Search

Deep sleep staging networks have reached top performance on large-scale datasets. However, these models perform poorer when training and testing on small sleep cohorts due to data inefficiency. Transferring well-trained models from large-scale datasets (source domain) to small sleep cohorts (target domain) is a promising solution but still remains challenging due to the domain-shift issue. In this work, an unsupervised domain adaptation approach, domain statistics alignment (DSA), is developed to bridge the gap between the data distribution of source and target domains. DSA adapts the source models on the target domain by modulating the domain-specific statistics of deep features stored in the Batch Normalization (BN) layers. Furthermore, we have extended DSA by introducing cross-domain statistics in each BN layer to perform DSA adaptively (AdaDSA). The proposed methods merely need the well-trained source model without access to the source data, which may be proprietary and inaccessible. DSA and AdaDSA are universally applicable to various deep sleep staging networks that have BN layers. We have validated the proposed methods by extensive experiments on two state-of-the-art deep sleep staging networks, DeepSleepNet+ and U-time. The performance was evaluated by conducting various transfer tasks on six sleep databases, including two large-scale databases, MASS and SHHS, as the source domain, four small sleep databases as the target domain. Thereinto, clinical sleep records acquired in Huashan Hospital, Shanghai, were used. The results show that both DSA and AdaDSA could significantly improve the performance of source models on target domains, providing novel insights into the domain generalization problem in sleep staging tasks.

Consumers’ transformers play an important role in power systems, and they are essential for operation reliability and commercial benefits. In the past, maintenance personnel had to spend plenty of time on examining consumers’ transformers one by one. Nowadays, with the wide deployment of power user electric energy data acquire system (PUEEDAS), informative metering data are becoming available, which can be utilized for further condition monitoring. Thus, this paper proposes a data-driven abnormal condition monitoring algorithm of data acquisition for consumers’ transformers, which could timely send abnormal condition alerts to operators and maintenance personnel. In the proposed algorithm, Spearman's rank correlation coefficient is utilized to show the degree of correlation among phase currents, and its t-Statistics is used to determine whether abnormal condition of data acquisition exists based on the hypothesis testing. Finally, actual acquisition data from Zhejiang power system in China are employed to validate the effectiveness of the proposed algorithm, and to analyze the characteristics of normal and abnormal conditions, respectively. Sensitive analyses on different significant levels and sampling rates are performed for considering its impact on monitoring results; the application in real power systems is also given to demonstrate the practicality of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Spatiotemporal data fusion is a methodology to generate images with both high spatial and temporal resolution. Most spatiotemporal data fusion methods generate the fused image at a prediction date based on pairs of input images from other dates. The performance of spatiotemporal data fusion is greatly affected by the selection of the input image pair. There are two criteria for selecting the input image pair: the “similarity” criterion, in which the image at the base date should be as similar as possible to that at the prediction date, and the “consistency” criterion, in which the coarse and fine images at the base date should be consistent in terms of their radiometric characteristics and imaging geometry. Unfortunately, the “consistency” criterion has not been quantitatively considered by previous selection strategies. We thus develop a novel method (called “cross-fusion”) to address the issue of the determination of the base image pair. The new method first chooses several candidate input image pairs according to the “similarity” criterion and then takes the “consistency” criterion into account by employing all of the candidate input image pairs to implement spatiotemporal data fusion between them. We applied the new method to MODIS–Landsat Normalized Difference Vegetation Index (NDVI) data fusion. The results show that the cross-fusion method performs better than four other selection strategies, with lower average absolute difference (AAD) values and higher correlation coefficients in various vegetated regions including a deciduous forest in Northeast China, an evergreen forest in South China, cropland in North China Plain, and grassland in the Tibetan Plateau. We simulated scenarios for the inconsistency between MODIS and Landsat data and found that the simulated inconsistency is successfully quantified by the new method. In addition, the cross-fusion method is less affected by cloud omission errors. The fused NDVI time-series data generated by the new method tracked various vegetation growth trajectories better than previous selection strategies. We expect that the cross-fusion method can advance practical applications of spatiotemporal data fusion technology. [ABSTRACT FROM AUTHOR]

Atmospheric disturbance, sensor malfunctions, and other factors can cause serious gap pixels in the Moderate Resolution Imaging Spectroradiometer (MODIS) normalized difference snow index (NDSI) products. In this article, MODIS NDSI gap pixels are reconstructed in a highly heterogeneous area with drastic snow accumulation and melting changes using a long short-term memory (LSTM) network. Three LSTM-based MODIS NDSI gap pixel reconstruction schemes, i.e., forward, backward, and bidirectional LSTM networks that separately use earlier, subsequent, and integrated earlier and subsequent timestamp information, are developed. NDSI information for the gap pixel is restored using the long-term spatiotemporal information for this pixel and its adjacent pixels. A case study of NDSI reconstruction in the source area of the Yellow River, northwestern China, during the 2018–2019 snow season, demonstrates that all three LSTM-based schemes can reliably generate spatiotemporally continuous NDSI data with an accuracy comparable to that of the original MODIS NDSI products under clear-sky conditions. The bidirectional LSTM-based scheme, which has the best performance, can achieve a desirable overall accuracy of 89.93%, with an omission error of 3.82% and a commission error of 6.25%, in terms of dichotomous evaluation based on in situ snow depth observations. The $R^{2}$ , average RMSE, overestimation error, and underestimation error are 0.95, 5.13%, 5.39, and 6.40%, respectively, in terms of the continuous value assessment based on the gap pixels assumption. Our results demonstrate the reliability and feasibility of the LSTM-based schemes in recovering the missing values in MODIS NDSI products by deeply excavating the spatial continuity and long-time series dependence of the snow cover. [ABSTRACT FROM AUTHOR]

GIS (gas-insulated metal-enclosed switchgear) is one of the important components in modern electrical power systems. Compared with traditional open switching devices, GIS has many advantages such as compact structure, smaller occupied area, little influence from environment as well as safe and reliable operation [1–3]. Statistical data show that equipment failure rate of GIS is only 20%–40% of traditional open switching devices. However, as GIS is designed as a fully enclosed structure, once something goes wrong, the diagnosis process is much more complex and the time necessary for fault repair becomes much longer [4–5]. For instance, a severe short circuit fault occurred in Jiangsu Power Grid, China in 2014 due to the development of cracks on a disc insulator. In the same year, abnormal discharges occurred in GIS substations because of a disconnector fault that led to large economic loss and undesired social impacts. Much work had, therefore, been done on analyzing transient events in gas insulated installations in China and internationally [6–9]. [ABSTRACT FROM AUTHOR]

Short-term load forecasting (STLF) is the basis of power system planning and operation. With regard to the fast-growing load in China, a novel two-stage hybrid forecasting method is proposed in this paper. In the first stage, daily load is forecasted by time-series methods; in the second stage, the deviation caused by time-series methods is forecasted considering the impact of relative factors, and then is added to the result of the first stage. Different from other conventional methods, this paper does an in-depth analysis on the impact of relative factors on the deviation between actual load and the forecasting result of traditional time-series methods. On the basis of this analysis, an adaptive algorithm is proposed to perform the second stage which can be used to choose the most appropriate algorithm among linear regression, quadratic programming, and support vector machine (SVM) according to the characteristic of historical data. These ideas make the forecasting procedure more accurate, adaptive, and effective, comparing with SVM and other prevalent methods. The effectiveness has been demonstrated by the experiments and practical application in China. [ABSTRACT FROM PUBLISHER]

