Low-quality Signals Research Articles

DEVELOPMENT OF SEISMIC METHODS FOR MONITORING THE GEOMECHANICAL CONDITION OF THE SAYANO-SHUSHENSKAYA HPP

Records obtained at seismological stations contain information not only about earthquakes, explosions, but also from various other sources of seismic waves. The sources of such waves can be various buildings and structures that vibrate with their own frequencies. Seismologists can understand the registered wave field, identify the waves from these sources and characterize them. It is possible to implement seismic methods of remote control over changes in the technical condition of various objects. Contemporary hydraulic structures were built a long time ago and aging processes in them lead to destruction of materials and formation of cracks, so these objects require continuous monitoring of their condition. The aim of this work is to investigate the possibility of determining the occurrence of cracks in the body of the dam of the Sayano-Shushenskaya hydroelectric power plant by analyzing its natural frequencies depending on the filling and drawdown of the reservoir. For this purpose, we placed a seismic station several kilometers away from the object of study. With the help of this station, as well as with the help of the seismological data obtained at the seismic station “Cheremushki”, located 4.5 km from the HPP, for 20 years, works were carried out to study the possibility of determining the natural frequencies of the dam with high accuracy when they change in time. The possibility of controlling the physical parameters of structures and operation of various units of the HPP for a long period of time was demonstrated. Examples of determination of frequencies of high- and low-quality signals are considered.

The optimal selection of mother wavelet function for analysis remote photoplethysmographic signals

Analysis of remote photoplethysmography signals is important for non-invasive real-time monitoring of the cardiovascular system. To prevent cardiovascular diseases, it is necessary to predict the disease, support remote medical care and integration with telemedicine. The aim of the work is to analyze the low-quality signal of a remote photoplethysmogram based on a wavelet transformation and selection of the corresponding mother wavelet function. The developed approach provides a wavelet analysis of the remote photoplethysmogram signal by means of the optimal choice of the mother wavelet function, which allows analyzing the cardiovascular system in the frequency-time domain. In accordance with the developed approaches, the approximation of the obtained data to the signals obtained by contact is more than 93% and thus confirms the possibility of using frequency-time signal analysis for remote photoplethysmography. On the basis of the wavelet transform, a principle has been formed that ensures obtaining a true plethysmogram without interference and noise for further study and analysis of the human cardiovascular system.

The Research of Intra-Pulse Modulated Signal Recognition of Radar Emitter under Few-Shot Learning Condition Based on Multimodal Fusion

Radar radiation source recognition is critical for the reliable operation of radar communication systems. However, in increasingly complex electromagnetic environments, traditional identification methods face significant limitations. These methods often struggle with high noise levels and diverse modulation types, making it difficult to maintain accuracy, especially when the Signal-to-Noise Ratio (SNR) is low or the available training data are limited. These difficulties are further intensified by the necessity to generalize in environments characterized by a substantial quantity of noisy, low-quality signal samples while being constrained by a limited number of desirable high-quality training samples. To more effectively address these issues, this paper proposes a novel approach utilizing Model-Agnostic Meta-Learning (MAML) to enhance model adaptability in few-shot learning scenarios, allowing the model to quickly learn with limited data and optimize parameters effectively. Furthermore, a multimodal fusion neural network, DCFANet, is designed, incorporating residual blocks, squeeze and excitation blocks, and a multi-scale CNN, to fuse I/Q waveform data and time–frequency image data for more comprehensive feature extraction. Our model enables more robust signal recognition, even when the signal quality is severely degraded by noise or when only a few examples of a signal type are available. Testing on 13 intra-pulse modulated signals in an Additive White Gaussian Noise (AWGN) environment across SNRs ranging from −20 to 10 dB demonstrated the approach’s effectiveness. Particularly, under a 5−way5−shot setting, the model achieves high classification accuracy even at −10dB SNR. Our research underscores the model’s ability to address the key challenges of radar emitter signal recognition in low-SNR and data-scarce conditions, demonstrating its strong adaptability and effectiveness in complex, real-world electromagnetic environments.

