Article
Energy & Fuels
Chu Zhang, Lei Hua, Chunlei Ji, Muhammad Shahzad Nazir, Tian Peng
Summary: A novel solar radiation prediction model based on wavelet transform, complete ensemble empirical mode decomposition with adaptive noise, improved atom search optimization and outlier-robust extreme learning machine is proposed in this study. The model utilizes denoising, decomposition, and optimization techniques to improve the accuracy and robustness of solar radiation prediction.
Article
Engineering, Multidisciplinary
Xiangyu Chang, Hao Wang, Yiming Zhang, Feiqiu Wang, Zhaozhong Li
Summary: This study presents a probabilistic model combining empirical models, Bayesian estimation, and relevance vector machine to predict convergence. Experimental results demonstrate that the proposed model outperforms other methods in terms of accuracy.
Article
Engineering, Marine
Yao Meng, Xianku Zhang, Guoqing Zhang, Xiufeng Zhang, Yating Duan
Summary: To establish a sparse and accurate ship motion prediction model, a novel Bayesian probability prediction model based on relevance vector machine (RVM) was proposed. The sparsity, effectiveness, and generalization of RVM were verified using two datasets. The proposed nonparametric models showed good prediction performance by ensuring both sparsity and high accuracy, with improved prediction accuracy and lower time consumption compared to the SVR.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Engineering, Marine
Jinwan Park, Jung-Sik Jeong
Summary: This study introduces an enhanced machine learning method to estimate ship collision risk, with the relevance vector machine (RVM) showing more accurate and efficient results compared to the conventional support vector machine (SVM). By supporting more reliable decision-making for navigators through precise risk estimation, early evasive actions can be facilitated.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2021)
Article
Materials Science, Multidisciplinary
Jun-Hyoung Park, Ji-Ho Cho, Jung-Sik Yoon, Jung-Ho Song
Summary: The non-invasive approach presented in this study utilizes optical emission spectroscopy (OES) and multivariate data analysis to monitor plasma parameters inside a radio-frequency (RF) plasma nitridation device. An empirical correlation was established for real-time monitoring using machine learning (ML) based on simultaneous OES and other diagnostics, achieving high prediction accuracy for electron density and temperature. This method provides in-situ and real-time analysis without disturbing the plasma or interfering with the process, making it especially useful in plasma processing.
Article
Energy & Fuels
Xingye Liu, Guangzhou Shao, Cheng Yuan, Xiaohong Chen, Jingye Li, Yangkang Chen
Summary: This paper proposes a reservoir properties prediction method based on a mixture of relevance vector regression experts. By incorporating multiple learning models, the method decomposes the complicated problem into simple sub-problems and improves the accuracy of prediction.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Long Tang, Yingjie Tian, Wenjun Li, Panos M. Pardalos
Summary: A newly proposed valley-loss regular simplex support vector machine (V-RSSVM) is presented in this paper for robust multiclass classification, with robustness to feature noise and outlier labels, as well as excellent sparseness. To train the V-RSSVM fast, a speeding up oriented initial solution strategy and solver were developed.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
He Yan, Liyong Fu, Yong Qi, Li Cheng, Qiaolin Ye, Dong-Jun Yu
Summary: Accurate and real-time prediction of short-term traffic states is crucial in intelligent transportation systems. This study proposes a novel multiclass classification least squares twin support vector machine model (PLSTSVM) based on a robust distance, which improves the prediction performance by adjusting parameters and using an integrated classification indicator system.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Energy & Fuels
Jie Zhao, Huaixun Zhang, Hongliang Zou, Jianguo Pan, Chengshi Zeng, Siyi Xiao, Jun Wang
Summary: This study proposes a method based on adaptive relevance vector machine (ARVM) to predict the fault probability of transmission line icing and achieve early warning. By optimizing model parameters and correcting prediction results, the proposed method can improve the accuracy of icing prediction and provide assistance for anti-icing and mitigation work in the electric power department.
