No abstract

Microarray data is an increasingly important tool for providing information on gene expression for analysis and interpretation. Researchers attempt to utilize the smallest possible set of relevant gene expression profiles in most gene expression studies to enhance tumor identification accuracy. This research aims to analyze and predicts colon cancer data employing a machine learning approach and feature selection technique based on a random forest classifier. More particularly, our proposed method can reduce the burden of high dimensional data and allow faster calculations by combining the "Mean Decrease Accuracy" and "Mean Decrease Gini" as feature selection methods into a renowned classifier namely Random Forest, with the aim of increasing the prediction model's accuracy level. In addition, we have also shown a comparative model analysis with selection of features and model without selection of features. The extensive experimental results have demonstrated that the proposed model with feature selection is favorable and effective which triumphs the best performance of accuracy.

No abstract

The Cardiotocography is the most broadly utilized technique in obstetrics practice to monitor fetal health condition. The foremost motive of monitoring is to detect the fetal hypoxia at early stage. This modality is also widely used to record fetal heart rate and uterine activity. The exact analysis of cardiotocograms is critical for further treatment. In this manner, fetal state evaluation utilizing machine learning technique using cardiotocogram data has achieved significant attention. In this paper, we implement a model based CTG data classification system utilizing a supervised Random Forest (RF) which can classify the CTG data based on its training data. As per the showed up results, the overall performance of the supervised machine learning based classification approach provided significant performance. In this study, Precision, Recall, F-Score and Rand Index has been employed as the metric to evaluate the performance. It was found that, the RF based classifier could identify normal, suspicious and pathologic condition, from the nature of CTG data with 94.8% accuracy.

This paper presents the identification of liquid slosh plant using the Hammerstein model based on modified Sine Cosine Algorithm (mSCA). A remote car that carries a container of liquid is considered as a liquid slosh experimental rig. In contrast to other research works, this paper considers a piece-wise affine function in a nonlinear function of the Hammerstein model, which is more generalized function. Moreover, a continuous-time transfer function is utilized in the Hammerstein model, which is more suitable to represent a real system. The mSCA method is used to tune both coefficients in the nonlinear function and the transfer function of the Hammerstein model such that the error between the identified output and the real experimental output is minimized. The effectiveness of the proposed framework is assessed in terms of the convergence curve response, output response, and the stability of the identified model through the pole-zero map. The results show that the mSCA based method is able to produce a Hammerstein model that yields identified output response closes to the real experimental slosh output with 82.12 % improvement of sum of quadratic error.