EI-ISOA-VMD: Adaptive denoising and detrending method for nuclear circulating water pump impeller

As a key component of the nuclear circulating water pump, it is difficult to extract effective information from low-quality impeller signal because of the interference noise and non-stationary trend, such as water flow impact, vibrations from unrelated components, and sensor noise. Traditional signal denoising methods, particularly those utilizing variational mode decomposition, often require manual parameter tuning, resulting in unsatisfactory outcome. To address these issues, this paper proposes a signal denoising and detrending method based on the evaluation index driven the improved seagull algorithm optimized for variational mode decomposition (EI-ISOA-VMD). During the optimization process, sinusoidal chaotic mapping is utilized for initializing the seagull population, while a tanh function is employed to design nonlinearly decreasing inertia weights. Furthermore, the Levy flight mechanism enhances the randomness of position updates and optimizes seagull individuals beyond the boundary range in order to form the improved seagull optimization algorithm. The denoising, detrending process, and evaluation index proposed in this paper are utilized as the fitness function for the improved seagull optimization algorithm to optimize key parameters of variational mode decomposition. During the denoising and detrending process, the trend component is initially selected using the mean ratio method. The useful, low noise and high noise intrinsic mode functions are screened by correlation coefficient and weighted permutation entropy. Subsequently, the low noise components are denoised by wavelet thresholding method, and the high noise components are discarded to finally reconstruct the signal. The experimental results demonstrate that the proposed method effectively eliminates noise and trend components in low-quality signal while preserving more valuable information.

A robust gap-filling method for predicting missing observations in daily Black Marble nighttime light data

ABSTRACT Nighttime light (NTL) remote sensing data plays a crucial role in comprehending changes in human activities. The availability of the daily lunar BRDF-corrected Black Marble NTL product (VNP46A2) enables the use of NTL data to detect and assess the impact of short-term emergencies. However, daily NTL data often experience missing values due to cloud cover and low-quality signals. To address this issue, many studies utilize monthly or annual time-composite NTL products, which restrict the timeliness and potential application scenarios of NTL data usage. Therefore, it is necessary to generate the gap-filled daily NTL product. This study presented a novel NTL gap-filling method comprising rough reconstruction based on spatiotemporal weighting and refined gap-filling using a Bidirectional Long Short-Term Memory (Bi-LSTM) model. We evaluate the accuracy of the proposed method using the “remove-reconstruct-compare” approach, which randomly removes some original data from the complete image, fills the gaps with the proposed gap-filling method, and compares the reconstructed NTL data with the original observations in Beijing, Shanghai, Xi’an and New York. The results reveal that when the rate of missing values in Beijing is 40% and 50%, the proposed gap-filling method achieves accuracy with mean coefficient of determination (R2) values of 0.834 and 0.841, accompanied by corresponding root mean square (RMSE) values of 7.793 and 7.171, respectively. Furthermore, the gap-filling accuracy was evaluated quantitatively, and our proposed gap-filling method performed better than the Spatial and Temporal Adaptive Reflectance Fusion Model (STARFM). Our proposed gap-filling method had R2 values of 0.685, 0.781, 0.720 and 0.642, which were higher than those for STARFM (0.430, 0.662, 0.221 and 0.345). The RMSE values of our gap-filling method were 9.628, 12.083, 10.963 and 19.882 for the four sites, while those of STARFM were 12.953, 14.872, 18.280 and 26.990, respectively. The temporal and spatial analysis results demonstrate that this model is robust, capturing city boundaries and NTL high-brightness hotspots with high accuracy and stability. The gap-filling model proposed in this study provides a new technique for expanding the potential applications and reliability of NASA’s daily Black Marble product (VNP46A2) in remote sensing.

A Robust Approach Assisted by Signal Quality Assessment for Fetal Heart Rate Estimation from Doppler Ultrasound Signal.