Article
Energy & Fuels
Abouzar Rajabi Behesht Abad, Hamzeh Ghorbani, Nima Mohamadian, Shadfar Davoodi, Mohammad Mehrad, Saeed Khezerloo-ye Aghdam, Hamid Reza Nasriani
Summary: Condensate reservoirs present unique challenges in the oil and gas industry, and machine learning methods show promise in predicting gas flow rates, with the MELM-PSO model demonstrating the highest accuracy.
Article
Computer Science, Interdisciplinary Applications
Siyu Chen, Chongshi Gu, Chaoning Lin, Kang Zhang, Yantao Zhu
Summary: This study introduces a novel probabilistic prediction approach based on optimized relevance vector machine for accurate and reliable safety monitoring of concrete dam displacement. Through parameter optimization and testing of kernel functions, it is found that the model performs best in predicting displacements out of range of the dataset, with the advantages of probabilistic output and providing confidence intervals.
ENGINEERING WITH COMPUTERS
(2021)
Article
Food Science & Technology
Sarah Curro, Stefania Balzan, Enrico Novelli, Luca Fasolato
Summary: Accurate species identification is crucial for ensuring food safety and preventing economic losses in the fishery sector. This study used morphological features and near-infrared spectroscopy (NIRS) to identify four species of cuttlefish, achieving a high overall accuracy of 93%.
Article
Multidisciplinary Sciences
Shuai Wang, Zongbao Zhang, Chao Wang
Summary: The mining of open pit mines is widespread in China, leading to many landslide accidents. Therefore, the issue of slope stability is emphasized. The stability of the slope directly affects mining efficiency and the overall safety of the mining process. According to statistics, there is a 15% chance of landslide risk in China's large-scale mines. As mining scale expands, slope stability becomes increasingly obvious, making it a major subject in the study of open-pit mine engineering.
SCIENTIFIC REPORTS
(2023)
Article
Computer Science, Artificial Intelligence
Hongquan Gui, Jialan Liu, Chi Ma, Mengyuan Li
Summary: The thermal error can reduce the machining accuracy of machine tools and needs to be effectively controlled. Previous studies mainly focused on the temporal feature of the thermal error and ignored the spatial feature. To address these challenges, a new dynamic TS memory graph convolutional network (DTSMGCN) model is proposed in this study to learn the dynamic TS features of the thermal error.
JOURNAL OF INTELLIGENT MANUFACTURING
(2023)
Article
Engineering, Electrical & Electronic
Bo Jiang, Haifeng Dai, Xuezhe Wei, Zhao Jiang
Summary: A reliable cycling aging prediction model based on data-driven methods is proposed in this study to address the adaptive and early prediction of lithium-ion battery remaining useful life. The model utilizes a multi-kernel RVM with particle swarm optimization to enhance learning and generalization abilities. A similarity criterion of battery capacity curves is proposed for early life prediction. Experimental results demonstrate the accurate prediction of failure cycle and capacity attenuation trajectory for different types of batteries, as well as the ability to learn general fading characteristics from other battery types.
