Search

While it is crucial to monitor the spatio-temporal dynamics of forests at the subpixel scale, most available nonlinear methods are used to predict forest cover fraction maps only at the acquisition time of the training samples and are, thus, unable to estimate time-series forest cover fraction beyond the acquisition time. Based on MODIS NDVI, VCF and Landsat tree canopy height data, we developed a spatio-temporal regression (STR) method to estimate annual forest cover fraction maps during 2000–2020 on China's Han River Basin. Results obtained by the proposed STR method achieved significantly higher accuracy (R2 = 0.897, RMSE = 0.1364, MAE = 0.077) than that obtained by a traditional nonlinear regression method. Moreover, the STR exhibits increased accuracy when using training samples from both 2000 and 2020 compared to those using training samples solely from either 2000 or 2020. We also introduced Landsat tree cover maps in 2005, 2010, and 2015 as reference data to verify the effectiveness of the STR method. The STR method was employed to produce annual forest cover fraction maps from 2000 to 2020. The outcomes revealed a distinct overall recovery trend of forest cover at both the pixel and subpixel scales in China's Han River Basin during 2000–2020, notably around the vicinity of the Danjiangkou reservoir area. In general, the STR method proposed in this research is superior in accurately tracking time-series high-intensity and low-intensity forest cover fraction changes in a complex forest ecosystem, which is composed of various forest types in a subtropical monsoon climate.

The series line-commutated converter (LCC) and modular multilevel converter (MMC) hybrid high-voltage direct current (HVDC) system provides a more economical and flexible alternative for ultra-HVDC (UHVDC) transmission, which is the so-called Baihetan-Jiangsu HVDC (BJ-HVDC) project of China. In one LCC and two MMCs ($1+2$) operation mode, the sub-module (SM) capacitors suffer the most rigorous overvoltage induced by three-phase-to-ground fault at grid-side MMC and valve-side single-phase-to-ground fault in internal MMC. In order to suppress such huge overvoltage, this paper demonstrates a novel alternative by employing the MMC-based embedded battery energy storage system (MMC-BESS). Firstly, the inducements of SM overvoltage are analyzed. Then, coordinated with MMC-BESS, new fault ride-through (FRT) strategies are proposed to suppress the overvoltage and improve the FRT capability. Finally, several simulation scenarios are carried out on PSCAD/EMTDC. The overvoltage suppression is verified against auxiliary device used in the BJ-HVDC project in a monopolar BJ-HVDC system. Further, the proposed FRT strategies are validated in the southern Jiangsu power grid of China based on the planning data in the summer of 2025. Simulation results show that the MMC-BESS and proposed FRT strategies could effectively suppress the overvoltage and improve the FRT capability.

Freshwater aquaculture in Jianghan Plain plays a key role in the whole industry of China. It was expanding rapidly to meet the fast-growing demand of consumption in these decades. The spatial distribution change of aquaculture in Jianghan Plain has attracted many researchers in recent years and it is worth further investigating. However, the accuracy and the quality of inland aquaculture classification and mapping still have space to be improved. Our study attempts to use Sentinel-1 and Sentinel-2 data to classify aquaculture areas, nonaquaculture water, and nonwater areas. We applied image segmentation and pixel-based feature computation to obtain candidate datasets. Recursive feature elimination (RFE) was used to find the optimal datasets which were then imported into a modified UNet for classification. This workflow was then applied to the annual datasets for better observation of the spatial change of aquaculture areas. In total, 12 indices and features were found most influential and preserved after RFE. The overall classification accuracy reached 96.83%, while the precision and recall of aquaculture areas reached 84.47% and 90.48%, respectively. The combination of object-based and pixel-based image analysis showed its advantage in inland aquaculture classification compared to other studies. Integrated rice–crawfish farming was found a key factor motivating the rapid development of aquaculture. Policies about the fishing ban and ecosystem restoration were also found deeply affecting the spatial change of aquaculture in Jianghan Plain.