Fetal heart rate (FHR) monitoring, typically using Doppler ultrasound (DUS) signals, is an important technique for assessing fetal health. In this work, we develop a robust DUS-based FHR estimation approach complemented by DUS signal quality assessment (SQA) based on unsupervised representation learning in response to the drawbacks of previous DUS-based FHR estimation and DUS SQA methods. We improve the existing FHR estimation algorithm based on the autocorrelation function (ACF), which is the most widely used method for estimating FHR from DUS signals. Short-time Fourier transform (STFT) serves as a signal pre-processing technique that allows the extraction of both temporal and spectral information. In addition, we utilize double ACF calculations, employing the first one to determine an appropriate window size and the second one to estimate the FHR within changing windows. This approach enhances the robustness and adaptability of the algorithm. Furthermore, we tackle the challenge of low-quality signals impacting FHR estimation by introducing a DUS SQA method based on unsupervised representation learning. We employ a variational autoencoder (VAE) to train representations of pre-processed fetal DUS data and aggregate them into a signal quality index (SQI) using a self-organizing map (SOM). By incorporating the SQI and Kalman filter (KF), we refine the estimated FHRs, minimizing errors in the estimation process. Experimental results demonstrate that our proposed approach outperforms conventional methods in terms of accuracy and robustness.

Live streaming selling strategies of online retailers with spillover effects

This paper investigates online retailers’ optimal strategies in a highly competitive market where they distribute products via regular selling or live streaming selling with spillover effects, and examines the impacts of these strategies on consumer surplus (CS) and social welfare (SW). Using analytical models, we first explore whether and when two competing online retailers to adopt the live streaming sales strategy in an online market with spillover effects. Furthermore, the implications of their optimal strategies on CS and SW are analyzed. Lastly, we relax our assumptions to consider some general scenarios: (1) When the two online retailers engage in sequential pricing, and (2) when some consumers are time-constrained. The main findings are as follows: (1) Online retailers should sometimes sell their products via live streaming, even though it is more likely to send a low quality signal to consumers. Although the positive spillover effects of other competitors’ live streams are strong, retailers may prefer their competitors to adopt the regular selling mode. (2) CS and SW would be significantly improved by the introduction of the live streaming mode when live streams can greatly enhance consumers’ quality beliefs and their spillover effects are relatively strong but not too strong. (3) Pricing sequences do not affect the optimal live streaming sales strategy, while the presence of time-constrained consumers makes online retailers less likely to sell through live streaming.

Correlation of short-term variation derived from novel ambulatory fetal electrocardiography monitor with computerized cardiotocography.

To compare short-term variation (STV) outputs from a novel self-applied non-invasive fetal electrocardiography (NIFECG) device with those obtained on computerized cardiotocography (cCTG). Technological and algorithmic limitations and mitigation strategies were also evaluated. This was a prospective cohort study of women with a singleton pregnancy over 28 + 0 weeks' gestation attending a tertiary London hospital for cCTG assessment between June 2021 and June 2022. Women underwent concurrent monitoring with both NIFECG and cCTG for up to 1 h. Postprocessing of NIFECG data using various filtering methods produced NIFECG-STV (eSTV) values, which were compared with cCTG-STV (cSTV) outputs. Linear correlation, mean bias, precision and limits of agreement were assessed for STV derived by the different methods of computation and mathematical correction. Overall, 306 concurrent NIFECG and cCTG traces were collected from 285 women. Fully filtered eSTV was correlated very strongly with cSTV (r = 0.911, P < 0.001), but generated results only in 142/306 (46.4%) 1-h traces owing to the removal of traces with lower-quality signals. Partial filtering generated more eSTV data (98.4%), but with a weak correlation with cSTV (r = 0.337, P < 0.001). The difference in STV between the monitors (eSTV-cSTV) increased with signal loss; in traces with > 60% signal loss, the values became highly discrepant. Removal of traces with > 60% signal loss resulted in a stronger correlation with cSTV, while still generating eSTV results for 65% of traces. Correcting these remaining eSTV values for signal loss using linear regression analysis further improved correlation with cSTV (r = 0.839, P < 0.001). The discrepancy between STV computed by NIFECG and cCTG necessitates signal filtering, exclusion of poor-quality traces and eSTV correction. This study demonstrates that, with such correction, NIFECG is able to produce STV values that are strongly correlated with those of cCTG. This evidence base for NIFECG monitoring and interpretation is a promising step forward in the development of safe and effective at-home fetal heart-rate monitoring. © 2023 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Does green transformation trigger green premiums? Evidence from Chinese listed manufacturing firms