Automatic dialect classification has emerged as an important area in the speech research field. Effective dialect classification is useful in developing robust speech systems, such as speech recognition and speaker identification. In this paper, two novel algorithms are proposed to improve dialect classification for text-independent spontaneous speech in Arabic and Spanish languages, along with probe results for Chinese. The problem considers the case where no transcripts but dialect labels are available for training and test data, and speakers are speaking spontaneously, which is defined as text-independent dialect classification. The Gaussian mixture model (GMM) is used as the baseline system for text-independent dialect classification. The major motivation is to suppress confused/distractive regions from the dialect language space and emphasize discriminative/sensitive information of the available dialects. In the training phase, a symmetric version of the Kullback–Leibler divergence is used to find the most discriminative GMM mixtures (KLD-GMM), where the confused acoustic GMM region is suppressed. For testing, the more discriminative frames are detected and used via the location of where the frames are in the GMM mixture feature space, which is termed frame selection decoding (FSD-GMM). The first KLD-GMM and second FSD-GMM techniques, are shown to improve dialect classification performance for three-way dialect tasks. The two algorithms and their combination are evaluated on dialects of Arabic and Spanish corpora. Measurable improvement is achieved in both two cases, over a generalized maximum-likelihood estimation GMM baseline (MLE-GMM). [ABSTRACT FROM PUBLISHER]

The article describes the use of a digital elevation model (DEM) and geographic information systems (GIS) spatial functions in quantifying mountains in China and their spatial patterns. It states that spatial analysis is a very important function because it differentiates GIS from computer cartography systems. Mountain quantification is reportedly important in developing digital mountains and other information systems. Information on the classification of the mountains is presented.

During the last decade, neural networks have emerged as one of the most powerful and accurate nonlinear models for load forecasting. However, using neural networks requires users to have in-depth knowledge to determine the model structure and parameters, which limits their wide application. To overcome this weakness, this paper proposes an integrated approach which combines a self-organizing fuzzy neural network (SOFNN) learning method with a bilevel optimization method. SOFNNs can automatically determine both the model structure and parameters, while the bilevel optimization method automatically selects the best pre-training parameters to ensure that the best fuzzy neural networks be identified. Therefore, the proposed approach is able to automatically identify the best fuzzy neural network for a given forecasting task and is much easier to use in practice. The proposed approach is tested on real-load data from the Southern Power Network of Hebei Province, China, and on the EUNITE competition data. Results show the proposed approach improves existing load forecasting models. [ABSTRACT FROM AUTHOR]

Defense Meteorological Satellite Program Operational Linescan System (DMSP-OLS) and Suomi National Polar-orbiting Partnership Visible Infrared Imaging Radiometer Suite (SNPP-VIIRS) data are valuable records of nighttime lights (NTLs) in analyzing socioeconomic development. However, inconsistencies between these data have severely restricted long time-series analyses. Published time-series NTL data sets are not widely available or accurate because the DMSP-OLS calibration is inadequate and some missing data in the SNPP-VIIRS data are seldom considered for patching. To address these issues, we calibrated DMSP-OLS data (1992–2013) by using a quadratic model based on a “pseudo-invariant pixel” method. Thereafter, an exponential smoothing model was used to predict and patch missing data in the monthly SNPP-VIIRS data (2013–2019). Outliers and noise were also removed from the annual data. In addition, a sigmoid model was employed to generate improved simulated DMSP-OLS (SDMSP-OLS) data (2013–2019), which were appended with the calibrated DMSP-OLS data (1992–2013) to develop improved DMSP-OLS-like data (1992–2019) in China. Finally, we qualitatively and quantitatively compared these data with published NTL data to examine data availability. Results showed that choosing invariant pixels to calibrate DMSP-OLS data can minimize discontinuity. The correlation between the SNPP-VIIRS data synthesized by the patched monthly SNPP-VIIRS data and the official annual SNPP-VIIRS data in 2015 ($R^{2} =0.931$) and 2016 ($R^{2} =0.930$) was higher than those of the two existing correction methods with $R^{2}$ values below 0.90. Spatial patterns of pixels in the improved SDMSP-OLS data in 2013 were more similar with the DMSP-OLS data than those in the published data. Strong correlations likewise existed between the total (average) pixel values of the improved SDMSP-OLS data (2013–2019) and the DMSP-OLS data in 2012. We also found that the improved DMSP-OLS-like data held strong linear correlations with different statistics, the average $R^{2}$ values of which were 0.931 and 0.654 at the national and provincial levels, respectively. Meanwhile, the average regression $R^{2}$ values between the two published data sets and statistics were 0.858/0.506 and 0.911/0.611, respectively. Our study has proven that the improved DMSP-OLS-like data (1992–2019) have immense potential to effectively evaluate socioeconomic development and anthropic activities. [ABSTRACT FROM AUTHOR]

Precipitable water vapor (PWV) products from the second generation of China’s geostationary meteorological satellite Fengyun-4A (FY-4A) have the advantage of high spatiotemporal resolution and can play an increasingly important role in the study of atmosphere and climate. Using the radiosonde, the global navigation satellite system (GNSS), and the European Centre for Medium-Range Weather Forecasts (ECMWF) ReAnalysis 5 (ERA5) reanalysis data, this study presented a comprehensive evaluation of PWV products from FY-4A for a one-year period from January 2019 to January 2020. Results indicated that FY-4A PWV data have a good agreement with radiosonde and GNSS measured ones with the same correlation coefficient of 0.976, and the root mean square errors (RMSEs) are 3.95 and 3.73 mm, respectively. Compared with the radiosonde and GNSS, the FY-4A Advanced Geostationary Radiation Imager (AGRI) was found to underestimate the water vapor during humid conditions when the PWV is greater than 50 mm. The magnitude of underestimation increases with the growth in water vapor content. In terms of spatial variability, the RMSE of FY-4A PWV decreases with the increase in latitude, while the relative RMSE (R-RMSE) displays an opposite pattern. RMSE from the comparison between FY-4A and ERA5 PWV varies from 0 to 6 mm depending upon the location. Statistics showed that 55.08%, 59.79%, and 83.13% RMSE values are less than 4 mm in the evaluation by radiosonde, GNSS, and ERA5, respectively. The seasonal and diurnal variations of RMSE showed that: 1) summer exhibited larger RMSE than winter and 2) daytime obtained slightly worse performance than nighttime. [ABSTRACT FROM AUTHOR]

A comparative experiment was carried out to discuss the detectability and influence factors on heterogeneous distributions of the stress field for underground panels in North China. The panels are situated in the center and the eastern margin of the North China plate, having similar layouts and stress states. Seismic surveys were performed before coal extractions, and travel-time topographies for refracted P-waves from stiff roofs were computed with a ray-based inversion. The tomographic distributions of P-wave velocity were interpreted by a K-means clustering to categorize the stress fields. The estimated high-stress anomalies show strong correlations with the monitored dynamic roof ruptures and high-energy microseisms. Besides, the relationship among high-stress areas, geological factors, and mined-out voids is also discussed through feature comparisons, Monte–Carlo simulations, and point process statistics. Our results show that the curvature variations and the mined-out voids are dominant factors that affect the heterogeneous distribution of the stress field in the panels. However, the leading causes of the curvature variations in the small-scale panels are different, but they do follow the large-scale regional patterns of the geological regime. [ABSTRACT FROM AUTHOR]

