Narrow Results

Electrocardiogram (ECG) is a noninvasive, effective and economical biomedical signal that is vital in diagnosing cardiovascular diseases. However, the acquiring process contaminates the ECG signal with several types of noises like Motion Artifacts, Power Line Interference and Baseline Wander. Hence, this paper proposes a new approach to detect and suppress the noises from ECG signals. The complete methodology comprises two stages: noise detection and noise suppression. The former stage applies Improved Complete Ensemble Empirical Mode Decomposition (CEEMD) to decompose the noisy ECG into Intrinsic Mode Functions (IMFs). Next, Maximum Absolute Amplitude (MAA) and Auto-Correlation Maximum Amplitude (AMA) are extracted and used to classify the type of noises from ECG. Then, the noisy ECG segments are processed through the second stage and decomposed into sub-bands through Discrete Wavelet Transform (DWT). Then, the sub-bands are categorized into noise-dominant and signal-dominant frequency bins, and only noise-dominant frequency bins are subjected to noise suppression through a newly proposed adaptive soft thresholding mechanism. The effectiveness of the proposed method is assessed by contaminating the ECG signals acquired from the MIT-BIH arrhythmia database with different noises at different Signal-Noise Ratios (SNRs). Three performance metrics, namely Output SNR, Root Mean Square Error (RMSE) and Pearson Correlation Coefficient (PCC), are employed to explore the superiority of the proposed method over state-of-the-art methods, which considered EMD and CEEMD as decomposition filters. The proposed method improved by an average of 3.5 dB in output SNR and 0.0290 in RMSE.

Due to its non-invasiveness and mobility, photo volumetric tracing (PPG)-based heart rate measurement has drawn a lot of attention. Heart rate is a crucial physiological signal in health monitoring. However, motion artifacts can seriously interfere with PPG signals in a sports setting, which significantly reduces the accuracy of heart rate estimates. This research proposes a hybrid artifact removal (HMR), signal reconstruction (SR), and deep learning (DL)-based heart rate estimate approach (DL$+$HMR$+$SR) to tackle this issue. To effectively analyze complex artifacts in dynamic settings, the technique combines the fine-grained optimization mechanism of signal reconstruction, the artifact separation approach of hybrid artifact removal, and the feature extraction capabilities of deep learning. Six datasets — running, hand waving, elliptical training, deep squatting, mixed motion, and beckoning — are used in this work to validate the method’s performance. It is then compared to several traditional approaches, including RandF, Temko, TROIKA, JOSS, EEMD, and CorNet. In terms of average error, trend matching, and artifact elimination, the experimental results demonstrate that the method in this paper performs better than the current methods. The average error of $2.4\pm 1.3$ BPM is significantly lower than that of the classical methods (the average error of TROIKA is $11.72\pm 15.98$ BPM). The approach presented in this study also shows excellent robustness and application in downstream tasks like emotion recognition, and its average F1 score outperforms that of the other methods under comparison. The findings demonstrate that the $\mathrm{\text{DL}}+\mathrm{\text{HMR}}+\mathrm{\text{SR}}$ technique effectively supports health monitoring in wearable devices due to its excellent generalization ability, high accuracy, and robustness in handling dynamic artifacts. This study establishes the groundwork for future advancements in motion artifact elimination approaches and offers fresh ideas for heart rate estimation solutions.

Quality assessment (QA) of magnetic resonance imaging (MRI) encompasses several factors such as noise, contrast, homogeneity, and imaging artifacts. Quality evaluation is often not standardized and relies on the expertise, and vigilance of the personnel, posing limitations especially with large datasets. Machine learning based on convolutional neural networks (CNNs) is a promising approach to address these challenges by performing automated inspection of MR images. In this study, a CNN for the detection of random head motion artifacts (RHM) in T1-weighted MRI as one aspect of image quality is proposed. A two-step approach aimed to first identify images exhibiting pronounced motion artifacts, and second to evaluate the feasibility of a more detailed three-class classification. The utilized dataset consisted of 420 T1-weighted whole-brain image volumes with isotropic resolution. Human experts assigned each volume to one of three classes of artifact prominence. Results demonstrate an accuracy of 95% for the identification of images with pronounced artifact load. The addition of an intermediate class retained an accuracy of 76%. The findings highlight the potential of CNN-based approaches to increase the efficiency of post-hoc QAs in large datasets by flagging images with potentially relevant artifact loads for closer inspection.