Super-resolution mapping (SRM) can effectively predict the spatial distribution of land cover classes within mixed pixels at a higher spatial resolution than the original remotely sensed imagery. The uncertainty of land cover fraction errors within mixed pixels is one of the most important factors affecting SRM accuracy. Studies have shown that SRM methods using deep learning techniques have significantly improved land cover mapping accuracy but have not coped well with spectral–spatial errors. This study proposes an end-to-end SRM model using a spectral–spatial generative adversarial network (SGS) with the direct input of multispectral remotely sensed imagery, which deals with spectral–spatial error. The proposed SGS comprises the following three parts: first, cube-based convolution for spectral unmixing is adopted to generate land cover fraction images. Second, a residual-in-residual dense block fully and jointly considers spectral and spatial information and reduces spectral errors. Third, a relativistic average GAN is designed as a backbone to further improve the super-resolution performance and reduce spectral–spatial errors. SGS was tested in one synthetic and two realistic experiments with multi/hyperspectral remotely sensed imagery as the input, comparing the results with those of hard classification and several classic SRM methods. The results showed that SGS performed well at reducing land cover fraction errors, reconstructing spatial details, removing unpleasant and unrealistic land cover artifacts, and eliminating false recognition.

Soft robotic glove with brain computer interfaces (BCI) control has been used for post-stroke hand function rehabilitation. Motor imagery (MI) based BCI with robotic aided devices has been demonstrated as an effective neural rehabilitation tool to improve post-stroke hand function. It is necessary for a user of MI-BCI to receive a long time training, while the user usually suffers unsuccessful and unsatisfying results in the beginning. To propose another non-invasive BCI paradigm rather than MI-BCI, steady-state visually evoked potentials (SSVEP) based BCI was proposed as user intension detection to trigger the soft robotic glove for post-stroke hand function rehabilitation. Thirty post-stroke patients with impaired hand function were randomly and equally divided into three groups to receive conventional, robotic, and BCI-robotic therapy in this randomized control trial (RCT). Clinical assessment of Fugl-Meyer Motor Assessment of Upper Limb (FMA-UL), Wolf Motor Function Test (WMFT) and Modified Ashworth Scale (MAS) were performed at pre-training, post-training and three months follow-up. In comparing to other groups, The BCI-robotic group showed significant improvement after training in FMA full score (10.05 ± 8.03, p = 0.001), FMA shoulder/elbow (6.2 ± 5.94, p = 0.0004) and FMA wrist/hand (4.3 ± 2.83, p = 0.007), and WMFT (5.1 ± 5.53, p = 0.037). The improvement of FMA was significantly correlated with BCI accuracy (r = 0.714, p = 0.032). Recovery of hand function after rehabilitation of SSVEP-BCI controlled soft robotic glove showed better result than solely robotic glove rehabilitation, equivalent efficacy as results from previous reported MI-BCI robotic hand rehabilitation. It proved the feasibility of SSVEP-BCI controlled soft robotic glove in post-stroke hand function rehabilitation.

In smart cities, intelligent learning environment is an important application scenario, and class attendance checking is an important measure to urge students to attend on time and ensure the quality of learning. Aiming at the existing problems in class attendance checking, such as low efficiency and easy to cheat, this paper proposes a student attendance management method named AMMoC (Attendance Management Method based on Crowdsensing). AMMoC includes two phases, i.e., the initialization phase and the authentication phase. In the initialization phase, a teacher sends an attendance checking request to the server. After receiving the request, the server sends a request to tell students to submit their location information, and then forms the student location map once the server receives all the response from students. In the authentication phase, the server verifies the truth of the location information by sending requests to several students to count the number of students. The authentication phase includes two modules, i.e., the task assignment module and the attendance verification module. In the task assignment module, AMMoC first finds the optimized sequence of subregions and verifiers by using the Monte Carlo algorithm, and then requires the verifiers to count the number of students in the subregion. Finally, the statistics results will be verified in the attendance verification module. Experiment comparisons and analyses show that AMMoC has the advantages of good anti-cheating performance, fast speed, and little disturbance to class, and is suitable for attendance checking applications in classroom environment.