The Chinese GF-1 satellite, the first satellite of the China High-resolution Earth Observation System launched in 2013, can be used to help estimate evapotranspiration (LE), which is important for myriad hydroclimatic and ecosystem science and applications. We propose a novel approach to use the GF-1 visible and near-infrared (VNIR) measurements at 16 m and 4-day resolutions to estimate LE. The NIR (near-infrared)–red spectral-domain (NRSD) model is coupled to a perpendicular soil moisture index (PSI) and a perpendicular vegetation index (PVI). We applied the model to the Huailai agricultural region of China with 55 scenes of GF-1 imagery during 2013–2017 and validated using ground measurements with footprint models for two eddy-covariance (EC) flux tower sites and one large aperture scintillometer (LAS) site. The results illustrate that the terrestrial daily LE can be estimated with squared correlation coefficients (R2) of 0.77–0.84 (p < 0.01) and root-mean-square error (RMSE) values of 17.9–21.5 W/m2 among all three sites. The site-calibrated statistics are improved by 0.14–0.25 for R2 and decreased by 4.2–8.3 W/m2 for RMSE as compared to the commonly used universal PT-JPL model. A satisfactory performance is achieved across all experimental conditions, encouraging the application of the NRSD model to estimate LE for other broad regions. [ABSTRACT FROM AUTHOR]

Accurate land use/land cover (LULC) mapping over a large area is essential to environmentally sustainable development. Recently, the Chinese government established a new national economic zone called the Xiongan New Area, and along with the upcoming large-scale urban construction, this area will inevitably experience a dramatic LULC change, which will threaten the local ecological balance. In this article, we proposed a two-stage approach for LULC mapping in the Xiongan New Area ahead of the forthcoming dense urban construction. The first stage is to obtain base-class maps through a supervised imagery classification. Specifically, we designed a new object-based framework consisting of automatic image segmentation, pixel-based probabilistic estimation, and area-weighted probability statistics for Sentinel-2 multiresolution imagery classification. The second stage is an LULC map refinement process in which the temporal features of each land use category are extracted to refine the LULC classification. Through the implementation of the proposed two-stage approach, an LULC map containing permanent water, temporal water, natural vegetation, barren land, built-up land, and cropland categories can be produced. Through an accuracy assessment, the proposed multiresolution imagery classification method achieved the highest overall accuracy of 88.58% and an average accuracy (AA) of 87.78% compared with conventional classification methods. After obtaining the refined LULC map, we find that the current Xiongan New Area is in a less developed state, that is, cropland accounts for the highest proportion of 51.59%, which is followed by natural vegetation (22.38%) and built-up land (15.69%). [ABSTRACT FROM AUTHOR]

Except for its known aspects of positioning, navigation, and timing (PNT), the Global Navigation Satellite System (GNSS) has extended its application to the rainfall forecasting. GNSS-derived zenith total delay (ZTD) or precipitable water vapor (PWV) has been used as a single factor to predict the occurrence of rainfall; however, the rainfall is highly correlated with myriad atmospheric parameters, which cannot be perfectly reflected by a single predictor. In this article, an improved rainfall forecasting model (IRFM) is proposed to forecast the rainfall. The IRFM considers five predictors: monthly PWV value, seasonal PWV/ZTD variations, and their first derivatives: it can forecast rainfall using a single predicator or an arbitrary combination of those predicators. The merit of IRFM is reducing the false forecasted rainfall (FFR) events and missed detected rainfall (MDR) events as much as possible while guaranteeing the true detected rainfall (TDR) events. An optimized selecting principle of predictors’ threshold has been determined using the percentile method. The test experiment has been performed using five GNSS stations derived from continuously operating reference system (CORS) network of Zhejiang province, China. The analysis reveals that the IRFM considering five predictors provides a better performance than that only using a single predictor or a combination of arbitrary predictors. The statistical result shows the average TDR value of more than 95%, FFR value of less than 30%, and MDR of less than 5%, respectively. Compared to the existing rainfall forecasting methods using ZTD or PWV, the IRFM reduces the FFR and MDR, respectively, with the lowest values, while the TDR value is the highest. [ABSTRACT FROM AUTHOR]

In recent years, bike-sharing systems have been widely deployed in many big cities, which provide an economical and healthy lifestyle. With the prevalence of bike-sharing systems, a lot of companies join the bike-sharing market, leading to increasingly fierce competition. To be competitive, bike-sharing companies and app developers need to make strategic decisions and predict the popularity of bike-sharing apps. However, existing works mostly focus on predicting the popularity of a single app, the popularity contest among different apps has not been explored yet. In this paper, we aim to forecast the popularity contest between Mobike and Ofo, two most popular bike-sharing apps in China. We develop CompetitiveBike, a system to predict the popularity contest among bike-sharing apps leveraging multi-source data. We extract two novel types of features: coarse-grained and fine-grained competitive features, and utilize Random Forest model to forecast the future competitiveness. In addition, we view mobile apps competition as a long-term event and generate the event storyline to enrich our competitive analysis. We collect data about two bike-sharing apps and two food ordering & delivery apps from 11 app stores and Sina Weibo, implement extensive experimental studies, and the results demonstrate the effectiveness and generality of our approach. [ABSTRACT FROM AUTHOR]

An extension of the dynamic capabilities model is evaluated in a rapidly changing and complex context: the global automotive sector. This industry is undergoing significant change to improve sustainable performance (e.g., alternative power train technologies with less pollution and better energy performance) responding to more stringent regulations and changing locus of innovation (i.e., suppliers investing more in R&D). Using a comparative and validated sample of 104 R&D projects in the U.S. and China, five hypotheses are tested and supported: 1) dynamic capabilities are significantly related to R&D project success, mediated by strategic intent (H1); 2) dynamic capabilities and resources operate independently and significantly in a model to predict sustainable R&D project success (H2); 3) for the U.S. data (a mature economy), there is a significant relationship between technology novelty and dynamic capabilities (H3), but not for the Chinese data, as predicted (H4); and 4) the Chinese economy does not experience the slowdown encountered in the U.S. economy (H5), but Chinese R&D is dominated by incremental improvements of existing products. These results sustain and clarify the differences in the dynamic capabilities model in mature and emerging economies for the global automotive industry. [ABSTRACT FROM AUTHOR]

Blockchain can be used to build a peer-to-peer, secure, and smart transaction system. As a horizontal technology that has changed several fields of industry, blockchain has tremendous potential to transform healthcare systems as well. In this article, a systematic review is conducted to critically evaluate 64 articles on blockchain-based healthcare systems, published between 2016 and January 2020 in 21 conferences, 33 journals, and ten online sources. The aim of this article is to answer three main questions. First, what are the applications of blockchain in the healthcare systems, and what are the structures and challenges of applying blockchain to a specific healthcare domain? Second, what are the technical, temporal, and spatial aspects of the currently developed blockchain applications for different healthcare domain? Third, what are the future research directions in designing and implementing blockchain-based healthcare systems? Statistical facts about the technical aspects of these 64 articles show that most of the proposed blockchain-based healthcare systems use private blockchain and Ethereum platforms; furthermore, the majority of the authors are affiliated with research institutions in the USA and China. We also discuss potential future research directions, e.g., integrating the blockchain in artificial intelligence based solutions, cloud-computing-based solutions, and parallel blockchain architecture. [ABSTRACT FROM AUTHOR]

This article develops and tests a primary conceptual model of the direct effects of business environment on supply chain integration (SCI) and an alternative moderation model to better understand the role of the environment in developing integration and financial performance improvement. Structural equation modeling and moderated regression are used to analyze the survey data collected from manufacturing firms in China. The results reveal significant positive relationships between environmental dynamism and all three dimensions of SCI, and between environmental hostility and internal integration. The results also indicate that internal integration fully mediates the relationships between environmental hostility and both customer and supplier integration. Supplier integration is significantly and positively associated with financial performance, whereas internal and customer integration are not significantly associated with performance. Importantly, through the test of an alternative model, environmental hostility and environmental dynamism are shown to affect SCI directly, rather than moderating the SCI-performance relationship. This article provides useful guidelines for managers to develop integrated supply chains to improve the financial performance under dynamic and hostile environments. [ABSTRACT FROM AUTHOR]

