Training and testing process for the classification of biomedical datasets in machine learning is very important. The researcher should choose carefully the methods that should be used at every step. However, there are very few studies on method choices. The studies in the literature are generally theoretical. Besides, there is no useful model for how to select samples in the training and testing process. Therefore, there is a need for resources in machine learning that discuss the training and testing process in detail and offer new recommendations. This article provides a detailed analysis of the training and testing process in machine learning. The article has the following sections. The third section describes how to prepare the datasets. Four balanced datasets were used for the application. The fourth section describes the rate and how to select samples at the training and testing stage. The fundamental sampling theorem is the subject of statistics. It shows how to select samples. In this article, it has been proposed to use sampling methods in machine learning training and testing process. The fourth section covers the theoretic expression of four different sampling theorems. Besides, the results section has the results of the performance of sampling theorems. The fifth section describes the methods by which training and pretest features can be selected. In the study, three different classifiers control the performance. The results section describes how the results should be analyzed. Additionally, this article proposes performance evaluation methods to evaluate its results. This article examines the effect of the training and testing process on performance in machine learning in detail and proposes the use of sampling theorems for the training and testing process. According to the results, datasets, feature selection algorithms, classifiers, training, and test ratio are the criteria that directly affect performance. However, the methods of selecting samples at the training and testing stages are vital for the system to work correctly. In order to design a stable system, it is recommended that samples should be selected with a stratified systematic sampling theorem.

Sub-synchronous resonance (SSR) phenomenon occurs due to the interaction between wind turbine generators and series-compensated transmission lines. A doubly-fed induction generator (DFIG) is considered one of the most widely implemented generators in wind energy conversion systems. SSR analysis based on the eigenvalue method is the most important among the used methods. The accuracy of the eigenvalue method depends on the initial values of state variables. Previously, the initial values of the state variables were calculated based on the iterative approach which is suffering from convergence problem, lacking accuracy, and requiring a long computation time. Moreover, many steps and details haven't been provided. Consequently, it is urgent to fill this gap and show how can implement the SSR analysis model in detail. In this paper, a new application of a recent analytical approach is proposed for SSR analysis. All information is provided, and the SSR analysis model of a DFIG-based series compensated wind farm is built step-by-step. In order to prove the effectiveness and accuracy of the proposed method, the eigenvalue analysis based on the proposed and iterative methods is compared with the time-domain simulation results at different wind speeds and variable compensation levels. The results prove that the eigenvalue analysis based on the proposed method is more precise, where it is consistent with the simulation results in all studied cases. MATLAB software is used to validate the results.

As synthetic antioxidants that are widely used in foods are known to cause detrimental health effects, studies on natural additives as potential antioxidants are becoming increasingly important. In this work, the total phenolic content (TPC) and antioxidant activity of Ficus carica Linn latex from 18 cultivars were investigated. The TPC of latex was calculated using the Folin–Ciocalteu assay. 1,1-Diphenyl-2-picrylhydrazyl (DPPH), 2,2′-azinobis-(3-ethylbenzothiazoline-6-sulfonic acid) (ABTS) and ferric ion reducing antioxidant power (FRAP) were used for antioxidant activity assessment. The bioactive compounds from F. carica latex were extracted via maceration and ultrasound-assisted extraction (UAE) with 75% ethanol as solvent. Under the same extraction conditions, the latex of cultivar ‘White Genoa’ showed the highest antioxidant activity of 65.91% ± 1.73% and 61.07% ± 1.65% in DPPH, 98.96% ± 1.06% and 83.04% ± 2.16% in ABTS, and 27.08 ± 0.34 and 24.94 ± 0.84 mg TE/g latex in FRAP assay via maceration and UAE, respectively. The TPC of ‘White Genoa’ was 315.26 ± 6.14 and 298.52 ± 9.20 µg GAE/mL via the two extraction methods, respectively. The overall results of this work showed that F. carica latex is a potential natural source of antioxidants. This finding is useful for further advancements in the fields of food supplements, food additives and drug synthesis in the future.

No abstract

No abstract