Comparison of Machine Learning Models for Non-invasive Fetal Electrocardiogram Monitoring using Abdominal Leads

• Item type: Symposium(1)
• 公開日: 2024-12-27
• タイトル: Comparison of Machine Learning Models for Non-invasive Fetal Electrocardiogram Monitoring using Abdominal Leads
• タイトル / 言語: en
• タイトル: Comparison of Machine Learning Models for Non-invasive Fetal Electrocardiogram Monitoring using Abdominal Leads
• 言語: eng
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_5794
• 資源タイプ: conference paper
• 著者所属: Department of Computer Engineering, Faculty of Engineering, Khon Kaen University
• 著者所属: Department of Computer, Faculty of Science and Technology, Chiang Mai Rajabhat University
• 著者所属: Department of Computer Engineering, Faculty of Engineering, Khon Kaen University
• 著者所属(英): en
• 著者所属(英): Department of Computer Engineering, Faculty of Engineering, Khon Kaen University
• 著者所属(英): en
• 著者所属(英): Department of Computer, Faculty of Science and Technology, Chiang Mai Rajabhat University
• 著者所属(英): en
• 著者所属(英): Department of Computer Engineering, Faculty of Engineering, Khon Kaen University
• 著者名: Palapon, Soontornpas; Piroon, Kaewfoongrungsri; Daranee, Hormdee
• 著者名(英): Palapon, Soontornpas; Piroon, Kaewfoongrungsri; Daranee, Hormdee
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Fetal electrocardiography (FECG) is a crucial tool for monitoring fetal health, traditionally relying on invasive methods to achieve accurate readings. This paper presents a non-invasive technique for FECG monitoring that utilizes machine learning algorithms to process signals obtained from leads attached to the maternal abdomen. The primary objective is to demonstrate that non-invasive methods can achieve accuracy comparable to that of invasive techniques. By employing signal processing and machine learning models, we extract and enhance FECG signals from maternal abdominal recordings, addressing challenges such as noise and signal overlap. Our results indicate that the proposed non-invasive approach, supported by machine learning, can closely approximate the accuracy of direct invasive FECG monitoring, offering a safer and more comfortable alternative for both mother and fetus. This study highlights the potential for non-invasive FECG monitoring to become a standard practice in prenatal care, reducing the risks associated with invasive procedures while maintaining high diagnostic reliability.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Fetal electrocardiography (FECG) is a crucial tool for monitoring fetal health, traditionally relying on invasive methods to achieve accurate readings. This paper presents a non-invasive technique for FECG monitoring that utilizes machine learning algorithms to process signals obtained from leads attached to the maternal abdomen. The primary objective is to demonstrate that non-invasive methods can achieve accuracy comparable to that of invasive techniques. By employing signal processing and machine learning models, we extract and enhance FECG signals from maternal abdominal recordings, addressing challenges such as noise and signal overlap. Our results indicate that the proposed non-invasive approach, supported by machine learning, can closely approximate the accuracy of direct invasive FECG monitoring, offering a safer and more comfortable alternative for both mother and fetus. This study highlights the potential for non-invasive FECG monitoring to become a standard practice in prenatal care, reducing the risks associated with invasive procedures while maintaining high diagnostic reliability.
• 書誌情報: Proceedings of Asia Pacific Conference on Robot IoT System Development and Platform; 巻 2024, p. 71-72, 発行日 2024-12-27
• 出版者 / 言語: ja
• 出版者: 情報処理学会