Drawing from resource drain theory, this article intends to investigate how and when leader family-to-work conflict (FWC) influences team innovation. We conduct two studies to test our model. In Study 1, we collect cross-sectional data from 107 research and development (R&D) team leaders from an electronic information company in China. In Study 2, we collect multisource and time-lagged data from 112 R&D team leaders and 371 members of a biopharmaceutical firm in China. Our research findings showed that leader FWC negatively affects team innovation via leader creative process engagement. Leader perceived organizational support (POS) alleviates the negative effect of leader FWC on leader creative process engagement. Leader POS also weakens the negative effect of leader FWC on team innovation via leader creative process engagement. We discuss the theoretical and practical implications of these results for team innovation, FWC, and POS. [ABSTRACT FROM AUTHOR]

The rising number of cyberattacks and cybercriminals around the world has put major threats on the cybersecurity and even the national security of many countries. In response, governments started to introduce policies and regulations to improve cybersecurity. It is increasingly realized that effective cybersecurity policy making largely depends upon optimized policy attention and the effective use of public resources. This article draws on the “attention-driven policy choice model” and the punctuated equilibrium theory to analyze the relationship between policy attention allocation, policy agenda setting, and the choice of policy tools in different periods of cybersecurity development. Using Chinese cybersecurity development as the main context, content analysis of policy texts was conducted to examine the pathway of cybersecurity policy development in China between 1994 and 2019. The findings suggest that there is evidence for punctuated equilibrium with policy stagnation and incrementality being broken up by major events which shift policy attention and subsequently affects agenda setting and the choice of policy tools. The findings of this article will provide important implications for the development of strategic foresight of cybersecurity and the effective use of public resources to improve cybersecurity. [ABSTRACT FROM AUTHOR]

Drones, or general UAVs, equipped with cameras have been fast deployed with a wide range of applications, including agriculture, aerial photography, and surveillance. Consequently, automatic understanding of visual data collected from drones becomes highly demanding, bringing computer vision and drones more and more closely. To promote and track the developments of object detection and tracking algorithms, we have organized three challenge workshops in conjunction with ECCV 2018, ICCV 2019 and ECCV 2020, attracting more than 100 teams around the world. We provide a large-scale drone captured dataset, VisDrone, which includes four tracks, i.e., (1) image object detection, (2) video object detection, (3) single object tracking, and (4) multi-object tracking. In this paper, we first present a thorough review of object detection and tracking datasets and benchmarks, and discuss the challenges of collecting large-scale drone-based object detection and tracking datasets with fully manual annotations. After that, we describe our VisDrone dataset, which is captured over various urban/suburban areas of 14 different cities across China from North to South. Being the largest such dataset ever published, VisDrone enables extensive evaluation and investigation of visual analysis algorithms for the drone platform. We provide a detailed analysis of the current state of the field of large-scale object detection and tracking on drones, and conclude the challenge as well as propose future directions. We expect the benchmark largely boost the research and development in video analysis on drone platforms. All the datasets and experimental results can be downloaded from https://github.com/VisDrone/VisDrone-Dataset. [ABSTRACT FROM AUTHOR]

Standards have profound effects on industrial productivity, international trade, and economic growth. For latecomer countries such as China, standards, and standardization are an important means to upgrade their industrial structure. Using the framework of a sectoral system of innovation, this article leverages China's hardware industry to investigate the relationships among factors that influence the performance of industrial upgrading via standards. Expert opinions and the decision making trial and evaluation laboratory method are used to evaluate the relationships. The evaluation results show that if some firms in a system have the capability to execute standardization and innovation, with the support of the government to build and shape standardization institutions and infrastructures, the knowledge and technological capabilities of the entire industry can be enhanced, leading to the gradual introduction of high-quality standardized products into markets by firms even as they move toward more knowledge-intensive segments. This article contributes to two academic fields. First, standards are an important but often neglected topic in the innovation system literature. This article not only investigates the neglected topic but also explores the mechanism through which standards influence industrial upgrading at the meso-level. Second, several previous studies assumed that the drivers of supplier upgrades in developing countries are mostly driven by powerful buyer firms that are based in advanced countries. However, this article finds that customer requirement is not the most influential driver of the industrial upgrading of developing countries. [ABSTRACT FROM AUTHOR]

Natural ester insulating oil not only has a biodegradation rate of almost 100% but also meets the carbon emission requirements of China’s “Carbon Peak and Carbon Neutrality” and the “European Green Deal” proposed by the European Union. It is considered to be a good substitute for mineral insulating oil. However, due to its higher kinematic viscosity than traditional mineral oil in low-temperature environments, it limits the safety promotion and application of transformers in cold regions. First, we design an experiment to test the kinematic viscosity and density of natural ester insulating oil. Under extremely harsh experimental conditions, we measure key experimental data such as kinematic viscosity. Second, the structure of the four main triglyceride molecules is optimized, and the molecular dynamics (MD) simulation technology is used to establish an MD model that can predict the kinematic viscosity of natural ester insulating oil (−20 °C to 20 °C). Finally, the model is further simplified by the free volume theory to better predict the kinematic viscosity of natural ester insulating oil. This study makes up for the lack of laboratory low-temperature testing of the kinematic viscosity of natural ester insulating oil and provides a convenient and reliable tool for predicting the kinematic viscosity of natural ester insulating oil. It can not only predict the natural ester insulating oil mixed in various proportions but also predict the kinematic viscosity of a certain natural ester molecule. Furthermore, it also provides a guiding direction for the improvement of low-temperature kinematic viscosity of natural ester insulating oil, as well as a strong reference for predicting other properties of other substances. [ABSTRACT FROM AUTHOR]

Silicone rubber (SR) is widely used in external insulation. However, the utilization of either high-temperature vulcanized (HTV) SR or liquid SR (LSR) remains controversial in China because of their differences in tracking and erosion resistance and aging resistance due to various amounts of nonreinforcing fillers. Here, the tracking and erosion behaviors of HTV and LSR during the inclined plane test (IPT) are captured and compared for a detailed comprehension of the difference between the two materials. The results revealed that LSR was easily carbonized and formed electrical tracks initially. Then, the carbonization slowed because of developing a protective ceramic layer. The relatively stable ceramic layer resulted in less frequent rapid erosion but increased the average arc burning time. An energy balance model of dry-band arcing (DBA) was established to evaluate DBA’s energy dissipation and absorption. Then, the emission spectra of DBA were collected to analyze the arc temperature and resistance more accurately. The energy input from the system is dissipated primarily through heating and evaporation of the liquid film, with radiant energy only accounting for a minuscule fraction. In different erosion states, the power absorbed by the surface of samples is different. LSR shows an average absorption power of 19.9 W in the initial carbonization state, which is higher than that of HTV (16.5 W). The average absorption power in the fast erosion state is the same for both samples at about 30 W. The absorption power at 20–25 W is considered the threshold range of relatively stable erosion. [ABSTRACT FROM AUTHOR]

Long-term electricity consumption forecasting has been a hot issue due to its importance in power systems planning. Recently, system dynamics (SD) have been considered a potential method for electricity consumption forecasting. However, traditional SD methods are failed in forecasting future power systems toward low-carbon, due to the complex influencing factors and the simple SD model structure. In this study, a novel method combining SD and the ImPACT equation is proposed to solve the above problem. First, a new influencing factor system including emerging factors is established to consider the development of future power system. Subsequently, the ImPACT equation is employed to decompose the electricity consumption into four subsystems. By doing this, the linkage between factors and electricity consumption can be better revealed, which helps to improve the forecasting accuracy. Next, models for quantifying the correlation between subsystems and factors are established using SD. Finally, the proposed method is verified by forecasting the power consumption of China in the future year 2030 to 2050. Furthermore, various scenarios are set to analyze the changing trend of future power consumption by different influencing factors. The results of this article can provide important basic information for power supply and power grid planning. [ABSTRACT FROM AUTHOR]

