Prenatal anxiety recognition model integrating multimodal physiological signal

Yanchi Bao, Mengru Xue, Jennifer Gohumpu, Yumeng Cao, Shitong Weng, Peidi Fang, Jiang Wu, Bin Yu

Research output: Journal PublicationArticlepeer-review

Abstract

Anxiety among pregnant women can significantly impact their overall well-being. However, the development of data-driven HCI interventions for this demographic is often hindered by data scarcity and collection challenges. In this study, we leverage the Empatica E4 wristband to gather physiological data from pregnant women in both resting and relaxed states. Additionally, we collect subjective reports on their anxiety levels. We integrate features from signals including Blood Volume Pulse (BVP), Skin Temperature (SKT), and Inter-Beat Interval (IBI). Employing a Support Vector Machine (SVM) algorithm, we construct a model capable of evaluating anxiety levels in pregnant women. Our model attains an emotion recognition accuracy of 69.3%, marking achievements in HCI technology tailored for this specific user group. Furthermore, we introduce conceptual ideas for biofeedback on maternal emotions and its interactive mechanism, shedding light on improved monitoring and timely intervention strategies to enhance the emotional health of pregnant women.

Original languageEnglish
Article number21767
JournalScientific Reports
Volume14
Issue number1
DOIs
Publication statusPublished - Dec 2024

Keywords

  • Anxiety model
  • Emotion recognition
  • Feature fusion
  • Multimodal physiological signal
  • Pregnant woman

ASJC Scopus subject areas

  • General

Fingerprint

Dive into the research topics of 'Prenatal anxiety recognition model integrating multimodal physiological signal'. Together they form a unique fingerprint.

Cite this