Article
Thermodynamics
Mohammad Ali Sahraei, Hakan Duman, Muhammed Yasin Codur, Ecevit Eyduran
Summary: This research aims to predict transport energy demand in Turkey using the MARS model, with the third MARS model selected as the best predictive model after evaluating multiple factors.
Article
Computer Science, Hardware & Architecture
Ankita Bose, Ching-Hsien Hsu, Sanjiban Sekhar Roy, Kun Chang Lee, Behnam Mohammadi-ivatloo, Satheesh Abimannan
Summary: The proposed hybrid model combines MARS and DNN to predict stock closing prices with a high accuracy of up to 92% on the KOSPI dataset. The model successfully reduces feature dimensions and uses data augmentation to further validate the results.
COMPUTERS & ELECTRICAL ENGINEERING
(2021)
Article
Automation & Control Systems
Lorenzo Nespoli, Vasco Medici
Summary: This paper presents a computationally efficient algorithm for fitting multivariate boosted trees and proves that multivariate trees outperform univariate trees when there is prediction correlation. The algorithm also allows for arbitrary regularization of predictions to enforce properties like smoothness, consistency, and functional relations. Applications and numerical results related to forecasting and control are presented.
JOURNAL OF MACHINE LEARNING RESEARCH
(2022)
Article
Engineering, Geological
Wengang Zhang, Chongzhi Wu, Yongqin Li, Lin Wang, P. Samui
Summary: This study utilizes machine learning algorithms to construct predictive models for assessing pile drivability, comparing the performance of Random Forest Regression (RFR) and Multivariate Adaptive Regression Splines (MARS) models. The results indicate that the RFR model outperforms MARS in terms of fitting and operational efficiency.
GEORISK-ASSESSMENT AND MANAGEMENT OF RISK FOR ENGINEERED SYSTEMS AND GEOHAZARDS
(2021)
Article
Automation & Control Systems
Bin Li, Brian D. Marx, Somsubhra Chakraborty, David C. Weindorf
Summary: Data heterogeneity poses a challenge in modern data analysis, with traditional statistical modeling methods struggling to perform well on such data. This study addresses a multivariate calibration problem in soil characterization, proposing a varying-coefficient signal regression model that outperforms other methods in external prediction error.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2021)
Article
Statistics & Probability
Jianhua Z. Huang, Ya Su
Summary: This paper develops a general theory on rates of convergence of penalized spline estimators for function estimation, allowing for various combinations of spline degree, penalty order, and smoothness of unknown functions. The theory's application spans across different contexts such as regression, density estimation, and estimation of spectral density function of a stationary time series.
ANNALS OF STATISTICS
(2021)
Article
Biochemical Research Methods
Ruiqing Zheng, Min Li, Xiang Chen, Siyu Zhao, Fang-Xiang Wu, Yi Pan, Jianxin Wang
Summary: Gene regulatory networks play a crucial role in biological processes and exhibit diversity under different biological conditions. Reconstructing these networks from gene expression data has been a significant challenge in the past decades. The proposed PBMarsNet method shows superior performance and generalization compared to other state-of-the-art methods in inferring directed GRNs from multifactorial gene expression data.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2021)
Article
Engineering, Environmental
Tengfei Wang, Hongfei Ma, Jiankun Liu, Qiang Luo, Qingzhi Wang, You Zhan
Summary: This study proposes a practical approach to assess the frost heave susceptibility of gravelly soils under unidirectional freezing conditions. Through frost heave tests and data analysis, an evaluation guideline for optimized railway roadbed is developed.
COLD REGIONS SCIENCE AND TECHNOLOGY
(2021)
Article
Computer Science, Information Systems
Geetabai S. Hukkeri, Sujay Raghavendra Naganna, Dayananda Pruthviraja, Nagaraj Bhat, R. H. Goudar
Summary: This research focuses on 1-step lead time forecasting of meteorological drought episodes using different models. The results show that the multivariate adaptive regression splines and gradient tree boosting models have higher accuracy and lower error rates compared to the artificial neural network model. The thematic maps created using spatial interpolation confirm the occurrence of drought in the district.
Article
Green & Sustainable Science & Technology
Ming Xie, Shuli Yan, Lifeng Wu, Liying Liu, Yongfeng Bai, Linghui Liu, Yanzeng Tong
Summary: This paper proposes a novel robust reweighted multivariate grey model (RWGM(1,N)) for accurately forecasting national-level greenhouse gas emissions. The model reduces overfitting with weighted factors and employs LASSO regression for variable selection, showing higher predictive accuracy and robust performance in simulating GHG emissions in EU member countries.
JOURNAL OF CLEANER PRODUCTION
(2021)
Article
Computer Science, Interdisciplinary Applications
Peder Bacher, Hjorleifur G. Bergsteinsson, Linde Frolke, Mikkel L. Sorensen, Julian Lemos-Vinasco, Jon Liisberg, Jan Kloppenborg Moller, Henrik Aalborg Nielsen, Henrik Madsen
Summary: Online forecasting is crucial for decision-making systems that rely on forecasts. These systems require frequent updates and the ability to adapt to changing data and models. The R package onlineforecast provides a flexible setup for creating and running custom models in an operational setting.