The signaling literature has focused on government financial signaling, yet little attention has been paid to government nonfinancial signaling. This study develops a signaling model in which visits from government officials are viewed as nonfinancial signals to certify the legitimacy and competitive advantage of young technology-based firms, in turn positively influencing the external investors’ investment decisions. Analyzing manually collected data of 1888 listed entrepreneurial firms in technology-based industries in China from 2009 to 2016, we find that the signal strength of the visits (reflected as the rank of officials) improves such firms’ access to external financing, including equity and debt financing. This signaling effect is contingent upon a similar signal (such as political connection) and the signaling environment (such as institutional development). In this article, we find that the effect of the visits becomes weak for host firms with political connections and those located in institutionally developed regions. Overall, we contribute to the signaling theory literature by investigating government nonfinancial signaling, revealing that similar signals substitute each other, and incorporating the signaling environment into our signaling model. [ABSTRACT FROM AUTHOR]

Semantic segmentation of the remote sensing images (RSIs) has attracted increasing interest in recent years. However, large-area segmentation of the woodland presents challenges. The wide distribution and diverse tree species of the woodland make feature extraction difficult. For this reason, an infrared attention network (InfAttNet) is proposed to extract woodland from multispectral RSIs. InfAttNet has an extra infrared spectral encoder which makes use of the sensitivity of vegetation to near-infrared and red edge spectrums. This extra encoder applies learning about vegetation to improve woodland segmentation. Several attention blocks are designed to enhance learning about vegetation features and so improve the performance. In addition, a new dataset is built, containing a large number of woodland RSIs and covering several typical woodland distribution regions in China. The experimental results demonstrate that compared with other networks, InfAttNet has the highest accuracy and is capable of rapid extraction of the woodland in RSIs. [ABSTRACT FROM AUTHOR]

As the successors of the Huanjing Jianzai-1 (HJ-1) series satellites in the Chinese Environmental Protection and Disaster Monitoring Satellite Constellation, the first two Huanjing Jianzai-2 (HJ-2) A/B satellites have been successfully launched on September 27, 2020. The polarized scanning atmospheric corrector (PSAC) sensors, onboard the HJ-2 A/B satellites, are served as the synchronously atmospheric correction instrument requiring a high-speed and accurate aerosol optical depth (AOD) algorithm. For this purpose, we proposed a neural network-based AOD retrieval model (named the AODNet) that takes full advantage of the multispectral measurements of PSAC for AOD retrieval at a high speed. The training of AODNet is conducted by the simulated observation data (currently applicable for the China region) from the forward calculation using the radiative transfer model. In this way, the land surface reflectance (LSR) is no need for our well-trained model. It is expected to be one of the effective ways to solve the ill-pose problem in the decoupling of the atmosphere and surface information in AOD retrieval. Either the Sun-sky radiometer Observation NETwork (SONET) AOD or the AErosol RObotic NETwork (AERONET) AOD was used to validate the AODNet AOD. The correlation coefficient is higher than 0.85, and more than 60% of the AODNet AOD can fall into the expected error envelope of ±(0.05+20%). The cross-comparison shows that the AODNet has better accuracy than MODIS dark target (DT) and deep blue (DB) algorithm. The air pollution episode is well characterized by the AODNet AOD using PSAC data. [ABSTRACT FROM AUTHOR]

China is the largest coal consumer in the world. The massive exploitation and utilization of coal resources have resulted in serious problems of heavy metal pollution and environmental contamination, such as soil degradation, water pollution, crop damage, and even threatening human lives. Therefore, monitoring soil heavy metal pollution quickly and in real time is an urgent task at present. This research not only formulated a new preprocessing method enlightened by few-shot learning for soil hyperspectral data but also combined it with other soil-related auxiliary information to extract effective information from the soil hyperspectrum, at the end of which different regression methods were adopted to predict soil heavy metal contamination. This test used 168 actual soil samples from the Eastern Junggar coalfield in Xinjiang for verification. Since copper in the soil is a trace element and the corresponding spectral characteristics are affected by other impurities, improper use of hyperspectral preprocessing methods may introduce interference information or may delete useful information, which makes the model effect unsatisfied. To effectively address the above-mentioned problems, the preprocessing method of this experiment combined the second-order differential derivation, and the data enhancement (DA) method together with the addition of auxiliary information to allow more effective features to be entered into the model. Next, the attentive interpretable tabular learning (TabNet) model was improved in three different ways using the original TabNet model and three improved TabNet models to create regression models. One of the improved TabNet models had the best effect, with a list of the top 30 features according to the degree of importance. Meanwhile, the regression prediction of Cu content using four different convolutional neural networks (CNNs) revealed that the model with the residual block was the strongest and slightly outperformed the improved TabNet model, but lacked interpretation of the input data. Besides, this experiment also employed different preprocessing methods for regression prediction on various models and found that the traditional preprocessing methods performed best in traditional regression models [e.g., partial least square regression (PLSR)] and underperformed in deep learning models. The selected optimal model was compared with PLSR and CNN models. The results indicated that both the improved TabNet model and the improved CNN model had better performance using the new preprocessing approach proposed in this article, with improved TabNet yielding a coefficient of determination ($\text{R}^{2}$), root-mean-square error (RMSE), and the ratio of performance to interquartile range (RPIQ) of 0.94, 1.341, and 4.474, respectively. The improved CNN model had a coefficient of determination of 0.942, an RMSE of 1.324, and an interquartile range of 4.531 in the test dataset. [ABSTRACT FROM AUTHOR]

Traditional steganography methods are usually designed on a lossless channel; thus, messages are often not extracted correctly from an image transmitted over a lossy channel that includes attacks such as scaling. To address this issue, in recent years, the field of robust steganography has emerged. In this paper, the process of image scaling by interpolation is first observed and serves as the basis for proposing the idea of inverse interpolation. Subsequently, the idea of constructing an inverse interpolation equation set is proposed to solve the problem of intersectional blocks during the inverse interpolation process. Then, the scaling factor’s valid range of inverse interpolation is analyzed. Next, the inverse interpolation is successfully applied in robust image steganography. A method that combines antiscaling and antidetection is proposed. Afterward, actual tests on the top 9 mobile phone brands with 28 models and 2 social communication apps that are currently popular in China are done. The scaling factor’s valid range of the proposed method is verified to match the actual lossy channel. The experimental results show that the proposed method achieves a reliable extraction of embedded messages for common interpolation scaling attacks while maintaining high statistical detection resistance. [ABSTRACT FROM AUTHOR]

Electricity theft behaviors have caused great harm to the economic benefits of power companies and the secure operation of power systems, thus electricity theft detection is paid much attention in the actual power supply management. In this work, a two-step electricity theft detection strategy is proposed to identify electricity theft users and predict potentially stolen electricity (PSE) for maximizing economic return. In the first step, a neural network model called convolutional autoencoder (CAE) is proposed for electricity theft identification, and the convolutional layer is adopted in CAE to extract and identify the abnormalities of electricity theft users against the uniformity and periodicity of normal power consumption features. In the second step, the PSE of each identified electricity theft user is predicted by the improved regression algorithm named Tr-XGBoost, which combines the extreme gradient boosting (XGBoost) algorithm and transfer adaptive boosting (TrAdaBoost) training strategy. The propsoed Tr-XGBoost could learn the relationship between the extracted electricity features and the PSE of each electricity theft user, and then the predicted PSE can be used to determine the list of electricity theft users to be inspected for maximizing economic return. Case studies on both the IEEE 33-bus test system and a low-voltage distribution system of a province in China show that the proposed two-step electricity theft detection strategy can improve the accuracy of electricity theft identification, and obtain a larger economic return because of a more accurate result of PSE prediction than other state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

