Tree species classification is important for the management and sustainable development of forest resources. Traditional object-oriented tree species classification methods, such as support vector ...machines, require manual feature selection and generally low accuracy, whereas deep learning technology can automatically extract image features to achieve end-to-end classification. Therefore, a tree classification method based on deep learning is proposed in this study. This method combines the semantic segmentation network U-Net and the feature extraction network ResNet into an improved Res-UNet network, where the convolutional layer of the U-Net network is represented by the residual unit of ResNet, and linear interpolation is used instead of deconvolution in each upsampling layer. At the output of the network, conditional random fields are used for post-processing. This network model is used to perform classification experiments on airborne orthophotos of Nanning Gaofeng Forest Farm in Guangxi, China. The results are then compared with those of U-Net and ResNet networks. The proposed method exhibits higher classification accuracy with an overall classification accuracy of 87%. Thus, the proposed model can effectively implement forest tree species classification and provide new opportunities for tree species classification in southern China.
Detection of RNA-binding proteins (RBPs) is essential since the RNA-binding proteins play critical roles in post-transcriptional regulation and have diverse roles in various biological processes. ...Moreover, identifying RBPs by computational prediction is much more efficient than experimental methods and may have guiding significance on the experiment design.
In this study, we present the RBPPred (an RNA-binding protein predictor), a new method based on the support vector machine, to predict whether a protein binds RNAs, based on a comprehensive feature representation. By integrating the physicochemical properties with the evolutionary information of protein sequences, the new approach RBPPred performed much better than state-of-the-art methods. The results show that RBPPred correctly predicted 83% of 2780 RBPs and 96% out of 7093 non-RBPs with MCC of 0.808 using the 10-fold cross validation. Furthermore, we achieved a sensitivity of 84%, specificity of 97% and MCC of 0.788 on the testing set of human proteome. In addition we tested the capability of RBPPred to identify new RBPs, which further confirmed the practicability and predictability of the method.
RBPPred program can be accessed at: http://rnabinding.com/RBPPred.html .
liushiyong@gmail.com.
Supplementary data are available at Bioinformatics online.
•We examine the ability of six hybrid models in the hindcast and forecast experiments.•Six hybrid models in the hindcast experiment perform better than the original models.•Six hybrid models in the ...forecast experiment perform worse than the original models.•The hybrid models are not suitable for forecasting monthly streamflow in this study.
A number of hydrological studies have proven the superior prediction performance of hybrid models coupled with data preprocessing techniques. However, many studies first decompose the entire data series into components and later divide each component into calibration and validation datasets to establish models, which sends some amount of future information into the decomposition and reconstruction processes. As a consequence, the resulting components used to forecast the value of a particular moment are computed using information from future values, which are not available at that particular moment in a forecasting exercise. Since most papers don’t present their model framework in detail, it is difficult to identify whether they are performing a real forecast or not. Even though several other papers have explicitly stated which experiment they are performing, a comparison between results in the hindcast and forecast experiments is still missing. Therefore, it is necessary to investigate and compare the performance of these hybrid models in the two experiments in order to estimate whether they are suitable for real forecasting. With the combination of three preprocessing techniques, such as wavelet analysis (WA), empirical mode decomposition (EMD) and singular spectrum analysis (SSA), and two modeling methods (i.e. ANN model and ARMA model), six hybrid models are developed in this study, including WA-ANN, WA-ARMA, EMD-ANN, EMD-ARMA, SSA-ANN and SSA-ARMA. Preprocessing techniques are used to decompose the data series into sub-series, and then these sub-series are modeled using ANN and ARMA models. These models are examined in hindcasting and forecasting of the monthly streamflow of two sites in the Yangtze River of China. The results of this study indicate that the six hybrid models perform better in the hindcast experiment compared with the original ANN and ARMA models, while the hybrid models in the forecast experiment perform worse than the original models and the performances of WA-based and EMD-based models vary largely across different extension methods. It can be concluded that the hybrid models are not suitable for monthly streamflow forecasting in this study. New extension methods and modified preprocessing techniques can improve the prediction performance of these hybrid models in forecast experiments.
•Graphene/nano-Au composite was synthesized by electrochemical co-reduction method in one step.•Glucose oxidase achieves direct electrochemistry on the graphene/nano-Au composite film.•The glucose ...biosensor shows a high sensitivity of 56.93μAmM−1cm−2 toward glucose.•Glucose was detected with a wide linear range and low detection limit.
