Fusion Retrieval of Sea Surface Barometric Pressure from the Microwave Humidity and Temperature Sounder and Microwave Temperature Sounder-II Onboard the Fengyun-3 Satellite

Both the Microwave Humidity and Temperature Sounder (MWHTS) and the Microwave Temperature Sounder-II (MWTS-II) operate on the Fengyun-3 (FY-3) satellite platform, which provides an opportunity to retrieve the sea surface barometric pressure (SSP) with high accuracy by fusing the observations from the 60 GHz, 118.75 GHz, and 183.31 GHz channels. The theory of retrieving SSP using passive microwave observations is analyzed, and the sensitivity test experiments of MWHTS and MWTS-II to SSP as well as the test experiments of the contributions of MWHTS and MWTS-II to SSP retrieval are carried out. The theoretical channel combination is established based on the theoretical analysis, and the SSP retrieval experiment is carried out based on the Deep Neural Network (DNN) for the theoretical channel combination. The experimental results show that the retrieval accuracy of SSP using the theoretical channel combination is higher than that of MWHTS or MWTS-II. In addition, based on the test results of the contributions of MWHTS and MWTS-II to the retrieval SSP, the optimal theoretical channel combination can be built, and can further improve the retrieval accuracy of SSP from the theoretical channel combination.

Artificial Intelligence Method of Flow Unit Division Based on Waveform Clustering: A Case Study on Zhetybay Oil Field, South Mangyshalk Basin, Kazakhstan

The Zhetybay Field is located in the South Mangyshlak Sub-basin, a delta front sedimentary reservoir onshore western Kazakhstan. It was discovered in 1961 and first produced by waterflooding in 1967. After more than 50 years of waterflooding development, the reservoirs are generally in the mid-to-high waterflooded stage and oil-water distribution becomes complicated and chaotic. It is very difficult to handle and identify so much logging data by hand since the oilfield has the characteristics of high-density well pattern and contains rich logging information with more than 2000 wells. The wave clustering method is used to divide the sedimentary rhythm of the logging curve. Sedimentary microfacies manifested as a regression sequence, with four types of composite sand bodies including the composite estuary bar and distributary channel combination, the estuary bar connected to the dam edge and the distributing channel combination, the isolated estuary bar and distributing channel combination, and the isolated beach sand. In order to distinguish the flow units, the artificial intelligence algorithm-support vector machine (SVM) method is established by learning the non-linear relationship between flow unit categories and parameters based on developing flow index and reservoir quality factor, summarizing permeability logarithm and porosity degree parameters in the sedimentary facies, and analyzing the production dynamic. The flow units in Zhetybay oilfield were classified into 4 types: A, B1, B2 and B3, and the latter three are the main types. Type A is distributed in the river, type B1 is distributed in the main body of the dam, type B2 is mainly distributed in the main body of the dam, and some of B2 is distributed in the dam edge, and B3 is located in the dam edge, sheet sand and beach sand. The results show that the accuracy of flow unit division by support vector machines reaches 91.1%, which clarifies the distribution law of flow units for oilfield development. This study is one of the significant keys for locating new wells and optimizing the workovers to increase recoverable reserves. It provides an effective guidance for efficient waterflooding in this oilfield.

Remote Blood Oxygen Estimation From Videos Using Neural Networks

<div>Blood oxygen saturation (SpO₂) is an essential indicator of respiratory functionality and is receiving increasing attention during the COVID-19 pandemic. Clinical findings show that it is possible for COVID-19 patients to have significantly low SpO₂ before any obvious symptoms. The prevalence of cameras has motivated researchers to investigate methods for monitoring SpO₂using videos. Most prior schemes involving smartphones are contact-based: They require a fingertip to cover the phone's camera and the nearby light source to capture re-emitted light from the illuminated tissue. In this paper, we propose the first convolutional neural network based noncontact SpO₂ estimation scheme using smartphone cameras. The scheme analyzes the videos of a participant's hand for physiological sensing, which is convenient and comfortable, and can protect their privacy and allow for keeping face masks on.</div><div>We design our neural network architectures inspired by the optophysiological models for SpO₂ measurement and demonstrate the explainability by visualizing the weights for channel combination. Our proposed models outperform the state-of-the-art model that is designed for contact-based SpO₂ measurement, showing the potential of our proposed method to contribute to public health. We also analyze the impact of skin type and the side of a hand on SpO₂ estimation performance.</div>