As part of ongoing efforts to contain the coronavirus disease (COVID-19) pandemic, understanding the role of asymptomatic patients in the transmission system is essential for infection control. However, the optimal approach to risk assessment and management of asymptomatic cases remains unclear. This study proposed a Susceptible, Exposed, Infectious, No symptoms, Hospitalized and reported, Recovered, Death (SEINRHD) epidemic propagation model. The model was constructed based on epidemiological characteristics of COVID-19 in China and accounting for the heterogeneity of social contact networks. The early community outbreaks in Wuhan were reconstructed and fitted with the actual data. We used this model to assess epidemic control measures for asymptomatic cases in three dimensions. The impact of asymptomatic cases on epidemic propagation was examined based on the effective reproduction number, abnormally high transmission events, and type and structure of transmission. Management of asymptomatic cases can help flatten the infection curve. Tracing 75% of the asymptomatic cases corresponds to a 32.5% overall reduction in new cases (compared with tracing no asymptomatic cases). Regardless of population-wide measures, household transmission is higher than other types of transmission, accounting for an estimated 50% of all cases. The magnitude of tracing of asymptomatic cases is more important than the timing; when all symptomatic patients were traced, tested, and isolated in a timely manner, the overall epidemic was not sensitive to the time of implementing the measures to trace asymptomatic patients. Disease control and prevention within families should be emphasized during an epidemic. Note to Practitioners—This article addresses the urgent need to assess the risk of another COVID-19 outbreak caused by asymptomatic cases and to find the optimal, most practical approach to asymptomatic case management. Previous studies mostly focused on the clinical and statistical characteristics of asymptomatic cases; few have evaluated the impact of asymptomatic case measures using mathematical modeling at the community scale. This study proposed a Susceptible, Exposed, Infectious, No symptoms, Hospitalized and reported, Recovered, Death (SEINRHD) propagation model based on local community structures and social contact networks, according to the development characteristics and trend of COVID-19 in a Chinese community. The conclusion provides theoretical support for emergency work of relevant departments in different periods of an epidemic. In the early stages of the epidemic, timely detection and isolation of symptomatic patients should be a priority. Where there are surplus resources for epidemic prevention, the authorities should consider increasing the proportion of asymptomatic patients being traced. Epidemic prevention measures among family members should be a primary focus of attention. This combination of strategies can help reduce the rate of viral transmission and result in extinguishing the epidemic. [ABSTRACT FROM AUTHOR]

Microchannel plate photomultiplier tubes (MCP-PMTs) with high temporal resolution and low dark count rates will be used as single-photon detectors for the Super Tau-Charm Facility (STCF) proposed in China. Similar to other RICH or DIRC detectors, MCP-PMTs in the STCF need to operate properly in an axial magnetic field of about 1.5 T. We study the magnetic field tolerance of MCP-PMTs with the simulation methods based on the Furman model as a secondary electron emission model and the particle-in-cell method for tracking electrons. The effects of MCP structural parameters (aperture $D$ , length-to-diameter ratio $L/D$ , bias angle $\theta $ , and applied voltage $U$) on the magnetic field tolerance are simulated. The results show that the smaller the $D$ and the smaller the $L/D$ of the MCP, the better its magnetic field tolerance. By increasing the MCP bias angle, its magnetic field tolerance increases first and then weakens. The applied voltage does not affect its magnetic field tolerance. Changing the angle between the magnetic field and the normal direction to the microchannel plate (MCP), the gain decays fastest when the magnetic field direction is parallel to the axial direction of the MCP channels; at a magnetic field direction of 60°, the MCP gain decays the slowest. For MCP-PMTs, the change in the magnetic field direction causes the alteration of the motion direction of the electron cloud in the gaps (cathode-MCP1, MCP1-MCP2, and MCP2-anode), which is the principal reason for the difference in its gain in different magnetic field directions with the same magnetic field strength. The magnetic field tolerance of different assembly methods of two MCPs (i.e., two, three, or four electrodes for applying high voltage) is simulated. The results show that two MCPs’ multiplication structure with the four-electrode assembly method is an appropriate choice. [ABSTRACT FROM AUTHOR]

The online retail market shows a sharp increase in traffic during holiday sales. The ability to distinguish customers who will likely purchase is critical for provisioning traffic and for providing cost-effective promotions. This paper uniquely studies the browsing and purchasing behaviors of online shoppers during a yearly sale event in China, the world’s largest online marketplace. Based on 31 million action logs gathered from wide residential areas, we characterize the steps leading to purchases and determine their precursors. We investigate the effect of time (e.g., date, time of date), environment (e.g., platform, viewed category), and action (e.g., session time, clicks, sequence) on purchases. Action cues from shopping behaviors can be used for early detection. While most shoppers start with strong intentions to purchase, yet the moment of ordering comes rather impulsively within 30 seconds to several minutes of browsing. The predictive accuracy reaches as a high AUC of 0.924. The findings in this paper provide an understanding of traffic during mega sale events that can help online shops plan and provide a better user experience for upcoming shopping festivals. [ABSTRACT FROM AUTHOR]

Purpose: This article aims to provide an integrated model and methodology for discovering valuable innovation knowledge and creative users in online innovative communities. Design/methodology/approach: The super-network integration approach is applied in constructing the user's innovation knowledge super-network (UIKSN) model based on knowledge fragments discovered from user-generated content (UGC) data using text mining methods. The social network analysis (SNA) methodology is then used to analyze the KSN model. An empirical research is conducted with China's Xiaomi online community to illustrate the UIKSN model and the SNA methodology. Findings: Compared with current methods, the proposed KSN model and SNA methodology are demonstrated to be more effective and valid in discovering valuable innovation knowledge including valuable innovations, innovation trends, creative users and their knowledge background, etc. Research limitations/implications: The results of KSN modeling and analysis are inevitably influenced by the performance of text mining methods. Practical implications: More and more companies start to adopt online community user's innovations in their new product developments. However, it is difficult to discover users’ opinions and innovations from the UGC due to its tremendous volume. Therefore, the KSN model and SNA methodology presented in this article are helpful for companies to manage online communities and to utilize users’ innovations effectively and efficiently. Originality/value: The article provides two main contributions in the study of online communities: 1) a well-justified model (users' innovation KSN, UIKSN) to explore online users’ contributions; 2) a new and more effective methodology to discover and analyze valuable innovations and innovative users. [ABSTRACT FROM AUTHOR]

Gravity measurement is an important geophysical prospecting method for mineral exploration. With most of the shallow ore deposits in China being exploited, the future targets for exploration will be aimed at the deep mineral resources about 4-km underground. To improve the resolving ability in the vertical direction of the 3-D density inversion to find deep-source minerals, we propose to achieve the inversion of gravity anomalies by combining power-spectrum derived adaptive weighting and cross-gradient regularization. First, spectral analysis is utilized to conduct the source-depth separation, and the adaptive weighting function is designed depending on the slope of the radial logarithmic power spectrum of the gravity anomaly, which can enhance the correspondence for the field sources with different depths to improve the vertical resolution relatively. Thus, each separated source with different depths could be given an adaptive weighting coefficient in each separated inversion. Second, the cross-gradient technique is introduced as a structural constraint in the objective function to further constrain the separated inversion process. By performing two-cuboid-source cases, it can be seen that this combination calculated approach has great potential to improve the quality of the inversion results. When examining the inversion of the actual gravity data from certain ore district in the west of Zhen’an, South Qinling, we speculate that a potential deep ore body would exist in the deposit via utilizing the recovered density model obtained by the proposed method. [ABSTRACT FROM AUTHOR]