To answer the question of whether the green transformation of firms can trigger green premiums plays a pivotal role in achieving the goal of carbon peak and carbon neutrality. By using 1087 manufacturing listed firms in China during 2010 and 2020, we first measure the green transformation degree of firms by extracting keywords from social responsibility reports based on text analysis. Then, the impact of overall green transformation, green strategy transformation and green action transformation on stock returns is explored by applying the fixed-effect panel model. The empirical results show that green transformation can improve stock returns, but in the long term, middle-quality and low-quality signals can be identified, and only high-quality signals can be persistent. Investor confidence instead of profitability of firms can be the influencing mechanism between green transformation and stock returns, and for different firms, the green premium brought by green transformation has heterogeneity.

Deep learning-based middle cerebral artery blood flow abnormality detection using flow velocity waveform derived from transcranial Doppler ultrasound

Since the brain is unlike any other organ in that it cannot store energy and has a high metabolic demand, constant blood flow is essential for healthy brain function. The maximum flow velocity waveform that is produced by transcranial doppler echo ultrasonography has different qualities for a healthy subject and a critically ill patient with conditions such as intraparenchymal or subarachnoid hemorrhage, hydrocephalus, or traumatic brain injury. Depending on the degree of the injury, the symptoms of traumatic brain damage can present themselves right away or not until days or weeks later. To aid in the early and accurate detection of patients with severe brain conditions, a classification system is proposedthat can distinguish between healthy control and patient utilizing the maximum flow velocity waveform derived from Transcranial doppler ultrasound. In this research, we manually labelled the data to remove mediocre and corrupted signals and pre-processed low-quality signals into high-quality ones using a Cycle Generative Adversarial Network (CycleGAN). This study proposes a two-stream deep learning model, DopplerNet2+, based on a Self-organized Operational Neural Network (Self-ONN), which achieves an overall accuracy, precision, recall, sensitivity, f1 score, and specificity of 99.45%, 99.45%, 99.45%, and 99.37% for the classification issue. DopplerNet2+ has a better area under the curve (AUC) of 1.00 and a better Kolmogorov-Smirnov (KS) statistic of 0.996 at the 0.812 thresholds than 11 other Self-ONN models trained with different inputs. The results show that the proposed models can successfully carry out the targeted classification task.

Multi-Boundary Empirical Path Loss Model for 433 MHz WSN in Agriculture Areas Using Fuzzy Linear Regression.

Path loss models are essential tools for estimating expected large-scale signal fading in a specific propagation environment during wireless sensor network (WSN) design and optimization. However, variations in the environment may result in prediction errors due to uncertainty caused by vegetation growth, random obstruction or climate change. This study explores the capability of multi-boundary fuzzy linear regression (MBFLR) to establish uncertainty relationships between related variables for path loss predictions of WSN in agricultural farming. Measurement campaigns along various routes in an agricultural area are conducted to obtain terrain profile data and path losses of radio signals transmitted at 433 MHz. Proposed models are fitted using measured data with "initial membership level" (μAI). The boundaries are extended to cover the uncertainty of the received signal strength indicator (RSSI) and distance relationship. The uncertainty not captured in normal measurement datasets between transmitter and receiving nodes (e.g., tall grass, weed, and moving humans and/or animals) may cause low-quality signal or disconnectivity. The results show the possibility of RSSI data in MBFLR supported at an μAI of 0.4 with root mean square error (RMSE) of 0.8, 1.2, and 2.6 for short grass, tall grass, and people motion, respectively. Breakpoint optimization helps provide prediction accuracy when uncertainty occurs. The proposed model determines the suitable coverage for acceptable signal quality in all environmental situations.

Unsupervised Learning-Based Non-Invasive Fetal ECG Muti-Level Signal Quality Assessment.

