Related references
Note: Only part of the references are listed.
Article
Thermodynamics
Xinxing Wei et al.
Summary: China aims to reach its peak CO2 emissions in 2030 and achieve carbon neutrality by 2060. Salt caverns, which can store CO2, are considered as excellent underground energy storage facilities. A correlation model is developed to predict the volume of underground salt caverns and China's CO2 emissions by 2030 based on recent data. An evaluation model for carbon capture capacity is also developed, along with a proposed method for comprehensive utilization of salt cavern energy storage. The research findings provide reference values for the large-scale development of salt caverns and carbon neutralization.
Article
Computer Science, Artificial Intelligence
Rustam Mussabayev et al.
Summary: K-means plays a vital role in data mining and is the simplest and most widely used algorithm under the Euclidean Minimum Sum-of-Squares Clustering (MSSC) model. However, its performance drastically drops when applied to vast amounts of data. Therefore, it is crucial to improve K-means by scaling it to big data using as few computational resources as possible. We propose a new parallel scheme of using K-means and K-means++ algorithms for big data clustering that outperforms the classical and recent state-of-the-art approaches in terms of solution quality and runtime.
PATTERN RECOGNITION
(2023)
Article
Thermodynamics
Connor Scott et al.
Summary: To mitigate carbon emissions from buildings, on-site renewable energy generation systems should be installed to supply energy without relying on the national grid. However, renewable generation sources are unreliable due to weather conditions. This research aims to compare benchmark machine learning algorithms for accurately forecasting photovoltaic (PV) generation at a university campus in central Manchester.
Article
Thermodynamics
Esma Kesriklioglu et al.
Summary: This study aimed to develop a high-performance ensemble learning model to classify total household energy expenditures using household consumption data from 11,521 households. New variables were created and the data was processed using the RapidMiner software program. The results showed that ensemble learning methods significantly enhanced the performance of individual machine learning methods.
Article
Energy & Fuels
Shao-Qun Dong et al.
Summary: This study proposes a practical and innovative ensemble learning strategy and principles to improve accuracy of lithofacies identification. The strategy combines machine learning methods as sub-classifiers to reduce variance errors in prediction and prevent overfitting through algorithm parameter setting and sub-dataset sampling. Comparisons between different machine learning algorithms show that not only decision tree, but also other single-classifiers and ensemble-learning-classifiers can be used as sub-classifiers, and the ensemble strategy and principles can enhance the accuracy of the original classifiers. Heterogeneous ensemble is more suitable for building a more powerful lithofacies identification model in practice.
Article
Energy & Fuels
Yulong Song et al.
Summary: New energy transportation is crucial for global energy industry's future, with new energy vehicles' air conditioning systems facing increasing demands. This study investigates CO2 as an alternative to HFC in bus/railway vehicle air conditioning systems, comparing their performances under different conditions and proposing the concept of CO2 equators for energy, environmental, and economic benefits.
Article
Green & Sustainable Science & Technology
Zhao Li et al.
Summary: This study proposes a data-driven algorithm for assessing the suitability of shallow geothermal energy based on the Entropy Weight Method and TOPSIS Method. The algorithm calculates weights using the Entropy Weight Method and assigns them to the TOPSIS model to determine the closeness coefficient. The algorithm overcomes the subjectivity of expert experience and is more suitable for selecting the best field-site. The algorithm was applied to Nantong, China and produced suitability maps based on the closeness coefficient.
Article
Thermodynamics
Dingding Hu et al.
Summary: With the rapid development of electric vehicles, understanding different types of EV users is crucial for business innovation in the EV sector. This study proposes an integrated approach using data mining and clustering analysis to classify EV users into six groups and provides marketing strategies to improve user loyalty and profitability for charging service enterprises.
Article
Green & Sustainable Science & Technology
Weiyi Chen et al.
