Article
Computer Science, Artificial Intelligence
Ziad Akram-Ali-Hammouri, Manuel Fernandez-Delgado, Eva Cernadas, Senen Barro
Summary: The Support Vector Machine is an important machine learning algorithm that performs well on many classification problems. However, it is slow and requires a lot of memory when dealing with large datasets. To address this issue, a fast support vector classifier is proposed with efficient training, small prototypes collection, and fast kernel spread selection method.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Information Systems
Zichen Zhang, Shifei Ding, Yuting Sun
Summary: This paper introduces a new method called multiple birth support vector regression (MBSVR), which constructs the regressor from multiple hyperplanes obtained by solving small quadratic programming problems, aiming for faster computation and better fitting precision.
INFORMATION SCIENCES
(2021)
Article
Chemistry, Multidisciplinary
Xiuzhen Li, Shengwei Li
Summary: Forecasting large-scale landslides development is complex, and a study has utilized multi-factor support vector regression machines to predict displacement rates, finding relationships between rainfall, reservoir water levels, and landslide displacement. The models showed high accuracies, with the two-factor model exhibiting the highest accuracy.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Artificial Intelligence
Bin Gu, Xiang Geng, Wanli Shi, Yingying Shan, Yufang Huang, Zhijie Wang, Guansheng Zheng
Summary: Ordinal regression is a significant task in supervised learning, and traditional SVOR methods face inefficiency in large-scale training due to complexity and high cost. This paper proposes a special SVOR formulation with implicit thresholds, and introduces two novel asynchronous parallel coordinate descent algorithms, AsyACGD and AsyORGCD, to accelerate SVOR training. Experimental results demonstrate the superiority of the proposed algorithms on several large-scale ordinal regression datasets.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Artificial Intelligence
M. Tanveer, A. Tiwari, R. Choudhary, M. A. Ganaie
Summary: This study proposes a novel large scale pinball twin support vector machine (LPTWSVM) to address the limitations of the twin support vector machines (TWSVMs), using a unique pinball loss function and improving model performance by eliminating matrix inversion calculation and minimizing structural risk.
Article
Environmental Sciences
Chih-Chun Liu, Tzu-Chi Lin, Kuang-Yu Yuan, Pei-Te Chiueh
Summary: This study utilizes the support vector machine (SVM) method to predict air quality and considers geographic features and time series. The results show high accuracy for short-term temporal prediction, with meteorological and climatic factors influencing seasonal differences. In the spatial inference stage, urbanization and city types were found to impact air quality, while agriculture and forest use, transportation use, residential use, and economic factors were correlated with AQIs.
Article
Automation & Control Systems
Sweta Sharma, Reshma Rastogi, Suresh Chandra
Summary: A novel twin parametric support vector machine using pinball loss function was proposed, which showed better efficiency and robustness than traditional hinge loss SVM in handling noise in large-scale data scenarios. The theoretical convergence of the method was established, and a modified version was introduced to address convergence issues, leading to faster and more reliable models with better generalization ability against noise and resampling in stochastic learning scenarios.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2021)
Article
Energy & Fuels
Keita Shono, Yohei Yamaguchi, Usama Perwez, Tao Ma, Yanjun Dai, Yoshiyuki Shimoda
Summary: The installation of building-integrated photovoltaic (BIPV) modules on building facades has great potential for decarbonizing urban building stock. A model was developed to estimate the hourly PV potential of building surfaces on a regional scale, and it was found that BIPV could satisfy 15%-48% of the annual electricity demand of commercial building stock in Tokyo by 2050. However, the larger-scale installation of BIPV may have negative impacts on the power system, including reduced asset utilization and increased flexibility needs.
Article
Nanoscience & Nanotechnology
Zhilong Wang, Yanqiang Han, Xirong Lin, Junfei Cai, Sicheng Wu, Jinjin Li
Summary: Lead-free double perovskites are considered stable and environmentally friendly optoelectronic alternatives, but their indirect band gaps and high effective masses may limit their efficiency. The proposed ensemble learning workflow successfully screened out six suitable candidates from over 23,314 unexplored double perovskites, two of which exhibit promising characteristics for application in photovoltaic devices. This machine learning approach greatly shortens the screening process and can significantly promote the development of photovoltaic technology.
ACS APPLIED MATERIALS & INTERFACES
(2022)
Article
Computer Science, Artificial Intelligence
Keiji Tatsumi, Shunsuke Tsujioka, Ryota Masui, Yoshifumi Kusunoki, Yeboon Yun
Summary: This paper focuses on the labor shortage issue in the construction industry, particularly in the field of large-scale infrastructure. By recognizing the risk scores at different sections of the construction site, the paper addresses the inconsistency in structure data and introduces multiclass SVMs to improve classification accuracy.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Huajuan Huang, Xiuxi Wei, Yongquan Zhou
Summary: This article reviews the recent developments in twin support vector regression (TSVR). It introduces the basic concepts and models of TSVR, summarizes the improved algorithms and applications in recent years, and analyzes the advantages and disadvantages of representative algorithms through experiments. The article also discusses the research conducted on TSVR.