Remote Blood Oxygen Estimation From Videos Using Neural Networks

<div>Blood oxygen saturation (SpO₂) is an essential indicator of respiratory functionality and is receiving increasing attention during the COVID-19 pandemic. Clinical findings show that it is possible for COVID-19 patients to have significantly low SpO₂ before any obvious symptoms. The prevalence of cameras has motivated researchers to investigate methods for monitoring SpO₂using videos. Most prior schemes involving smartphones are contact-based: They require a fingertip to cover the phone's camera and the nearby light source to capture re-emitted light from the illuminated tissue. In this paper, we propose the first convolutional neural network based noncontact SpO₂ estimation scheme using smartphone cameras. The scheme analyzes the videos of a participant's hand for physiological sensing, which is convenient and comfortable, and can protect their privacy and allow for keeping face masks on.</div><div>We design our neural network architectures inspired by the optophysiological models for SpO₂ measurement and demonstrate the explainability by visualizing the weights for channel combination. Our proposed models outperform the state-of-the-art model that is designed for contact-based SpO₂ measurement, showing the potential of our proposed method to contribute to public health. We also analyze the impact of skin type and the side of a hand on SpO₂ estimation performance.</div>

Flex-Printed Ear-EEG Sensors for Adequate Sleep Staging at Home

A comfortable, discrete and robust recording of the sleep EEG signal at home is a desirable goal but has been difficult to achieve. We investigate how well flex-printed electrodes are suitable for sleep monitoring tasks in a smartphone-based home environment. The cEEGrid ear-EEG sensor has already been tested in the laboratory for measuring night sleep. Here, 10 participants slept at home and were equipped with a cEEGrid and a portable amplifier (mBrainTrain, Serbia). In addition, the EEG of Fpz, EOG_L and EOG_R was recorded. All signals were recorded wirelessly with a smartphone. On average, each participant provided data for M = 7.48 h. An expert sleep scorer created hypnograms and annotated grapho-elements according to AASM based on the EEG of Fpz, EOG_L and EOG_R twice, which served as the baseline agreement for further comparisons. The expert scorer also created hypnograms using bipolar channels based on combinations of cEEGrid channels only, and bipolar cEEGrid channels complemented by EOG channels. A comparison of the hypnograms based on frontal electrodes with the ones based on cEEGrid electrodes (κ = 0.67) and the ones based on cEEGrid complemented by EOG channels (κ = 0.75) both showed a substantial agreement, with the combination including EOG channels showing a significantly better outcome than the one without (p = 0.006). Moreover, signal excerpts of the conventional channels containing grapho-elements were correlated with those of the cEEGrid in order to determine the cEEGrid channel combination that optimally represents the annotated grapho-elements. The results show that the grapho-elements were well-represented by the front-facing electrode combinations. The correlation analysis of the grapho-elements resulted in an average correlation coefficient of 0.65 for the most suitable electrode configuration of the cEEGrid. The results confirm that sleep stages can be identified with electrodes placement around the ear. This opens up opportunities for miniaturized ear-EEG systems that may be self-applied by users.

Evaluating the Observability in the Combination Process of the Height Measurement Signals

In the modern navigation system, the height channel is always the most unstable channel. Combination processing the height measurement signals by using the Kalman filter algorithm can improve the precision of the high measurement. However, in the process of performing the signal processing algorithm by using the Kalman filter, the transition time to obtain the set status is long. Moreover, within different flight conditions, the inertia height meter will be combined with the supporting height meter to get the structure of the combination height meter in order to process the height measurement signals more precisely. In this article, the authors proposed using the criterion for evaluating the observable level to improve the quality of height measurement signal processing. The research results were simulated on three combined high measurements, in which the inertia height meter (IHM) (the basic meter) was combined with one or two supporting height meters (the radio height meter [RHM] and the barometer [AHM]) to show the correctness of the proposed algorithm.