A Pulse Signal Preprocessing Method Based on the Chauvenet Criterion

Abstract

Pulse signals are widely used to evaluate the status of the human cardiovascular, respiratory, and circulatory systems. In the process of being collected, the signals are usually interfered by some factors, such as the spike noise and the poor-sensor-contact noise, which have severely affected the accuracy of the subsequent detection models. In recent years, some methods have been applied to processing the above noisy signals, such as dynamic time warping, empirical mode decomposition, autocorrelation, and cross-correlation. Effective as they are, those methods are complex and difficult to implement. It is also found that the noisy signals are tightly related to gross errors. The Chauvenet criterion, one of the gross error discrimination criterions, is highly efficient and widely applicable for being without the complex calculations like decomposition and reconstruction. Therefore, in this study, based on the Chauvenet criterion, a new pulse signal preprocessing method is proposed, in which adaptive thresholds are designed, respectively, to discriminate the abnormal signals caused by spike noise and poor-sensor-contact noise. 81 hours of pulse signals (with a sleep apnea annotated every 30 seconds and 9,720 segments in total) from the MIT-BIH Polysomnographic Database are used in the study, including 35 minutes of poor-sensor-contact noises and 25 minutes of spike noises. The proposed method was used to preprocess the pulse signals, in which 9,684 segments out of a total of 9,720 were correctly discriminated, and the accuracy of the method reached 99.63%. To quantitatively evaluate the noise removal effect, a simulation experiment is conducted to compare the Jaccard Similarity Coefficient (JSC) calculated before and after the noise removal, respectively, and the results show that the preprocessed signal obtains higher JSC, closer to the reference signal, which indicates that the proposed method can effectively improve the signal quality. In order to evaluate the method, three back-propagation (BP) sleep apnea detection models with the same network structure and parameters were established, respectively. Through comparing the recognition rate and the prediction rate of the models, higher rates were obtained by using the proposed method. To prove the efficiency, the comparison experiment between the proposed Chauvenet-based method and a Romanovsky-based method was conducted, and the execution time of the proposed method is much shorter than that of the Romanovsky method. The results suggest that the superiority in execution time of the Chauvenet-based method becomes more significant as the date size increases.

Integrative population pharmacokinetic/pharmacodynamic analysis of nemonoxacin capsule in Chinese patients with community-acquired pneumonia

“…The inappropriate data were removed in order to improve the robustness of PPK model, such as the data in case of poor subject compliance, mishandling of blood samples, inappropriately higher plasma concentrations or outliers, plasma concentrations lower than LLOQ, significant deviation of plasma concentration at the same time point based on Chauvenet Criterion (data will be removed if it meets the following requirement: |observation -mean| > W n *(standard deviation), where W n is the Chauvenet coefficient. Cumulative normal distribution probability of Chauvenet coefficient is 1-1/(4*n), where n is sample size (Ni et al, 2019)), or abnormal data revealed by diagnostic plot of PPK model, and the absolute value of weighted residual (|WRES|) > 5.…”

Determinantes en la Contratación de Trabajadores para las Empresas Manufactureras Ecuatorianas

“…Posteriormente, se aplicó el criterio de Chauvenet para eliminar los datos atípicos. Este criterio consiste en establecer un rango de probabilidad con todas las muestras de un conjunto de datos, también se especifica el valor medio, en el cual todos los datos fuera del rango se eliminan (Ni et al, 2019). Finalmente, se realizó una revisión exhaustiva de las cuentas para corroborar que los números expuestos tengan concordancia y verificar que existió el mismo número de empresas todos los años.…”

High-Dimensional Feature Space for Diabetes Diagnosis and Identification of Diabetic-Sensitive Features in Ayurvedic Nadi Signals

“…There have been several studies to identify suitable sensor and data collection devices with pressure sensors [4][5][6], piezoelectric sensors [4], optical sensors [5], and condenser microphones [2]. Signal preprocessing steps such as adaptive techniques [9,10], and filter-based methods [11,12] for noise removal, along with denoising and baseline wander removal, have been commonly utilized. Similar to other pulse signals, Nadi pulse segmenting [11,13] and outlier removal steps maximize the information extraction from the collected data.…”

“…A set of time and frequency data was analyzed with Independent Component Analysis(ICA), concluding it has the potential to be used as a classification method for diseases [8]. A two-dimensional feature extraction method that included the within-class information giving periodic and non-periodic features has been tested for diabetic diagnosis [9]. The authors have used a set of ratio-based features in both the time and frequency domains [18,19] for diabetes diagnosis as well.…”

“…A variety of classification methods such as Support Vector Machine (SVM), Wavelet transforms, Autoregressive models, Artificial Neural Networks (ANN) [20,21], and Convolution Neural Networks (CNN) [10] have been used in the diagnosis of conditions such as liver problems [11], diabetes [17,20,21] and pregnancy [9] detection with pulse gathered according to different oriental medicine based pulse acquisition techniques.…”