Article
Computer Science, Artificial Intelligence
Quentin Klopfenstein, Samuel Vaiter
Summary: This paper investigates the addition of linear constraints to Support Vector Regression with a linear kernel, proving that the problem remains a semi-definite quadratic problem. A generalization of the Sequential Minimal Optimization algorithm is proposed to solve the optimization problem with linear constraints, showing convergence. Practical performance of this approach is demonstrated on simulated and real datasets, highlighting its usefulness compared to classical methods.
Article
Energy & Fuels
Takahiro Takamatsu, Hideaki Ohtake, Takashi Oozeki
Summary: This study proposes a prediction model for reducing the overestimation of solar irradiance, which poses a risk to the power system. The model utilizes Support Vector Quantile Regression and Meso-scale Ensemble Prediction System data, and the performance of the model is evaluated using forecasting errors. Results show that the model can effectively reduce the overestimation when parameters are properly adjusted.
Article
Physics, Multidisciplinary
Huan Liu, Jiankai Tu, Chunguang Li
Summary: This paper proposes a distributed SVOR algorithm to solve ordinal regression problems in distributed environments. Theoretical analysis and experimental results demonstrate that the proposed method can achieve good performance in scenarios where privacy protection or centralized data processing is not feasible.
Article
Chemistry, Analytical
Juan Salazar-Carrillo, Miguel Torres-Ruiz, Clodoveu A. Davis, Rolando Quintero, Marco Moreno-Ibarra, Giovanni Guzman
Summary: This paper introduces how to geocode and predict traffic congestion using social media data, build a prediction model, and display spatial distribution using heat maps, demonstrating that social media is a good alternative for gathering dynamic city information.
Article
Ecology
Nahid Mohajeri, Agust Gudmundsson, Jean-Louis Scartezzini
ECOLOGICAL MODELLING
(2015)
Article
Green & Sustainable Science & Technology
Nahid Mohajeri, Govinda Upadhyay, Agust Gudmundsson, Dan Assouline, Jerome Kaempf, Jean-Louis Scartezzini
Article
Energy & Fuels
Dan Assouline, Nahid Mohajeri, Jean-Louis Scartezzini
Article
Construction & Building Technology
Morgane Le Guen, Lucas Mosca, A. T. D. Perera, Silvia Coccolo, Nahid Mohajeri, Jean-Louis Scartezzini
ENERGY AND BUILDINGS
(2018)
Article
Green & Sustainable Science & Technology
Nahid Mohajeri, Dan Assouline, Berenice Guiboud, Andreas Bill, Agust Gudmundsson, Jean-Louis Scartezzini
Article
Energy & Fuels
N. Mohajeri, A. Gudmundsson, T. Kunckler, G. Upadhyay, D. Assouline, J. H. Kampf, J. L. Scartezzini
Article
Energy & Fuels
Dan Assouline, Nahid Mohajeri, Agust Gudmundsson, Jean-Louis Scartezzini
Article
Green & Sustainable Science & Technology
Nahid Mohajeri, A. T. D. Perera, Silvia Coccolo, Lucas Mosca, Morgane Le Guen, Jean-Louis Scartezzini
Article
Engineering, Environmental
Federico Amato, Fabian Guignard, Alina Walch, Nahid Mohajeri, Jean-Louis Scartezzini, Mikhail Kanevski
Summary: This study proposes a method using machine learning to reconstruct the spatio-temporal field of wind speed and estimate wind power, and applies it to Switzerland, revealing the country's significant wind power potential.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2022)
Article
Medicine, General & Internal
Marina Romanello, Claudia Di Napoli, Paul Drummond, Carole Green, Harry Kennard, Pete Lampard, Daniel Scamman, Nigel Arnell, Sonja Ayeb-Karlsson, Lea Berrang Ford, Kristine Belesova, Kathryn Bowen, Wenjia Cai, Max Callaghan, Diarmid Campbell-Lendrum, Jonathan Chambers, Kim R. van Daalen, Carole Dalin, Niheer Dasandi, Shouro Dasgupta, Michael Davies, Paula Dominguez-Salas, Robert Dubrow, Kristie L. Ebi, Matthew Eckelman, Paul Ekins, Luis E. Escobar, Lucien Georgeson, Hilary Graham, Samuel H. Gunther, Ian Hamilton, Yun Hang, Risto Hanninen, Stella Hartinger, Kehan He, Jeremy J. Hess, Shih-Che Hsu, Slava Jankin, Louis Jamart, Ollie Jay, Ilan Kelman, Gregor Kiesewetter, Patrick Kinney, Tord Kjellstrom, Dominic Kniveton, Jason K. W. Lee, Bruno Lemke, Yang Liu, Zhao Liu, Melissa Lott, Martin Lotto Batista, Rachel Lowe, Frances MacGuire, Maquins Odhiambo Sewe, Jaime Martinez-Urtaza, Mark Maslin, Lucy McAllister, Alice McGushin, Celia McMichael, Zhifu Mi, James Milner, Kelton Minor, Jan C. Minx, Nahid Mohajeri, Maziar Moradi-Lakeh, Karyn Morrissey, Simon Munzert, Kris A. Murray, Tara Neville, Maria Nilsson, Nick Obradovich, Megan B. O'Hare, Tadj Oreszczyn, Matthias Otto, Fereidoon Owfi, Olivia Pearman, Mahnaz Rabbaniha, Elizabeth J. Z. Robinson, Joacim Rocklov, Renee N. Salas, Jan C. Semenza, Jodi D. Sherman, Liuhua Shi, Joy Shumake-Guillemot, Grant Silbert, Mikhail Sofiev, Marco Springmann, Jennifer Stowell, Meisam Tabatabaei, Jonathon Taylor, Joaquin Trinanes, Fabian Wagner, Paul Wilkinson, Matthew Winning, Marisol Yglesias-Gonzalez, Shihui Zhang, Peng Gong, Hugh Montgomery, Anthony Costello
