Research on Multiple Spectral Ranges with Deep Learning for SpO2 Measurement

Oxyhemoglobin saturation by pulse oximetry (SpO2) has always played an important role in the diagnosis of symptoms. Considering that the traditional SpO2 measurement has a certain error due to the number of wavelengths and the algorithm and the wider application of machine learning and spectrum combination, we propose to use 12-wavelength spectral absorption measurement to improve the accuracy of SpO2 measurement. To investigate the multiple spectral regions for deep learning for SpO2 measurement, three datasets for training and verification were built, which were constructed over the spectra of first region, second region, and full region and their sub-regions, respectively. For each region under the procedures of optimization of our model, a thorough of investigation of hyperparameters is proceeded. Additionally, data augmentation is preformed to expand dataset with added noise randomly, increasing the diversity of data and improving the generalization of the neural network. After that, the established dataset is input to a one dimensional convolution neural network (1D-CNN) to obtain a measurement model of SpO2. In order to enhance the model accuracy, GridSearchCV and Bayesian optimization are applied to optimize the hyperparameters. The optimal accuracies of proposed model optimized by GridSearchCV and Bayesian Optimization is 89.3% and 99.4%, respectively, and trained with the dataset at the spectral region of six wavelengths including 650 nm, 680 nm, 730 nm, 760 nm, 810 nm, 860 nm. The total relative error of the best model is only 0.46%, optimized by Bayesian optimization. Although the spectral measurement with more features can improve the resolution ability of the neural network, the results reveal that the training with the dataset of the shorter six wavelength is redundant. This analysis shows that it is very important to construct an effective 1D-CNN model area for spectral measurement using the appropriate spectral ranges and number of wavelengths. It shows that our proposed 1D-CNN model gives a new and feasible approach to measure SpO2 based on multi-wavelength.

Оптические и фотолюминесцентные свойства тонкой пленки оксида цинка на подложке из тантала лития

Presents the results of the study of the structural, optical and photo luminescent properties of the thin films ZnO on LiNbO3 substrate. The results of X-ray structural analysis of a zinc oxide film synthesized on a single-crystal LiTaO3 substrate and on a KU-1 quartz substrate are presented. Present the transmission spectra, reflection spectra and the spectral dependence of zinc oxide thin films on substrate LiTaO3 and the structure of ZnO-SiO2 in the ultraviolet and visible spectral ranges.

Beyond Beer’s Law: Quasi-Ideal Binary Liquid Mixtures

We have recorded attenuated total reflection infrared spectra of binary mixtures in the (quasi-)ideal systems benzene–toluene, benzene–carbon tetrachloride, and benzene–cyclohexane. We used two-dimensional correlation spectroscopy, principal component analysis, and multivariate curve resolution to analyze the data. The 2D correlation proves nonlinearities, also in spectral ranges with no obvious deviations from Beer’s approximation. The number of principal components is much higher than two and multivariate curve resolution carried out under the assumption of the presence of a third component, results in spectra which only show bands of the original components. The results negate the presence of third components, since any complex should have lower symmetry than the individual molecules and thus more and/or different infrared-active bands in the spectra. Based on Lorentz–Lorenz theory and literature values of the optical constants, we show that the nonlinearities and additional principal components are consequences of local field effects and the polarization of matter by light. Lorentz–Lorenz theory is, however, not able to explain, for example, the different blueshifts of the strong A2u band of benzene in the three mixtures. Obviously, infrared spectroscopy is sensitive to the short-range order around the molecules, which changes with content, their shapes, and their anisotropy.

Analysis of the spectral properties of wheat growth in different vegetation periods

The article presents a technique for studying space images based on the analysis of the spectral brightness coefficient (SBC) of space images of the earth's surface. Recognition of plant species, soils, and territories using satellite images is an applied task that allows to implement many processes in agriculture and automate the activities of farmers and large farms. The main tool for analyzing satellite imagery data is the clustering of data that uniquely identifies the desired objects and changes associated with various reasons. Based on the data obtained in the course of experiments on obtaining numerical SBC values, the patterns of behavior of the processes of reflection of vegetation, factors that impede the normal growth of plants, and the proposed clustering of the spectral ranges of wave propagation, which can be used to determine the type of objects under consideration, are revealed. Recognition of these causes through the analysis of SBC satellite images will create an information system for monitoring the state of plants and events to eliminate negative causes. SBC data is divided into non-overlapping ranges, i.e. they form clusters reflecting the normal development of plant species and deviations associated with negative causes. If there are deviations, then there is an algorithm that determines the cause of the deviation and proposes an action plan to eliminate the defect. It should be noted that the distribution of the brightness spectra depends on the climatic and geographical conditions of the plant species and is unique for each region. This study refers to the Akmola region, where grain crops are grown

