Recent Studies show exponential growth in heart diseases and cardiac ailments cases endangering the patient’s life. An automated smartphone application can ease symptoms monitoring, medical aids and treatment compliance that usually are challenging and frustrating tasks. In this work, we proposed a stepwise procedure used for the functional development of a smartphone app. To identify a cardiac situation, reliably and accurately understanding the ECG heartbeats is a complex and crucial task. In this process, precise categorization of heartbeats is critically essential. We developed a 26 layered Deep CNN-based model that correctly categorized ECG heartbeats in ‘Normal Beat(Non-Ectopic),’ ‘Supraventricular Ectopic Beat,’ ‘Ventricular Ectopic Beat,’ ‘Fusion Beat’ and ‘Unknown Beat.’ The proposed model is tested on a publicly available MIT-BIH ECG Heartbeat categorization dataset. The test results affirm that the developed method classifies the ECG heartbeats in mentioned five rhythms (classes) by an average accuracy of 98.80 percent. Furthermore, the developed classifier model accomplishes better results in terms of average accuracy while comparing it with recent similar works.
1 October 2020 in International Journal of Wireless Information Networks
Pregnancy-related complications are increasing globally, necessitating timely and accurate risk prediction for effective clinical intervention. This paper presents NurtureNest, an internet of things-enabled machine learning framework for automated pregnancy risk assessment. The system integrates wearable sensor data from smartwatches with user-provided clinical parameters via a mobile application, enabling continuous remote monitoring. Historical clinical data are used to train multiple machine learning models for multi-class classification of pregnancy risk into low-, medium-, and high-risk categories. Ensemble learning techniques are independently trained and evaluated alongside conventional machine learning classifiers to assess their effectiveness in pregnancy risk prediction. Experimental results show that LightGBM achieves the highest performance with 92.86% test accuracy and 95.04% cross-validation accuracy. Model performance is validated using ROC analysis and feature importance evaluation. The proposed framework enables early risk detection and supports timely clinical decision-making, improving maternal healthcare outcomes.