Article
Mathematics
Junbo Zhang, Daoji Li, Yingzhi Xia, Qifeng Liao
Summary: This paper proposes a new two-step approach to estimate 1-km-resolution PM2.5 concentrations in Shanghai using satellite data. The approach refines AOD data to a higher resolution using a Bayesian retrieval method and then uses a hierarchical Gaussian process model to estimate PM2.5 concentrations. The results show accurate predictive performance of the proposed approach.
Article
Green & Sustainable Science & Technology
Yu Shi, Yueting Hou, Yue Yu, Zhaoyang Jin, Mohamed A. A. Mohamed
Summary: This paper proposes a power system state estimation method based on sampling for generalized M-estimation of optimized parameters. Compared to traditional robust state estimation, the generalized M-estimator based on projection statistics improves the robustness of state estimation, and the proposed optimized parameter determination method improves the overall accuracy of state estimation by appropriately adjusting its robustness.
Article
Computer Science, Information Systems
Tingrui Liu, Xin Li, Liguo Tan, Shenmin Song
Summary: This study proposes an algorithm based on an incremental learning model for multiobjective estimation of distributions. The algorithm incorporates an adaptive learning mechanism to discover the structure of the Pareto-optimal set during evolutionary search. Experimental results demonstrate a significant improvement over several benchmark tests.
INFORMATION SCIENCES
(2021)
Article
Mathematics, Applied
Xinggang Zhang, Xiaochun Lu
Summary: In this study, a new algorithm for online variance components estimation (Online-VCE) of geodetic data is developed based on the batch expectation-maximization (EM) algorithm and stochastic approximation theory. The Online-VCE algorithm is validated using simulated and real data PPP experiments, showing its potential for real-time atmospheric stochastic modeling in future applications.
COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION
(2021)
Article
Engineering, Multidisciplinary
Mayank Kumar Jha, Sanku Dey, Refah Alotaibi, Ghadah Alomani, Yogesh Mani Tripathi
Summary: This paper considers the estimation of stress-strength reliability using both frequentist and Bayesian methods when both stress and strength variables follow unit generalized exponential distributions. The frequentist methods include maximum likelihood, least squares, weighted least squares, and maximum product spacing methods. The Bayesian methods use gamma and weighted Lindley priors for model parameters. Monte-Carlo simulation studies are conducted to evaluate the performance of the proposed estimates, and an engineering dataset is analyzed to demonstrate the applicability of the methods.
AIN SHAMS ENGINEERING JOURNAL
(2022)
Article
Engineering, Mechanical
Zhuo Wang, Pengjian Shang
Summary: This paper proposes a new approach called generalized distance components (GDISCO) for estimating the complexity of time series from the perspectives of time and space. Compared with existing methods, GDISCO not only provides the total complexity, but also calculates the complexity within and between the components of pooled samples. The effectiveness of GDISCO is verified through simulated data, showing consistent and monotonic variation of the complexity measure as parameters change.
NONLINEAR DYNAMICS
(2022)
Article
Computer Science, Artificial Intelligence
Zhiyuan Zhao, Xuelong Li
Summary: Crowd counting, an essential task in crowd analysis with great significance in public safety, has gained increasing attention recently. Existing methods for crowd counting using convolutional neural networks and density maps fail to accurately represent scale changes caused by perspective effects. To overcome this challenge, we propose a scale-sensitive crowd density map estimation framework, which incorporates adaptive density maps, deformable density map decoders, and auxiliary branches. Experimental results demonstrate the effectiveness of the proposed framework, and visualization shows that deformable convolutions capture the scale variation of targets.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Article
Multidisciplinary Sciences
Buwen Cao, Renfa Li, Sainan Xiao, Shuguang Deng, Xiangjun Zhou, Lang Zhou
Summary: In this study, a new method called ComSim-MINE was proposed, which combines miRNA function similarities and network topology similarities based on module identification. Experimental results showed that this method achieved satisfactory results in terms of the composite score of the miRNA function interaction network.
Article
Agriculture, Multidisciplinary
Linh Nguyen, Dung K. Nguyen, Truong X. Nghiem, Thang Nguyen
Summary: Efficiently monitoring microalgal density in closed systems is crucial. Existing image analysis methods are limited to specific strains, so this paper proposes a generic approach to optimize the parameters and applies a nonlinear regression model for accurate estimation of microalgal density. The effectiveness of this approach is demonstrated through experiments with real-world data.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Agriculture, Multidisciplinary
Weikang Liu, Runmei Luo, Junyutai Hu, Juncong Chen, Wenhao Luo, Xiuyun Xue, Shuran Song, Daozong Sun
Summary: To achieve precision spraying, predicting pesticide application dose based on plant canopy structure is crucial. However, current precision spraying techniques lack consideration for the effect of canopy characteristics on droplet particle distribution, resulting in suboptimal droplet deposition. This study explores the effects of canopy density and spraying volume on droplet deposition distribution in simulated citrus tree canopies and develops a prediction model for droplet deposition.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2023)
Article
Engineering, Electrical & Electronic
Shanmou Chen, Qiangqiang Zhang, Dongyuan Lin, Shiyuan Wang
Summary: This letter proposes a novel geometric unscented Kalman filter (GUF) with generalized loss (GL) to estimate the state of the power system (PS) for forecasting aid. The GL-GUF combines the strength of robust information learning against non-Gaussian disturbances and the advantages of GUF in handling strong model nonlinearity with high accuracy and stability. Simulations on IEEE 14-bus and 30-bus test systems confirm the high precision and robustness of GL-GUF for non-Gaussian disturbances.
IEEE SIGNAL PROCESSING LETTERS
(2022)
Article
Mathematics, Applied
Cong Wu
Summary: Based on the generalized deconvolution model, this paper constructs the corresponding multiwavelet estimator and studies its optimal estimation of point-wise risk under local regularization condition. The multiwavelet estimator is constructed by combining noise information and the upper bound of point-wise risk between density function and corresponding multiwavelet estimator in local regular space is studied. An adaptive multiwavelet estimator is constructed using a data-driven method and its convergence order is also studied. Finally, the optimality of the multiwavelet estimator and the data-driven estimator is discussed.
RESULTS IN MATHEMATICS
(2023)
Article
Thermodynamics
Wentao Ma, Peng Guo, Xiaofei Wang, Zhiyu Zhang, Siyuan Peng, Badong Chen
Summary: A robust CKF enhanced by the generalized maximum correntropy criterion (GMCC) is developed in this work, which can accurately estimate the SOC of lithium batteries under different operating conditions, especially in the presence of non-Gaussian noise, demonstrating its excellent performance.
Article
Mathematics
Qiang Yang, Yong Li, Xu-Dong Gao, Yuan-Yuan Ma, Zhen-Yu Lu, Sang-Woon Jeon, Jun Zhang
Summary: The paper proposes an adaptive covariance scaling estimation of distribution algorithm (ACSEDA) based on the Gaussian distribution model, which calculates the covariance based on a larger number of promising individuals to solve complex optimization problems effectively.
Article
Computer Science, Information Systems
Qianlong Dang, Weifeng Gao, Maoguo Gong
Summary: Estimation of distribution algorithm (EDA) is a stochastic optimization algorithm based on probability distribution model. This paper proposes an efficient mixture sampling model (EMSM) to address the poor diversity and premature convergence issues in Gaussian EDA (GEDA). By combining EMSM with enhancing Gaussian estimation of distribution algorithm (EDA(2)), a new GEDA variant named EMSM-EDA is developed. Experimental results demonstrate that EMSM-EDA is efficient and competitive.
INFORMATION SCIENCES
(2022)