The series line-commutated converter (LCC) and modular multilevel converter (MMC) hybrid HVDC system provides a more economical and flexible alternative for UHVDC transmission. With the LCC DC voltage reduction, no current cut-off will occur under slight rectifier-side AC faults. However, with the limitation of the MMC voltage modulation ratio, when the rectifier-side AC fault is extremely acute, the current cut-off will unavoidably exist, resulting in enormous impacts on AC and DC systems. To reduce the risk of the current cut-off and improve fault recovery, this paper proposes an enhanced coordinated control strategy. First, under the varying severity of rectifier-side AC faults, the $U$ - $I$ operation characteristics are meticulously analyzed. Then, the third harmonic voltage injection (THVI) and reactive power dynamic adjustment (RPDA) are introduced to expand the operation range of MMC DC voltage. Based on the enlarged operation range, a backup DC current control of MMC is proposed to adaptively regulate the MMC DC voltage relying on the fault severity. Finally, the feasibility and effectiveness of the proposed coordinated control strategy is verified through several simulation scenarios of varied fault severity on PSCAD/EMTDC. The simulation results show that, the proposed control enlarges the system operation range, improves the fault recovery, and significantly reduces the risk of current cut-off.

Modular multilevel converter based high voltage direct current (MMC-HVDC) transmission systems may increase the short-circuit current and affect the AC fault clearing of circuit breakers. To address this issue, this paper analyzes the influence of the MMC on the short-circuit current when a symmetrical or asymmetrical fault occurs in the AC system. Firstly, the influence mechanism of the MMC on the short-circuit current under symmetrical AC faults is studied. It is found that the short-circuit current magnitude at the fault point is mainly affected by the q -axis output current of the MMC. For the single-phase line-ground fault, the three-sequence equivalent circuit of the MMC is analyzed, and the calculation method of the three-sequence short-circuit current is presented. It is observed that the negative- and zero-sequence currents at the valve side of the MMC are both zero, and the positive-sequence current is determined by MMC operating conditions. Besides, the short-circuit current magnitude under the single-phase line-ground fault is also mainly related to the q -axis output current of the MMC. Based on these results, an additional controller is proposed to reduce the short-circuit current under the symmetrical and asymmetrical faults. Finally, the effectiveness of the proposed mechanism and suppression control is verified by PSCAD/EMTDC simulations.

To cope with severe environmental problems, the government has implemented strict emission control policies, and promoted the use of technology such as shore power (SP) in the form of subsidies. The SP providers of the shipping lines like the ports provide better SP services to shipping lines by improving its reliability, such as safety and standardization. This paper examines a two-echelon maritime supply chain consisting of a port and a shipping line under government green subsidy and explores the subsidy mechanism and its impact. The optimal government subsidy intensity and subsidy reduction point are confirmed using game theory. The system dynamics (SD) method is used to analyze the influence and evolution of practical problems such as government subsidy efficiency, information asymmetry, and inconsistent decision-making periods under multiple games utilizing the optimal response function. The paper shows that both shipper SP preference and decision period affect the SP reliability. When the shipper's preference is high, the actual shipper's subsidies and government subsidies are inefficient. Information asymmetry borne by ports and shipping line causes considerable fluctuations in the game and does not affect the actual subsidies received by shippers. Also, shipping line downstream of the supply chain are more affected by it. This paper offers insight for the government to formulate subsidy policies in the maritime supply chain.

Real-time flood forecasting of small- and medium-sized rivers in areas with scarce hydrological data is an urgent problem that needs to be solved. Traditional hydrological model parameters cannot be fully trained owing to a lack of data; thus, results obtained by such models are not satisfactory. We need a new way to solve the forecasting problem for small- and medium-sized rivers. We found that the time series of some feature variables have evident change trajectories in spatial dimension, and the change of some feature variables in the spatial dimension has a decisive influence on flooding processes, such as the spatial distribution of rainfall. To reflect the change of feature variables in spatial dimension with to solve the problem of the lack of hydrological data, we constructed a rainfall-flow pattern composed of a spatial-temporal dynamic time warping algorithm and multi-feature algorithm to measure the similarity of hydrological time series. In the experimental watersheds, we used rainfall-flow patterns to forecast the short-term flood streamflow, and satisfactory results were obtained. This suggests that the algorithm is suitable for hydrological studies and improves the accuracy of real-time flood forecasting for longer forecast periods.

In this paper, the triple-phase-shift (TPS) control with certain unified boundary conditions is applied to a dual-bridge series resonant converter (DBSRC) for applications needing bidirectional energy flow ability. The control strategy is unified for the whole variation range of load, input/output voltage and with simple calculation. By using this unified boundary control, the circulating energy is minimized significantly. A wide soft switching operation range can be achieved as well. Furthermore, based on the analysis results of unified boundary conditions, an improved unified boundary control with duty cycle compensation is also proposed. The ZVS operations of all sides switches can be maintained for wide converter gain and load with high efficiency. The procedure of design for important parameters is given. Finally all works are verified through actual experimental tests on a 500W laboratory prototypes successfully.

