Article
Materials Science, Multidisciplinary
Ruihao Zhang, Shan Qing, Xiaohui Zhang, Jiachen Li, Yiqing Liu, Xulin Wen
Summary: In this study, machine learning techniques were used to simulate the convective heat transfer coefficients of Fe3O4 magnetic nanofluids in a pipe. Multiple Linear Regression Analysis (MLR), Radial Basis Function-Backpropagation (RBF-BP), and Least Squares-Support Vector Machines (LS-SVM) were employed, with the LS-SVM model demonstrating superiority. The simulations were evaluated using mean square error (MSE) and regression coefficient (R2), and the model predictions were validated through visual comparisons.
MATERIALS TODAY COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Pramod Kumar Soni, Navin Rajpal, Rajesh Mehta, Vikash Kumar Mishra
Summary: Advancements in remote sensing technology have led to abundant information about landcover in remote sensing data, with the Sentinel-2 satellite providing high spatial resolution multispectral imagery. This study focused on classifying urban areas in Delhi and found that the Support Vector Machine classifier achieved the highest accuracy among the classifiers used.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Amira Echtioui, Wassim Zouch, Mohamed Ghorbel, Chokri Mhiri
Summary: In this study, a new method for classifying motor imagery tasks based on Convolutional Neural Network (CNN) was proposed. The EEG signals were preprocessed and spatial and frequency-time features were extracted. Four proposed models were tested using BCI Competition IV 2a dataset, and the CNN-SVM model achieved the best results. The experimental results showed promising accuracy, precision, recall, and F1 score of 64.33%, 65.05%, 66.11%, and 64.11%, respectively.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Interdisciplinary Applications
K. Parand, M. Razzaghi, R. Sahleh, M. Jani
Summary: In this paper, a numerical method based on least squares support vector regression is proposed for solving Volterra integral equations of the first and second kind. The method combines support vector regression with an orthogonal kernel and Galerkin and collocation spectral methods. An optimization problem is formulated and transformed into solving a system of algebraic equations. Numerical results demonstrate the sparsity of the resulting system and the efficiency of the proposed method.
ENGINEERING WITH COMPUTERS
(2022)
Article
Mathematics, Interdisciplinary Applications
A. Pakniyat, K. Parand, M. Jani
Summary: In this paper, a numerical method based on the least-squares support vector regression and spectral methods is developed for solving differential equations on unbounded domains. Hermite functions are used as the orthogonal kernel of the support vector regression, reducing the resulting optimization problem to a linear system in both collocation and Galerkin approaches. The accuracy and efficiency of the method are demonstrated and compared with existing methods through numerical examples, including fractional differential equations.
CHAOS SOLITONS & FRACTALS
(2021)
Article
Spectroscopy
Hao Jin, Gui -Mei Dong, Hai-Yun Wu, Yan-Rong Yang, Ming-Yue Huang, Meng -Yuan Wang, Ren-Jie Yang
Summary: A qualitative analysis method for melamine-adulterated milk based on two-trace two-dimensional auto-correlation spectra was proposed. Infrared spectroscopy was used to measure the spectral data of pure milk and melamine-adulterated milk. The intensity of auto-correlation peaks at specific wave numbers was selected as independent variables for modeling. The method achieved 100% accuracy for individual brands and 99.05% accuracy for all four brands combined.
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
(2023)
Article
Chemistry, Analytical
Abdul Razaque, Mohamed Ben Haj Frej, Muder Almi'ani, Munif Alotaibi, Bandar Alotaibi
Summary: This paper introduces a land use classification method based on improved SVM-RBF and SVM-Linear, evaluating the impact of parameter optimization on accuracy through cross-validation. The results show that these new methods have higher accuracy, reliability, and fault tolerance compared to traditional and state-of-the-art algorithms.
Article
Computer Science, Artificial Intelligence
Zhongbo Sun, Xin Zhang, Keping Liu, Tian Shi, Jing Wang
Summary: This paper proposes an active motion intention recognition technology based on LS-SVM and ZNN, which successfully estimates the continuous motion angles of knee joint and hip joint. By processing the sEMG signal and establishing a noise-suppressing neural network, accurate identification and noise elimination are achieved, providing valuable reference for lower limb joint movement of patients.
