Early prostate cancer diagnosis by using artificial neural networks and support vector machines

The aim of this study is to design a classifier based expert system for early diagnosis of the organ in constraint phase to reach informed decision making without biopsy by using some selected features. The other purpose is to investigate a relationship between BMI (body mass index), smoking factor, and prostate cancer. The data used in this study were collected from 300 men (100: prostate adenocarcinoma, 200: chronic prostatism or benign prostatic hyperplasia). Weight, height, BMI, PSA (prostate specific antigen), Free PSA, age, prostate volume, density, smoking, systolic, diastolic, pulse, and Gleason score features were used and independent sample t-test was applied for feature selection. In order to classify related data, we have used following classifiers; scaled conjugate gradient (SCG), Broyden–Fletcher–Goldfarb–Shanno (BFGS), and Levenberg–Marquardt (LM) training algorithms of artificial neural networks (ANN) and linear, polynomial, and radial based kernel functions of support vector machine (SVM). It was determined that smoking is a factor increases the prostate cancer risk whereas BMI is not affected the prostate cancer. Since PSA, volume, density, and smoking features were to be statistically significant, they were chosen for classification. The proposed system was designed with polynomial based kernel function, which had the best performance (accuracy: 79%). In Turkish Family Health System, family physician to whom patients are applied firstly, would contribute to extract the risk map of illness and direct patients to correct treatments by using expert system such proposed.     

Effect of combined application of plant extract and vacuum packaged treatment on the quality of hot smoked rainbow trout

The effect of plant extract (bay leaf, rosemary, black cumin seed and lemon oil) treatment on the shelf life of vacuum-packaged fish was studied. Hot smoked rainbow trout was treated with 1 % plant extracts, and their shelf lives were compared with those of control (only vacuum packaged) samples. Samples were stored at 2 °C and sensory evaluation as well as chemical and microbiological analyses were conducted weekly. The control group was spoiled after four weeks of storage. In contrast the addition of plant extracts decreased microbiological activity. The results obtained from this study showed that the shelf life of hot smoked trout stored in cold storage (+2 °C), as determined by overall acceptability of all data, was 6 weeks for rosemary, black cumin seed, and lemon oil treatment plus vacuum packaged fish and 7 weeks for bay leaf oil treatment plus vacuum packaged smoked fish.     

Single-step ahead prediction based on the principle of concatenation using grey predictors

In literature a number of different methods are proposed to improve the prediction accuracy of grey models. However, most of them are computationally expensive, and this may prohibit their extensive use. This paper describes a much simpler scheme, based on the principle of concatenation, in which unit step predictions are concatenated by replacing the missing outputs by their previously predicted values. Despite its extreme simplicity, it is shown that the predicted values thus derived results in a better performance than the methods proposed in the literature. Simulation studies show the effectiveness of the proposed algorithm when applied to nonlinear function predictions.     

Resistorless floating immittance function simulators employing current controlled conveyors and a grounded capacitor

In this paper, new floating immittance function simulators employing second-generation current controlled conveyors are proposed. The first four of the presented circuits employ only a single grounded capacitor as passive component and can realize either a negative or a positive floating inductor or capacitor. The last two of the proposed circuits do not employ passive components and can realize either negative or positive floating resistances. All of the proposed circuits do not require passive element matching. As an application, a third-order butterworth filter is realized using the proposed positive floating inductance simulator. SPICE simulation results and large signal behavior of the filter are included.     

All‐pass sections with rich cascadability and IC realization suitability

In this paper, two new circuit configurations for realizing voltage‐mode (VM) all‐pass sections (APSs) are presented. The proposed circuits employ only two differential voltage current conveyors (DVCCs) and are cascadable with other VM circuits due to their high‐input and low‐output impedances. The first configuration uses a grounded resistor and a grounded capacitor without requiring matching constraints, whereas the second employs two grounded resistors and a grounded capacitor with a single matching condition. While the first configuration can realize only one all‐pass response, the second can provide inverting and non‐inverting all‐pass responses with selection of appropriate input port. Adding two grounded resistors to the proposed filters, variable gain APSs can also be obtained. As applications, two quadrature oscillators, each of which using one of the proposed all‐pass circuits, one grounded resistor and one grounded capacitor are presented. SPICE simulation results are included to verify the theory. Copyright © 2010 John Wiley & Sons, Ltd.     

