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.     

A knowledge-based scheduling system for Emergency Departments

A knowledge-based reactive scheduling system is proposed to answer the requirements of Emergency Departments (EDs). The algorithm includes detailed patient priority, arrival time, flow time and doctor load. The main aim is to determine the patients who have higher priorities initially, and then minimize their waiting times. To achieve this aim, physicians and the other related workers can use an interactive system. In this study, we evaluated the existing system by comparing the proposed system. Also, reactive scheduling cases were evaluated for some items such as decreasing the number of doctors, changing durations and entering of an urgent patient to the system. All experiments were performed with proposed algorithm and right shift rescheduling approach.     

Survival of Helicobacter pylori in Turkish fermented sucuk and heat-treated sucuk during production

The aim of this study was to investigate the survival of Helicobacter pylori during production of sucuk (Turkish fermented sausage). The sucuk mixture was inoculated with H. pylori ATCC 43504 to produce a final level in the mixture of ～5 × 10(6) CFU/g. Samples in group I were fermented and dried traditionally at 22°C for 7 days. Samples in groups II and III were subjected to the traditional fermentation at 22°C for 3 days. After fermentation, group II samples were fermented and dried at 35°C for 4 days and group III samples were treated with heat until the core temperature reached 65°C. On the first day of fermentation, a 1-log reduction in H. pylori was found in all groups. The H. pylori levels in all groups increased by about 1 log CFU/g by the third day of fermentation and reached the inoculation level. On the fifth and seventh days of fermentation, no appreciable change occurred in the level of H. pylori in groups I and II. After heat treatment, the H. pylori levels were below the level of detection. These results suggest that H. pylori can grow during sucuk fermentation and that a heat treatment should be used during sucuk processing to destroy H. pylori.     

Application of artificial neural network to estimate power generation and efficiency of a new axial flux permanent magnet synchronous generator

An estimation study on the output power and the efficiency of a new-designed axial flux permanent magnet synchronous generator (AFPMSG) is performed. For the estimation algorithm, a multi-layer feedforward artificial neural network (ANN) is developed. Various experimental results from the generator have been used for the training purpose in the cases of different electrical loads and rotational speeds. Some experimental data is kept out of the training process for testing the network and the errors have been evaluated after the formation of the network. According to the findings, a network with three layers has been adequate to achieve very good error percentage between the ANN and laboratory studies. The maximal testing error percentages are found to be nearly 3% and 4% for the output power and efficiency estimations, respectively. According to that finding, the developed ANN has a good property that it can be used in place of the designed generator, especially when the generator mathematical model is required. In addition, since power and efficiency are important for present applications, the present tool can be used to estimate the data for those characteristics of the machines and even it can be beneficial for the applications, where a nonlinear relationship among the power generation, generator efficiency, speed and load is required.     

Cogging torque reduction by optimal design of PM synchronous generator for wind turbines

In this study, design and optimization of a surface-mounted permanent magnet synchronous generator (PMSG) have been carried out for use in low power wind turbines. In the successive optimization steps based upon the parametric solution method, design parameters of skew, pole embrace, and pole arc offset are chosen to be optimized so that the cogging torque is reduced. Cogging torque is a type of torque ripple coming from the machine design and causes undesired vibration and acoustic noise during the operation of machine. Moreover, although the effect of cogging torque in high power surface-mounted PMSGs is not sensible, it becomes important in low power applications to maintain good dynamical behavior. Analytical and finite element analysis (FEA) are conducted after obtaining the magnet structure that provides minimum cogging torque. Electrical and electromagnetic distributions are presented according to the changes in the corresponding design parameters. While the cogging torque in the initial design is 522.7 mNm, it has been reduced to 49.1 mNm in the optimized generator, which in turn means an improvement of about 90%. The generator under consideration has the specifications of 2.5 kW, 120 V, 14-pole with an inner type-rotor.     

Dielectric Properties of Coronene Film Deposited onto Silicon Substrate by Spin Coating for Optoelectronic Applications

Silicon - To determine the electrical modulus, dielectric properties, and ac conductivity of Coronene semiconductor layer, we have produced Al/Coronene/n-Si structure by using the thermally...     

Dynamic job shop scheduling for missed due date performance

In this research, missed due date in terms of mean absolute lateness (MAL) and mean square lateness (MSL) has been considered as a performance criterion and a scheduling study has been performed to improve the missed due date performance in dynamic, stochastic, multi machine job shop environments. In the study, a new due date assignment model was proposed and a new dynamic dispatching rule was developed. The results indicate that the proposed due date assignment model is very successful for improving the missed due date performance and the developed dispatching rule is also very successful for meeting the assigned due dates.     

Analysis of voltage and frequency-dependent series resistance and interface states of Al/ZnCo2O4: Gelatin/n-Si diode

Journal of Materials Science: Materials in Electronics - In this work, which aims to investigate the capacitance and conductance properties of ZnCo2O4-doped Gelatin, 5% ZnCo2O4-doped Gelatin film...     

Locality of global stochastic interaction in directed acyclic networks

The hypothesis of invariant maximization of interaction (IMI) is formulated within the setting of random fields. According to this hypothesis, learning processes maximize the stochastic interaction of the neurons subject to constraints. We consider the extrinsic constraint in terms of a fixed input distribution on the periphery of the network. Our main intrinsic constraint is given by a directed acyclic network structure. First mathematical results about the strong relation of the local information flow and the global interaction are stated in order to investigate the possibility of controlling IMI optimization in a completely local way. Furthermore, we discuss some relations of this approach to the optimization according to Linsker's Infomax principle.