NEURAL PROCESSING LETTERS
(2023)
Article
Computer Science, Interdisciplinary Applications
K. Parand, A. A. Aghaei, M. Jani, A. Ghodsi
Summary: In this paper, a machine learning method utilizing LS-SVR is developed for the numerical solution of Fredholm integral equations. Two different approaches for training the network are proposed. Numerical examples are conducted to demonstrate the accuracy and efficiency of the method.
MATHEMATICS AND COMPUTERS IN SIMULATION
(2021)
Article
Green & Sustainable Science & Technology
Wei Huang, Leixiang Wu, Zhuowei Wang, Shirichiro Yano, Jiake Li, Gairui Hao, Jianmin Zhang
Summary: Predicting periphyton biomass is crucial for controlling algal biomass in rivers. The study compared three models and found that the least squares-support vector machine (LS-SVM) model outperformed others. These findings can help improve river management and reduce excess periphyton growth downstream.
JOURNAL OF CLEANER PRODUCTION
(2021)
Article
Computer Science, Artificial Intelligence
Umesh Gupta, Deepak Gupta
Summary: This article discusses the shortcomings of existing methods for binary classification problems and proposes a new approach called LS-STBSVM that improves generalization performance and effectively handles computational burden by incorporating total within-class and between-class information.
APPLIED INTELLIGENCE
(2023)
Article
Engineering, Marine
Haitong Xu, C. Guedes Soares
Summary: This study proposes a data-driven truncated LS-SVM method for estimating the hydrodynamic coefficients of a nonlinear manoeuvring model. The method is validated using experimental data and yields convincing results with reduced parameter uncertainty when using a large training set.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Interdisciplinary Applications
Yash Khurana, Pramod Kumar Soni, Devershi Pallavi Bhatt
Summary: This paper uses multi-temporal medium resolution Sentinel-2 imagery to classify the densely populated urban area of Delhi-NCR into five different land cover classes using the support vector machine (SVM) algorithm, and compares the effects of different SVM kernel functions on land cover classification performance. The radial basis function (RBF) kernel achieves the best results. The experimental results are compared with the maximum likelihood classification (MLC) method, showing that SVM with RBF kernel improves the overall accuracy by 10% compared to the polynomial kernel and by 3% compared to MLC. The analysis of the study area's multitemporal spectral imagery reflects increases in built-up area (road network, buildings) and water bodies, as well as decreases in barren land and vegetation.
EARTH SCIENCE INFORMATICS
(2023)
Article
Mathematics, Applied
K. Parand, M. Hasani, M. Jani, H. Yari
Summary: This paper presents a new method based on least squares support vector regression (LS-SVR) for solving linear and nonlinear Volterra-Fredholm integral equations. By introducing dual variables, the optimization problem associated with the integral equation is transformed into a linear system. Legendre polynomials are used as the kernel for LS-SVR. The proposed method is tested on various problems, with numerical results compared to existing methods to demonstrate its accuracy and efficiency.
COMPUTATIONAL & APPLIED MATHEMATICS
(2021)
Article
Computer Science, Information Systems
Haiqi Wang, Liuke Li, Lei Che, Haoran Kong, Qiong Wang, Zhihai Wang, Jianbo Xu
Summary: This study introduces a geospatial LS-SVR model that takes into account both the spatial and attribute characteristics of geospatial objects. By incorporating spatial weight matrices into the LS-SVR model, the prediction accuracy is improved.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2021)
Article
Engineering, Environmental
Wenxian Liu, Jinxiu Feng, Ruilian Yin, Yifeng Ni, Dong Zheng, Wenbin Que, Xinxin Niu, Xiaojing Dai, Wenhui Shi, Fangfang Wu, Jintao Yang, Xiehong Cao
Summary: The study introduces a new method for efficient production of H2O2 by tailoring the surface structure and coordination environment of cobalt-carbon hybrids to achieve high 2e(-) selectivity. The CoNCF electrodes synthesized exhibit excellent H2O2 selectivity in acidic media, showing potential practical applications.