To monitor fetal health and growth, fetal heart rate is a critical indicator. The non-invasive fetal electrocardiogram is a widely employed measurement for fetal heart rate estimation, which is extracted from the electrodes placed on the surface of the maternal abdomen. The qualities of the fetal ECG recordings, however, are frequently affected by the noises from various interference sources. In general, the fetal heart rate estimates are unreliable when low-quality fetal ECG signals are used for fetal heart rate estimation, which makes accurate fetal heart rate estimation a challenging task. So, the signal quality assessment for the fetal ECG records is an essential step before fetal heart rate estimation. In other words, some low-quality fetal ECG signal segments are supposed to be detected and removed by utilizing signal quality assessment, so as to improve the accuracy of fetal heart rate estimation. A few supervised learning-based fetal ECG signal quality assessment approaches have been introduced and shown to accurately classify high- and low-quality fetal ECG signal segments, but large fetal ECG datasets with quality annotation are required in these methods. Yet, the labeled fetal ECG datasets are limited. Proposed methods: An unsupervised learning-based multi-level fetal ECG signal quality assessment approach is proposed in this paper for identifying three levels of fetal ECG signal quality. We extracted some features associated with signal quality, including entropy-based features, statistical features, and ECG signal quality indices. Additionally, an autoencoder-based feature is calculated, which is related to the reconstruction error of the spectrograms generated from fetal ECG signal segments. The high-, medium-, and low-quality fetal ECG signal segments are classified by inputting these features into a self-organizing map. The experimental results showed that our proposal achieved a weighted average F1-score of 90% in three-level fetal ECG signal quality classification. Moreover, with the acceptable removal of detected low-quality signal segments, the errors of fetal heart rate estimation were reduced to a certain extent.

A synthetic denoising algorithm for full-waveform induced polarization based on deep learning

Induced polarization (IP) is a widely used geophysical exploration technique. Continuous random noise is one of the most prevalent interferences that can seriously contaminate the IP signal and distort the apparent electrical characteristics. We develop a noise separation algorithm based on deep learning to overcome this issue. The standard IP signals are first produced by combining the Cole-Cole model and Fourier series decomposition, and then the mathematical simulation is used to generate various types of random noise interferences, which are subsequently added to the IP signals. Then, a denoising autoencoder deep neural network structure is built and trained by using noisy signals as input samples and pure signals as output samples. The resulting optimum network is capable of automatically reconstructing a clean IP signal from the noisy input. This network is tested using synthetic data sets. The trained neural network can perform the noise reduction of thousands of survey points in a matter of seconds and reduce signal distortion from approximately 25% to less than 5%. Deep learning-based denoising provides superior computation speed and precision compared with the wavelet denoising and smoothing filtering approach. The data for high-quality signals do not vary considerably before and after noise reduction. The noise interferences are successfully suppressed for low-quality signals. Based on the findings, the denoising autoencoder deep neural network has a promising future for suppressing random noise interferences, which can aid in improving the quality of IP data with high efficiency and precision.

Signal Quality Index for the fetal heart rates: Development and improvements for fetal monitoring

Fetal heart rate (FHR) monitoring is the most widely used tool in clinics to assess fetal health. However, FHR with low-quality signals may somehow exaggerate the risk of the fetus suffering from acidemia, thus contributing to an increase in cesarean section rates. If there is an algorithm capable to identify and reject low-quality signals and then calculate heart rate parameters only on high-quality signals, inappropriate obstetric interventions may be greatly reduced. Currently, only the Signal Quality Index (SQI) is available for adults. When we applied SQI to fetal data, its performance drops dramatically. To fill the gap in the fetal signal quality index, we developed an easy-to-use Fetal heart rate Signal Quality Index (FSQI) in this paper. Firstly, we used a human-in-the-loop strategy to reduce the amount of data annotation effort. Secondly, we developed the FSQI algorithm oriented towards the fetus to identify low-quality signal segments. Further, we proposed a post-processing technique based on fine-grained recognition to identify low-quality signal segments more accurately. Finally, we applied the FSQI algorithm in combination with the existing FHR deceleration event detection algorithm to test the effectiveness of the algorithm. The results showed that the FSQI algorithm we developed achieved an overall accuracy of 99.8842% in signal quality classification, while also eliminating 94.92% of the incorrectly detected deceleration events of current state-of-the-art methods.

