Enhancing Imbalance Learning: A Novel Slack-Factor Fuzzy SVM Approach

In real-world applications, class-imbalanced datasets pose significant challenges for machine learning algorithms, such as support vector machines (SVMs), particularly in effectively managing imbalance, noise, and outliers. Fuzzy support vector machines (FSVMs) address class imbalance by assigning varying fuzzy memberships to samples; however, their sensitivity to imbalanced datasets can lead to inaccurate assessments. The recently developed slack-factor-based FSVM (SFFSVM) improves traditional FSVMs by using slack factors to adjust fuzzy memberships based on misclassification likelihood, thereby rectifying misclassifications induced by the hyperplane obtained via different error cost (DEC). Building on SFFSVM, we propose an improved slack-factor-based FSVM (ISFFSVM) that introduces a novel location parameter. This novel parameter significantly advances the model by constraining the DEC hyperplane's extension, thereby mitigating the risk of misclassifying minority class samples. It ensures that majority class samples with slack factor scores approaching the location threshold are assigned lower fuzzy memberships, which enhances the model's discrimination capability. Extensive experimentation on a diverse array of real-world KEEL datasets demonstrates that the proposed ISFFSVM consistently achieves higher F1-scores, Matthews correlation coefficients (MCC), and area under the precision-recall curve (AUC-PR) compared to baseline classifiers. Consequently, the introduction of the location parameter, coupled with the slack-factor-based fuzzy membership, enables ISFFSVM to outperform traditional approaches, particularly in scenarios characterized by severe class disparity. The code for the proposed model is available at \url{https://github.com/mtanveer1/ISFFSVM}.

Labour Monitoring in Pregnant Women Using Phonocardiography, Electrocardiography and Electromyography Technique

Continuous monitoring of fetal and maternal vital signs, particularly during labor, can be critical for the child and mother's health. We present a novel wearable electronic system that measures, in real-time, maternal heart rate using phonocardiography (PCG) and Electrocardiography (ECG). Uterine contractions using electromyography (EMG). When in later stages we employed ECG technique for maternal heart rate monitoring. The heart rate is determined using moving average filters to remove noises in the signal and ACF(Autocorrelation Function) for determining periodicity. For UC monitoring we stick to the same EMG technique. We also tried employing EMG technique to monitor the Fetal Heart Rate(FHR). But, in later stages of this design, this idea was aborted as we concluded that it needs further research on pregnancy stages and would require more intricate sensor integration that might not be in our reach at the moment. The system is accurate, low-cost, and portable, so it can be deployed at primary healthcare centers in low-income countries. The system can also be used by women in the comfort of their homes. At the same time, the data collected is transferred to their doctor for analysis and diagnosis, which can bring a revolutionary change in the continuous monitoring of fetal wellbeing during labor.