Article
Computer Science, Information Systems
Eduardo Pavez, Antonio Ortega
Summary: This paper examines covariance estimation with missing data, proposing unbiased estimators for different missing data mechanisms and obtaining upper bounds for their estimation errors in operator norm. The results provide new upper bounds for non-uniform and dependent missing data scenarios.
IEEE TRANSACTIONS ON INFORMATION THEORY
(2021)
Article
Engineering, Aerospace
Augusto Aubry, Vincenzo Carotenuto, Antonio De Maio, Massimo Rosamilia, Stefano Marano
Summary: This article discusses the problem of adaptive radar detection in a missing-data context and proposes the use of maximum likelihood estimation (MLE) and the expectation-maximization (EM) algorithm to handle the optimal design strategy, evaluating the performance of the designed framework.
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS
(2022)
Article
Mathematics, Applied
Binhong Yao, Peixing Li
Summary: In recent years, functional data analysis (FDA) and reproducing kernel Hilbert space (RKHS) have been commonly used in various applications. However, the application of RKHS framework to study the covariance of incomplete functional data is rare. This paper investigates the global estimation error of the covariance function obtained from fragmented data, considering the connection between functional data and RKHS. The simulation results demonstrate the validity of the theoretical findings by comparing the estimation errors of two types of functional data.
APPLIED MATHEMATICS AND COMPUTATION
(2023)
Article
Computer Science, Information Systems
Marko Niemela, Sami Ayramo, Tommi Karkkainen
Summary: The study introduces a new toolbox for handling data with missing values, which includes functions for data preprocessing, distance estimation, clustering, and cluster validation, providing core elements for comprehensive cluster analysis methodologies.
Article
Engineering, Electrical & Electronic
C. Haley
Summary: This article generalizes Chave's estimator for multitaper spectral density to coherence and phase estimation, with the addition of bootstrapped confidence intervals. Two examples are provided, demonstrating the improved performance of the missing-data coherence estimator over the Daniell-smoothed coherence estimator in real data with gaps. The case of two time series with different missing indices is also discussed.
IEEE SIGNAL PROCESSING LETTERS
(2021)
Article
Engineering, Electrical & Electronic
Augusto Aubry, Antonio De Maio, Stefano Marano, Massimo Rosamilia
Summary: This paper addresses the estimation of structured covariance matrix in radar signal processing applications in the presence of missing data. A general procedure using the expectation-maximization algorithm is developed for optimizing the observed-data likelihood function. The study contextualizes the estimation technique for two radar problems and introduces detection techniques based on classic information criteria.
IEEE TRANSACTIONS ON SIGNAL PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Shaojing Sheng, Xianjie Guo, Kui Yu, Xindong Wu
Summary: This study proposes a novel method for local causal structure learning with missing data, named misLCS. It addresses the issues of low accuracy, low efficiency, and instability in existing algorithms by incorporating iterative data imputation, data subset strategy, and mutual information-based feature selection. Experimental results demonstrate that misLCS outperforms other algorithms in terms of accuracy.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Automation & Control Systems
Timothy Cannings, Yingying Fan
Summary: This paper introduces a novel approach to estimation problems in the presence of missing data. The proposed Correlation-Assisted Missing data (CAM) estimator exploits the relationship between observations with missing features and those without missing features, leading to improved prediction accuracy. Theoretical analysis and practical demonstrations demonstrate that the CAM estimator has lower mean squared error and is effective in various estimation problems.
JOURNAL OF MACHINE LEARNING RESEARCH
(2022)
Article
Computer Science, Artificial Intelligence
Xinyu Zhang, Zhiwei Li, Zhenhong Zou, Xin Gao, Yijin Xiong, Dafeng Jin, Jun Li, Huaping Liu
Summary: Noise is always a significant issue in object detection, causing confusion in model reasoning and reducing the informativeness of data. To address this, we propose a universal uncertainty-aware multimodal fusion model that adaptsively selects valid information from both point clouds and images. Our model reduces randomness and generates reliable output, as demonstrated by experiments on the KITTI 2-D object detection dataset.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Mathematics
Jorge R. Sosa Donoso, Miguel Flores, Salvador Naya, Javier Tarrio-Saavedra
Summary: This work presents a methodology for detecting outliers in functional data that considers both their shape and magnitude. The Local Correlation Integral (LOCI) method, a multivariate anomaly detection technique, has been extended and adapted for functional data using distance calculations in Hilbert spaces. The methodology has been validated through simulation studies and application to real data, showing good performance in scenarios with inter-curve dependence, particularly when outliers are due to curve magnitudes. Results are further supported by the successful application of the methodology to a meteorological database, outperforming other competitive methods.
Article
Computer Science, Artificial Intelligence
Thu T. Nguyen, Khoi Minh Nguyen-Duy, Duy Ho Minh Nguyen, Binh T. Nguyen, Bruce Alan Wade
Summary: Parameter estimation is a crucial problem, especially in the presence of missing values in the dataset. This paper proposes a novel algorithm that directly finds the maximum likelihood estimates for randomly missing datasets without the need for imputation preprocessing. The empirical results demonstrate the superior estimation performance and lower time consumption of the proposed algorithm.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Engineering, Multidisciplinary
Sudarshan R. Khond, Vijay S. Kale, Makarand Sudhakar Ballal
Summary: Communication infrastructure is crucial for the control and protection of modern distribution systems. This article proposes a data mining method to detect bad/noisy data and utilizes machine learning models to estimate the value of the detected bad data signals.
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS
(2023)
Article
Mathematics
Fatimah Alshahrani, Ibrahim M. Almanjahie, Tawfik Benchikh, Omar Fetitah, Mohammed Kadi Attouch
Summary: This study investigates the estimation of the regression function using the kernel method in the presence of missing at random responses, assuming spatial dependence, and complete observation of the functional regressor. The asymptotic properties of the estimator are constructed, and the probability convergence (with rates) as well as the asymptotic normality of the estimator are derived under certain weak conditions. Simulation studies and real data analysis demonstrate the superior performance of the proposed estimator especially when there are a large number of missing at random data.
JOURNAL OF MATHEMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Necla Kochan, G. Yazgi Tutuncu, Goknur Giner
Summary: This study introduces a new approach based on local dependence function to estimate covariance matrix in order to improve the classification performance of RNA-Seq data sets. This new method assumes that dependencies between genes are locally defined rather than completely dependent.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Phimmarin Keerin, Tossapon Boongoen
Summary: This paper aims to develop new imputation methods to handle missing values in astronomical data analysis, particularly in the classification of transient events in a sky survey. The proposed Iterative-CKNN and Iterative-CLLS models extend the cluster directed selection of neighbors framework and achieve better performance than baseline models and Bayesian Principal Component Analysis. These methods have practical implications for classifying transients.
INFORMATION PROCESSING & MANAGEMENT
(2022)