Hi-LASSO: High-Dimensional LASSO

Youngsoon, Kim; Hao, Jie; Mallavarapu, Tejaswini; Park, Joong-Yang; Kang, Min-Hee

doi:10.1109/access.2019.2909071

Cited by 27 publications

(15 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LASSO regression performs L1 regularization and the aim is to get the subset of predictors that decrease the error rate of prediction for a target attribute [22].…”

Section: Machine Learning Algorithmsmentioning

confidence: 99%

Makine Öğrenmesi Algoritmalarını Kullanarak Rüzgar Enerjisi Üretimi Tahmini

Yurek¹,

Birant²,

Yürek³

2021

Deu Muhendislik Fakultesi Fen Ve Muhendislik

View full text Add to dashboard Cite

Renewable energy becomes progressively popular in the world because renewable resources such as solar, geothermal, wind energy are clean, inexhaustible and come from natural sources. Wind energy is one of the most significant resources of renewable energy and it plays a key role in the generation of electricity. Thus, accurate wind power estimation is crucial to deal with the challenges to balance energy trading, planning, scheduling decisions and strategies of wind power generation. This study proposes a prediction model to solve a real-life problem in the renewable energy sector by accurately estimating the amount of wind energy production per hour in the next 24 hours by applying machine learning (ML) techniques using historical wind power generation data and weather forecasting reports. In the proposed approach, first, an unsupervised ML method (i.e., the K-Means clustering algorithm) is applied to group data into meaningful clusters; then, these clusters are accepted as new feature values and added to the dataset to enlarge it; finally, a supervised ML method (i.e., regression) is performed for prediction. This study compares nine supervised learning algorithms: K-Nearest Neighbors, Support Vector Regression, Random Forest, Extra Trees, Gradient Boosting, Ridge Regression, Least Absolute Shrinkage and Selection Operator, Decision Tree, and Convolutional Neural Network. The aim of this study is to investigate the success of different ML algorithms on real-world data of wind turbines and propose a methodology to benchmark various machine learning algorithms to choose the most accurate final model for wind power generation prediction.

show abstract

“…LASSO regression performs L1 regularization and the aim is to get the subset of predictors that decrease the error rate of prediction for a target attribute [22].…”

Section: Machine Learning Algorithmsmentioning

confidence: 99%

Makine Öğrenmesi Algoritmalarını Kullanarak Rüzgar Enerjisi Üretimi Tahmini

Yurek¹,

Birant²,

Yürek³

2021

Deu Muhendislik Fakultesi Fen Ve Muhendislik

View full text Add to dashboard Cite

show abstract

“…where n denotes the exponent (n=2); min The Lasso is based on the following linear model [41]: where 0   is the shrinkage tuning parameter.…”

Section: B Contingency Filteringmentioning

confidence: 99%

Security-Constrained Multi-Objective Optimal Power Flow for a Hybrid AC/VSC-MTDC System With Lasso-Based Contingency Filtering

2020

IEEE Access

View full text Add to dashboard Cite

In order to coordinate the economy and voltage quality of a meshed AC/VSC-MTDC system, a new corrective security-constrained multi-objective optimal power flow (SC-MOPF) method is presented in this paper. A parallel SC-MOPF model with N-1 security constraints is proposed for corrective control actions of the meshed AC/DC system, in which the minimization of the generation cost and voltage deviation are used as objective functions. To solve this model, a novel parallel bi-criterion evolution indicator based evolutionary algorithm (BCE-IBEA) algorithm is developed to seek multiple well-spread Pareto-optimal solutions through the introduction of parallel computation. In this process, a least absolute shrinkage and selection operator (Lasso)-based N-1 contingency filtering scheme with a composite security index is developed to efficiently screen out the most severe cases from all contingencies. And thereby, the best compromise solutions reflecting the preferences of different decision makers are automatically determined via an integrated decision making technique. Case studies in the modified IEEE 14-and 300bus systems demonstrate that the presented approach manages to address this SC-MOPF problem with significantly improved computational efficiency.INDEX TERMS AC/DC system, multi-objective optimization, optimal power flow, VSC-HVDC, decision making, contingency filtering ,2 c PI are the c PI values, which are respectively obtained by using the Lasso approach and the direct computation according to (19).

show abstract

“…We recently proposed a high-dimensional LASSO (Hi-LASSO) that theoretically improves the predictive power and feature selection performance on High-Dimension, Low Sample Size (HDLSS) data [8]. Hi-LASSO (1) alleviates bias introduced from bootstrapping, (2) satisfies the global oracle property, and (3) provides a Parametric Statistical Test for Feature Selection in Bootstrap regression modeling (PSTFSboot).…”

Section: Introductionmentioning

confidence: 99%

Hi-LASSO: High-performance python and apache spark packages for feature selection with high-dimensional data

Jung

Park

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

High-dimensional LASSO (Hi-LASSO) is a powerful feature selection tool for high-dimensional data. Our previous study showed that Hi-LASSO outperformed the other state-of-the-art LASSO methods. However, the substantial cost of bootstrapping and the lack of experiments for a parametric statistical test for feature selection have impeded to apply Hi-LASSO for practical application. In this paper, the Python package and its Spark library are efficiently implemented in a parallel manner for practice with real-world problems, as well as providing the capability of the parametric statistical tests for feature selection on high-dimensional data. We demonstrate Hi-LASSO’s outperformance with various intensive experiments in a practical manner. Hi-LASSO will be efficiently and easily performed by using the packages for feature selection. Hi-LASSO packages are publicly available at https://github.com/datax-lab/Hi-LASSO under the MIT license. The packages can be easily installed by Python PIP, and additional documentation is available at https://pypi.org/project/hi-lasso and https://pypi.org/project/Hi-LASSO-spark.Author summaryWe provide the brief presentation in the literature of Hi-LASSO comparing to Random LASSO. Then, we describe Hi-LASSO’s open-source packages in Python and Apache Spark, specifying parameters. The open-source packages improves efficiency and scalability of Hi-LASSO, so that the time-consuming bootstrapping-based parametric statistical test can be practically applied for high-dimensional data. We conducted intensive experiments to assess the performance of the packages with the parametric statistical test using simulation data, semi-real datasets, and TCGA cancer dataset. The Hi-LASSO packages showed outstanding and robust performance in feature selection. The packages are available through PyPI and can be easily installed using Python PIP.

show abstract

Hi-LASSO: High-Dimensional LASSO

Cited by 27 publications

References 17 publications

Makine Öğrenmesi Algoritmalarını Kullanarak Rüzgar Enerjisi Üretimi Tahmini

Makine Öğrenmesi Algoritmalarını Kullanarak Rüzgar Enerjisi Üretimi Tahmini

Security-Constrained Multi-Objective Optimal Power Flow for a Hybrid AC/VSC-MTDC System With Lasso-Based Contingency Filtering

Hi-LASSO: High-performance python and apache spark packages for feature selection with high-dimensional data

Contact Info

Product

Resources

About