Classification is mainly challenged by the problems in the dataset. When dataset have uneven distribution of data among classes, then class imbalance problem arise. Class imbalance with noise creates immense effect on classification of instances of classes. The main focus of this article is to provide the detail comparative analysis of seven Resampling techniques under 16 noisy imbalanced datasets using C4.5 classifier. The performance evaluation is done by using AUC, F1 score, G-mean. Based on the evaluation, article inferred that SMOTE-ENN perform better than rest of resampling techniques.
This research introduces a unique fetal monitoring system grounded in the bioimpedance technique, also recognized as Electrical Impedance Tomography (EIT). The mechanism comprises a phantom, experimental setup, and information acquisition methods, designed to evaluate its capacity via phantom (mother)-based complete evaluations. To validate its effectiveness, a sequence of experiments are performed with the use of diverse phantoms geared up with 8, or 4 electrodes. By making use of EIT current patterns and measuring the ensuing voltage points, the device’s abilities have been assessed. The proposed EIT-based fetal monitoring system achieved accurate impedance measurements with voltage outputs ranging from 0.3 mV to 4.38 mV across various phantoms. EIT gives distinct advantages over traditional imaging modalities, allowing noninvasive monitoring and recording of dispensed electric-powered fields within a closed object. This revolutionary approach is characterized by its person-pleasant interface, affordability, and suitability for mass healthcare applications, making it available to underserved communities and primary healthcare workers.