Article
Automation & Control Systems
Enjamamul Hoq, Osama Aljarrah, Jun Li, Jing Bi, Alfa Heryudono, Wenzhen Huang
Summary: This article explores different methods for predicting full stress fields in random heterogeneous materials, including model order reduction with classical machine learning and computer vision-based deep learning. The study finds that deep learning methods provide more accurate predictions with reduced errors compared to classical machine learning techniques.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Chemistry, Multidisciplinary
Hiskias Dingeto, Juntae Kim
Summary: While Machine Learning has security flaws, this paper proposes a Universal Adversarial Training algorithm using an AC-GAN to generate adversarial examples. By enhancing the AC-GAN architecture and comparing its performance to other models, it is shown that generative models are better suited for boosting adversarial security through adversarial training.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Alaa Abu-Srhan, Mohammad A. M. Abushariah, Omar S. Al-Kadi
Summary: Conditional Generative Adversarial Network (cGAN) is modified by combining adversarial loss with non-adversarial loss functions to improve model performance in image-to-image translation tasks. The best combination of loss functions for image-to-image translation on the Facades dataset is WGAN adversarial loss with L1 and content non-adversarial loss functions. The model generates fine structure images and captures both high and low frequency details of translated images. The practicality of the proposed work is demonstrated through image in-painting and lesion segmentation.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Environmental Sciences
Daning Tan, Yu Liu, Gang Li, Libo Yao, Shun Sun, You He
Summary: This paper introduces a new image transformation model, Serial GANs, which utilizes Serial Despeckling GAN and Colorization GAN to address issues in SAR-to-optical transformation. The model shows advantages in feature reconstruction and parameter efficiency, demonstrating great potential in decoupling image transformation.
Article
Biochemical Research Methods
Chang Sun, Ping Xuan, Tiangang Zhang, Yilin Ye
Summary: This study proposes a graph convolutional autoencoder and generative adversarial network (GAN) based method (GANDTI) for predicting novel drug-target interactions (DTIs). By constructing a drug-target heterogeneous network and regularizing the feature vectors of nodes into a Gaussian distribution, GANDTI outperforms other methods for drug repositioning.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2022)
Article
Thermodynamics
Xiaogang Cheng, Fei Ren, Zhan Gao, Luoxi Wang, Lei Zhu, Zhen Huang
Summary: This paper proposes a new method to study the formation and distribution of soot in turbulent jet flames. The method uses multiplicative algebraic reconstruction technique (MART) for three-dimensional reconstruction of the flame and conditional-generative adversarial network (C-GAN) for two-dimensional soot signal prediction. By combining these two methods, the three-dimensional distribution of soot particles can be reconstructed. The accuracy of the method is verified through validation experiments and it has the potential to be applied to predict other optical signals.
COMBUSTION AND FLAME
(2023)
Article
Computer Science, Artificial Intelligence
Yueqing Wang, Liang Deng, Yunbo Wan, Zhigong Yang, Wenxiang Yang, Cheng Chen, Dan Zhao, Fang Wang, Yang Guo
Summary: This study proposes an intelligent method based on a conditional generative adversarial network (cGAN) to predict the pressure coefficients (Cp) of airfoil. The method addresses existing issues and achieves a significant speedup compared with traditional computational fluid dynamics (CFD) simulation.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Thermodynamics
Xiaoqiao Huang, Qiong Li, Yonghang Tai, Zaiqing Chen, Jun Liu, Junsheng Shi, Wuming Liu
Summary: This paper proposes a novel TSFCGANs algorithm for photovoltaic power prediction, which combines CGANs, CNN, and Bi-LSTM to improve prediction accuracy. The generator and discriminator play a continuous game to optimize the parameters of the generator. Experimental results show that the proposed method outperforms other models in terms of prediction accuracy.
