ALBERT

Description: This paper introduces a novel semi-supervised tri-training classification algorithm based on diversity measurement for hyperspectral imagery. In this algorithm, three measures of diversity, i.e., double-fault measure, disagreement metric and correlation coefficient, are applied to select the optimal classifier combination from different classifiers, e.g., support vector machine (SVM), multinomial logistic regression (MLR), extreme learning machine (ELM) and k-nearest neighbor (KNN). Then, unlabeled samples are selected using an active learning (AL) method, and consistent results of any other two classifiers combined with a spatial neighborhood information extraction strategy are employed to predict their labels. Moreover, a multi-scale homogeneity (MSH) method is utilized to refine the classification result with the highest accuracy in the classifier combination, generating the final classification result. Experiments on three real hyperspectral data indicate that the proposed approach can effectively improve classification performance.

Description: Water, Vol. 10, Pages 659: Satellite-Based, Multi-Indices for Evaluation of Agricultural Droughts in a Highly Dynamic Tropical Catchment, Central Vietnam Water doi: 10.3390/w10050659 Authors: Tien Le Thuy Du Duong Du Bui Minh Duc Nguyen Hyongki Lee Characterization of droughts using satellite-based data and indices in a steep, highly dynamic tropical catchment, like Vu Gia Thu Bon, which is the most important basin in central Vietnam, has remained a challenge for many years. This study examined the six widely used vegetation indices (VIs) to effectively monitor droughts that are based on their sensitivity with precipitation, soil moisture, and their linkage with the impacts on agricultural crop production and forest fires. Six VIs representing the four main groups, including greenness-based VIs (Vegetation Condition Index), water-based VIs (Normalized Difference Water Index, Land Surface Water Index), temperature-based VIs (Temperature Condition Index), and combined VIs (Vegetation Health Index, Normalized Difference Drought Index) were tested using MODIS data from January 2001 to December 2016 with the support of cloud-based Google Earth Engine computational platform. Results showed that droughts happened almost every year, but with different intensity. Vegetation stress was found to be mainly attributed to precipitation in the rice paddy fields and to temperature in the forest areas. Findings revealed that combined vegetation indices were more sensitive drought indicators in the basin, whereas their performance was different by vegetation type. In the rice paddy fields, NDDI was more sensitive to precipitation than other indices; it better captured droughts and their impacts on crop yield. In the forest areas, VHI was more sensitive to temperature, and thus had better performance than other VIs. Accordingly, NDDI and VHI were recommended for monitoring droughts in the agricultural and forest lands, respectively. The findings from this study are crucial to map drought risks and prepare an effective mitigation plan for the basin.

Description: Gait phase is widely used for gait trajectory generation, gait control and gait evaluation on lower-limb exoskeletons. So far, a variety of methods have been developed to identify the gait phase for lower-limb exoskeletons. Angular sensors on lower-limb exoskeletons are essential for joint closed-loop controlling; however, other types of sensors, such as plantar pressure, attitude or inertial measurement unit, are not indispensable.Therefore, to make full use of existing sensors, we propose a novel gait phase recognition method for lower-limb exoskeletons using only joint angular sensors. The method consists of two procedures. Firstly, the gait deviation distances during walking are calculated and classified by Fisher’s linear discriminant method, and one gait cycle is divided into eight gait phases. The validity of the classification results is also verified based on large gait samples. Secondly, we build a gait phase recognition model based on multilayer perceptron and train it with the phase-labeled gait data. The experimental result of cross-validation shows that the model has a 94.45% average correct rate of set (CRS) and an 87.22% average correct rate of phase (CRP) on the testing set, and it can predict the gait phase accurately. The novel method avoids installing additional sensors on the exoskeleton or human body and simplifies the sensory system of the lower-limb exoskeleton.