Summary: This study develops an XGBoost-based model to assess the seismic vulnerability of buildings in Kavrepalanchok, Nepal. The SMOTE technique is used to handle data imbalance, and the performance of the model is evaluated along with the investigation of important features. The findings include the superior performance of the model and the significant features that influence the overall building damage.
JOURNAL OF CLEANER PRODUCTION
(2022)
Article
Automation & Control Systems
Mingyang Zhang et al.
Summary: This study builds a model to predict repeat purchasers using Tmall's dataset, incorporating innovations such as feature engineering, data imbalance processing, and fusion models. The results show that these innovations have improved the model's prediction performance.
INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL
(2022)
Article
Engineering, Civil
Zhenyuan Zhang et al.
Summary: This study introduces an effective framework based on machine learning to model air traveler repurchasing behavior, which is proven to be superior through comparisons with other algorithms. The utility of this framework is further validated through a field experiment.
JOURNAL OF ADVANCED TRANSPORTATION
(2022)
Article
Mathematical & Computational Biology
Yang Su et al.
Summary: This paper explores the decline of traditional market business models and the rise in consumer cognition, proposing a fusion model that uses deep learning to predict user preferences. By analyzing user characteristics and behaviors, and pushing relevant products, accurate e-commerce marketing goals are achieved. Experimental results demonstrate the superiority and practical value of the model.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2022)
Article
Energy & Fuels
Bing-Yuan Hong et al.
Summary: This paper aims to establish a liquid loading prediction model for natural gas pipeline using machine learning, which can accurately predict the liquid loading and provide technical support for gas pipeline flow assurance. The data-driven model improves calculation efficiency and reduces workload, and is based on a large number of simulations and various working conditions.
Article
Thermodynamics
Mohamed Massaoudi et al.
Summary: This paper introduces an effective computing framework for Short-Term Load Forecasting (STLF) using stacked generalization approach with three models, demonstrating its performance through validation and contributions in novel algorithm, effective technique, critical analysis for hyperparameter optimization, and comparative study.
Article
Energy & Fuels
Bhaskar Patnaik et al.
Summary: This study introduces a novel approach for microgrid fault detection and classification using feature extraction and machine learning. By combining MODWT and XGBoost as an intelligent MPS, the proposed method is validated on standard test models under different conditions, demonstrating its effectiveness and robustness.
Article
Thermodynamics
Ramon Gomes da Silva et al.
Summary: This paper introduces a decomposition-ensemble learning model to predict wind energy for a turbine in a wind farm in Parazinho city, Brazil, with high accuracy and efficiency.
Article
Automation & Control Systems
Haoliang Cui et al.
Summary: Traditional e-commerce user classification methods are not suitable for social e-commerce users, therefore, it is necessary to improve and optimize them according to the characteristics of social e-commerce users. The proposed method can accurately classify social e-commerce users as shown through testing on actual data.
INTELLIGENT AUTOMATION AND SOFT COMPUTING
(2021)
Article
Multidisciplinary Sciences
Cheng-Ju Liu et al.
Article
Computer Science, Artificial Intelligence
Anil Kumar et al.
NEURAL COMPUTING & APPLICATIONS
(2019)
Article
Computer Science, Hardware & Architecture
R. Logesh et al.
MOBILE NETWORKS & APPLICATIONS
(2019)
Article
Computer Science, Software Engineering
Sara Ouaftouh et al.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2019)
Article
Green & Sustainable Science & Technology
David Gabriel de Barros Franco et al.
JOURNAL OF CLEANER PRODUCTION
(2018)
Article
Thermodynamics
Kejun Wang et al.
Article
Business
Rui Qin et al.
ELECTRONIC COMMERCE RESEARCH AND APPLICATIONS
(2017)
Review
Green & Sustainable Science & Technology
Kaile Zhou et al.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2016)
Article
Computer Science, Artificial Intelligence
Haoran Xie et al.
Article
Computer Science, Artificial Intelligence
Anil K. Jain
PATTERN RECOGNITION LETTERS
(2010)