Scholarlink

<p>Pregnancy care often lacks continuous, personalized monitoring, which can lead to higher rates of cesarean section and preventable complications for both mother and baby. To address these challenges, we propose a federated learning-based pregnancy (FLP) care system, which offers a novel solution by integrating a mobile application with smartwatch technology to promote healthier pregnancy outcomes and support normal deliveries. Through the mobile app, FLP collects patient information, provides personalized exercise and dietary guidance, predicts early labor signs, and builds a supportive user community. The smartwatch, equipped with a fetal heart rate monitoring patch, captures fetal electrocardiogram (ECG) signals to ensure well-being, promptly alerting users to potential concerns. As patient privacy is central to FLP, we employ federated learning so that sensitive health data remain securely on the user’s device. The system’s reliability is reinforced through comprehensive development, including data preprocessing, feature extraction, model training, and validation. Results show that the proposed method has improved accuracy compared to existing methods.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Federated Learning for Pregnancy Care: Smartwatch and Mobile App for Fetal Monitoring and Promoting Normal Deliveries

  • 期刊论文

  • 发表日期：

    2025年7月8日

查看全文
  • V. S. S. L. Deepak Janapa,
  • Nikhil Venkata Satya Sai Sundaraneedi,
  • Purushotham Reddy Tiyyagura,
  • Lakshmi Sai Gayathri Maddu,
  • Sravan Kumar Sikhakolli,
  • Karthikeyan Elumalai,
  • Lakshmi Kuruguntla,
  • Vineela Chandra Dodda

摘要

Pregnancy care often lacks continuous, personalized monitoring, which can lead to higher rates of cesarean section and preventable complications for both mother and baby. To address these challenges, we propose a federated learning-based pregnancy (FLP) care system, which offers a novel solution by integrating a mobile application with smartwatch technology to promote healthier pregnancy outcomes and support normal deliveries. Through the mobile app, FLP collects patient information, provides personalized exercise and dietary guidance, predicts early labor signs, and builds a supportive user community. The smartwatch, equipped with a fetal heart rate monitoring patch, captures fetal electrocardiogram (ECG) signals to ensure well-being, promptly alerting users to potential concerns. As patient privacy is central to FLP, we employ federated learning so that sensitive health data remain securely on the user’s device. The system’s reliability is reinforced through comprehensive development, including data preprocessing, feature extraction, model training, and validation. Results show that the proposed method has improved accuracy compared to existing methods.