Special Issue Introduction
Special Issues List
Aims and Scope
Article Processing Charge
Open Access Policy
1796-2021 (Online); 2374-4367 (Print)
Prof. Maode Ma
Prof. Jalel Ben-Othman, Prof. Nobuo Funabiki
Prof. Jason Z. Kang
or comments to
Assoc. Prof. Maode Ma
School of Electrical & Electronic Engineering, Nanyang Technological University, Singapore
I'm very happy and honored to take on the position of editor-in-chief of JCM, which is a high-quality journal with potential and I'll try my every effort to bring JCM to a next level...
Welcome Prof. Abdelhalim Zekry from Egypt to join the Editorial board of JCM.
Volume 15, No. 6 have both been indexed by Scopus.
Volume 15, No. 7 has been published online!
Volume 12, No. 3, March 2017
Matrix Completion under Gaussian Models Using MAP and EM Algorithms
, Viswanathan Swaminathan
, and Ratnesh Kumar
1. Dept. of Elec. & Comp. Eng., Iowa State University, Ames, IA 50010, United States
2. Adobe Research, Adobe Systems Inc., San Jose, CA 95110, United States
—Completing a partially-known matrix (matrix completion) is an important problem in the field of data mining and signal processing, and has been successfully applied to sensor localization and recommendation system. Low-rank and factorization models are the two most popular and successful classes of models used for matrix completion. In this paper, we investigate another approach based on statistical estimation which has previously been used for matrix completion. In an initial work involving Gaussian Models (GM), the formulation
was inaccurate necessitating an ad-hoc empirical diagonal loading to a covariance matrix, requiring additional tuning, and making the final estimate of model parameters difficult to interpret. An accurate formulation using a correct objective function based on likelihood estimation already exists in statistical literature, which we utilize here to learn the model parameters using an Expectation Maximization (EM) algorithm. This approach no longer needs tuning and performs better in the numerical experiments. Owing to the difference that stems from the difference in choice of objective function, we not
e that the original method leads to an underestimated covariance matrix necessitating an artificial diagonal loading, while the method we use provides a Maximum Likelihood (ML) estimate of the model parameters. We also validate our approach using realworld data from MovieLens, EachMovie and Netflix.
—Matrix completion, sensor localization, recommendation system, expectation maximization algorithm, Gaussian model, maximum likelihood estimate
Cite: Gang Wu, Viswanathan Swaminathan, and Ratnesh Kumar, "Matrix Completion under Gaussian Models Using MAP and EM Algorithms," Journal of Communications, vol. 12, no. 3, pp. 180-186, 2017. Doi: 10.12720/jcm.12.3.180-186
High Accuracy Signal Recognition Algorithm Based on Machine Learning for Heterogeneous Cognitive Wireless Networks
Gracefully Mitigating Communication Protocol Reuse Breakdowns
Copyright © 2013-2020 Journal of Communications, All Rights Reserved