IEEE JOURNAL OF EMERGING AND SELECTED TOPICS IN POWER ELECTRONICS
(2023)
Article
Operations Research & Management Science
Sangheum Hwang, Myong K. Jeong
ANNALS OF OPERATIONS RESEARCH
(2018)
Article
Materials Science, Multidisciplinary
D. Mishra, Y. -H. Cho, M. -B. Shim, S. Hwang, S. Kim, C. Y. Park, S. Y. Seo, S. -H. Yoo, S. -H. Park, Y. E. Pak
COMPUTATIONAL MATERIALS SCIENCE
(2015)
Article
Computer Science, Artificial Intelligence
Sangheum Hwang, Jiho Yoo, Chanhee Lee, Sang Hyun Lee
EXPERT SYSTEMS WITH APPLICATIONS
(2016)
Article
Management
Dohyun Kim, Chungmok Lee, Sangheum Hwang, Myong K. Jeong
JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY
(2016)
Article
Radiology, Nuclear Medicine & Medical Imaging
Ju Gang Nam, Sunggyun Park, Eui Jin Hwang, Jong Hyuk Lee, Kwang-Nam Jin, Kun Young Lim, Thienkai Huy Vu, Jae Ho Sohn, Sangheum Hwang, Jin Mo Goo, Chang Min Park
Article
Computer Science, Artificial Intelligence
Mitko Veta, Yujing J. Heng, Nikolas Stathonikos, Babak Ehteshami Bejnordi, Francisco Beca, Thomas Wollmann, Karl Rohr, Manan A. Shah, Dayong Wang, Mikael Rousson, Martin Hedlund, David Tellez, Francesco Ciompi, Erwan Zerhouni, David Lanyi, Matheus Viana, Vassili Kovalev, Vitali Liauchuk, Hady Ahmady Phoulady, Talha Qaiser, Simon Graham, Nasir Rajpoot, Erik Sjoblom, Jesper Molin, Kyunghyun Paeng, Sangheum Hwang, Sunggyun Park, Zhipeng Jia, Eric I-Chao Chang, Yan Xu, Andrew H. Beck, Paul J. van Diest, Josien P. W. Pluim
MEDICAL IMAGE ANALYSIS
(2019)
Article
Chemistry, Analytical
Jaemoon Hwang, Sangheum Hwang
Summary: This paper proposes a method to enhance the performance of segmentation models for medical images by jointly learning the global structure information. Experimental results demonstrate that the proposed method not only improves segmentation performance but also enhances robustness against domain shifts.
Article
Computer Science, Artificial Intelligence
Jeongeun Park, Seungyoun Shin, Sangheum Hwang, Sungjoon Choi
Summary: This article proposes a robust learning method that can learn a clean target distribution from noisy and corrupted training data while estimating the underlying noise pattern. By using a mixture-of-experts model to distinguish different types of predictive uncertainty, it demonstrates the importance of estimating uncertainty in elucidating corruption patterns. The article also introduces a novel validation scheme for evaluating the performance of corruption pattern estimation. The proposed method is extensively assessed in the field of computer vision.
PATTERN RECOGNITION
(2023)
Article
Computer Science, Artificial Intelligence
Jihyo Kim, Jiin Koo, Sangheum Hwang
Summary: Deep neural networks have achieved outstanding performance but suffer from over-confident predictions for unknown samples. Previous studies tackled this issue through specific tasks like misclassification detection or out-of-distribution detection. In this work, we propose the unknown detection task, which integrates these individual tasks, to rigorously evaluate deep neural networks' capabilities. We found that Deep Ensemble consistently outperforms other methods, but all methods are only successful for specific types of unknowns.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Sangwoo Lee, Yejin Lee, Geongyu Lee, Sangheum Hwang
Summary: Deep segmentation networks typically consist of an encoder and decoder for feature extraction and restoration to produce segmentation results. A supervised contrastive embedding approach is proposed to enhance feature maps using contrastive loss for improved segmentation performance. Empirical results demonstrate the effectiveness of this method in enhancing segmentation performance across various architectures.
Article
Computer Science, Information Systems
Jaehoon Koo, Sangheum Hwang
Summary: The study proposes a defect pattern analysis method based on density-based clustering (DBC), which includes statistical testing for detecting abnormal defects in wafer maps and clustering of defect patterns, both steps performed simultaneously using core points from DBC. The proposed method is shown to accurately identify spatial dependence among defects with much less computational effort compared to existing methods.
Article
Computer Science, Information Systems
Minyoung Park, Seungyeon Lee, Sangheum Hwang, Dohyun Kim
Article
Computer Science, Information Systems
Sangheum Hwang, Hyeon Gyu Yeo, Jung-Sik Hong
Article
Computer Science, Theory & Methods
Sangheum Hwang, Dohyun Kim
INTERNATIONAL JOURNAL OF FUZZY LOGIC AND INTELLIGENT SYSTEMS
(2018)
Proceedings Paper
Computer Science, Theory & Methods
Sangheum Hwang, Sunggyun Park
DEEP LEARNING IN MEDICAL IMAGE ANALYSIS AND MULTIMODAL LEARNING FOR CLINICAL DECISION SUPPORT
(2017)