Hyperspectral Pansharpening in the Reflective Domain with a Second Panchromatic Channel in the SWIR II Spectral Domain

Hyperspectral pansharpening methods in the reflective domain are limited by the large difference between the visible panchromatic (PAN) and hyperspectral (HS) spectral ranges, which notably leads to poor representation of the SWIR (1.0–2.5 μm) spectral domain. A novel instrument concept is proposed in this study, by introducing a second PAN channel in the SWIR II (2.0–2.5 μm) spectral domain. Two extended fusion methods are proposed to process both PAN channels, namely, Gain-2P and CONDOR-2P: the first one is an extended version of the Brovey transform, whereas the second one adds mixed pixel preprocessing steps to Gain-2P. By following an exhaustive performance-assessment protocol including global, refined, and local numerical analyses supplemented by supervised classification, we evaluated the updated methods on peri-urban and urban datasets. The results confirm the significant contribution of the second PAN channel (up to 45% of improvement for both datasets with the mean normalised gap in the reflective domain and 60% in the SWIR domain only) and reveal a clear advantage for CONDOR-2P (as compared with Gain-2P) regarding the peri-urban dataset.

Complex-Coefficient Microwave Photonic Filter Based on Orthogonally Polarized Optical Single-Sideband Modulation

A complex-coefficient microwave photonic filter with continuous tunability is proposed and experimentally demonstrated. The filter taps are based on a 360° tunable microwave photonic phase shifter, which is realized by orthogonally polarized optical single-sideband (OSSB) modulation. The experimental results are shown and regarded as good performance for the proposed filter. The phase shift for the two taps covers a full 360° range from 8 GHz to 26 GHz. Frequency responses with different center frequency are measured within 20–21 GHz with the full free spectral ranges (FSRs) of 185 MHz and 285 MHz, respectively.

High Photoresponse Black Phosphorus TFTs Capping with Transparent Hexagonal Boron Nitride

Black phosphorus (BP), a single elemental two-dimensional (2D) material with a sizable band gap, meets several critical material requirements in the development of future nanoelectronic applications. This work reports the ambipolar characteristics of few-layer BP, induced using 2D transparent hexagonal boron nitride (h-BN) capping. The 2D h-BN capping have several advantages over conventional Al2O3 capping in flexible and transparent 2D device applications. The h-BN capping technique was used to achieve an electron mobility in the BP devices of 73 cm2V−1s−1, thereby demonstrating n-type behavior. The ambipolar BP devices exhibited ultrafast photodetector behavior with a very high photoresponsivity of 1980 mA/W over the ultraviolet (UV), visible, and infrared (IR) spectral ranges. The h-BN capping process offers a feasible approach to fabricating n-type behavior BP semiconductors and high photoresponse BP photodetectors.

Quiet-Filament Eruptions and Coronal Jets as Causes of Depressions in Microwave Radio Emission

Several solar events with different types of negative microwave bursts have been studied using data from different spectral ranges. The total radio flux data obtained at the Ussuriysk Observatory, the Nobeyama Observatory, the US Air Force Radio Solar Telescope Network (RSTN), and the spectropolarimeter of the Institute of Solar–Terrestrial Physics, Siberian Branch of the Russian Academy of Sciences (ISTP SB RAS) were used. The images were analyzed using data from the SDO/AIA space observatory in the 304 Å channel and the Nobeyama radio heliograph at a frequency of 17 GHz. It was shown that the “isolated” depressions of radio emission were caused by the absorption of radiation from radio sources and/or vast regions of the quiet Sun by low-temperature material of a large eruptive filament in the absence of flares. This confirmed the conclusions of the previous studies. It was revealed that the cause of negative bursts of the “pre-burst depression” type was the screening of a near-limb radio source by the material of coronal jets. In the case of a weak flare accompanying the jet, the negative burst could also be of the “isolated” type. A case of a previously unreported occurrence of a deeper depression of radio emission at high frequencies as compared to low frequencies was considered. It was shown that negative bursts are not as rare phenomena as previously thought.