Motion Artifact Detection and Reduction in Bed-Based Ballistocardiogram

Alivar, Alaleh; Carlson, Charles; Suliman, Ahmad; Warren, Steve; Prakash, Punit; Thompson, David E.; Natarajan, Balasubramaniam

doi:10.1109/access.2019.2894115

Cited by 15 publications

(6 citation statements)

References 36 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sensors for BCG are diverse, including bed-based EMFi film sensors [120,121], bedbased loadcell sensors [122], bed-based hydraulic sensors [123], scale-based sensors [124], PVDF sensors [125,126], etc. Accelerometer-based BCG measurements can be acquired by inserting a micro-electro-mechanical system (MEMS) accelerometer into a chair [118] or by attaching one to the center of mass (CoM) of the human body [127].…”

Section: Instrumentationmentioning

confidence: 99%

“…Yu et al [133] proposed a novel adaptive recursive least squares (ARLS) filter to remove motion artifacts in SCG measurements that were collected during the standing and walking movements of the subjects. Motion artifacts found in bed-based [121] and scale-based [143] BCG measurements were also tackled, where the former detected motion artifacts based on dual thresholds, and the latter added secondary strain gauge sensors to the scale to detect motion artifacts.…”

Section: Signal Processing Approaches To Extract the Hrmentioning

confidence: 99%

See 1 more Smart Citation

An Overview of the Sensors for Heart Rate Monitoring Used in Extramural Applications

Galli

Montree

Que

et al. 2022

Sensors

View full text Add to dashboard Cite

This work presents an overview of the main strategies that have been proposed for non-invasive monitoring of heart rate (HR) in extramural and home settings. We discuss three categories of sensing according to what physiological effect is used to measure the pulsatile activity of the heart, and we focus on an illustrative sensing modality for each of them. Therefore, electrocardiography, photoplethysmography, and mechanocardiography are presented as illustrative modalities to sense electrical activity, mechanical activity, and the peripheral effect of heart activity. In this paper, we describe the physical principles underlying the three categories and the characteristics of the different types of sensors that belong to each class, and we touch upon the most used software strategies that are currently adopted to effectively and reliably extract HR. In addition, we investigate the strengths and weaknesses of each category linked to the different applications in order to provide the reader with guidelines for selecting the most suitable solution according to the requirements and constraints of the application.

show abstract

Section: Instrumentationmentioning

confidence: 99%

Section: Signal Processing Approaches To Extract the Hrmentioning

confidence: 99%

An Overview of the Sensors for Heart Rate Monitoring Used in Extramural Applications

Galli

Montree

Que

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…As mentioned earlier, the results of this study are based on BCGs with no motion artifacts. When processing longer BCG segments, where motion artifacts are unavoidable, an automatic motion detection algorithm such as in [41] may prove useful. The preferred peak-detection method as identified by this work can then be applied to the remaining clean BCG data.…”

Section: H Future Workmentioning

confidence: 99%

Performance Comparison for Ballistocardiogram Peak Detection Methods

et al. 2019

Self Cite

View full text Add to dashboard Cite

A number of research groups have proposed methods for ballistocardiogram (BCG) peak detection toward the identification of individual cardiac cycles. However, objective comparisons of these proposed methods are lacking. This paper, therefore, conducts a systematic and objective performance evaluation and comparison of several of these approaches. Five peak-detection methods (three replicated from the literature and two adapted from code provided by the methods' authors) are compared using data from 30 volunteers. A basic cross-correlation approach was also included as a sixth method. Two high-performing methods were identified: the method proposed by Sadek et al. and the method proposed by Brüser et al. The first achieved the highest average peak-detection rate of 94%, the lowest average false alarm rate of 0.0552 false alarms per second, and a relatively small mean absolute error between the real and detected peaks: 0.0175 seconds. The second method achieved the lowest mean absolute error of 0.0088 seconds between the real and detected peaks, an average peak-detection success rate of 89%, and 0.0766 false alarms per second. All metrics are averaged across participants. INDEX TERMS Ballistocardiogram, heartbeat, heartbeat interval, heart rate, heart rate variability, load cells, statistical signal analysis, wavelets.

show abstract

“…In [4][5][6], MAs are detected by using time measures based on statistical features of the sensor signal (cECG and BCG). Artifact segments are then either discarded or a reduction algorithm is applied.…”

Section: Introductionmentioning

confidence: 99%

Motion Artifact Detection and Classification for Unobtrusive Cardiorespiratory Signals Using Machine Learning

Linschmann¹,

Revander²,

Leonhardt³

et al. 2022

Computing in Cardiology Conference (CinC)

View full text Add to dashboard Cite

For personal health care applications, unobtrusive sensors, such as reflective photoplethysmography (rPPG), capacitive electrocardiography (cECG) or ballistocardiography (BCG), are used with increasing frequency. While these sensors provide more comfort for the user, they exhibit a lower signal-to-noise ratio (SNR) and especially suffer from motion artifacts (MAs). Therefore, methods for reliable detection of MAs as well as their classification in the case of, for example, sleep analysis, are researched. In this paper, support vector machines (SVM) are investigated for the detection and classification of motion artifacts. Two methods for classification with respect to eight classes of movements are presented. First, a direct multi-class classification, and second, a multi-class classification after perfect detection. Waveform-related features are created and used for the training of the SVMs. An openly available dataset (UnoVis data set) which provides nine recordings of six channels of signals with annotations for motion is used. For the binary classification, an accuracy, sensitivity and specificity of 91%, 71%, 97% (test set) and 92%, 73% and 98% (validation set) are achieved respectively. For the direct multi-class classification, the SVM's performance is rather poor with mean accuracies, sensitivities and specificities of 77%, 21% and 93% (test set) and 78%, 28% and 93% (validation set) respectively. Similar results were achieved for perfect prediction.

show abstract

Motion Artifact Detection and Reduction in Bed-Based Ballistocardiogram

Cited by 15 publications

References 36 publications

An Overview of the Sensors for Heart Rate Monitoring Used in Extramural Applications

An Overview of the Sensors for Heart Rate Monitoring Used in Extramural Applications

Performance Comparison for Ballistocardiogram Peak Detection Methods

Motion Artifact Detection and Classification for Unobtrusive Cardiorespiratory Signals Using Machine Learning

Contact Info

Product

Resources

About