An EM algorithm for GMM parameter estimation in the presence of censored and dropped data with potential application for indoor positioning

Vu, Trung Kien; Hoàng, Mạnh Kha; Le, Hung Lan

doi:10.1016/j.icte.2018.08.001

Cited by 13 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…11 A GMM can represent the law of anything when the sample data points are large enough. 12,13 The GMM clustering algorithm is used to identify the heat load pattern and improve the reliability of the district heating system. 14 Based on the EM algorithm, the parameters of the generalized gamma mixed model are derived through Bayesian estimation.…”

Section: Retracted: Numerical Inversion Of Gaussian Mixture Model For...mentioning

confidence: 99%

RETRACTED: Numerical inversion of Gaussian mixture model for gas explosion shock wave based on a Markov chain Monte Carlo algorithm

Zhang

Gong

et al. 2021

International Journal of Electrical Engineering & Education

View full text Add to dashboard Cite

Using Markov chain Monte Carlo (MCMC) random sampling, a Gaussian mixture model (GMM) of the overpressure of a blast shock wave based on parameter optimization of an expectation-maximization (EM) algorithm is proposed to improve the accuracy of sampling. The probability of an explosion caused by gas accumulation under different conditions is obtained from statistics of gas explosion accidents. The explosion equivalent and shock wave overpressure are estimated by using field gas data. The data sets of different types of gas explosions and their corresponding density distribution functions are established. The EM algorithm is used for iterative calculation, and the optimal distribution of each gas explosion data set is obtained. The parameters are built according to a posteriori optimization. A state transition matrix is used to achieve numerical inversion of the overpressure of an MCMC gas explosion shock wave. The inversion results are based on the actual conditions of the mine. On the premise of improving the accuracy of the random simulation, the overpressure value of shock wave is more in line with the law of disaster change, which provides theoretical support for safety protection during a disaster.

show abstract

Section: Retracted: Numerical Inversion Of Gaussian Mixture Model For...mentioning

confidence: 99%

RETRACTED: Numerical inversion of Gaussian mixture model for gas explosion shock wave based on a Markov chain Monte Carlo algorithm

Zhang

Gong

et al. 2021

International Journal of Electrical Engineering & Education

View full text Add to dashboard Cite

show abstract

“…For estimating parameters of a probabilistic model in the presence of missing data, the EM algorithm [16], [17] is one of the most feasible estimators among available novel approaches. The results in [15] showed the effectiveness of the EM algorithm for the CD-GMM. However, this approach can only be used for parameter estimation of the GMM with known number of components.…”

Section: Parameter Estimation and Model Selectionmentioning

confidence: 87%

“…However, in [8], [11], [13] the censoring and dropping problems have not been considered. With respect to the above mentioned issues, this paper proposes to utilize the GMM including censored and dropped observations (CD-GMM) [15] to model the distribution of the Wi-Fi RSSI data.…”

Section: The Characteristics Of the Measured Wi-fi Rssi Datamentioning

confidence: 99%

“…In (15), the term p(x n ;  j , ) is the continuous probability density function parameterized by  j , .…”

Section: M-stepmentioning

confidence: 99%

“…This approach can deal with the multi-component problem. However, as mentioned in [15], when censored and dropped data presented in collected data, the standard EM algorithm produced biased estimates and, hence, it leads to high positioning error.…”

Section: Positioning Accuracymentioning

confidence: 99%

See 2 more Smart Citations

Performance Enhancement of Wi-Fi Fingerprinting-Based IPS by Accurate Parameter Estimation of Censored and Dropped Data

Vu¹,

Hoàng²,

Le³

2019

RADIOENGINEERING

View full text Add to dashboard Cite

In complex indoor environments, the censoring, dropping, and multi-component problems may present in the observable data. This is due to the attenuation of signals, the unexpected operation of equipments, and the changing surrounding environment. Censoring refers to the fact that sensors on portable devices are unable to measure Received Signal Strength Index (RSSI) values below a certain threshold, for example, −100 dBm with typical smart phones. Dropping means that, occasionally, RSSI measurements of Wi-Fi access points are not available, although their value is clearly above the censoring threshold. The multi-component problem occurs when the measured data varies due to obstacles as well as user directions; doors closed or open; and so forth. Taking these problems into consideration, this paper proposes a novel approach to enhance the performance of the Wi-Fi Fingerprinting based Indoor Positioning System (WF-IPS). The proposed method is verified through simulated data and real field data. The experimental results show that our proposal outperforms the other state-of-the-art WF-IPS approaches both in positioning accuracy and computational cost. KeywordsIPS, EM algorithm, censored and dropped data, Gaussian Mixture Model (GMM), Bayesian Information Criterion (BIC) k k J J J , ,..., PF , max J=J J J max J

show abstract

A Monte Carlo simulation approach for the assessment of health risk from NO$$_{3}^{-}$$-N perturbation in groundwater

Afrifa

Ansah-Narh

Ibrahim

et al. 2023

Model. Earth Syst. Environ.

View full text Add to dashboard Cite

An EM algorithm for GMM parameter estimation in the presence of censored and dropped data with potential application for indoor positioning

Cited by 13 publications

References 8 publications

RETRACTED: Numerical inversion of Gaussian mixture model for gas explosion shock wave based on a Markov chain Monte Carlo algorithm

RETRACTED: Numerical inversion of Gaussian mixture model for gas explosion shock wave based on a Markov chain Monte Carlo algorithm

Performance Enhancement of Wi-Fi Fingerprinting-Based IPS by Accurate Parameter Estimation of Censored and Dropped Data

A Monte Carlo simulation approach for the assessment of health risk from NO$$_{3}^{-}$$-N perturbation in groundwater

Contact Info

Product

Resources

About