Description: Remote Sensing, Vol. 9, Pages 1175: Monitoring Thermal Pollution in Rivers Downstream of Dams with Landsat ETM+ Thermal Infrared Images Remote Sensing doi: 10.3390/rs9111175 Authors: Feng Ling Giles Foody Hao Du Xuan Ban Xiaodong Li Yihang Zhang Yun Du Dams play a significant role in altering the spatial pattern of temperature in rivers and contribute to thermal pollution, which greatly affects the river aquatic ecosystems. Understanding the temporal and spatial variation of thermal pollution caused by dams is important to prevent or mitigate its harmful effect. Assessments based on in-situ measurements are often limited in practice because of the inaccessibility of water temperature records and the scarcity of gauges along rivers. By contrast, thermal infrared remote sensing provides an alternative approach to monitor thermal pollution downstream of dams in large rivers, because it can cover a large area and observe the same zone repeatedly. In this study, Landsat Enhanced Thematic Mapper Plus (ETM+) thermal infrared imagery were applied to assess the thermal pollution caused by two dams, the Geheyan Dam and the Gaobazhou Dam, located on the Qingjiang River, a tributary of the Yangtze River downstream of the Three Gorges Reservoir in Central China. The spatial and temporal characteristics of thermal pollution were analyzed with water temperatures estimated from 54 cloud-free Landsat ETM+ scenes acquired in the period from 2000 to 2014. The results show that water temperatures downstream of both dams are much cooler than those upstream of both dams in summer, and the water temperature remains stable along the river in winter, showing evident characteristic of the thermal pollution caused by dams. The area affected by the Geheyan Dam reaches beyond 20 km along the downstream river, and that affected by the Gaobazhou Dam extends beyond the point where the Qingjiang River enters the Yangtze River. Considering the long time series and global coverage of Landsat ETM+ imagery, the proposed technique in the current study provides a promising method for globally monitoring the thermal pollution caused by dams in large rivers.

Description: Energies, Vol. 11, Pages 848: A Robust Digital Control Strategy Using Error Correction Based on the Discrete Lyapunov Theorem Energies doi: 10.3390/en11040848 Authors: Guiping Du Jiajian Li Fada Du Zhifei Liu This paper presents a robust digital control strategy using error correction techniques to improve the robustness of conventional deadbeat control methods. The proposed control method, based on the discrete converter models, determined control law using an error correction technique based on the discrete Lyapunov stability theorem. The steady-state performance and dynamic response of the presented method was analyzed and verified. The experimental results showed that the method derived in this paper not only offered improved robustness, but also endowed the grid current with lower Total Harmonic Distortion (THD), while still maintaining a fast, dynamic response.

Description: Forests, Vol. 9, Pages 505: Fatty Acids Variation in Seed of Eucommia ulmoides Populations Collected from Different Regions in China Forests doi: 10.3390/f9090505 Authors: Qingxin Du Lu Wang Panfeng Liu Jun Qing Caowen Sun Zhiqiang Sun Hongyan Du Fruits of 240 Eucommia ulmoides Oliver individuals were collected from 12 different geographical regions across a wide area of China. The seed oil content ranged from 28.54% in Guilin and Lueyang to 31.35% in Chaoyang. Gas chromatography–mass spectrometry analysis of the seed oil revealed that linolenic acid (56.68–60.70%), oleic acid (16.31–17.80%), and linoleic acid (11.02–13.32%) were the major components, and the oil showed good potential for the food and health care industries. Three levels (high, medium, and low) of linolenic acid and oil content were observed among the 12 populations according to principal component analysis. Canonical correspondence analysis showed that environmental factors had a large influence on oil content and fatty acids composition and explained 89.33% of the total variance. Latitude and precipitation were key environmental factors and were significantly correlated with the fatty acid composition of E. ulmoides seeds.

Description: On-site soils are increasingly used in the treatment and restoration of ecosystems to harmonize with the local landscape and minimize costs. Eight natural soils from diverse ecological zones in the source area of a drinking-water reservoir in central China are used as adsorbents for the uptake of phosphorus from aqueous solutions. The X-ray fluorescence (XRF) spectrometric and BET (Brunauer-Emmett-Teller) tests and the Scanning Electron Microscopy (SEM) and Fourier Transform Infrared (FTIR) spectral analyses are carried out to investigate the soils’ chemical properties and their potential changes with adsorbed phosphorous from aqueous solutions. The intra-particle diffusion, pseudo-first-order, and pseudo-second-order kinetic models describe the adsorption kinetic processes. Our results indicate that the adsorption processes of phosphorus in soils occurred in three stages and that the rate-controlling steps are not solely dependent on intra-particle diffusion. A quantitative comparison of two kinetics models based on their linear and non-linear representations, and using the chi-square (χ2) test and the coefficient of determination (r2), indicates that the adsorptive properties of the soils are best described by the non-linear pseudo-second-order kinetic model. The adsorption characteristics of aqueous phosphorous are determined along with the essential kinetic parameters.

