A Universal Framework for Extracting Inter-Beat Interval from Heterogeneous Unobtrusive Sensors
Author Information
Author(s): Bai Zhongrui, Wu Pang, Geng Fanglin, Zhang Hao, Chen Xianxiang, Du Lidong, Wang Peng, Li Xiaoran, Fang Zhen, Wu Yirong, Cataldo Andrea, Bayford Richard
Primary Institution: Shanghai Jiao Tong University
Hypothesis
Can heterogeneous sensor fusion improve the accuracy of inter-beat interval extraction?
Conclusion
The proposed HSF-IBI framework enhances the detection rate and accuracy of inter-beat interval extraction from heterogeneous sensors.
Supporting Evidence
- The proposed framework achieved detection rate enhancements of 6.25% and 5.21% on two datasets.
- The mean absolute errors for the proposed framework were 5.25 ms and 4.56 ms on the two datasets.
- The framework successfully integrates data from heterogeneous sensors.
- Results indicate that the proposed method outperforms existing IBI extraction methods.
Takeaway
This study created a new way to measure heartbeats using different types of sensors, making it easier and more accurate to track heart health without needing to wear anything.
Methodology
The study used a novel framework combining template matching, harmonic summation, and signal quality index to extract inter-beat intervals from data collected by various unobtrusive sensors.
Potential Biases
The integration of multiple channels increases computational demands, which may introduce biases in real-time applications.
Limitations
The study primarily involved healthy young participants in controlled settings, which may limit the generalizability of the findings.
Participant Demographics
19 healthy participants in Dataset A and 34 healthy participants in Dataset B.
Statistical Information
P-Value
p<0.05
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website