Using the semi-tensor product method, this paper studies the set stability of Boolean networks (BNs) with stochastic function perturbations. First, the definition of one-column function perturbation for BNs is defined, and two kinds of stochastic function perturbations are formulated. Second, by constructing a state transition matrix, a new criterion is proposed for the set stability of BNs with probabilistic function perturbation. Third, the set stability of BNs with Markov jump function perturbation is studied by calculating the state probability distribution. Finally, the obtained results are applied to D. melanogaster segmentation polarity gene network.

Modular multilevel converter (MMC)-based high-voltage direct current (HVDC) grid is a promising technology for multiple offshore wind farms (OWFs) to form interconnected offshore grids. However, in the MMC-HVdc grid, the converter terminals connecting the OWFs could only be passively pre-charged by the ones connecting active ac networks via the dc lines during the start-up process. Under this condition, the start-up process of HVdc grid of the passive-side converters becomes significantly complicated. This paper, considering an HVdc grid integrating multiple passive-side converters, investigates its start-up process with three main contributions: 1) a modified nearest level modulation (NLM) method is proposed for the passive-side converters to mitigate the inrush currents after they are deblocked; 2) based on the dc-side equivalent models, the inter-converter resonances and oscillations between the passive-side converters are analyzed after they are deblocked, and; 3) an oscillation damping controller is proposed to provide the electrical damping of inter-converter oscillations between the passive-side converters. The simulation results in PSCAD/EMTDC from a four-terminal MMC-HVDC grid with two terminals connecting the OWFs verify the effectiveness of the proposed start-up control schemes.

Hierarchical topic models, such as hierarchical Latent Dirichlet Allocation (hLDA)and its variations, can organize topics into a hierarchy automatically. On the other hand, there are lots of documents associated with hierarchical label information. Incorporating these information into the topic modeling process can help users to obtain a more reasonable hierarchical structure. However, after analyzing various real-world datasets, we find that these hierarchical labels are ambiguous and conflicting in some levels, which introduces error and restriction to the latent topic and the hierarchical structure exploration process. We call it the horizontal topic expansion problem. To address this problem, in this paper, we propose a novel hierarchical topic model named horizontal and vertical hierarchical topic model (HV-HTM), which aims to incorporate the observed hierarchical label information into the topic generation process, while keeping the flexibility of horizontal and vertical expansion of the hierarchical structure in the modeling process. We conduct experiments on BBC news and Yahoo! Answers datasets and evaluate the effectiveness of HV-HTM on three evaluation metrics. The experimental results show that HV-HTM has a significant improvement on topic modeling, compared to the state-of-the-art models, and it can also obtain a more interpretable hierarchical structure.

To meet the women appearance needs, we present a novel virtual experience approach of facial makeup transfer, developed into windows platform application software. The makeup effects could present on the user's input image in real time, with an only single reference image. The input image and reference image are divided into three layers by facial feature points landmarked: facial structure layer, facial color layer, and facial detail layer. Except for the above layers are processed by different algorithms to generate output image, we also add illumination transfer, so that the illumination effect of the reference image is automatically transferred to the input image. Our approach has the following three advantages: 1) Black or dark and white facial makeup could be effectively transferred by introducing illumination transfer; 2) Efficiently transfer facial makeup within seconds compared to those methods based on deep learning frameworks, and; 3) Reference images with the air-bangs could transfer makeup perfectly.

The localization of multiple signal sources based on Time Of Arrival (TOA) measurements in wireless sensor networks is investigated in this paper. When the signal sources cannot be distinguished by their signatures or other unique characteristics, the correspondence between the sources and the TOA measurements at different sensors is unknown, which makes the multi-source localization problem quite challenging. A self-clustering measurement combination method is proposed for the problem. The source location estimate obtained by the hyperbolic localization algorithm is used as the clustering pattern, and the scatter of the patterns of different subsets of TOA measurements is defined as a criterion function, which is extremized by the combination of TOA measurements from the same source. A three-step heuristic clustering algorithm is pursued to resolve the TOA ambiguity, and its mean square error performance and computational complexity are also analyzed. The simulation and experiment indicate that the presented method has higher location accuracy and lower complexity compared with the existing methods.