CHEMICAL ENGINEERING JOURNAL
(2022)
Article
Engineering, Environmental
Xidong Zhang, Yamei Zeng, Wenyan Shi, Zui Tao, Jianjun Liao, Changzhi Ai, Hewei Si, Zhipeng Wang, Adrian C. Fisher, Shiwei Lin
Summary: This study demonstrates the construction of high-performance S-scheme heterojunctions 2H-MoSe2/TiO2 NRAs and (1 T-2H)-MoSe2/TiO2 NRAs for efficient photoelectrocatalytic generation of H2O2. Experimental results show a 3.3-fold increase in H2O2 production rate for the former and a 4.7-fold enhancement for the latter biphasic interface. The 1 T metallic MoSe2 plays a crucial role as a charge carrier transfer bridge in promoting S-type charge transportation.
CHEMICAL ENGINEERING JOURNAL
(2022)
Article
Environmental Sciences
Chuang Wang, Jinying Du, Xiaoyong Deng, Rui Chen, Zhiwei Zhao, Wenxin Shi, Fuyi Cui
Summary: This study systematically investigated the removal of fluoroquinolones (NOR) in VUV/Fe3+/H2O2 process, demonstrating its efficiency in increasing degradation rate and mineralization rate while reducing energy consumption and economic cost.
Article
Thermodynamics
Zixu Yang, Youlin Zhang, Hansong Xiao, Rong Zhuang, Xiangfei Liang, Mengdi Cui, Xin Li, Jiaan Zhao, Qi Yuan, Ruiqi Yang, Baolong Wang, Wenxing Shi
Summary: According to current usage trends, the use of room air conditioners is expected to triple by 2050. This paper proposes an ultra-efficient air conditioner with smart evaporative cooling ventilation and photovoltaic system to address the goal of climate change. The developed prototype showed significant energy savings and received the global cooling prize, demonstrating a reliable solution for energy-saving room air conditioners.
ENERGY CONVERSION AND MANAGEMENT
(2022)
Article
Chemistry, Multidisciplinary
Pujing Zhang, Tong Cai, Qingli Zhou, Guangwei She, Wanlin Liang, Yuwang Deng, Tingyin Ning, WenSheng Shi, Liangliang Zhang, Cunlin Zhang
Summary: The performance of terahertz devices can be significantly improved by using optical regulation strategy with the aid of hybrid materials, such as gold nanobipyramids (AuNBPs). The introduction of AuNBPs can effectively enhance the modulation depth of terahertz modulators, and an ultrahigh modulation enhancement can be achieved in the AuNBPs hybrid metamaterials. The optical regulation with AuNBPs is attributed to increased damping rate and higher coupling coefficient.
Article
Nanoscience & Nanotechnology
Wenxian Liu, Wenbin Que, Xuhai Shen, Ruilian Yin, Xilian Xu, Dong Zheng, Jinxiu Feng, Xiaojing Dai, Xinxin Niu, Fangfang Wu, Wenhui Shi, Xiehong Cao
Summary: In this study, a facile coordinative reconstruction strategy was used to transform Ti-MOF into nanosheet-assembled hollow structure with exposed metal sites. The surface and internal structure of the reconstructed MOF can be well tuned via altering the conversion time. The reconstructed MOF exhibits significantly higher catalytic activity in a desulfurization reaction.
Article
Chemistry, Multidisciplinary
Xiaoyan Wang, Xiaona Hu, Shiqing Li, Wenhui Shi, Shujing Li, Yuxi Zhang
Summary: Sustained-release antimicrobial nanofibers (PVA-Lut-IC-NF) synthesized using electrospinning technique exhibit excellent antibacterial effects, especially against Staphylococcus aureus. With appropriate slow release and effective concentration maintenance, they have potential applications in food, pharmaceuticals, and healthcare settings.
