Article
Energy & Fuels
Junxian Wang, Yinbo Xu, Pingchang Sun, Zhaojun Liu, Jiaqiang Zhang, Qingtao Meng, Penglin Zhang, Baiqiang Tang
Summary: The total organic carbon (TOC) content is an important parameter for evaluating oil shale resources. Prediction methods based on resistivity, density, acoustic, and gamma ray logging curves have been used to predict TOC content. The study found that the artificial neural networks (ANN) model had the strongest prediction ability, followed by the linear regression (LR) model, while the Delta logR model had the lowest prediction ability. The difference in porosity characteristics caused by organic matter content is the primary factor affecting the inversion of TOC content logging between oil shale and source rock.
GEOMECHANICS AND GEOPHYSICS FOR GEO-ENERGY AND GEO-RESOURCES
(2022)
Article
Optics
Wei Zeng, Yunkang Liao, Ying Chen, Qun Ying Diao, Zi Ying Fu, Feiyan Yao
Summary: In this study, a laser ultrasonic detection method based on the PSO-SVM algorithm is proposed to identify and detect human skin tumors. The physical model of laser ultrasound in human skin tumors is established, and sensitive features are extracted for classification and identification using the SVM. The simulation results demonstrate that the proposed method has a good classification effect and provides a new approach for laser ultrasound detection of skin tumors.
OPTICS AND LASER TECHNOLOGY
(2023)
Article
Geochemistry & Geophysics
Shib Sankar Ganguli, Mohamed Mehdi Kadri, Akash Debnath, Souvik Sen
Summary: This study introduces the problem of TOC estimation in a Bayesian framework to enhance the prediction accuracy of TOC content and quantify the uncertainty in model prediction. By comparing with empirical models, we demonstrate that the Bayesian approach provides more reliable predictions and additional information on prediction uncertainty in TOC estimation. Furthermore, we derive important information about depositional environments to characterize high TOC content zones in organic shale formations using this approach.
Article
Geosciences, Multidisciplinary
Jier Zhao, Xinmin Ge, Yiren Fan, Jianyu Liu, Yiguo Chen, Lei Xing
Summary: This study presents a genetic algorithm-driven support vector machine method for identifying the kerogen type. By utilizing geological conditions, well logging, and geochemical data, this method enables accurate determination of the kerogen type and evaluation of prediction results.
Article
Chemistry, Multidisciplinary
Liu Xiaorui, Yang Jiamin, Yuan Longji
Summary: In this study, a support vector machine (SVM) model with RBF kernel function combined with sparrow search algorithm (SSA) optimization was developed to predict the HHV and nitrogen content (No) values of torrefied biomass based on the feedstock properties and torrefaction conditions. The results showed that SSA optimization significantly improved the prediction performance of the SVM model for both HHV and No. The agreement between experimental data and SSA-SVM predicted values demonstrated the high predictive precision of the model. This study provides a reference for the utilization of torrefied biomass in solid fuels and the design of torrefaction facilities.
Article
Mathematics, Applied
Hongxin Xue, Lingling Zhang, Haijian Liang, Liqun Kuang, Huiyan Han, Xiaowen Yang, Lei Guo
Summary: Web-based search query data analysis can effectively predict the spread of influenza, but selecting keywords and prediction methods are key challenges for improving prediction accuracy. This study built an influenza prediction model based on historical data and keywords, and proposed a new optimization algorithm to enhance prediction accuracy.
Article
Energy & Fuels
Jiangtao Sun, Wei Dang, Fengqin Wang, Haikuan Nie, Xiaoliang Wei, Pei Li, Shaohua Zhang, Yubo Feng, Fei Li
Summary: In this study, three machine learning models (random forest, support vector regression, and XGBoost) were proposed to predict the TOC content using well logs. The results show that the random forest model provides the best predictive accuracy.
Article
Computer Science, Information Systems
Guoquan Li, Linxi Yang, Zhiyou Wu, Changzhi Wu
Summary: Proximal support vector machine (PSVM) is a variant of support vector machine (SVM) which aims to generate a pair of non-parallel hyperplanes for classification. Introducing l(0)-norm regularization in PSVM enables simultaneous selection of important features and removal of redundant features for classification. The proposed method utilizes a continuous nonconvex function and difference of convex functions algorithms (DCA) to solve the optimization problem efficiently.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Tong Gao, Hao Chen
Summary: In this study, a multicycle disassembly-based decomposition algorithm (MCD-DA) is proposed to efficiently solve the training problem of multiclass support vector machine (SVM). MCD-DA constructs a graph model to re-express the constraints in multiclass SVM, partitions the complex feasible region into simple sub-feasible regions, and designs multiple cycle-based disassembly strategies to update the working variables analytically. Experimental results demonstrate that MCD-DA outperforms typical optimization algorithms for more sample cases.
