensing- and communication-neighbor degrees which can be used as design criteria in a sensor network are defined and calculated. The model is verified by simulations whose outcomes closely match the analytical results.     

Determination of Mean Velocity and Discharge in Natural Streams Using Neuro-Fuzzy and Neural Network Approaches

The applicability of artificial neural networks (ANNs) and the adaptive neuro-fuzzy inference system (ANFIS) for determination of mean velocity and discharge of natural streams is investigated. The 2,184 field data obtained from four different sites on the Sarimsakli and Sosun streams in central Turkey were used in the study. ANNs and ANFIS models use the inputs, water surface velocity and water surface slope, to estimate the mean velocity and discharges of natural streams. The accuracies of both models were compared with the multiple-linear regression (MLR) model. The comparison results showed that the ANFIS model performed better than the ANNs and regression models for estimating mean velocity and discharge. The ANN model also showed better accuracy than the MLR model. The root mean square errors (RMSE) and mean absolute relative errors (MARE) of the MLR model were reduced by 88 and 91 % using the ANFIS model in estimating discharges, respectively. It is found that the optimal ANFIS model with RMSE of 0,063, MARE of 3,47 and determination coefficient (R²) of 0,996 in the test period is superior in estimation of discharge than the MLR model with RMSE of 0,532, MARE of 38,9 and R² of 0,776, respectively. The study reveals that the ANFIS technique can be successfully used for estimating the mean velocity and discharge of natural streams by using only the inputs of water surface velocity and water surface slope.     

Process Variation-Aware Multiple-Fault Diagnosis of Thermometer-Coded Current-Steering DACs

In this brief, we first introduce a process-variation-aware test-point generation method. With this method, faults are not obscured by process variations and we are able to generate new test points by measuring a very limited number of current values on-chip and estimating values of the remaining currents. We furthermore introduce a multiple-fault diagnosis procedure where we use the process-variation aware test-point generation method. The proposed methods can also be used for structural test. For the application, we have used a thermometer coded current steering digital to analog converter, as they are widely used due to their suitability for high speed applications and the symmetric design is suitable for the application of our method. We introduce a design-for-test hardware for the diagnosis cost reduction, while implementing our methods. Experimental results show that parametric errors as small as 20% can be diagnosed with up to 97.8% accuracy     

The role of MRI in prostate cancer: current and future directions

Magnetic Resonance Materials in Physics, Biology and Medicine - There has been an increasing role of magnetic resonance imaging (MRI) in the management of prostate cancer. MRI already plays an...     

Electrospinning of single and multilayered scaffolds for tissue engineering applications

Optimized electrospinning conditions were applied to produce single and multilayered (ML) scaffolds composed of polycaprolactone, collagen and elastin. The ML scaffold was cross-linked with glutaraldehyde to increase the stability. Morphological and structural characteristics of the scaffolds were measured by SEM and FTIR analyses. Results revealed that polymers combined to each other well and uniform fibers were obtained with the diameters ranging from 156 ± 53 to 1536 ± 293 nm. Contact angle measurements were performed to investigate the hydrophilic character of each structure. It was observed that incorporation of the natural polymers into the blends increased the hydrophilicity. Mechanical tests proved that collagen contributed to fabricate stiffer structures while elastin provided more elasticity. Biocompatibility of the scaffolds was examined by SEM analysis and WST-1 test with mouse fibroblast cells (L929) in vitro. Results exhibited that the addition of natural polymers increased the cell growth, and none of the single and ML scaffolds presented cytotoxic effect.