Toward breast cancer survivability prediction models through improving training space

Due to the difficulties of outlier and skewed data, the prediction of breast cancer survivability has presented many challenges in the field of data mining and pattern precognition, especially in medical research. To solve these problems, we have proposed a hybrid approach to generating higher quality data sets in the creation of improved breast cancer survival prediction models. This approach comprises two main steps: (1) utilization of an outlier filtering approach based on C-Support Vector Classification (C-SVC) to identify and eliminate outlier instances; and (2) application of an over-sampling approach using over-sampling with replacement to increase the number of instances in the minority class. In order to assess the capability and effectiveness of the proposed approach, several measurement methods including basic performance (e.g., accuracy, sensitivity, and specificity), Area Under the receiver operating characteristic Curve (AUC) and F-measure were utilized. Moreover, a 10-fold cross-validation method was used to reduce the bias and variance of the results of breast cancer survivability prediction models. Results have indicated that the proposed approach leads to improving the performance of breast cancer survivability prediction models by up to 28.34% due to the improved training data space.     

Evaluation of Weighted Impulse Radio for Ultra-Wideband Localization

This research paper presents indoor localization using weighted localization algorithm (WLA) with impulse radio for ultra-windband. The ultra-wide band is wireless technology short range system, especially in, an indoor localization. In this paper, the proposed process consists of two parts: Firstly, a data collected by measurement environment in a Line-of-Sight using impulse radio and secondly extension weighted localization algorithm with wireless ultra-wideband (WUWB) for localization short-range system in an indoor environment. Its can be improve the distance error. The results are evaluated by the cumulative distribution function to check a probability of distance error. The results provided good improvement which increase the wireless indoor localization precision less than 1 m. The proposed WLA for WUWB localization can be used in various applications for the wireless indoor environment.

     

Flower-like microparticles and novel superparamagnetic properties of new binary Co1/2Fe1/2(H2PO4)2·2H2O obtained by a rapid solid state route at ambient temperature

A new binary Co_1/2Fe_1/2(H₂PO₄)₂·2H₂O was synthesized by a simple, rapid and cost-effective method using CoCO₃-Fe(c)-H₃PO₄ system at ambient temperature. Thermal treatment of the obtained Co_1/2Fe_1/2(H₂PO₄)₂·2H₂O at 600 °C yielded as a binary cobalt iron cyclotetraphosphate CoFeP₄O₁₂. The FTIR and XRD results of the synthesized Co_1/2Fe_1/2(H₂PO₄)₂·2H₂O and its final decomposed product CoFeP₄O₁₂ indicate the monoclinic phases with space group P2₁/n and C2/c, respectively. The particle morphologies of both binary metal compounds appear the flower-like microparticle shapes. Room temperature magnetization results show novel superparamagnetic behaviors of the Co_1/2Fe_1/2(H₂PO₄)₂·2H₂O and its final decomposed product CoFeP₄O₁₂, having no hysteresis loops in the range of ±10,000 Oe with the specific magnetization values of 0.045 and 12.502 emu/g at 10 kOe, respectively. The dominant physical properties of the obtained binary metal compounds (Co_1/2Fe_1/2(H₂PO₄)₂·2H₂O and CoFeP₄O₁₂) are compared with the single compounds (M(H₂PO₄)₂·2H₂O and M₂P₄O₁₂; where M = Co, Fe), indicating the presence of Co ions in substitution position of Fe ions.