基于凝结水变负荷技术的深度滑压节能控制

针对发电机组的一次调频和自动发电控制(AGC)的负荷控制品质与稳定低节流损失运行的机组节能需求产生矛盾的问题,以及现有凝结水变负荷技术和滑压优化技术的局限性,提出了基于凝结水变负荷技术的深度滑压节能控制策略,通过凝结水变负荷提高机组响应电网一次调频和AGC指令的能力,从而实现机组的最优滑压运行。以某亚临界350 MW机组为例,对基于凝结水变负荷技术的深度滑压节能控制策略进行了可行性和有效性验证。结果表明,机组在达到电网考核指标的前提下实现了深度滑压节能自动控制,节流损失大幅降低,每台机组年平均可节约煤耗1.13g/(kW·h),按煤价600元/t计算,每年可节约62.2万元,节能效果显著。同时,缓解了长期存在的电网一次调频和AGC考核与机组节能运行的矛盾。     

Comparison of the mechanical and biological properties of self-adhering materials

Purpose: The purpose of the present study was to compare the Vickers hardness numbers (VHNs), roughness numbers (RNs) and biological compatibility of glass carbomer (Glass Fill), resin-modified glass ionomer (Fuji II LC) and self-adhering flowable composite (Vertise Flow) materials. Materials and methods: Disc-shaped specimens of test materials (n = 15/group) were prepared, and VHNs and RNs were determined after 24 h. A direct contact test was used for cytotoxicity evaluation. Cell viability was measured for 24 h post-exposition with a photometric test (MTT assay; n = 16). Data were analysed using one-way analysis of variance with a post hoc Tukey’s test, the Kruskal–Wallis test and the Mann–Whitney U-test (p < 0.05). Results: Fuji II LC had the highest VHN. The VHN of Fuji II LC differed significantly from those of the other materials (p < 0.05). The RNs of Fuji II and Glass Fill were higher than that of Vertise Flow (p < 0.05). The self-adhering materials were not significantly cytotoxic compared with the control group (p > 0.05). Conclusions: The materials tested in this study showed a similar lack of cytotoxicity. The VHN of Fuji II LC was the highest, and the RN of Vertise Flow was the lowest.     

Numerical treatment of a quasilinear initial value problem with boundary layer

The paper deals with the singularly perturbed quasilinear initial value problem exhibiting initial layer. First the nature of solution of differential problem before presenting method for its numerical solution is discussed. The numerical solution of the problem is performed with the use of a finite-fitted difference scheme on an appropriate piecewise uniform mesh (Shishkin-type mesh). An error analysis shows that the method is first-order convergent except for a logarithmic factor, in the discrete maximum norm, independently of the perturbation parameter. Finally, numerical results supporting the theory are presented.     

Faster RRT-based Nonholonomic Path Planning in 2D Building Environments Using Skeleton-constrained Path Biasing

This paper presents a faster RRT-based path planning approach for regular 2-dimensional (2D) building environments. To minimize the planning time, we adopt the idea of biasing the RRT tree-growth in more focused ways. We propose to calculate the skeleton of the 2D environment first, then connect a geometrical path on the skeleton, and grow the RRT tree via the seeds generated locally along this path. We conduct batched simulations to find the universal parameters in manipulating the seeds generation. We show that the proposed skeleton-biased locally-seeded RRT (skilled-RRT) is faster than the other baseline planners (RRT, RRT*, A*-RRT, Theta*-RRT, and MARRT) through experimental tests using different vehicles in different 2D building environments. Given mild assumptions of the 2D environments, we prove that the proposed approach is probabilistically complete. We also present an application of the skilled-RRT for unmanned ground vehicle. Compared to the other baseline algorithms (Theta*-RRT and MARRT), we show the applicability and fast planning of the skilled-RRT in real environment.     

Classification of physiological disorders in apples fruit using a hybrid model based on convolutional neural network and machine learning methods

Neural Computing and Applications - Physiological disorders in apples are due to post-harvest conditions. For this reason, automatic identification of physiological disorders is important in...