A5100444007- Fuzzy Systems and Optimization
- Multi-Criteria Decision Making
- Advanced Statistical Methods and Models
- Matrix Theory and Algorithms
- Algebraic and Geometric Analysis
- Water-Energy-Food Nexus Studies
- Radioactive element chemistry and processing
- Statistical Methods and Inference
- Probability and Risk Models
- Metal-Organic Frameworks: Synthesis and Applications
- Statistical Methods and Bayesian Inference
- Advanced Photocatalysis Techniques
- Advanced Statistical Process Monitoring
- Textile materials and evaluations
- Advanced Fiber Optic Sensors
- Nonlinear Differential Equations Analysis
- Image and Object Detection Techniques
- Bayesian Methods and Mixture Models
- Stock Market Forecasting Methods
- Grey System Theory Applications
- Optimal Experimental Design Methods
- Soil Geostatistics and Mapping
- Fuzzy Logic and Control Systems
- Spatial and Panel Data Analysis
- Algebraic structures and combinatorial models
Tsinghua University
2014-2023
Zhengzhou Children's Hospital
2022
Guizhou University
2021-2022
Xiaomi (China)
2022
Lanzhou University of Finance and Economics
2020
Key Laboratory of Nuclear Radiation and Nuclear Energy Technology
2020
China University of Geosciences (Beijing)
2020
Yunnan University
2019
Hebei University of Engineering
2018
Library and Archives Canada
2013
The objective of uncertain time series analysis is to explore the relationship between imprecise observation data over and predict future values, where these are variables in sense uncertainty theory. In this paper, method maximum likelihood used estimate unknown parameters autoregressive model, distributions disturbance terms simultaneously obtained. Based on fitted forecast value confidence interval derived. Besides, mean squared error proposed measure goodness fit among different...
The objective of time series analysis is to study the relationship between data over and predict future values. Traditionally, statisticians assume that observation are precise, we can get some exact However, in many cases, imprecise available. We these uncertain variables sense uncertainty theory. In this paper, ridge method used compute unknown parameters autoregressive model. First, estimation given. shrinkage parameter obtained by trace analysis. Based on fitted model, forecast value...
This paper aims to employ time series analysis forecast the per capita output of yarn in China. We note from random that residual data did not pass normality and homogeneous distribution tests. It means disturbance term cannot be assumed as a variable. The autoregressive model is suitable. In this situation, employs an uncertain which Besides, hypothesis test designed evaluate whether fits observed values well. From study, we conclude good fit for yarn.
As a basic model, an uncertain regression model with autoregressive time series errors has been investigated. This paper proposes another fundamental model—uncertain moving average errors—by assuming that the of have structure. Then principle least squares is used to estimate unknown parameters in model. Based on fitted forecast value and confidence interval future data are derived. Finally, example presented verify feasibility this approach.
The concept of data depth in non-parametric multivariate descriptive statistics is the generalization univariate rank method to data. Halfspace a measure depth. Given set S points and point p, halfspace (or rank) k p defined as minimum number contained any closed with on its boundary. Computing NP-hard, it equivalent Maximum Feasible Subsystem problem. In this thesis mixed integer program formulated big-M for We suggest branch cut algorithm. algorithm, Chinneck's heuristic algorithm used...
In this paper, we present an analysis of transverse mode competition mechanism in multicore fiber lasers based on the transversally-resolved steady rate equations with consideration gain distribution and propagation loss. Based model, output beam properties 7-core 19-core are simulated numerically when applying a plane reflection mirror Talbot cavity as feedback boundary conditions, respectively. We propose new parameter brightness factor to find out best distance. also give influence core...
An uncertain random variable is a measurable function on the chance space. It used to describe mixing phenomena with both randomness and uncertainty. The sequence of variables indexed by integers. Three types convergence concept have been defined, namely, in distribution, almost surely measure, some theorems obtained. main purpose this paper provide limit sequences. First, we construct two examples illustrate concepts measure for variables. Then an inequality presented, which states...
Low-Rank Adaptation (LoRA) is a widely used technique for fine-tuning large pre-trained or foundational models across different modalities and tasks. However, its application to time series data, particularly within models, remains underexplored. This paper examines the impact of LoRA on contemporary models: Lag-Llama, MOIRAI, Chronos. We demonstrate LoRA's potential forecasting vital signs sepsis patients in intensive care units (ICUs), emphasizing models' adaptability previously unseen,...
In this paper, we introduce the Hom-algebra setting of notions matching Rota-Baxter algebras, (tri)dendriform algebras and (pre)Lie algebras. Moreover, study properties relationships between categories these Hom-algebraic structures.
Abstract Objective The seasonal trend of ARIMA product was used to predict the incidence HRSV infection in Zhengzhou area and explore application model predicting rate ALRTI caused by . Methods Based on time series construction from January 2018 2020, 2021 2022 verified HRSV, results were validated. Results Model (1,0,1) (0,1,1) 12 is best model, with BIC = 8.319, Ljung-Box 20.787, P 0.160. average relative error predicted actual values March 339.33%, value within 95% confidence interval...