Automated Machine Learning-Based Gestational Monitoring Framework in Wearable Internet of Things Environment

Recently, Internet of Things (IoT) and wearable technologies have become popular in diverse areas, and smart health is an important application area. Specifically, IoT and wearable technologies find useful in linking different medicinal gadgets, sensors, and physicians in offering better healthcare services in remote areas. It results in enhanced patient safety, minimum healthcare cost, improved healthcare service accessibility, and high operational efficiency in the healthcare sector. At the same time, high-quality care during pregnancy is essential to determine the probable difficulties earlier and guarantee the healthiness of mother as well as fetus. Several research works have been existed in the literature to monitor the maternal lifetime. But they are developed for a particular health issue and based on short-term data collection approaches. Since maternal monitoring necessitates long-term services, this paper designs an automated machine learning-based gestational monitoring framework in wearable IoT environment. The goal of this paper is to derive a new improved salp swarm optimization (ISSO) with extreme learning machine (ELM), called ISSO-ELM model for continual maternal health monitoring. The ISSO-ELM model encompasses different sub-processes namely data acquisition, pre-processing, classification, and parameter optimization. The presented model enables IoT devices and wearables to gather healthcare data about pregnant women. Then, the gathered data are pre-processed to remove the unwanted noise. Besides, the ELM model is employed as a classifier to determine the occurrence of difficulties. Moreover, ISSO algorithm is applied as a parameter tuning technique to optimally adjust the parameters that exist in the ELM model. The extensive experimental analysis highlighted the enhanced performance of the ISSO-ELM model over the recent state-of-art methods with the precision, recall, and accuracy of 94.00, 88.00, and 90.07%.