Photoplethysmograph Signal Reconstruction Based on a Novel Hybrid Motion Artifact Detection–Reduction Approach. Part I: Motion and Noise Artifact Detection

Abstract

Motion and noise artifacts (MNA) are a serious obstacle in utilizing photoplethysmogram (PPG) signals for real-time monitoring of vital signs. We present a MNA detection method which can provide a clean vs. corrupted decision on each successive PPG segment. For motion artifact detection, we compute four time-domain parameters: (1) standard deviation of peak-to-peak intervals (2) standard deviation of peak-to-peak amplitudes (3) standard deviation of systolic and diastolic interval ratios, and (4) mean standard deviation of pulse shape. We have adopted a support vector machine (SVM) which takes these parameters from clean and corrupted PPG signals and builds a decision boundary to classify them. We apply several distinct features of the PPG data to enhance classification performance. The algorithm we developed was verified on PPG data segments recorded by simulation, laboratory-controlled and walking/stair-climbing experiments, respectively, and we compared several well-established MNA detection methods to our proposed algorithm. All compared detection algorithms were evaluated in terms of motion artifact detection accuracy, heart rate (HR) error, and oxygen saturation (SpO2) error. For laboratory controlled finger, forehead recorded PPG data and daily-activity movement data, our proposed algorithm gives 94.4, 93.4, and 93.7% accuracies, respectively. Significant reductions in HR and SpO2 errors (2.3 bpm and 2.7%) were noted when the artifacts that were identified by SVM-MNA were removed from the original signal than without (17.3 bpm and 5.4%). The accuracy and error values of our proposed method were significantly higher and lower, respectively, than all other detection methods. Another advantage of our method is its ability to provide highly accurate onset and offset detection times of MNAs. This capability is important for an automated approach to signal reconstruction of only those data points that need to be reconstructed, which is the subject of the companion paper to this article. Finally, our MNA detection algorithm is real-time realizable as the computational speed on the 7-s PPG data segment was found to be only 7 ms with a Matlab code.

Characterization of Artifact Signals in Neck Photoplethysmography

“…its duration in time units (seconds , which represented the standard deviation of feature values for a rest or artifact interval. As demonstrated in [9], the standard deviation value of time domain features captures the variability of successive poor-quality PPG pulses.…”

“…The variations in vascular volume across the body imply that the AC and DC components are diversely distorted under the same artifact. Unique artifacts can affect particular body parts as, PPG sensors positioned along the arm (including finger, wrist and upper arm) demonstrated to be mainly susceptible to arm movements whereas forehead sensors were not affected by these but by head movements instead ( [8], [9]). Artifacts are also oximetry mode dependent.…”

“…The most critical ones are usually due to motion, and many signal processing techniques have already been proposed in the literature to filter them. These include: discrete wavelet transforms ( [11], [12]), Fourier series analysis [13], adaptive filtering ( [14], [15]), Independent Component Analysis [16] or detection/reduction approaches ( [9], [17], [18]). However, the specificity of artifacts to the site of measurement and the type of sensor, do not make these solutions straightforwardly transferable to other body parts.…”

Real alerts and artifact classification in archived multi-signal vital sign monitoring data: implications for mining big data

“…Adaptive filtering algorithms have been proposed [27-30], along with alert-related filters that recover signals at defined intervals in cases of periodic noise patterns [31, 32], and signal reconstruction [33]. However the problem we seek to address is different as it applies to already collected offline data to be cleaned for mining purposes.…”

A General Applicable Sphygmogram Discriminator for Detecting Arrhythmia & Motion Artifact

“…Consequently, as those amateurish home users couldn't handle and use the monitoring devices expertly, it is Manuscript received August 24, 2015; revised December 4, 2015. necessary to remedy the disadvantages of unintelligent data sampling and lower the operation request and criteria when data is being gathered. Up to now, there are some relevant research achievements including the threshold analysis [4]; the AIR (amplitude/interval ratio) method using the relationship between amplitude and pulse-topulse interval to analyze Electrocardiography (ECG) and PPG signals [5]; similarity analysis of waveform in every cycle [6]; and the Support Vector Machine (SVM) based method to detect and remove the motion and noise systematically and coherently [7]. Unfortunately, these methods [4], [6], [7] focus on removing all looked abnormal waveforms including some important pathological information like arrhythmia shown in Fig.…”