NEW JOURNAL OF CHEMISTRY
(2022)
Article
Multidisciplinary Sciences
Jing Tian, Daniel R. Utter, Lujia Cen, Pu-Ting Dong, Wenyuan Shi, Batbileg Bor, Man Qin, Jeffrey S. McLean, Xuesong He
Summary: This study reveals the function and impact of the acquired arginine deiminase system (ADS) in Saccharibacteria during the transition from the environment to the mammalian microbiome, and demonstrates its role in the mutualistic interaction and partner selection between Saccharibacteria and host bacteria.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2022)
Article
Chemistry, Physical
Ning Liu, Jinxing Wu, Fuhao Fei, Jianqiu Lei, Wenyan Shi, Guixiang Quan, Shuai Zeng, Xiaodong Zhang, Liang Tang
Summary: The study demonstrates that the exposure of different facets in the iron-based MOF MIL-88B(Fe) correlates closely with catalytic activity, with MIL-88B(Fe)-1 showing the best catalytic performance. Presence of Cl, SO42, and NO3 inhibits the degradation of IBP, and the optimum PS dosage used was 60 mg/L. XPS analysis revealed that MIL-88B(Fe)-1 had more Fe2+ content. This work provides new insights into the synergism between photocatalysis and persulfate activation by facet-controlled MOFs for environmental remediation.
JOURNAL OF COLLOID AND INTERFACE SCIENCE
(2022)
Article
Engineering, Environmental
Yanei Xue, Penghui Shao, Mingli Lin, Yixing Yuan, Wenxin Shi, Fuyi Cui
Summary: This study investigates the influence of defects on catalytic activity by optimizing the concentration of sulfur vacancies in a catalyst. The results show that the influence of sulfur vacancy concentration on catalytic activity varies, revealing the fundamental essence of defect behavior affecting crystal catalytic activity.
JOURNAL OF HAZARDOUS MATERIALS
(2022)
Article
Engineering, Multidisciplinary
Dongliang Fu, Wei Gao, Wentao Shi, Qunfei Zhang
Summary: In this paper, a novel robust kernel least logarithmic absolute difference (KLLAD) algorithm is proposed to address the performance degradation issue of kernel adaptive filtering (KAF) algorithms in the presence of non-Gaussian impulsive noise. The simulation results demonstrate that the KLLAD algorithm achieves significant improvement in terms of robustness and convergence speed.
MATHEMATICAL PROBLEMS IN ENGINEERING
(2022)
Article
Chemistry, Multidisciplinary
Yang Yuan, Qing Zhang, Lin Yang, Liguang Wang, Wenbo Shi, Pengfei Liu, Rui Gao, Lirong Zheng, Zhongwei Chen, Zhengyu Bai
Summary: Increasing the portion of highly active metal centers in M-N-C catalysts is crucial for enhancing the overall performance of the oxygen reduction reaction (ORR). A facet strain strategy using a trans-layer compressive strain is proposed, which effectively activates the primitive FeN4 catalytic centers. The redesigned catalyst with compressed Fe-N bonds exhibits improved ORR activity compared to the conventional Fe-N-C and commercial Pt/C benchmarks.
ADVANCED FUNCTIONAL MATERIALS
(2022)
Article
Chemistry, Analytical
Zixu He, Diankai Liu, Ya Liu, Xiaohua Li, Wen Shi, Huimin Ma
Summary: A novel Golgi-targeted fluorescent probe has been developed for sensing and imaging nitric oxide (NO) in the Golgi apparatus. The probe shows accurate Golgi-targeting ability and high selectivity for NO. The study also reveals a significant increase of NO in the Golgi apparatus in an Alzheimer's disease model.
ANALYTICAL CHEMISTRY
(2022)
Article
Agricultural Engineering
Jiawei Fan, Wei Li, Bing Zhang, Wenxin Shi, Piet N. L. Lens
Summary: This study shows that the removal efficiency of azo dyes by AGS increases at low salinity levels, but the microbial cell viability of AGS is negatively affected at high salinity levels, leading to a decrease in removal and nutrient removal efficiencies. The removal of AO7 is achieved through adsorption and biodegradation.
BIORESOURCE TECHNOLOGY
(2022)
Article
Business, Finance
Wen Shi, Xiaogang Bi
Summary: This research examines the impact of Buddhism on mergers & acquisitions (M&As) performance using data from 4622 M&A transactions of Chinese public firms between 2004 and 2018. The findings provide ample evidence that acquirers located in regions with a higher intensity of Buddhism achieve better short-term and long-term performance after the merger. Furthermore, the study reveals that state ownership plays a crucial role in mitigating this effect, and the value creation is driven by higher deal completion rates and fewer violation cases for acquiring firms. Finally, the study addresses the issue of endogeneity, and the results remain unchanged.
ACCOUNTING AND FINANCE
(2023)