Article
Computer Science, Artificial Intelligence
Darren Wei Wen Low, Akshay Chaudhari, Dharmesh Kumar, A. Senthil Kumar
Summary: This paper presents the use of Convolutional Neural Networks-Forming Prediction (CNN-FP) in predicting geometric errors in die-less single point incremental forming (SPIF). The CNN-FP model was trained to quantify local geometries and achieved good performance in most validation tests. However, limitations in the training samples resulted in degraded performance in some instances.
JOURNAL OF INTELLIGENT MANUFACTURING
(2023)
Article
Chemistry, Analytical
Sung In Cho, Jae Hyeon Park, Suk-Ju Kang
Summary: The proposed method utilizes heterogeneous losses to train the generator, improving the restoration quality of structural information. The strength of the structural loss is adaptively adjusted by the discriminator for each input patch to maximize improvements. By incorporating depth wise separable convolution-based module with dilated convolution and symmetric skip connection, the proposed GAN achieves improved denoising quality while reducing computational complexity compared to CNN denoiser. Experiments show improved visual information fidelity and feature similarity index values compared to existing methods.
Article
Acoustics
Jia Luo, Jinying Huang, Jiancheng Ma, Hongmei Li
Summary: This study demonstrated the application and evaluation of conditional deep convolutional generative adversarial networks in mechanical fault diagnosis. Three evaluation metrics were proposed, successfully distinguishing generated samples from real samples, validating the effectiveness of GANs in the field of mechanical diagnosis.
JOURNAL OF VIBRATION AND CONTROL
(2022)
Article
Chemistry, Multidisciplinary
Kyungho Yu, Juhyeon Noh, Hee-Deok Yang
Summary: This paper presents a method for automatically extracting line drawings representing geometric characteristics from cartoon images, aiming to shorten the time required for creating 3D models. Experimental results demonstrate the effectiveness of the proposed method.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Interdisciplinary Applications
Juhun Lee, Robert M. Nishikawa
Summary: This study demonstrates the feasibility of using simulated mammograms to detect mammographically-occult cancer in women with dense breasts. The researchers utilize a Conditional Generative Adversarial Network (CGAN) to simulate normal mammograms and a Convolutional Neural Network (CNN) to detect cancer. The results indicate that CGAN simulated mammograms can aid in the detection of mammographically-occult cancer.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Energy & Fuels
Xiangya Bu, Qiuwei Wu, Bin Zhou, Canbing Li
Summary: In this paper, a hybrid short-term load forecasting (STLF) model using conditional generative adversarial network (CGAN) with convolutional neural network (CNN) and semi-supervised regression is proposed to improve the accuracy of STLF.
Article
Computer Science, Artificial Intelligence
Saqib Ejaz Awan, Mohammed Bennamoun, Ferdous Sohel, Frank Sanfilippo, Girish Dwivedi
Summary: A new method for imputing missing data based on its class-specific characteristics using Conditional Generative Adversarial Networks (CGAN) was proposed, achieving superior performance compared with state-of-the-art and popular imputation approaches in testing.
Article
Geochemistry & Geophysics
Zhi Zhong, Alexander Y. Sun, Xinming Wu
JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH
(2020)
Article
Energy & Fuels
Guanglong Sheng, Yuliang Su, Farzam Javadpour, Wendong Wang, Shiyuan Zhan, Jinghua Liu, Zhi Zhong
Article
Engineering, Petroleum
Zhi Zhong, Alexander Y. Sun, Bo Ren, Yanyong Wang
Summary: This paper introduces a deep-learning-based proxy modeling approach for efficiently forecasting reservoir pressure and fluid saturation in heterogeneous reservoirs during waterflooding. The developed Co-GAN proxy model can accurately predict dynamic reservoir states and well production rates with high accuracy.
Article
Environmental Sciences
Alexander Y. Sun, Bridget R. Scanlon, Himanshu Save, Ashraf Rateb
Summary: The study used an automated machine learning workflow to reconstruct GRACE-like data and fill the gap between two GRACE missions. The results showed satisfactory performance in testing over the CONUS, indicating the importance of using multiple machine learning models in combination for training and optimization.
