Article
Computer Science, Interdisciplinary Applications
Pierre Dubois, Thomas Gomez, Laurent Planckaert, Laurent Perret
Summary: This paper investigates the use of data-driven methods for the reconstruction of unsteady fluid flow fields. The proposed framework is based on the combination of machine learning tools: dimensionality reduction to extract dominant spatial directions from data, reconstruction algorithm to recover encoded data by limited measurements and cross-validation for hyperparameter optimization. The results suggest that proper machine learning approaches to fluid flow data can lead to effective reconstruction models that can be used for the rapid estimation of complex flows.
JOURNAL OF COMPUTATIONAL PHYSICS
(2022)
Article
Neurosciences
Shengchao Zhang, Sarah E. Goodale, Benjamin P. Gold, Victoria L. Morgan, Dario J. Englot, Catie Chang
Summary: Patterns in fMRI data can reflect dynamic changes in the brain and are related to individual and group differences in behavior, cognition, and clinical traits. Detecting vigilance states in fMRI data without external measurements is challenging. This study shows that vigilance levels can be detected in the low-dimensional structure of fMRI data, even within individual time frames.
Article
Computer Science, Artificial Intelligence
Hongyuan Zhang, Yanan Zhu, Xuelong Li
Summary: This study proposes a novel projected clustering framework to capture the essence of deep clustering by summarizing the core properties of powerful models, especially deep models. The framework introduces an aggregated mapping, consisting of projection learning and neighbor estimation, to obtain clustering-friendly representation. The study also addresses the problem of severe degeneration in simple clustering-friendly representation learning, and develops a self-evolution mechanism to alleviate the risk of over-fitting.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Article
Biology
Ke Cao, Karin Verspoor, Elsie Chan, Mark Daniell, Srujana Sahebjada, Paul N. Baird
Summary: By reducing the dimensionality of the Pentacam parameter set through principal component analysis and applying the random forest algorithm, this study achieved efficient identification of subclinical keratoconus.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Telecommunications
Neeraj Kumar, Upendra Kumar
Summary: The paper explores the development of an intelligent Intrusion Detection System (IDS) through a review of relevant research, focusing on feature selection and classification algorithms. Experimental results show that the proposed method outperforms existing DM and ML based approaches in achieving maximum intrusion detection accuracy with minimal computing cost.
WIRELESS PERSONAL COMMUNICATIONS
(2022)
Review
Pharmacology & Pharmacy
Hanna Baltrukevich, Sabina Podlewska
Summary: With the increased availability of crystal structures and computational power, structure-based drug design tools have been extensively used in drug development. Docking and molecular dynamics simulations provide detailed information about ligand-receptor interactions, but require protein structures and computational resources. As the use of docking and molecular dynamics grows, the output data also increases, necessitating approaches to analyze and interpret the results of these tools.
FRONTIERS IN PHARMACOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Jiaqi Ma, Yipeng Zhang, Lefei Zhang
Summary: In this study, a method called DMSMF is proposed to address the drawbacks of existing multiview data clustering methods. By extending linear discriminant analysis and NMF to a multiview version, and incorporating novel regularization terms and optimization algorithms, satisfactory clustering performance is achieved.
PATTERN RECOGNITION
(2021)
Review
Computer Science, Artificial Intelligence
Tinghua Wang, Xiaolu Dai, Yuze Liu
Summary: The article provides an in-depth survey of learning methods using the Hilbert-Schmidt independence criterion (HSIC) for various learning problems, such as feature selection, dimensionality reduction, clustering, and kernel learning and optimization. It systematically reviews typical learning models based on the HSIC, ranging from supervised learning to unsupervised learning, traditional machine learning to transfer learning and deep learning. The relationships between learning methods using the HSIC and other relevant learning algorithms are also discussed, aiming to provide practitioners valuable guidelines for their specific domains by elucidating the similarities and differences of these learning models.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Gengshi Huang, Zhengming Ma, Tianshi Luo
Summary: This paper introduces a statistic for measuring the correlation between two random variables using kernelized cross-covariance criterion (kCCC), and applies kCCC to data dimensionality reduction combined with local geometric property preservation method and manifold learning dimensionality reduction method, to maintain both global statistical characteristics and local geometric characteristics simultaneously.
JOURNAL OF MATHEMATICAL IMAGING AND VISION
(2021)
Article
Computer Science, Artificial Intelligence
Caio Flexa, Walisson Gomes, Igor Moreira, Ronnie Alves, Claudomiro Sales
Summary: Dimensionality Reduction (DR) is important in understanding high-dimensional data, and the Polygonal Coordinate System (PCS) presented in this work offers an efficient geometric approach for this purpose. The study also introduces a new version of the t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm using a PCS-based deterministic strategy, showcasing the efficiency of PCS in data embedding compared to other DR algorithms.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Himansu Das, Bighnaraj Naik, H. S. Behera, Shalini Jaiswal, Priyanka Mahato, Minakhi Rout
Summary: This paper proposes a Neuro-Fuzzy model with post-feature reduction for analyzing complex biomedical data. The model handles uncertainty by fuzzifying input patterns and employs post-feature reduction to filter out irrelevant, redundant, and noisy features. The effectiveness of the proposed model has been tested and validated with benchmark biomedical data.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Feiping Nie, Xia Dong, Xuelong Li
Summary: The article introduces the UPGO framework for dimensionality reduction and clustering, which unifies graph construction and projection learning. It also generalizes the framework to tackle the semisupervised case (SPGO), providing experimental results and theoretical analysis on the effectiveness and convergence of the proposed frameworks.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Marco Capo, Aritz Perez, Jose A. Lozano
Summary: In this article, a feature selection technique for the K-means algorithm is proposed, which is based on a novel feature relevance measure and aims to reduce K-means error and computational costs. Experimental results show that the proposed method consistently outperforms other feature selection techniques and feature extraction techniques in terms of clustering performance and computational time.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Kaizhi Chen, Chengpei Le, Shangping Zhong, Longkun Guo, Ge Xu
Summary: This work proposes a linear dimensionality reduction method that considers both the nearest neighbor structure and global features simultaneously.