PATTERN RECOGNITION
(2023)
Article
Cell Biology
Jesus Garcia-Banuelos, Eden Oceguera-Contreras, Ana Sandoval-Rodriguez, Blanca Estela Bastidas-Ramirez, Silvia Lucano-Landeros, Daniela Gordillo-Bastidas, Belinda C. Gomez-Meda, Arturo Santos, Eira Cerda-Reyes, Juan Armendariz-Borunda
Summary: Intramuscular delivery of an adenoviral vector containing proMMP-8 gene cDNA (AdhMMP8) is safe and effective in achieving liver fibrosis regression, reducing inflammation and profibrogenic gene expression.
Article
Computer Science, Artificial Intelligence
Jesse Lopes
Summary: This paper discusses the representations of deep convolutional neural networks and argues that supplementation by Quine's apparatus is necessary to achieve concepts and represent objects. It also proposes a Fodorian hybrid model based on statistical learning to overcome regress and circularity and achieve objective representation.
MINDS AND MACHINES
(2023)
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
Construction & Building Technology
Anna Hola, Slawomir Czarnecki
Summary: The article presents the results of experimental research and numerical analyses, and also shows the usefulness of the random forest algorithm and the support vector machine for the non-destructive identification of the moisture content of brick walls in historic buildings. To train and test the models, a representative dataset, including 290 sample sets and 7 predictor variables, was used. The analyses showed that the random forest algorithm is the most predisposed model for the non-destructive assessment of the Umc mass moisture content of brick walls in historic buildings, with the highest value of R2 and the lowest values of RMSE, MAE, and MAPE.
AUTOMATION IN CONSTRUCTION
(2023)
Article
Environmental Sciences
Ru Liu, Jianbing Peng, Yanqiu Leng, Saro Lee, Mahdi Panahi, Wei Chen, Xia Zhao
Summary: This study evaluates landslide susceptibility in Zhenping County using a hybrid model, combining SVR with GWO and FA, based on a database of landslides and various conditioning factors. The results show that the SVR-GWO model performs the best in spatial prediction of landslides, followed by SVR-FA and SVR models. The hybrid models improve the performance of the single SVR model and show good prospects for regional-scale landslide spatial modeling.
Article
Automation & Control Systems
Hamza Moussa, Farid Dahmoune, Mohamed Hentabli, Hocine Remini, Lotfi Mouni
Summary: Box-Behnken design and support vector regression optimized using dragonfly algorithm were employed to optimize and predict the total phenolic and saponin content from Carthamus caeruleus L. rhizome. The antioxidant activity of rhizomes and leaves parts was also compared using different assays. The results showed that the optimized conditions were obtained and the established model successfully predicted the extraction process.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2022)
Article
Geochemistry & Geophysics
Qiang Guo, Hongbing Zhang, Kuiye Wei, Zhen Li, Zuoping Shang
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2019)
Article
Energy & Fuels
Yi-Xin Pan, Hong-Bing Zhang, Yun-Jin Hu, Xing-Bin Liu, Min Wang
Summary: This experimental study investigated the effects of oil-water two-phase-stratified flow rates, inlet water cut, and pipe inclinations on the characteristics of the interfacial wave. The results showed that the interfacial wave characteristics are strongly influenced by flow rates, inlet water cut, and pipe inclinations, with analysis based on the stabilizing force and destabilizing force of the oil-water flow.
ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS
(2021)
Article
Geochemistry & Geophysics
Feilong Han, Hongbing Zhang, Qiang Guo, Zuoping Shang, Tiancai Li
EXPLORATION GEOPHYSICS
(2019)
Article
Geosciences, Multidisciplinary
Feilong Han, Hongbing Zhang, Qiang Guo, Jianwen Rui, Qiuyan Ji
ARABIAN JOURNAL OF GEOSCIENCES
(2019)
Article
Geochemistry & Geophysics
Qiang Guo, Hongbing Zhang, Haitao Cao, Wei Xiao, Feilong Han
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2020)
Article
Geochemistry & Geophysics
Feilong Han, Hongbing Zhang, Snehamoy Chatterjee, Qiang Guo, Shulin Wan
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2020)
Article
Energy & Fuels
Dailu Zhang, Hongbing Zhang, Jianwen Rui, Yixin Pan, Xingbin Liu, Zuoping Shang
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2020)
Article
Geosciences, Multidisciplinary
Nizam Ud Din, Zhang Hongbing
Article
Geosciences, Multidisciplinary
Feilong Han, Hongbing Zhang, Jianwen Rui, Kuiye Wei, Dailu Zhang, Wei Xiao
MARINE AND PETROLEUM GEOLOGY
(2020)
Article
Geosciences, Multidisciplinary
Jianwen Rui, Hongbing Zhang, Quan Ren, Lizhi Yan, Qiang Guo, Dailu Zhang
MARINE AND PETROLEUM GEOLOGY
(2020)