Search

Your search keyword '"Zomaya, A."' showing total 1,933 results
Start Over Author "Zomaya, A." Language english
1,933 results on '"Zomaya, A."'

3. Quick-MIMIC: A Multimodal Data Extraction Pipeline for MIMIC with Parallelization

Author

Yutao Dou, Wei Li, Yangtao Zheng, Xiaojun Yao, Huanxiang Liu, Albert Y. Zomaya, and Shaoliang Peng

Subjects
mimic dataset, data extraction pipeline, data integration, Electronic computers. Computer science, QA75.5-76.95
Abstract

Medical big data with artificial intelligence are vital in advancing digital medicine. However, the opaque and non-standardised nature embedded in most medical data extraction is prone to batch effects and has become a significant obstacle to reproducing previous works. This paper aims to develop an easy-to-use time-series multimodal data extraction pipeline, Quick-MIMIC, for standardised data extraction from MIMIC datasets. Our method can fully integrate different data structures into a time-series table, including structured, semi-structured, and unstructured data. We also introduce two additional modules to Quick-MIMIC, a pipeline parallelization method and data analysis methods, for reducing the data extraction time and presenting the characteristics of the extracted data intuitively. The extensive experimental results show that our pipeline can efficiently extract the needed data from the MIMIC dataset and convert it into the correct format for further analytic tasks.

Published
2024
Full Text
View/download PDF

8. Enhancing Building-Integrated Photovoltaic Power Forecasting with a Hybrid Conditional Generative Adversarial Network Framework

Author

Dong Ha Choi, Wei Li, and Albert Y. Zomaya

Subjects
BIPV, time series, data augmentation, GAN, Conditional GAN, TimeGAN, Technology
Abstract

This paper presents a novel framework that integrates Conditional Generative Adversarial Networks (CGANs) and TimeGAN to generate synthetic Building-Integrated Photovoltaic (BIPV) power data, addressing the challenge of data scarcity in this domain. By incorporating time-related attributes as conditioning information, our method ensures the preservation of chronological order and enhances data fidelity. A tailored learning scheme is implemented to capture the unique characteristics of solar power generation, particularly during sunrise and sunset. Comprehensive evaluations demonstrate the framework’s effectiveness in generating high-quality synthetic data, evidenced by a 79.58% improvement in the discriminative score and a 13.46% improvement in the predictive score compared to TimeGAN. Moreover, integrating the synthetic data into forecasting models resulted in up to 23.56% improvement in mean absolute error (MAE) for BIPV power generation predictions. These results highlight the potential of our framework to enhance prediction accuracy and optimize data utilization in renewable energy applications.

Published
2024
Full Text
View/download PDF

24. Interaction between damping characteristics and the initial‐stage short‐circuit current of MMC‐HVDC transmission systems

Author

Boyu Qin, Wansong Liu, Xingyue Zhou, Tao Ding, Wei Li, and Albert Y. Zomaya

Subjects
Control of electric power systems, d.c. transmission, Power convertors and power supplies to apparatus, Electronics, TK7800-8360
Abstract

Abstract This paper studies the interaction between the damping characteristics and the initial‐stage short‐circuit current of modular multilevel converter based high voltage direct current (MMC‐HVDC) transmission system. First, the MMCs' input–output characteristics are obtained through the operator approach, and the influences of both linear part and nonlinear part are analysed. Second, an input–output characteristics based short‐circuit current calculation method is proposed. Third, an eigenvalue‐based comprehensive index is proposed to evaluate the damping characteristics of the MMC‐HVDC transmission system. Finally, the interaction between the damping characteristics and the initial‐stage DC short‐circuit current is analysed under different system parameters and DC system structures. The analysis results show that there is a negative correlation between the system damping characteristics and the average rising rate of the short‐circuit current. The proposed index G can effectively evaluate the short‐circuit current of MMC‐HVDC and can provide guidance for the planning of DC system structure, the selection of operation mode and system parameters.

Published
2021
Full Text
View/download PDF

27. Enhancing Building-Integrated Photovoltaic Power Forecasting with a Hybrid Conditional Generative Adversarial Network Framework.

Author

Choi, Dong Ha, Li, Wei, and Zomaya, Albert Y.

Subjects
GENERATIVE adversarial networks, DATA augmentation, SUNRISE & sunset, SOLAR energy, ENERGY consumption
Abstract

This paper presents a novel framework that integrates Conditional Generative Adversarial Networks (CGANs) and TimeGAN to generate synthetic Building-Integrated Photovoltaic (BIPV) power data, addressing the challenge of data scarcity in this domain. By incorporating time-related attributes as conditioning information, our method ensures the preservation of chronological order and enhances data fidelity. A tailored learning scheme is implemented to capture the unique characteristics of solar power generation, particularly during sunrise and sunset. Comprehensive evaluations demonstrate the framework's effectiveness in generating high-quality synthetic data, evidenced by a 79.58% improvement in the discriminative score and a 13.46% improvement in the predictive score compared to TimeGAN. Moreover, integrating the synthetic data into forecasting models resulted in up to 23.56% improvement in mean absolute error (MAE) for BIPV power generation predictions. These results highlight the potential of our framework to enhance prediction accuracy and optimize data utilization in renewable energy applications. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results