BackgroundFetal heart rate (FHR) monitoring is a screening tool used by obstetricians to evaluate the fetal state. Because of the complexity and non-linearity, a visual interpretation of FHR signals using common guidelines usually results in significant subjective inter-observer and intra-observer variability. Objective: Therefore, computer aided diagnosis (CAD) systems based on advanced artificial intelligence (AI) technology have recently been developed to assist obstetricians in making objective medical decisions.MethodsIn this work, we present an 8-layer deep convolutional neural network (CNN) framework to automatically predict fetal acidemia. After signal preprocessing, the input 2-dimensional (2D) images are obtained using the continuous wavelet transform (CWT), which provides a better way to observe and capture the hidden characteristic information of the FHR signals in both the time and frequency domains. Unlike the conventional machine learning (ML) approaches, this work does not require the execution of complex feature engineering, i.e., feature extraction and selection. In fact, 2D CNN model can self-learn useful features from the input data with the prerequisite of not losing informative features, representing the tremendous advantage of deep learning (DL) over ML.ResultsBased on the test open-access database (CTU-UHB), after comprehensive experimentation, we achieved better classification performance using the optimal CNN configuration compared to other state-of-the-art methods: the averaged ten-fold cross-validation of the accuracy, sensitivity, specificity, quality index defined as the geometric mean of the sensitivity and specificity, and the area under the curve yielded results of 98.34, 98.22, 94.87, 96.53 and 97.82%, respectivelyConclusionsOnce the proposed CNN model is successfully trained, the corresponding CAD system can be served as an effective tool to predict fetal asphyxia objectively and accurately.

Nanocomposite with a room-temperature ultra-low resistivity far below that of conventional metals like copper is considered as the next generation conductor. However, many technical and scientific problems are encountered in the fabrication of such nanocomposite materials at present. Here, we report the rapid and efficient fabrication and characterization of a novel nitrogen-doped graphene-copper nanocomposite. Silk fibroin was used as a precursor and placed on a copper substrate, followed by the microwave plasma treatment. This resulted nitrogen-doped graphene-copper composite possesses an electrical resistivity of 0.16 µΩ·cm at room temperature, far lower than that of copper. In addition, the composite has superior thermal conductivity (538 W/m·K at 25 °C) which is 138% of copper. The combination of excellent thermal conductivity and ultra-low electrical resistivity opens up potentials in next-generation conductors.

Graphene quantum dots (GQDs) exhibit unique luminescent properties because of quantum confinement and edge effects. However, low quantum yields and tedious multistep processes have limited universal application of GQDs. In this article, we report a novel simple and green method to prepare nitrogen-doped GQDs (N-GQDs) that exhibit excellent photophysical properties. The N-GQDs were synthesized in a one-step process by means of transforming C 60 molecules in a microwave-activated nitrogen plasma process. The as-synthesized N-GQDs were dispersed into graphene sheets, forming composite nanodots with a uniform size distribution. The resulting N-GQDs showed bright blue photoluminescence emission with an excitation-independent behavior. The physical mechanisms responsible for the unique photophysical properties of the N-GQDs were elucidated in the study. The N-GQDs exhibited high sensitivity and selectivity to ferric ion sensing with a limit of detection of 4 × 10 −7 M, which demonstrates the potential to be an excellent nanosensor for ion sensing.

Vertical few-layer graphene (V-FLG) sheet is expected to be a high field emitter due to its electrical properties and open surface with sharp edges. However, the complicated and tedious preparation method using gaseous carbon-containing precursor limited the universal application of V-FLG. This paper reports a novel, simple, and green method to prepare vertical nitrogen-doped few-layer graphene (V-NFLG) on the metal surfaces that exhibit excellent field emission properties. The V-NFLG was grown on a Cu substrate using C60 as a precursor with the help of a nitrogen microwave plasma. Growth and doping mechanisms for the few-layer graphene are suggested based on microwave plasma emission spectra of C60/nitrogen. The as-prepared NFLG exhibits remarkable field emission performance, with a high field enhancement factor (7430 at the high field), a low turn-on field (1.45 V/μm at 10 μA/cm2), and high stability (within ±4%), showing its great potential for field emission applications.

The photoluminescence quantum yield of N-doped carbon dots was brought up to 84% by hybridizing with CdTe QDs.