Article
Construction & Building Technology
Nahid Mohajeri, Alina Walch, Alison Smith, Agust Gudmundsson, Dan Assouline, Tom Russell, Jim Hall
Summary: Using machine learning random forests algorithm and exploratory data analysis, we propose density scenarios and housing capacity estimates for potential residential lands in the Oxford-Cambridge Arc region in the UK. Our study suggests that the impact of housing growth on natural capital can be significantly reduced by using compact development patterns, protecting land with high-value natural capital, and utilizing low-biodiversity brownfield sites.
SUSTAINABLE CITIES AND SOCIETY
(2023)
Proceedings Paper
Energy & Fuels
Alina Walch, Roberto Castello, Nahid Mohajeri, Fabian Guignard, Mikhail Kanevski, Jean-Louis Scartezzini
INNOVATIVE SOLUTIONS FOR ENERGY TRANSITIONS
(2019)
Proceedings Paper
Engineering, Electrical & Electronic
Dan Assouline, Nahid Mohajeri, Agust Gudmundsson, Jean-Louis Scartezzini
IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM
(2018)
Proceedings Paper
Environmental Sciences
Dan Assouline, Nahid Mohajeri, Jean-Louis Scartezzini
EARTH RESOURCES AND ENVIRONMENTAL REMOTE SENSING/GIS APPLICATIONS VIII
(2017)
Article
Energy & Fuels
Siddharth Sradhasagar, Omkar Subhasish Khuntia, Srikanta Biswal, Sougat Purohit, Amritendu Roy
Summary: In this study, machine learning models were developed to predict the bandgap and its character of double perovskite materials, with LGBMRegressor and XGBClassifier models identified as the best predictors. These models were further employed to predict the bandgap of novel bismuth-based transition metal oxide double perovskites, showing high accuracy, especially in the range of 1.2-1.8 eV.
Article
Energy & Fuels
Wei Shuai, Haoran Xu, Baoyang Luo, Yihui Huang, Dong Chen, Peiwang Zhu, Gang Xiao
Summary: In this study, a hybrid model based on numerical simulation and deep learning is proposed for the optimization and operation of solar receivers. By applying the model to different application scenarios and considering multiple performance objectives, small errors are achieved and optimal structure parameters and heliostat scales are identified. This approach is not only applicable to gas turbines but also heating systems.
Article
Energy & Fuels
Mubashar Ali, Zunaira Bibi, M. W. Younis, Muhammad Mubashir, Muqaddas Iqbal, Muhammad Usman Ali, Muhammad Asif Iqbal
Summary: This study investigates the structural, mechanical, and optoelectronic properties of the BaCuF3 fluoroperovskite using the first-principles modelling approach. The stability and characteristics of different cubic structures of BaCuF3 are evaluated, and the alpha-BaCuF3 and beta-BaCuF3 compounds are found to be mechanically stable with favorable optical properties for solar cells and high-frequency UV applications.
Article
Energy & Fuels
Dong Le Khac, Shahariar Chowdhury, Asmaa Soheil Najm, Montri Luengchavanon, Araa mebdir Holi, Mohammad Shah Jamal, Chin Hua Chia, Kuaanan Techato, Vidhya Selvanathan
Summary: A novel recycling system is proposed in this study to decompose and reclaim the constituent materials of organic-inorganic perovskite solar cells (PSCs). By utilizing a one-step solution process extraction approach, the chemical composition of each layer is successfully preserved, enabling their potential reuse. The proposed recycling technique helps mitigate pollution risks, minimize waste generation, and reduce recycling costs.
Article
Energy & Fuels
Peijie Lin, Feng Guo, Xiaoyang Lu, Qianying Zheng, Shuying Cheng, Yaohai Lin, Zhicong Chen, Lijun Wu, Zhuang Qian
Summary: This paper proposes an open-set fault diagnosis model for PV arrays based on 1D VoVNet-SVDD. The model accurately diagnoses various types of faults and is capable of identifying unknown fault types.