WATER RESOURCES RESEARCH
(2021)
Article
Mathematics
Yong Zhang, Dongbao Zhou, Wei Wei, Jonathan M. Frame, Hongguang Sun, Alexander Y. Sun, Xingyuan Chen
Summary: A hierarchical framework of fractional advection-dispersion equations (FADEs) was proposed in this study for modeling pollutants moving in river corridors at a full spectrum of scales. The selection of FADEs' index depended on scale, type of geomedium, and type of available observation dataset.
Article
Environmental Sciences
Bridget R. Scanlon, Ashraf Rateb, Donald R. Pool, Ward Sanford, Himanshu Save, Alexander Sun, Di Long, Brian Fuchs
Summary: Climate and human activities have significant impacts on total water storage in 14 major aquifers in the United States, with long-term trends tracked by GRACE satellites. In humid regions such as the eastern U.S., drought has little impact on TWS, while in semi-arid regions in the southwest and south-central U.S., TWS depletion is significant.
ENVIRONMENTAL RESEARCH LETTERS
(2021)
Article
Environmental Sciences
Bridget R. Scanlon, Ashraf Rateb, Assaf Anyamba, Seifu Kebede, Alan M. MacDonald, Mohammad Shamsudduha, Jennifer Small, Alexander Sun, Richard G. Taylor, Hua Xie
Summary: Water resources management in Africa is critical. This study assesses the spatiotemporal variability in water storage and its controls in major African aquifers. The results show declining trends in water storage in northern Africa due to irrigation water use, while rising trends are found in western Africa due to land use change and increased recharge. Climate extremes strongly control water storage in eastern and southern Africa.
ENVIRONMENTAL RESEARCH LETTERS
(2022)
Article
Environmental Sciences
Meixian Liu, Jieyin Huang, Alexander Y. Sun, Kelin Wang, Hongsong Chen
Summary: The study found that drought-stressed vegetation tended to alleviate agricultural droughts, and this ability was influenced by vegetation types and climate changes. Although vegetation can help alleviate agricultural droughts, changes in agricultural droughts are still primarily driven by climate changes, especially precipitation.
SCIENCE OF THE TOTAL ENVIRONMENT
(2022)
Article
Environmental Sciences
Zhen Li, Zizhan Zhang, Bridget R. Scanlon, Alexander Y. Sun, Yun Pan, Shuqing Qiao, Hansheng Wang, Qiuyang Jia
Summary: This study developed an improved method to estimate sediment input changes in the Bohai Sea using GRACE data and satellite altimetry. The results revealed seasonal variations in sediment input and the contribution of coastal erosion.
SCIENCE OF THE TOTAL ENVIRONMENT
(2022)
Article
Geochemistry & Geophysics
Harpreet Kaur, Zhi Zhong, Alexander Sun, Sergey Fomel
Summary: Geologic carbon sequestration involves injecting captured carbon dioxide into subsurface formations for long-term storage. This study presents a deep-learning framework for monitoring CO2 saturation and determining the geologic controls on storage. The trained model accurately estimates CO2 saturation values and plume extent using time-lapse seismic data.
INTERPRETATION-A JOURNAL OF SUBSURFACE CHARACTERIZATION
(2022)
Article
Geosciences, Multidisciplinary
Alexander Y. Sun, Peishi Jiang, Zong-Liang Yang, Yangxinyu Xie, Xingyuan Chen
Summary: Rivers and river habitats worldwide are facing sustained pressure from human activities and global environmental changes. It is crucial to quantify and manage river states in a timely manner for public safety and natural resource protection. This study presents a multistage, physics-guided, graph neural network (GNN) approach for basin-scale river network learning and streamflow forecasting.
HYDROLOGY AND EARTH SYSTEM SCIENCES
(2022)
Article
Energy & Fuels
Alexander Y. Sun
Article
Geosciences, Multidisciplinary
Meixian Liu, Alexander Y. Sun
GEOPHYSICAL RESEARCH LETTERS
(2020)
Article
Energy & Fuels
Zhi Zhong, Alexander Y. Sun, Yanyong Wang, Bo Ren
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2020)