COVID-19 Outbreak Prediction with Machine Learning DOI Open Access
Sina Ardabili,

Amir Mosavi,

Pedram Ghamisi

и другие.

Опубликована: Окт. 8, 2020

Several outbreak prediction models for COVID-19 are being used by officials around the world to make informed-decisions and enforce relevant control measures. Among standard global pandemic prediction, simple epidemiological statistical have received more attention authorities, they popular in media. Due a high level of uncertainty lack essential data, shown low accuracy long-term prediction. Although literature includes several attempts address this issue, generalization robustness abilities existing needs be improved. This paper presents comparative analysis machine learning soft computing predict as an alternative SIR SEIR models. wide range investigated, two showed promising results (i.e., multi-layered perceptron, MLP, adaptive network-based fuzzy inference system, ANFIS). Based on reported here, due highly complex nature variation its behavior from nation-to-nation, study suggests effective tool model outbreak. provides initial benchmarking demonstrate potential future research. Paper further that real novelty can realized through integrating

Язык: Английский

COVID-19 Outbreak Prediction with Machine Learning DOI Creative Commons
Sina Ardabili,

Amir Mosavi,

Pedram Ghamisi

и другие.

Algorithms, Год журнала: 2020, Номер 13(10), С. 249 - 249

Опубликована: Окт. 1, 2020

Several outbreak prediction models for COVID-19 are being used by officials around the world to make informed decisions and enforce relevant control measures. Among standard global pandemic prediction, simple epidemiological statistical have received more attention authorities, these popular in media. Due a high level of uncertainty lack essential data, shown low accuracy long-term prediction. Although literature includes several attempts address this issue, generalization robustness abilities existing need be improved. This paper presents comparative analysis machine learning soft computing predict as an alternative susceptible–infected–recovered (SIR) susceptible-exposed-infectious-removed (SEIR) models. wide range investigated, two showed promising results (i.e., multi-layered perceptron, MLP; adaptive network-based fuzzy inference system, ANFIS). Based on reported here, due highly complex nature variation its behavior across nations, study suggests effective tool model outbreak. provides initial benchmarking demonstrate potential future research. further that genuine novelty can realized integrating SEIR

Язык: Английский

Процитировано

325
A review on social spam detection: Challenges, open issues, and future directions DOI
Sanjeev Rao, Anil Kumar Verma, Tarunpreet Bhatia

и другие.

Expert Systems with Applications, Год журнала: 2021, Номер 186, С. 115742 - 115742

Опубликована: Авг. 14, 2021

Язык: Английский

Процитировано

145
Privacy-preserving federated learning for residential short-term load forecasting DOI Creative Commons
Joaquín Delgado Fernández, Sergio Potenciano Menci,

Chul Min Lee

и другие.

Applied Energy, Год журнала: 2022, Номер 326, С. 119915 - 119915

Опубликована: Сен. 15, 2022

With high levels of intermittent power generation and dynamic demand patterns, accurate forecasts for residential loads have become essential. Smart meters can play an important role when making these as they provide detailed load data. However, using smart meter data forecasting is challenging due to privacy requirements. This paper investigates how requirements be addressed through a combination federated learning preserving techniques such differential secure aggregation. For our analysis, we employ large set simulate different models affect performance privacy. Our simulations reveal that combining both accuracy near-complete Specifically, find combinations enable level information sharing while ensuring the processed models. Moreover, identify discuss challenges applying learning, aggregation short-term forecasting.

Язык: Английский

Процитировано

73
Virtual Screening Algorithms in Drug Discovery: A Review Focused on Machine and Deep Learning Methods DOI Creative Commons
Tiago Alves de Oliveira, Michel Pires da Silva, Eduardo Habib Bechelane Maia

и другие.

Drugs and Drug Candidates, Год журнала: 2023, Номер 2(2), С. 311 - 334

Опубликована: Май 5, 2023

Drug discovery and repositioning are important processes for the pharmaceutical industry. These demand a high investment in resources time-consuming. Several strategies have been used to address this problem, including computer-aided drug design (CADD). Among CADD approaches, it is essential highlight virtual screening (VS), an silico approach based on computer simulation that can select organic molecules toward therapeutic targets of interest. The techniques applied by VS structure ligands (LBVS), receptors (SBVS), or fragments (FBVS). Regardless type be applied, they divided into categories depending algorithms: similarity-based, quantitative, machine learning, meta-heuristics, other algorithms. Each category has its objectives, advantages, disadvantages. This review presents overview algorithms VS, describing them showing their use contribution development process.