A simple, green and controllable approach was employed for electrochemical synthesize of the graphene/nano-Au composites. The process was that graphene oxide and HAuCl4 was electrochemically co-reduced onto the glassy carbon electrode (GCE) by cyclic voltammetry in one step. The obtained graphene/nano-Au/GCE exhibited high electrocatalytic activity toward H2O2, which resulted in a remarkable decrease in the overpotential of H2O2 electrochemical oxidation compared with bare GCE. Such electrocatalytic behavior of the graphene/nano-Au/GCE permitted effective low-potential amperometric biosensing of glucose via the incorporation of glucose oxidase (GOD) with graphene/nano-Au. An obvious advantage of this enzyme electrode (graphene/nano-Au/GOD/GCE) was that the graphene/nano-Au nanocomposites provided a favorable microenvironment for GOD and facilitated the electron transfer between the active center of GOD and electrode. The immobilized GOD showed a direct, reversible redox reaction. Furthermore, the graphene/nano-Au/GOD/GCE was used as a glucose biosensor, displaying a low detection limit of 17μM (S/N=3), a high sensitivity of 56.93μAmM−1cm−2, acceptable reproducibility, very good stability, selectivity and anti-interference ability.
Display omitted
•1D/2D CdS nanorod@Ti3C2 MXene (CdS@Ti3C2) composite was synthesized.•CdS@Ti3C2 composite exhibits photocatalytic H2 production rate of 63.5276 μmol h−1.•CdS@Ti3C2 composite exhibits ...photocatalytic N2 fixation rate of 293.06 μmol L−1 h−1.•The conductive Ti3C2 MXene can significantly promote electron transfer.•The accordion-like multilayers of CdS@Ti3C2 composite can provide more active sites.
In this study, the unique 1D/2D CdS nanorod@Ti3C2 MXene (CdS@Ti3C2) composites photocatalysts are prepared by a hydrothermal strategy. The suitable band structure and superior electronic reduction capability of CdS in CdS@Ti3C2 composites are achieved, efficiently prolong the light absorption range and enhance photocatalytic performance of CdS. Moreover, Ti3C2 MXene NSs with good electronic transfer capability can prevent photoinduced carrier recombination, and the accordion-like multilayer can provide more reactive sites. The best sample of CdS@Ti3C2 with 15 mg Ti3C2 MXene adding amount exhibits super good photocatalytic H2 evolution rate (63.53 μmol h−1), and photocatalytic nitrogen fixation rate of 293.06 μmol L−1 h−1. The corresponding apparent quantum efficiencies (AQE) are 2.28% and 7.88%, respectively, higher than those of pure CdS NRs and CdS@Pt (0.1 wt%). Besides, CdS@Ti3C2-15 composite shows good long-term stability under simulated sunlight irradiation.
A dual‐phase all‐inorganic composite CsPbBr3‐CsPb2Br5 is developed and applied as the emitting layer in LEDs, which exhibited a maximum luminance of 3853 cd m–2, with current density (CE) of ≈8.98 cd ...A–1 and external quantum efficiency (EQE) of ≈2.21%, respectively. The parasite of secondary phase CsPb2Br5 nanoparticles on the cubic CsPbBr3 nanocrystals could enhance the current efficiency by reducing diffusion length of excitons on one side, and decrease the trap density in the band gap on the other side. In addition, the introduction of CsPb2Br5 nanoparticles could increase the ionic conductivity by reducing the barrier against the electronic and ionic transport, and improve emission lifetime by decreasing nonradiative energy transfer to the trap states via controlling the trap density. The dual‐phase all‐inorganic CsPbBr3‐CsPb2Br5 composite nanocrystals present a new route of perovskite material for advanced light emission applications.
Dual‐phase CsPbBr3‐CsPb2Br5 composites for all‐inorganic perovskite light emitting diodes (LEDs) are fabricated, which exhibit significantly improved performance, representing a great increase in the CE and EQE, about 21‐ and 18‐fold improvement than that of the best reported CsPbBr3 LEDs. The dual‐phase all‐inorganic CsPbBr3‐CsPb2Br5 composite nanocrystals present a new route of perovskite material for advanced light emission applications.
The 21st century is the era of big data in the Internet. Online shopping has become a trend, and e-commerce has developed rapidly. With the exponential increase of the amount of commodity image data, ...the management of massive commodity image database restricts the development of e-commerce to some extent. In order to effectively manage goods and improve the accuracy and efficiency of product image retrieval, this paper uses content-based methods to classify e-commerce images. Aiming at the problems of insufficient classification accuracy and long classification training time in e-commerce image classification, an adaptive momentum learning rate based LBP-DBN training algorithm--AML-LBP-DBN and commodity image classification method based on image local feature multi-level clustering and image-class nearest neighbor classifier are proposed. By simulating the commodity identification dataset RPC, the results show that the proposed method has obvious advantages in the classification training time and classification accuracy of e-commerce images.
