A Robust Variable Selection Method for Sparse Online Regression via the Elastic Net Penalty

Wang, Wentao; Liang, Jiaxuan; Liu, Rong; Song, Yong; Zhang, Min

doi:10.3390/math10162985

Cited by 10 publications

(6 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It combines the strengths of two other regularization methods, L1: least absolute shrinkage and selection operator (LASSO) and L2: Ridge regression regularization. EN can handle multicollinearity, which occurs when some predictors correlate strongly (Wang, Liang, Liu, Song, & Zhang, 2022). The LASSO regularization can encounter problems of inconsistency and instability in the presence of multicollinearity since it may arbitrarily select one predictor over another.…”

Section: Elastic Net (En)mentioning

confidence: 99%

Predicting medical waste generation and associated factors using machine learning in the Kingdom of Bahrain

Al-Omran,

Khan

2024

Environ Sci Pollut Res

View full text Add to dashboard Cite

Effective planning and managing medical waste necessitate a crucial focus on both the public and private healthcare sectors. This study uses machine learning techniques to estimate medical waste generation and identify associated factors in a representative private and a governmental hospital in Bahrain. Monthly data spanning from 2018 to 2022 for the private hospital and from 2019 to February 2023 for the governmental hospital was utilized. The ensemble voting regressor was determined as the best model for both datasets. The model of the governmental hospital is robust and successful in explaining 90.4% of the total variance.Similarly, for the private hospital, the model variables are able to explain 91.7% of the total variance. For the governmental hospital, the significant features in predicting medical waste generation were found to be the number of inpatients, population, surgeries, and outpatients, in descending order of importance. In the case of the private hospital, the order of feature importance was the number of inpatients, deliveries, personal income, surgeries, and outpatients. These findings provide insights into the factors influencing medical waste generation in the studied hospitals and highlight the effectiveness of the ensemble voting regressor model in predicting medical waste quantities.

show abstract

Section: Elastic Net (En)mentioning

confidence: 99%

Predicting medical waste generation and associated factors using machine learning in the Kingdom of Bahrain

Al-Omran,

Khan

2024

Environ Sci Pollut Res

View full text Add to dashboard Cite

show abstract

“…Although it amplifies the regression performance (quality of fit), this method might underestimate the penalty, ultimately reducing selection efficiency. With small values of λ, the majority of the coefficients do not achieve a 0 value, leading to a larger dataset [21]. This limitation leads to the underperformance of ridge regression in analyzing numerous features.…”

Section: Ridgementioning

confidence: 99%

“…When high multicollinearity is present, ridge may outperform LASSO and EN. However, LASSO shows a superior capability to select features, while EN improves estimations over datasets with unknown variance [21].…”

Section: Elastic Netmentioning

confidence: 99%

Analyzing factors influencing global precious metal markets: A feature selection study

et al. 2023

View full text Add to dashboard Cite

Precious metals are valuable commodities providing superior protection against risky financial exposure. Identifying factors influencing the market is crucial for anticipating changes. Forecast applications utilize stochastic models capable of learning from historical data to project future values. The dataset is a vital component for prediction tools since all estimations begin with constructing the appropriate information. Detecting the association between input and output is essential to filter data, as including unrelated variables could destabilize the response. Feature selection considers removing uncorrelated attributes before incorporating them as inputs to the predictor. This study employs three regression-based algorithms to examine 58 precious assets from gold, silver, platinum, and palladium markets against several variables cited in the literature. Relationships were detected using regressive feature selection methods, known as least absolute shrinkage and selection operator (LASSO), ridge, and elastic net (EN). Results demonstrate that the proposed algorithms achieved satisfactory performance on 42 assets, justified through a reliable fit and acceptable error. The remaining 16 assets exhibited large deviations with considerably poor regression quality, indicating considerable nonlinearity. Attributes were selected with a detailed emphasis on those exerting the most substantial impact on a particular metal. Based on computational analysis, most investments are susceptible to macroeconomic factors. Some assets may present hedging capabilities towards key features, including stock index, exchange rates, and bond yield. An assessment of common variables among each metal revealed that real GDP growth and interest rates are vital indicators for the precious metal market. Overall, the simulation outcomes show no consistent commonalities amongst attributes within the same asset class in a country. Feature selection from this research offers necessary information regarding time-series dynamics, serving as a basis to project trends. The filtered dataset is expected to enhance the reliability of nonlinear predictive algorithms by removing inaccurate correlations to lower computational load. Furthermore, the outcome provides information regarding correlations affecting global precious metal investments over five-year period. These discussions are necessary for investors considering such commodities as potential portfolio diversifiers.

show abstract

“…Detailed mathematical formulations of entropy, computation of maximum values and mean values reported in [21][22][23] have been used in this paper to compute CFI1 to CFI7.…”

Section: Classification Of Pqementioning

confidence: 99%

Power Quality Detection and Categorization Algorithm Actuated by Multiple Signal Processing Techniques and Rule-Based Decision Tree

Singh¹,

Sharma²,

Garg³

et al. 2023

Sustainability

View full text Add to dashboard Cite

This paper introduces a power quality (PQ) detection and categorization algorithm actuated by multiple signal processing techniques and rule-based decision tree (RBDT). This is aimed to recognize PQ events of simple nature and higher order multiplicity with less computational time using hybridization of the signal processing techniques. A voltage waveform with a PQ event (PQE) is processed using the Stockwell transform (ST) to compute the Stockwell PQ detection index (SPDI). The voltage waveform is also processed using the Hilbert transform (HT) to compute the Hilbert PQ detection index (HPDI). A voltage waveform is also decomposed using the Discrete Wavelet transform (DWT) to compute the classification feature index (CFI) [CFI1 to CFI4]. A combined PQ detection index (CPDI) is computed by multiplication of the SPDI, the HPDI and CFI1 to CFI4. Incidence of a PQE on a voltage signal is located with the help of a location PQ disturbance index (LPDI) which is computed by differentiating the CPDI with respect to time. CFI5, CFI6 and CFI7 are computed from the SPDI, the HPDI and the CPDI, respectively. Categorization of PQ events is performed using CFI1 to CFI7 by the rule-based decision tree (RBDT) with the help of simple decision rules. We conclude that the proposed algorithm is effective to identify the PQE with an accuracy of 98.58% in a noise-free environment and 97.62% in the presence of 20 dB SNR (signal-to-noise ratio) noise. Ten simple nature PQEs and eight combined PQ events (CPQEs) with multiplicity of two, three and four are effectively detected and categorized using the algorithm. The algorithm is also tested to detect a sag PQ event due to a line-to-ground (LG) fault incident on a practical distribution utility network. The performance of the investigated method is compared with a DWT-based technique in terms of accuracy of classification with and without noise, maximum computational time of PQ detection and multiplicity of PQE which can be effectively detected. A simulation is performed using the MATLAB software. MATLAB codes are used for modelling the PQE disturbances and the proposed algorithm using mathematical formulations.

show abstract

A Robust Variable Selection Method for Sparse Online Regression via the Elastic Net Penalty

Cited by 10 publications

References 31 publications

Predicting medical waste generation and associated factors using machine learning in the Kingdom of Bahrain

Predicting medical waste generation and associated factors using machine learning in the Kingdom of Bahrain

Analyzing factors influencing global precious metal markets: A feature selection study

Power Quality Detection and Categorization Algorithm Actuated by Multiple Signal Processing Techniques and Rule-Based Decision Tree

Contact Info

Product

Resources

About