Description: Sustainability, Vol. 10, Pages 844: Sustainable Strategies for Transportation Development in Emerging Cities in China: A Simulation Approach Sustainability doi: 10.3390/su10030844 Authors: Liyin Shen Lei Du Xining Yang Xiaoyun Du Jinhuan Wang Jianli Hao With the rapid development of emerging cities in China, policy makers are faced with the challenges involved in devising strategies for providing transportation systems to keep pace with development. These challenges are associated with the interactive effects among a number of sophisticated factors involved in transportation systems. This paper presents a system dynamics simulation approach to analyze and select transportation development strategies in order to achieve good sustainability performance once they are implemented. The simulation approach consists of three modules: a socio-economic module, a demand module, and a supply module. The approach is validated through applying empirical data collected from the Shenzhen statistical bulletins. Three types of transport development strategies are selected for the city and examined for their applicability and effects through simulation. The strategies are helpful for reducing decision-making mistakes and achieving the goal of sustainable urban development in most emerging cities.

Description: Remote Sensing, Vol. 10, Pages 417: A Randomized Subspace Learning Based Anomaly Detector for Hyperspectral Imagery Remote Sensing doi: 10.3390/rs10030417 Authors: Weiwei Sun Long Tian Yan Xu Bo Du Qian Du This paper proposes a randomized subspace learning based anomaly detector (RSLAD) for hyperspectral imagery (HSI). Improved from robust principal component analysis, the RSLAD assumes that the background matrix is low-rank, and the anomaly matrix is sparse with a small portion of nonzero columns (i.e., column-wise). It also assumes the anomalies do not lie in the column subspace of the background and aims to find a randomized subspace of the background to detect the anomalies. First, random techniques including random sampling and random Hadamard projections are implemented to construct a coarse randomized columns subspace of the background with reduced computational cost. Second, anomaly columns are searched and removed from the coarse randomized column subspace by solving a series of least squares problems, resulting in a purified randomized column subspace. Third, the nonzero columns in the anomaly matrix are located by projecting all the pixels on the orthogonal subspace of the purified subspace, and the anomalies are finally detected based on the L2 norm of the columns in the anomaly matrix. The detection performance of RSLAD is compared with four state-of-the-art methods, including global Reed-Xiaoli (GRX), local RX (LRX), collaborative-representation based detector (CRD), and low-rank and sparse matrix decomposition base anomaly detector (LRaSMD). Experimental results show good detection performance of RSLAD with lower computational cost. Therefore, the proposed RSLAD offers an alternative option for hyperspectral anomaly detection.

Description: Water, Vol. 9, Pages 938: Characteristics and Factors Influencing the Hysteresis of Water Area–Stage Curves for Poyang Lake Water doi: 10.3390/w9120938 Authors: Aiping Huang Wenqi Peng Xiaobo Liu Yanliang Du Shijie Zhang Shiyan Wang Fei Du Fei Dong Flood dynamics of large lake floodplain systems are typically complex. This paper analyses the characteristics and factors that influence the hysteresis of water area–stage curves for Poyang Lake, the largest freshwater lake in China characterized by complex geomorphology and upstream–downstream exchange conditions. For this purpose, a two-dimensional hydrodynamic model (EFDC) based on seven scenarios is established. The results indicate that the area–stage curve presents significant hysteretic characteristics due to different water surface gradients that emerge during the water-rising and water-falling periods. Counter-clockwise, clockwise, and splayed hysteresis directions observed at the northern, southern, and central hydrometric stations, respectively, are found in Poyang Lake for the first time. Upstream catchment inflows and Hukou stage reflecting the downstream condition are the main factors that influence hysteresis. The temporal fluctuation of catchment inflows and Hukou stage has a remarkably positive impact on hysteresis, namely, an increase in fluctuation brings about a larger hysteresis. The effects of magnitude change in the two factors on hysteresis are opposing. Catchment inflows are positively related, while the decline of the Hukou stage will produce a more pronounced hysteresis. The outcomes of this study will benefit the water management of Poyang Lake and other similar large lakes.