Short-term quantitative precipitation forecasting (SQPF) using weather radar is an important but challenging problem as one must cope with inherent nonlinearity and spatiotemporal correlation in the data. In this article, we propose a novel deep learning model, named Inductive spatiotemporal Graph Convolutional Networks (InstGCNs), to overcome these issues in SQPF. The proposed InstGCN can learn a nonlinear mapping from historical radar reflectivity to future rainfall amounts and extract informative spatiotemporal representations simultaneously. Specifically, we first provide a formal definition for formulating the SQPF problem from a graph perspective. Then, based on radar reflectivity and rain gauge observation, we propose a novel graph construction approach that utilizes a special elliptic structure to model the spatial dependence of precipitation areas. In addition, a new Node level Differential Block (Node-DB) is introduced to tackle the nonstationary temporal dependence. To execute inductive graph learning for unseen nodes, we design to decompose a whole graph into subgraphs. We conduct extensive experiments on three real-world datasets in East China and a public weather radar dataset in the southeastern parts of France. The experimental results confirm the advantages of InstGCN compared with several state of the arts. [ABSTRACT FROM AUTHOR]

Due to the continuous intensification of human activities in the ocean, the frequent outbreaks of red tide have caused great harm to the marine environment and ecology. Thus, the rapid detection and monitoring of red tide become particularly important. At present, the main monitoring methods depend on artificial and buoy data, as well as optical satellite remote sensing. However, these methods may not be able to effectively deal with the characteristics of red tide bloom, such as suddenness and unpredictability. The global navigation satellite system-reflectometry (GNSS-R) is an emerging technology that makes use of navigation signals as a remote sensing opportunity to obtain Earth surface information. GNSS-R has already been proved to be capable of retrieving sea surface parameters (e.g., dielectric constant and sea surface roughness) closely related to the outbreak of a red tide. In this article, we proposed a new method to estimate red tide density, which utilizes an all-new model associating GNSS-R observations with sea surface red tide density. This method can remove the weather influence and greatly decrease the revisit period, which is much longer for optical red tide remote sensing methods. The Landsat-8 near-infrared data and TechDemoSat-1 (TDS-1) GNSS-R data of a red tide outbreak in the sea off the Tsingtao coast in China are used to build and test the proposed method. The results demonstrate that the correlation coefficient is 0.73, and the root mean square error of retrieved red tide density is 2.84%, which shows that the GNSS-R technology shows great potential to perform the rapid and preliminary red tide monitoring and judgment. [ABSTRACT FROM AUTHOR]

The phrase ?made in China? is everywhere, just not in our health care system. China ranks as the world?s third-largest medical device market and is expected to become the second-largest market in the world in five to seven years. However, almost all of China?s hospitals, not to mention its larger first-class hospitals, use imported devices. For a very long time, foreign-made products have dominated the middle- and high-end markets, leaving to Chinese companies the low-end products with low profit margins. According to recent statistics provided by the China Chamber of Commerce for Import and Export of Medicine and Health Products, 90% of value-added high-tech devices, which account for 70% of ?China?s medical device market, are imported. Why can?t Chinese companies compete with multinational biomedical corporations? Is it because of a lack of money or intelligence? [ABSTRACT FROM PUBLISHER]

Engineering geophysical prospecting is used to identify anomalous underground bodies, which are typically identified by inversion results. In recent years, machine learning has been applied to many geophysics studies, including geophysical data processing and fault prediction. Machine learning methods can also be used to identify complex anomalous bodies as direct identification can be difficult due to the complexity of local anomalous bodies. We propose a U-Net network to extract anomalous bodies from inverse results. Our model uses the regional similarity of the stratigraphic structure around the anomalous bodies, and then, the neural network extracts the regional background from the geophysical inversion results. Finally, the local anomalous bodies can be subtracted from the predicted regional results and the original inversion results. We designated a large number of datasets for training and designed triangular models for testing. Resistivity data for contaminated soil in a crane storage yard in Shanghai, China, were then processed and the resistivity range was calculated. We processed resistivity and polarizability data from Yantong Mountain, Heibei, China, to determine the degree of mineralization in the area. [ABSTRACT FROM AUTHOR]

Myocardial infarction (MI) is the myocardial necrosis caused by persistent ischemia and hypoxia of coronary arteries. People do not realize that they are suffering from MI until they have a heart attack. Early MI detection plays a vital role in symptom relief and improvement in the performance of daily activities. However, conventional MI detection methods require expensive and inconvenient medical tests, e.g., intrusive blood tests or wear electrocardiogram (ECG) sensors, which can only be performed in medical institutions. In this paper, we introduce a contactless and non-intrusive MI detection method based on wireless sensing that monitors abnormalities in heartbeats. Specifically, we present Health-Radio, a radar-based system towards early MI detection. Health-Radio extracts heart rate variability (HRV) from the RF signals reflected from users. In particular, with our carefully designed signal processing algorithms, Health-Radio is able to not only obtain heartbeat signals when the user is stationary, but also tolerate interference when the user is performing certain activities, e.g., eating, reading and browsing the Internet. We have recruited 30 MI patients from the Central Hospital of Wuhan, China, and 30 healthy university students to conduct comprehensive evaluations of the performance of Health-Radio. The experiment results show that Health-Radio can achieve a median MI detection accuracy of 81.2 percent when the users are stationary, which is comparable to ECG-based MI detection. Even when the users are not stationary, Health-Radio can still achieve a median detection accuracy of 66.5 percent. Health-Radio is promising in providing a new paradigm for smart-home healthcare in the future. [ABSTRACT FROM AUTHOR]

Hyperspectral/multispectral and panchromatic of optical remote sensing images are commonly used for multisensor image fusion, which has been applied in various applications of Earth observation. However, the utilization of optical remote sensing data suffers from the limitation of bad weather and cloud contamination. To address aforementioned issue and enhance spatial details of polarimetric synthetic aperture radar (PolSAR) image, a novel dual-domain super-resolution image fusion method is proposed by combining improved spherically invariant random vector (ISIRV) model with generalized adaptive linear combination approximation (GALCA) technology in this study. The proposed method decomposes the task of image fusion into polarimetric and texture domain fusion by integrating polarimetric components of PolSAR image and texture detail component of panchromatic image, which can significantly improve spatial resolutions of the PolSAR image while preserving polarimetric information. The data fusion experiment is implemented with three data sets including panchromatic images of Gaofen-1 (GF-1) and Gaofen-2 (GF-2) and the quad-pol SAR data of Gaofen-3 (GF-3) and Radarsat-2. Results show that the proposed dual-domain image fusion method provides a better performance compared with state-of-the-art multisensor fusion methods (BT, PCA, GS, indusion, and PRACS) regarding qualitative and quantitative evaluations. In addition, results of image fusion are applied to image classification over agricultural and urban areas of China, which shows that classification accuracy is significantly improved when compared with the result using only the original image. [ABSTRACT FROM AUTHOR]