Order execution cost analysis is one of the most important problems in financial investments. Many previous research works model the problem as a cost classification or regression task. However, due to insufficient real orders, performances of those models are not satisfying. Moreover, unlimited simulated orders generated by market simulators are not exploited by the analysis approach. In this paper, we propose an order execution cost estimation approach by using limited real orders and unlimited simulated orders. The approach 1) employs exploratory data analysis to explore the patterns and relationships included in the raw data, and selects the appropriate features for model training, 2) trains supervised models on labeled orders as baselines to estimate order execution cost, 3) trains three Semisupervised Learning (SSL) models on both labeled and simulated orders to improve the estimation performances, where a. Semisupervised Support Vector Machine (S3VM) makes a low-density separation on labeled and unlabeled orders, b. Tri-Training performs bootstrap sampling on the labeled orders to obtain three labeled training sets to make disagreement for labeling unlabeled orders, and c. Label Propagation (LP) model propagates the order execution cost labels of the labeled orders to the unlabeled ones on a graph and adjusts the labels based on local and global consistency. Experiments are conducted on real and simulated order datasets. Results of the experiments show that the SSL models perform better than the baselines, where S3VM optimized by Adam, Random Forest (RF) based Tri-Training and Radial Basic Function (RBF) based LP can make use of the information of unlabeled orders to tremendously improve classification performances in F1 score.

It is difficult and challenging to evaluate the aesthetics quality of images from multiple angles. Since humans' perception of images comes from many factors, the integrated image aesthetic quality assessment cannot be easily summarized by few attributes. A comprehensive evaluation is supposed to predict many aesthetic attributes across not only one dataset. This requires the model to have not only high accuracy, but also strong generalization ability, resulting in a better prediction on multiple models and datasets. Recent work shows that deep convolution neural network can be used to extract image features and further evaluate the total score of images, and the method of evaluation are lacking of sufficient detailed features. In this paper, we propose a multi-task convolution neural network with more incremental features. We show the results in the way of a hexagon map, which is called aesthetic radar map. This allows the network model to fit different attributes in various datasets better.

Stock prediction is always an attractive problem. With the expansion of information sources, news-driven stock prediction based on sentiments of social media, such as sentiment polarities in financial news, becomes more and more popular. However, the distributions of news articles among different stocks are skewed, which makes stocks with few news have few training samples for their prediction models, and thus leads to low prediction accuracy in the stock predictions. To address this problem, we propose sentimental transfer learning, which transfers sentimental information learned from news-rich stocks (source) to the news-poor ones (target), and prediction performances of the later ones are, therefore, improved. In this approach, the financial news articles of both the source and target stocks are first mapped into the same feature space that is constructed by sentiment dimensions. Second, we develop three different transfer principles in order to explore different transfer scenarios: 1) the source and target stocks’ historical price time series are highly correlated; 2) the source and target stocks are in the same sector and the former is the most news-rich one in the sector; and 3) the source stock has the highest prediction performance in validation data set. Third, a majority voting mechanism is designed based on the principles. The voting mechanism is to select the most proper source stock from the candidate stocks that are generated by different principles. Stock predictions are finally made based on the prediction models trained on the selected stocks. Experiments are conducted based on the data of Hong Kong Stock Exchange stocks from 2003 to 2008. The empirical results show that sentiment transfer learning can improve the prediction performance of the target stocks, and the performances are better and more stable with the source stocks selected by the voting mechanism.

Diagonal loading provides a powerful and effective way to improve the robustness of the standard Capon beamformer. Several parameter-free robust adaptive beamformers (RAB) are considered in this paper. We reveal that the performances of them have somewhat degradation when the number of snapshots or that of sensors is large. To solve this problem, we emphatically study the well-known generalized linear combination-based method, the performance of which may degrade severely when the number of sensors increases, and propose a novel parameter-free technique, which is a combination of noise reduction preprocessing technique and truncated minimum mean square error criterion. As most of the parameter-free RAB techniques are very sensitive to the desired signal steering vector mismatch, this paper further proposes to construct a series connection between these RAB techniques and a steering vector estimation (SVE) method, where the SVE is implemented by a convex optimization technique. Simulation results show that the proposed method can achieve a promising performance in comparison with the competing methods.