A Preliminary Earthquake Detection from The Seismic Temporary Network in The Opak Fault

Microseismic observation is a mandatory tool for analysing and imaging the progress of source earthquake mechanism. The observation of low-quality signal is usually found because of false detection, transient signals by natural noise, or related to seismometer condition and some human activities. Therefore, we try to figure the microseismic phenomenon after major earthquake in the Jogjakarta fault that was generated by an active fault namely Opak Fault. We used the seismic data recording from the seismic project that was installed in 2006 cover the Jogjakarta region. We used one week data to see the potential detection and highlight the possible of positive or negative false detection. With total 16 stations, we got ~500 events in only one week recording. We used a various threshold with 110 to scan all the dataset and we obtained ~450 events with 50-100 events with possible of false positives. Meanwhile, the threshold of 112 has < 50 events that could be suitable with the waveforms. The example results of 120 thresholds figure a strong event that is located by highly resolution of stack coherent from some stations with precise of P and S phase fitting. This study present the first automatic earthquake locations that can provide more detail of seismic structure information in the Jogjakarta region.

How to capitalize on investors by using information presentation and feedback on crowdfunding projects.

As an innovative financing activity, online crowdfunding is characterized by extremely high information asymmetry. To reduce this information asymmetry, crowdfunding companies typically use information presentation, feedback, and other means to convey more information about the fundraising project to investors. Whether the information presentation and feedback affect the investment behavior of nonprofessional ordinary investors is yet to be determined. Moreover, the method by which the information presentation and feedback influence the investment behavior and consequently, the financing performance of crowdfunding companies, has to be identified as well. Currently, research on this subject remains deficient. Therefore, with signal theory and the difference in the cost of information transmission considered, this study classifies the information released by fundraisers on the crowdfunding platform into two categories: low-quality signal and high-quality signal. Projects on the JD.com Crowdfunding website are then used as research samples to explore how the difference in signal quality in the information presentation and feedback of crowdfunding projects influences financing performance from the perspective of investors. The results show that low-quality signals such as video duration, the number of updates, and the number of comments on projects positively affect the success of crowdfunding; meanwhile, crowdfunding experience, which represents high-quality signals, positively moderates the relationship between project video duration, project updates, and crowdfunding success.

Non-invasive Fetal ECG Signal Quality Assessment based on Unsupervised Learning Approach.

The non-invasive fetal electrocardiogram (FECG) derived from abdominal surface electrodes has been widely used for fetal heart rate (FHR) monitoring to assess fetal well-being. However, the accuracy of FECG-based FHR estimation heavily depends on the quality of FECG signal itself, which can generally be affected by several interference sources such as maternal heart activities and fetal movements. Hence, FECG signal quality assessment (SQA) is an essential task to improve the accuracy of FHR estimation by removing or interpolating low-quality FECG signals. In recent research, various SQA methods based on supervised learning have been proposed. Although these methods could perform accurate SQA, they require large labeled datasets. Nevertheless, the labeled datasets for the FECG SQA are very limited. In this paper, to address this limitation, we propose an unsupervised learning-based SQA method for identifying high and low-quality FECG signal segments. Specifically, a fully convolutional network (FCN)-based autoencoder (AE) is trained for reconstructing a spectrogram derived from FECG. An AE-based feature related to reconstruction error is then calculated to identify high and low-quality FECG segments. In addition, entropy-based features, statistical features, and ECG signal quality indices (SQIs) are also extracted. The high and low-quality segments are identified by feeding the extracted features into self-organizing map (SOM). The experimental results showed that our proposal achieved an accuracy of 98% in high and low-quality signal classification.