Article
Statistics & Probability
Yongli Zhang, Craig Rolling, Yuhong Yang
Summary: In this paper, a new method is proposed for modeling and forecasting correlation matrices, allowing correlations to be nonlinearly driven by common factors. The nonlinear common factor (NCF) method simplifies estimation and provides more flexibility than previous methods. This method is demonstrated using energy prices in Boston.
JOURNAL OF MULTIVARIATE ANALYSIS
(2021)
Article
Economics
Jieying Jiao, Zefan Tang, Peng Zhang, Meng Yue, Jun Yan
Summary: This paper proposes a cyberattack-resilient load forecasting approach based on an adaptive robust regression method, where the observations are trimmed based on their residuals. Comparison study shows that the proposed method outperforms the standard robust regression in various settings.
INTERNATIONAL JOURNAL OF FORECASTING
(2022)
Article
Engineering, Geological
Mohsin Usman Qureshi, Zafar Mahmood, Ali Murtaza Rasool
Summary: This paper analyzes the in situ permeability in limestone and sandstone formations for hydraulic structures in Oman and examines the relationship between permeability and rock quality designation. The study finds that in situ permeability decreases as rock quality designation increases at certain depths.
JOURNAL OF ROCK MECHANICS AND GEOTECHNICAL ENGINEERING
(2022)
Article
Multidisciplinary Sciences
Meryem Bekar Adiguzel, Mehmet Ali Cengiz
Summary: Multivariate Adaptive Regression Splines (MARS) is a non-parametric regression analysis method that is useful for model selection in high-dimensional data. It has the advantage of identifying and modeling complex, non-linear relationships between variables without requiring assumptions, as well as automatically selecting variables to simplify the model building process and prevent overfitting.
Article
Construction & Building Technology
Samiran Khorat, Debashish Das, Rupali Khatun, Sk Mohammad Aziz, Prashant Anand, Ansar Khan, Mattheos Santamouris, Dev Niyogi
Summary: Cool roofs can effectively mitigate heatwave-induced excess heat and enhance thermal comfort in urban areas. Implementing cool roofs can significantly improve urban meteorology and thermal comfort, reducing energy flux and heat stress.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Qi Li, Jiayu Chen, Xiaowei Luo
Summary: This study focuses on the vertical wind conditions as a main external factor that limits the energy assessment of high-rise buildings in urban areas. Traditional tools for energy assessment of buildings use a universal vertical wind profile estimation, without taking into account the unique wind speed in each direction induced by the various shapes and configurations of buildings in cities. To address this limitation, the study developed an omnidirectional urban vertical wind speed estimation method using direction-dependent building morphologies and machine learning algorithms.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Xiaojun Luo, Lamine Mahdjoubi
Summary: This paper presents an integrated blockchain and machine learning-based energy management framework for multiple forms of energy allocation and transmission among multiple domestic buildings. Machine learning is used to predict energy generation and consumption patterns, and the proposed framework establishes optimal and automated energy allocation through peer-to-peer energy transactions. The approach contributes to the reduction of greenhouse gas emissions and enhances environmental sustainability.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Ying Yu, Yuanwei Xiao, Jinshuai Chou, Xingyu Wang, Liu Yang
Summary: This study proposes a dual-layer optimization design method to maximize the energy sharing potential, enhance collaborative benefits, and reduce the storage capacity of building clusters. Case studies show that the proposed design significantly improves the performance of building clusters, reduces energy storage capacity, and shortens the payback period.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Felix Langner, Weimin Wang, Moritz Frahm, Veit Hagenmeyer
Summary: This paper compares two main approaches to consider uncertainties in model predictive control (MPC) for buildings: robust and stochastic MPC. The results show that compared to a deterministic MPC, the robust MPC increases the electricity cost while providing complete temperature constraint satisfaction, while the stochastic MPC slightly increases the electricity cost but fulfills the thermal comfort requirements.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Somil Yadav, Caroline Hachem-Vermette
Summary: This study proposes a mathematical model to evaluate the performance of a Double Skin Facade (DSF) system and its impact on indoor conditions. The model considers various design parameters and analyzes their effects on the system's electrical output and room temperature.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Ruijun Chen, Holly Samuelson, Yukai Zou, Xianghan Zheng, Yifan Cao
Summary: This research introduces an innovative resilient design framework that optimizes building performance by considering a holistic life cycle perspective and accounting for climate projection uncertainties. The study finds that future climate scenarios significantly impact building life cycle performance, with wall U-value, windows U-value, and wall density being major factors. By using ensemble learning and optimization algorithms, predictions for carbon emissions, cost, and indoor discomfort hours can be made, and the best resilient design scheme can be selected. Applying this framework leads to significant improvements in building life cycle performance.
ENERGY AND BUILDINGS
(2024)