The gas electron multiplier (GEM) detector in combination with a solid converter has been widely used in the field of neutron detection in recent decades. Typically, the submillimeter is an important indicator for neutron detectors to satisfy many applications requiring a high spatial resolution. This article proposes a novel method to improve the spatial resolution of ceramic GEM detectors by adding a stopping layer on top of the solid 10B4C neutron converter. This will restrict the emission of the secondary ion products of large angles and consequently improve the spatial resolution. The Monte Carlo program FLUKA is used to validate the method, and the verification experiments are carried out at beam line #20 (BL20) of the China Spallation Neutron Source (CSNS). The experimental results are approximately in agreement with the simulations. The measured spatial resolution is 1.87 mm for the GEM neutron detector operated at ambient pressure with a 1 $\mu \text{m}$ -thick 10B4C converter and a drift gap of 4 mm, eventually, it is improved to ~0.8 mm by coating a 3 $\mu \text{m}$ -thick titanium on top of the 10B4C converter. [ABSTRACT FROM AUTHOR]

Numerical precipitation prediction plays a crucial role in weather forecasting and has broad applications in public services including aviation management and urban disaster early-warning systems. However, numerical weather prediction (NWP) models are often constrained by a systematic bias due to coarse spatial resolution, lack of parameterizations, and limitations of observation and conventional meteorological models, including constrained sample size and long-tail distribution. To address these issues, we present a data-driven deep learning model, named the ordinal distribution autoencoder (ODA), which principally includes a precipitation confidence network and a combinatorial network that contains two blocks, i.e., a denoising autoencoder block and an ordinal distribution regression block. As an expert-free model for bias correction of precipitation, it can effectively correct numerical precipitation prediction based on meteorological data from the European Centre for Medium-Range Weather Forecasts (ECMWF) and SMS-WARMS, an NWP model used in East China. Experiments in the two NWP models demonstrate that, compared with several classical machine-learning algorithms and deep learning models, our proposed ODA generally performs better in bias correction. [ABSTRACT FROM AUTHOR]

Gridded precipitation products with fine resolutions and qualities are of great importance for understanding the global water–carbon-energy cycles at various spatiotemporal scales. Though continuous developments in Satellite Remote Sensing fields have been providing great strengths for measuring the precipitation from space, merging precipitation products from different sources, especially the gauge observations, is still the optimal way for obtaining high-quality precipitation data. Currently, the mainstream merging methods mainly focus on merging the rain rates without the considerations of rain events. In this study, we propose a new assumption that both rain events and rain rates should be considered in the merging procedures rather than only the rain rates. To meet our assumption, a morphology-based adaptive spatio-temporal merging algorithm (MASTMA) for combining various precipitation products is proposed, in which the morphology theory is first introduced to comprehensively consider the influences from both rain events and rain rates. The multisource and multiscale precipitation products including the gauge-based data (CPC-U, 0.5°, daily), the satellite-based data [Global Satellite Mapping of Precipitation by Moving Vector with Kalman (GSMaP-MVK), 0.1°, hourly; integrated multisatellite retrievals for global precipitation measurement late run (IMERG-LR), 0.1°, half-hourly], and the reanalysis data (ERA5-land, 0.1°, hourly), have been comprehensively considered in MASTMA for generating the final estimates (MASTMA-F, 0.1°, hourly) over the southeastern regions of the Mainland China in the periods from 2016 to 2019. The main conclusions include but are not limited to: 1) considerations on rain events contribute significantly to the final merged results, especially when eliminating false extreme values over the regions where precipitation is greatly overestimated; 2) the MASTMA could optimally integrate the advantages from multisource precipitation products with different resolutions, particularly from the perspective of the spatial distributions; and 3) the final merged estimates using MASTMA outperform the contemporary state-of-the-art precipitation products especially in terms of modified Kling–Gupta Efficiency (mKGE) and critical success index (CSI). Additionally, the results of this study suggest that MASMTA is a new promising merging approach with great robustness and applicability, and has the foreseeable potentials for the operational run to generate the optimal global merged precipitation products. [ABSTRACT FROM AUTHOR]

High spatial resolution precipitation data are important for hydrological modeling and meteorological applications, especially at regional scales. Statistical downscaling methods for satellite precipitation products using the normalized difference vegetation index (NDVI) have been carried out in many regions to provide high spatial resolution precipitation. These methods generally use NDVI and precipitation at the same time, assuming that there is a real-time response of vegetation to precipitation. However, this assumption does not hold in many scenarios. It is known that different vegetation types exhibit different response times to precipitation, i.e., there is a possible lag in the response of vegetation to precipitation depending on the vegetation/landcover type. Therefore, it is not appropriate to estimate precipitation using NDVI collected at the same time. To better represent the relationship between precipitation and vegetation, this article develops a new vegetation index based on adaptive lag phase (VIAL) estimated from a new growth rate that is adaptive to landcover type. Based on VIAL, a new local precipitation downscaling method called LPVIAL is proposed, which essentially considers the nonstationary relationship between precipitation and VIAL. The performance of LPVIAL is assessed by downscaling Integrated Multi-satellitE Retrievals for Global Precipitation Measurement (IMERG) from 0.1° to 1-km spatial resolution over the Pearl River Basin in Southern China from 2010 to 2017 at 16-day temporal resolution, and the downscaled products are validated against ground observations. Results indicate that the high-resolution precipitation data obtained from the new downscaling approach perform well, and the accuracy is higher than traditional approaches. With the enhancement of spatial resolution, LPVIAL downscaled products show more detailed spatial information of precipitation with smooth distribution, and the downscaled products have slightly higher accuracy compared with IMERG. It is, therefore, suggested that the adaptive lag phase should be considered in the satellite precipitation product downscaling process. [ABSTRACT FROM AUTHOR]

Cardiovascular disease has become one of the leading causes of death in China, accounting for 45.5% of all deaths in rural areas and 43.16% in urban areas. Hence, its early diagnosis is important. With the development of intravascular imaging technology, the intravascular ultrasound (IVUS) is widely used. The available commercial mechanical rotary side-looking IVUS (SL-IVUS) transducers are driven by external motors that use long flexible shafts to transmit the rotation. However, when the transducer passes through a long-curved blood vessel, it easily causes the nonuniform rotation distortion (NURD) of the image. A catheter which contains a distal motor and sodium chloride (NaCl) solution is presented in this study as an attempt to solve such issues. The NaCl solution is used to connect the transducer and micromotor so that the motor can directly drive the transducer to rotate and acquire the information of the blood vessel. The results showed that the center frequency and −6-dB fraction bandwidth of the single element were 47 MHz and 98%, respectively. The SL-IVUS catheter consists of a distal motor, with speed stability and high resolution, and has the potential to diagnose cardiovascular disease. This novel structure can decrease the dimension at the top of the catheter and reduce the risks of clinical diagnosis. [ABSTRACT FROM AUTHOR]

Converting wind energy into ammonia (WtA) has been recognized as a promising pathway to produce “green” ammonia compared with traditional coal-based technologies. As the key part of WtA, Power-to-Ammonia (PtA) has great potential to facilitate the usage of wind generation. This paper proposes a co-planning approach for regional wind resources-based ammonia industry and the electric network (EN). To this end, PtA is first modeled as a flexible power load of power systems with spatial and temporal constraints on hydrogen supply chains (HSC). Then a novel co-planning model of WtA and EN is established to optimize the WtA configuration and the EN expansion. An alternating direction method of multipliers (ADMM) based algorithm is introduced to effectively solve this model. Real data of Inner Mongolia Province in China is adopted to verify the effectiveness and significance of the proposed approach. It is shown that the siting and operation flexibility of PtA with HSC can reduce the expansion burden of EN. The co-planning of WtA and EN can significantly enhance wind power utilization and reduce total investment costs. Furthermore, feasibility analysis on WtA in comparison with coal-to-ammonia (CtA) and ultra-high voltage transmission (UHV) provides helpful guidelines for the realization of WtA. [ABSTRACT FROM AUTHOR]