The automatic recognition of QRS complexes in an Electrocardiography (ECG) signal is a critical step in any programmed ECG signal investigation, particularly when the ECG signal taken from the pregnant women additionally contains the signal of the fetus and some motion artifact signals. Separation of ECG signals of mother and fetus and investigation of the cardiac disorders of the mother are demanding tasks, since only one single device is utilized and it gets a blend of different heart beats. In order to resolve such problems we propose a design of new reconfigurable Subtractive Savitzky–Golay (SSG) filter with Digital Processor Back-end (DBE) in this paper. The separation of signals is done using Independent Component Analysis (ICA) algorithm and then the motion artifacts are removed from the extracted mother’s signal. The combinational use of SSG filter and DBE enhances the signal quality and helps in detecting the QRS complex from the ECG signal particularly the R peak accurately. The experimental results of ECG signal analysis show the importance of our proposed method.

ECG signals play a vital role in the diagnosis of cardiovascular conditions. However, they often suffer from the effects of various noise sources, including baseline wandering, respiratory artifact noise, power line interference and electrode motion artifacts. To overcome these challenges, it is imperative to implement low-frequency signal noise reduction strategies. Such strategies aim to significantly improve the quality of ECG signals, thus promoting more accurate and reliable diagnosis of cardiovascular disorders. This paper conducts a comparative analysis to assess the effectiveness of commonly used filtering and wavelet techniques in reducing Baseline Wander (BW) noise within ECG signals generated by the influence of breathing or electrode movements. It is common to observe the selection and evaluation of only one particular technique in the existing literature. In contrast, this study aims to provide a comprehensive comparative analysis, providing insight into the performance and relative merits of different techniques. Our research uses both filtering and Discrete Wavelet Transform (DWT) techniques in baseline noise removal. In this context, a reference point is established utilizing noise-free signals and a meticulous investigation of the wavelet-based approach that most effectively eliminates the resulting noise is provided. Subsequently, we assess the reference input and output signal via Signal-to-Noise Ratio (SNR) and Kolmogorov–Smirnov statistical test measurements. The most important contribution of this work to the scientific community resides in the comprehensive examination of IIR/FIR-based and wavelet method-based filtering methods capable of yielding the highest SNR levels across various ECG signals with various types of BW noise. Additionally, the effectiveness of the Chebychev-II filter in BW noise removal is highlighted. Our study was conducted using the MATLAB platform and code command lines were shared to facilitate the reproduction of our study by other researchers. It is considered that this study will be an important reference in the selection of effective techniques for removing BW noise within ECG signals.

The single-cycle pulse waves’ morphological characteristics can reflect rich physiological and pathological information about the human cardiovascular system, playing an important role in continuous blood pressure monitoring and cardiovascular disease risk warning. Pulse signals belong to weak physiological signals, and the acquisition process is easily affected by factors such as adjacent channel interference and motion artifacts, leading to abnormal cycles and affecting subsequent feature extraction. Therefore, based on support vector machines (SVM), a single-cycle pulse waveform recognition algorithm is proposed. Using a multi-channel pulse wave acquisition device to collect radial artery pulse signals from 150 subjects. Preprocess the signal to obtain a single-cycle pulse waveform. A total of 54 frequency domain and time-frequency domain feature parameters were extracted by using Fourier transform and wavelet transform to extract the frequency domain and time-frequency domain features. Use the principal components analysis (PCA) method to reduce parameter dimensions. Using the SVM for model training to achieve the classification of single-cycle effective pulse signals, pseudo noise and interference signals. The results show that the algorithm’s classification accuracy is 97.42%, indicating that the algorithm can effectively identify pulse signals, pseudo noise and interference signals, laying the foundation for modeling and suppressing interference signals in the next step.

Noninvasive techniques, surface electromyography (sEMG) in particular, are being increasingly employed for assessing muscle activity. In these studies, local oxygen consumption and muscle metabolism are of great interest. Measurements can be performed noninvasively using optics-based methods such as near-infrared spectroscopy (NIRS). By combining energy consumption data provided by NIRS with muscle level activation data from sEMG, we may gain an insight into the metabolic and functional characteristics of muscle tissue. However, muscle motion may induce artifacts into EMG and NIRS. Thus, the inclusion of simultaneous motion measurements using accelerometers (ACMs) enhances possibilities to perceive the effects of motion on NIRS and EMG signals.

This paper reviews the current state of noninvasive EMG and NIRS-based methods used to study muscle function. In addition, we built a combined sEMG/NIRS/ACM sensor to perform simultaneous measurements for static and dynamic exercises of a biceps brachii muscle. Further, we discuss the effect of muscle motion in response of NIRS and EMG when measured noninvasively. Based on our preliminary studies, both NIRS and EMG supply specific information on muscle activation, but their signal responses also showed similarities with acceleration signals which, in this case, were supposed to be solely sensitive to motions.