The recent progress of indoor organic photovoltaics (IOPVs) is reviewed in this work for abundant low power consumption applications. In recent years, organic solar cells have attracted significant ...attention to harvest solar energy. However, many drawbacks of such as discontinuous adequate sunlight, heat instability, and strong illumination instability inhibit outdoor organic photovoltaic technology from entering solar panel market. As the market of IoT nodes (e.g. sensors, watches, calculators, remote control, hearing aid, and monitors) used in relatively mild indoor environment rapidly grows, the demand for artificial light energy harvesters to supply continuous and cordless power for the indoor environment has emerged. Organic photovoltaic technology for indoor harvesters is one of the reliable candidates because the energy level of organic materials is tunable to match the indoor light source spectra so that its power conversion efficiency (PCE) outweighs that of most of the other indoor harvesters. Indoor organic photovoltaics exhibit the PCE over 30% with an output power of 150 μWcm−2 under the illuminance of artificial lights, which is high enough to drive numerous indoor applications. This review summarizes the performance mechanism of organic photovoltaics (OPVs) when the illuminance is switched from 1-sun to dim light, the research progress for indoor energy transformation, and the viewpoint to speed up the development of IOPVs.
Display omitted
•Recent progress and trends in indoor organic photovoltaics (IOPVs) are discussed.•The mechanism of how to achieve highly efficient IOPVs when the illuminance is switched from 1-sun to dim light.•The method of IOPVs performance characterization is outlined.•Power conversion efficiency (PCE) of IOPV technology outweighs that of all the other types of indoor energy harvester.•A brief summary with current challenges and future perspectives are discussed in order to speed up the development of IOPVs.
Long noncoding RNAs (lncRNAs) are RNAs whose transcripts are longer than 200nt in length and lack the ability to encode proteins due to lack of specific open reading frames. lncRNAs were once thought ...to represent transcriptome noise or garbage sequences and a byproduct of RNA polymerase II (Pol II), and thereby ignored by researchers. In fact, lncRNA was involved in a wide variety of physiological and pathological processes in organisms. Comprehensive study of lncRNA does not only provide explanations to the physiological and pathological processes of living organisms, but also gives us new perspectives to the diagnosis, prevention and treatment of some clinical diseases. Therefore, the study of lncRNA is a very broad field of great research value and significance.
This article reviews the function of lncRNAs and their role in major human diseases.
Numerous studies show that lncRNA might serve as a biomarker for diagnosis and prognosis of various diseases. Compared to conventional biomarkers, lncRNA seems to have a higher diagnostic and prognostic values, not only because of their tissue and disease specific expression patterns, but also due to their highly stable physical and chemical properties.
•A method of extracting tree height using DSM of stereo image and DEM is proposed.•Build different AGB estimation models through incorporation of tree height variable.•The forests AGB estimation ...model with tree height alleviates the saturation problem.
The forest tree height and aboveground biomass (AGB) are important indicators for monitoring changes and trends in forest carbon storage and terrestrial carbon fluxes. Accurate large-scale wall-to-wall mapping of the forest tree height and AGB remain challenging due to the limited data availability for extraction tree height and the data signal saturation problem in AGB estimation. In this study, we explored the potential of forest tree height mapping using stereo imageries, and analyzed whether accounting for such information, in addition to optical sensor data, could improve the performance of AGB estimations of coniferous forests in a case study in North China. First, a spatially continuous tree height product was obtained using Ziyuan-3 satellite (ZY-3) stereo images combined with a digital elevation model (DEM) obtained from Advanced Land Observing Satellite (ALOS) data. Second, two AGB estimation models were established by combining the forest tree height with vegetation index, spectral, biophysical (from Sentinel-2 images), and topographic variables. A random forest algorithm was utilized to evaluate the effect of including the tree height variable in the AGB estimation. The results showed that the tree height estimation using the nadir and forward views of the ZY-3 stereo images was more accurate than that based on the nadir and backward views from the same images. The AGB estimation model incorporating the tree height variable with a coefficient of determination value of 0.7789, a root mean square error (RMSE) value of 29.815 Mg/ha and a relative RMSE of 23.42% was more robust and effective, thereby demonstrating thatthe tree height variable can be used to alleviate the data signal saturation issue successfully. The proposed approach can provide new insight into forest tree height mapping and AGB products obtained from satellite stereo images and freely accessible Sentinel-2 multispectral images.