Язык: Английский

Процитировано

71
Review of multi-fidelity models DOI Open Access
M. Giselle Fernández-Godino

Advances in Computational Science and Engineering, Год журнала: 2023, Номер 1(4), С. 351 - 400

Опубликована: Янв. 1, 2023

Multi-fidelity models provide a framework for integrating computational of varying complexity, allowing accurate predictions while optimizing resources. These are especially beneficial when acquiring high-accuracy data is costly or computationally intensive. This review offers comprehensive analysis multi-fidelity models, focusing on their applications in scientific and engineering fields, particularly optimization uncertainty quantification. It classifies publications modeling according to several criteria, including application area, surrogate model selection, types fidelity, combination methods year publication. The study investigates techniques combining different fidelity levels, with an emphasis models. work discusses reproducibility, open-sourcing methodologies benchmarking procedures promote transparency. manuscript also includes educational toy problems enhance understanding. Additionally, this paper outlines best practices presenting multi-fidelity-related savings standardized, succinct yet thorough manner. concludes by examining current trends modeling, emerging techniques, recent advancements, promising research directions.

Язык: Английский

Процитировано

45
Deep Learning and Machine Learning in Hydrological Processes Climate Change and Earth Systems a Systematic Review DOI
Sina Ardabili,

Amir Mosavi,

Majid Dehghani

и другие.

Lecture notes in networks and systems, Год журнала: 2020, Номер unknown, С. 52 - 62

Опубликована: Янв. 1, 2020

Язык: Английский

Процитировано

132
Data Science in Economics: Comprehensive Review of Advanced Machine Learning and Deep Learning Methods DOI Creative Commons
Saeed Nosratabadi,

Amirhosein Mosavi,

Puhong Duan

и другие.

Mathematics, Год журнала: 2020, Номер 8(10), С. 1799 - 1799

Опубликована: Окт. 16, 2020

This paper provides a comprehensive state-of-the-art investigation of the recent advances in data science emerging economic applications. The analysis is performed on novel methods four individual classes deep learning models, hybrid machine learning, and ensemble models. Application domains include broad diverse range economics research from stock market, marketing, e-commerce to corporate banking cryptocurrency. Prisma method, systematic literature review methodology, used ensure quality survey. findings reveal that trends follow advancement which outperform other algorithms. It further expected will converge toward evolution sophisticated

Язык: Английский

Процитировано

122
Review of multi-fidelity models DOI Creative Commons
M. Giselle Fernández-Godino

arXiv (Cornell University), Год журнала: 2016, Номер unknown

Опубликована: Янв. 1, 2016

Multi-fidelity models provide a framework for integrating computational of varying complexity, allowing accurate predictions while optimizing resources. These are especially beneficial when acquiring high-accuracy data is costly or computationally intensive. This review offers comprehensive analysis multi-fidelity models, focusing on their applications in scientific and engineering fields, particularly optimization uncertainty quantification. It classifies publications modeling according to several criteria, including application area, surrogate model selection, types fidelity, combination methods year publication. The study investigates techniques combining different fidelity levels, with an emphasis models. work discusses reproducibility, open-sourcing methodologies benchmarking procedures promote transparency. manuscript also includes educational toy problems enhance understanding. Additionally, this paper outlines best practices presenting multi-fidelity-related savings standardized, succinct yet thorough manner. concludes by examining current trends modeling, emerging techniques, recent advancements, promising research directions.

Язык: Английский

Процитировано

115
Semi-supervised anomaly detection algorithms: A comparative summary and future research directions DOI
Miryam Elizabeth Villa-Pérez, Miguel Á. Álvarez‐Carmona, Octavio Loyola‐González

и другие.

Knowledge-Based Systems, Год журнала: 2021, Номер 218, С. 106878 - 106878

Опубликована: Фев. 21, 2021

Язык: Английский

Процитировано

105
Improving Sentiment Analysis for Social Media Applications Using an Ensemble Deep Learning Language Model DOI Open Access
Ahmed Alsayat

Arabian Journal for Science and Engineering, Год журнала: 2021, Номер 47(2), С. 2499 - 2511

Опубликована: Окт. 11, 2021

Язык: Английский

Процитировано

102