Article
Environmental Sciences
Can Liu, Yunhua Luo, Zhongjun Yu, Jie Feng
Summary: This paper investigates the problem of inverse synthetic aperture radar imaging for a non-stationary moving target and proposes a non-search imaging method based on parameter estimation and sparse decomposition. The received radar echoes are modeled as chirp signals with varying chirp rates and center frequencies. The Lv's distribution (LVD) is introduced to accurately estimate these parameters. Via sparse representation using a redundant chirp dictionary, the signals are reconstructed, and an efficient algorithm is developed for sparse decomposition. The reconstructed data is then utilized to employ adaptive joint time-frequency imaging techniques for generating high-quality images of the non-stationary moving target. Simulated experiments and measured data processing results confirm the validity of the proposed method.
Article
Engineering, Electrical & Electronic
Ihor Javorskyj, Roman Yuzefovych, Ivan Matsko, Zbigniew Zakrzewski
Summary: This article explores the estimation of the basic frequency of periodically correlated random processes using the least squares method. The properties of the estimator are analyzed, and bias and variance formulas are obtained based on nonlinear equations. The method is validated using simulated sequences and a real-life vibration signal.
DIGITAL SIGNAL PROCESSING
(2022)
Article
Mathematics
Hao Ding, Zhanfeng Wang, Yaohua Wu, Yuehua Wu
Summary: This paper focuses on sparse high-dimensional multivariate generalized linear models with coexisting homogeneity and heterogeneity sets of predictors. The proposed new adaptive regularized method helps identify the homogeneity set of predictors and improves parameter estimation efficiency. It also yields a smaller variance compared to methods that do not consider the existence of a homogeneity set. Extensive simulation studies and real data examples are provided to demonstrate the effectiveness of the proposed method.
COMMUNICATIONS IN MATHEMATICS AND STATISTICS
(2023)
Article
Mathematics
Amour T. Gbaguidi Amoussou, Freedath Djibril Moussa, Carlos Ogouyandjou, Mamadou Abdoul Diop
Summary: This paper considers nonparametric estimation for a stationary strongly mixing and manifold-valued process (X-j), proposing kernel density estimators for the joint probability density function, conditional probability density functions, and conditional expectations of functionals of X-j given the past behavior of the process in a non-Euclidean and not necessarily i.i.d setting. Strong consistency of these estimators is demonstrated under sufficient conditions, with their performance evaluated through simulation studies and real data analysis.
COMMUNICATIONS IN MATHEMATICS AND STATISTICS
(2022)
Article
Computer Science, Information Systems
Jianqiao Chen, Ping Zhang, Nan Ma, Xiaodong Xu
Summary: This paper proposes a novel hierarchical-block channel estimation scheme for massive MIMO systems based on Bayesian learning frameworks. By characterizing the delay-domain sparse channel structure and inferring the channel vector and associated hyperparameters using an iterative Bayesian learning scheme, our proposed scheme outperforms comparison methods in terms of channel recovery and performance improvement.
IEEE WIRELESS COMMUNICATIONS LETTERS
(2022)
Article
Statistics & Probability
Wanfeng Liang, Yunfei Guo, Yue Wu
Summary: This paper addresses the problem of detecting common gradual changepoints in panel data, proposing an iterative algorithm to improve the accuracy of changepoint location estimation. The effectiveness and improvement of the method are illustrated through Monte Carlo simulation results and analysis of daily returns of stock indices.
Article
Statistics & Probability
Marta Ferreira
Summary: This study considers the cycles estimator introduced in Ferreira and Ferreira (Ann Inst Henri Poincare Probab Stat 54(2):587-605, 2018) within Extreme Value Theory. A reduced bias estimator based on the Jackknife methodology is presented, along with the application of the bootstrap technique for inference and obtaining confidence intervals. Performance analysis based on simulation indicates that our proposal effectively reduces bias and compares favorably with some well-known methods. Additionally, the methods are applied to real data.
COMPUTATIONAL STATISTICS
(2023)
Article
Computer Science, Interdisciplinary Applications
Yunfei Guo, Tao Wang, Zhonghua Li
Summary: The paper discusses the impact of the independence assumption on availability estimation when dependence actually exists. Consistency and asymptotic normality of the estimator of limiting availability are derived under regular conditions. Simulations are conducted to study the effect of dependence on availability estimation.
JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION
(2021)
Article
Automation & Control Systems
Julian D. Schiller, Matthias A. Mueller
Summary: In this article, a suboptimal moving horizon estimator for nonlinear systems is proposed. The feasibility-implies-stability/robustness paradigm is transferred from model predictive control to moving horizon estimation, ensuring robust stability of the estimator. The design allows for the choice between a standard least squares approach and a time-discounted modification for improved theoretical guarantees. The proposed estimator is applied to a nonlinear chemical reactor process, showing significant improvement in estimation results with just a few iterations of the optimizer. Different solvers are employed to illustrate the flexibility of the design, and performance is compared with state-of-the-art fast moving horizon estimation schemes.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2023)
Article
Computer Science, Artificial Intelligence
Yicheng Yang, Jae Kwang Kim, In Ho Cho
Summary: The fractional hot-deck imputation (FHDI) is a general imputation method for handling multivariate missing data. However, it lacks efficiency when dealing with big incomplete data. To overcome this limitation, a parallel version called P-FHDI is developed, which shows favorable speedup for large incomplete datasets.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Engineering, Electrical & Electronic
Qi Shi, Yangyu Liu, Shunqing Zhang, Shugong Xu, Vincent K. N. Lau
Summary: By utilizing super-resolution image recovery scheme and recurrent network structure, a novel channel estimation scheme has been developed, which outperforms conventional methods in both stationary and non-stationary environments.
IEEE TRANSACTIONS ON COMMUNICATIONS
(2021)
Article
Computer Science, Interdisciplinary Applications
Zhihao Zheng, Shuming Gao, Chun Shen
Summary: This paper proposes a progressive block decomposition algorithm that simplifies models by suppressing features and recovers the suppressed features to obtain a consistency-ensured block structure.
ENGINEERING WITH COMPUTERS
(2022)
Article
Statistics & Probability
Marta Ferreira
Summary: Assessing the risk of extreme phenomena is closely related to the theory of extreme values. In the context of time series, analyzing the smoothness of its trajectory contributes to the assessment of risk associated with extreme observations. This study focuses on inferential analysis of the upper tail smoothness coefficient in time series using subsampling techniques, proposing an estimator with reduced bias, and investigating confidence intervals estimation and smoothness detection using a block bootstrap methodology. An application to real data is also presented.
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
(2023)
Article
Economics
Harold D. Chiang, Bing Yang Tan
Summary: This article examines the asymptotic properties and alternative inference methods for kernel density estimation (KDE) for dyadic data. It establishes uniform convergence rates for dyadic KDE and proposes a modified jackknife empirical likelihood procedure for inference. The results are extended to cover incomplete dyadic data and simulations demonstrate the effectiveness of the proposed procedure. The method is illustrated through a study of airport congestion in the United States.
JOURNAL OF BUSINESS & ECONOMIC STATISTICS
(2023)
Article
Engineering, Electrical & Electronic
Ghania Fatima, Prabhu Babu, Petre Stoica
Summary: A new method is proposed to estimate the covariance matrix with non-negative off-diagonal elements, which is useful in portfolio selection in finance. By incorporating the non-negativity constraint in the maximum likelihood estimation problem and utilizing a block coordinate descent algorithm, the proposed method shows better performance than a state-of-the-art method based on numerical simulations.
IEEE SIGNAL PROCESSING LETTERS
(2022)