Photoplethysmography-Based Respiratory Rate Estimation Algorithm for Health Monitoring Applications

PurposeRespiratory rate can provide auxiliary information on the physiological changes within the human body, such as physical and emotional stress. In a clinical setup, the abnormal respiratory rate can be indicative of the deterioration of the patient's condition. Most of the existing algorithms for the estimation of respiratory rate using photoplethysmography (PPG) are sensitive to external noise and may require the selection of certain algorithm-specific parameters, through the trial-and-error method.MethodsThis paper proposes a new algorithm to estimate the respiratory rate using a photoplethysmography sensor signal for health monitoring. The algorithm is resistant to signal loss and can handle low-quality signals from the sensor. It combines selective windowing, preprocessing and signal conditioning, modified Welch filtering and postprocessing to achieve high accuracy and robustness to noise.ResultsThe Mean Absolute Error and the Root Mean Square Error of the proposed algorithm, with the optimal signal window size, are determined to be 2.05 breaths count per minute and 2.47 breaths count per minute, respectively, when tested on a publicly available dataset. These results present a significant improvement in accuracy over previously reported methods. The proposed algorithm achieved comparable results to the existing algorithms in the literature on the BIDMC dataset (containing data of 53 subjects, each recorded for 8 min) for other signal window sizes.ConclusionThe results endorse that integration of the proposed algorithm to a commercially available pulse oximetry device would expand its functionality from the measurement of oxygen saturation level and heart rate to the continuous measurement of the respiratory rate with good efficiency at home and in a clinical setting.

Towards Robust Gesture Recognition by Characterizing the Sensing Quality of WiFi Signals

WiFi-based gesture recognition emerges in recent years and attracts extensive attention from researchers. Recognizing gestures via WiFi signal is feasible because a human gesture introduces a time series of variations to the received raw signal. The major challenge for building a ubiquitous gesture recognition system is that the mapping between each gesture and the series of signal variations is not unique, exact the same gesture but performed at different locations or with different orientations towards the transceivers generates entirely different gesture signals (variations). To remove the location dependency, prior work proposes to use gesture-level location-independent features to characterize the gesture instead of directly matching the signal variation pattern. We observe that gesture-level features cannot fully remove the location dependency since the signal qualities inside each gesture are different and also depends on the location. Therefore, we divide the signal time series of each gesture into segments according to their qualities and propose customized signal processing techniques to handle them separately. To realize this goal, we characterize signal's sensing quality by building a mathematical model that links the gesture signal with the ambient noise, from which we further derive a unique metric i.e., error of dynamic phase index (EDP-index) to quantitatively describe the sensing quality of signal segments of each gesture. We then propose a quality-oriented signal processing framework that maximizes the contribution of the high-quality signal segments and minimizes the impact of low-quality signal segments to improve the performance of gesture recognition applications. We develop a prototype on COTS WiFi devices. The extensive experimental results demonstrate that our system can recognize gestures with an accuracy of more than 94% on average, and significant improvements compared with state-of-arts.

An audio processing pipeline for acquiring diagnostic quality heart sounds via mobile phone

Recently, heart sound signals captured using mobile phones have been employed to develop data-driven heart disease detection systems. Such signals are generally captured in person by trained clinicians who can determine if the recorded heart sounds are of diagnosable quality. However, mobile phones have the potential to support heart health diagnostics, even where access to trained medical professionals is limited. To adopt mobile phones as self-diagnostic tools for the masses, we would need to have a mechanism to automatically establish that heart sounds recorded by non-expert users in uncontrolled conditions have the required quality for diagnostic purposes. This paper proposes a quality assessment and enhancement pipeline for heart sounds captured using mobile phones. The pipeline analyzes a heart sound and determines if it has the required quality for diagnostic tasks. Also, in cases where the quality of the captured signal is below the required threshold, the pipeline can improve the quality by applying quality enhancement algorithms. Using this pipeline, we can also provide feedback to users regarding the cause of low-quality signal capture and guide them towards a successful one. We conducted a survey of a group of thirteen clinicians with auscultation skills and experience. The results of this survey were used to inform and validate the proposed quality assessment and enhancement pipeline. We observed a high level of agreement between the survey results and fundamental design decisions within the proposed pipeline. Also, the results indicate that the proposed pipeline can reduce our dependency on trained clinicians for capture of diagnosable heart sounds.