CONNECTION SCIENCE
(2022)
Article
Chemistry, Multidisciplinary
Shuyu Qin, Yichen Guo, Alibek T. Kaliyev, Joshua C. Agar
Summary: This study utilizes machine learning methods to analyze electromechanical switching mechanisms in materials spectroscopy and overcomes common pitfalls. By using multiple experimental datasets and specific algorithms, researchers successfully achieve automatic detection of complex switching mechanisms in ferroelectric materials.
ADVANCED MATERIALS
(2022)
Article
Thermodynamics
B. Fiorina, R. Mercier, G. Kuenne, A. Ketelheun, A. Avdic, J. Janicka, D. Geyer, A. Dreizler, E. Alenius, C. Duwig, P. Trisjono, K. Kleinheinz, S. Kang, H. Pitsch, F. Proch, F. Cavallo Marincola, A. Kempf
COMBUSTION AND FLAME
(2015)
Article
Engineering, Mechanical
Giandomenico Lupo, Christophe Duwig
JOURNAL OF ENGINEERING FOR GAS TURBINES AND POWER-TRANSACTIONS OF THE ASME
(2018)
Article
Thermodynamics
Ehsan Fooladgar, Christophe Duwig
COMBUSTION AND FLAME
(2018)
Article
Energy & Fuels
Luis Cifuentes, Ehsan Fooladgar, Christophe Duwig
Article
Thermodynamics
Erdzan Hodzic, Mehdi Jangi, Robert-Zoltan Szasz, Christophe Duwig, Marco Geron, Juliana Early, Laszlo Fuchs, Xue-Song Bai
COMBUSTION SCIENCE AND TECHNOLOGY
(2019)
Article
Mechanics
Marc Rovira, Klas Engvall, Christophe Duwig
Article
Mechanics
Yazhou Shen, Mohamad Ghulam, Kai Zhang, Ephraim Gutmark, Christophe Duwig
Article
Physics, Fluids & Plasmas
Marc Rovira, Klas Engvall, Christophe Duwig
Summary: This study presents a modal analysis of counterflowing jets at different velocity ratios using large eddy simulations (LESs) and proper orthogonal decomposition (POD). The research explores the three-dimensional turbulent structure and the origin and development of coherent structures in this flow configuration. Results show that planar two-dimensional (2D) and three-dimensional spectral POD analyses are in close agreement with existing literature.
PHYSICAL REVIEW FLUIDS
(2021)
Article
Energy & Fuels
Marc Rovira, Klas Engvall, Christophe Duwig
Summary: The study focuses on limiting gaseous nitrogen oxide emissions and explores the use of low-temperature oxidation by ozone as a solution for NOx removal. Three-dimensional large eddy simulations are used to study turbulent reacting flow inside a NOx-O3 reactor, and plug-flow reactor simulations are employed to identify optimal chemical kinetic mechanisms. The results aid in strategy development for validation, and the findings highlight the benefits of a high mixing efficiency reactor geometry.
Article
Thermodynamics
Reza Attarzadeh, Marc Rovira, Christophe Duwig
Summary: Triply Periodic Minimal Surfaces (TPMS) show promising thermophysical properties, making them suitable for the production of low-temperature waste heat recovery systems. The study conducted simulations to quantify the performance of a TPMS based heat exchanger and found an optimized lattice design providing the highest thermal performance. This research can help improve the fabrication of TPMS heat exchangers for recycling waste heat in low temperature thermal systems.
INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER
(2021)
Article
Construction & Building Technology
Parastoo Sadeghian, Christophe Duwig, Olof Skoldenberg, Ann Tammelin, Ardalan Rahimi Hosseini, Sasan Sadrizadeh
Summary: Patient warming is an effective method to prevent hypothermia during surgeries, but concerns about air pollution from warming blankets should be considered. Research shows that using forced-air warming blankets can significantly increase air temperature at the wound area, providing more effective warming during surgery.
ADVANCES IN BUILDING ENERGY RESEARCH
(2022)
Article
Thermodynamics
E. Hodzic, E. Alenius, C. Duwig, R. S. Szasz, L. Fuchs
COMBUSTION SCIENCE AND TECHNOLOGY
(2017)
Article
Engineering, Environmental
Xinping Zhang, Yuxin Guo, Xiaoyang Liu, Shun-Yu Wu, Ya-Xuan Zhu, Shao-Zhe Wang, Qiu-Yi Duan, Ke-Fei Xu, Zi-Heng Li, Xiao-Yu Zhu, Guang-Yu Pan, Fu-Gen Wu
Summary: This study develops a nanotrigger HCFT for simultaneous photodynamic therapy and light-triggered ferroptosis therapy. The nanotrigger can relieve tumor hypoxia, induce enhanced photodynamic reaction, and facilitate the continuation of Fenton reaction, ultimately leading to lethal ferroptosis in tumor cells.
CHEMICAL ENGINEERING JOURNAL
(2024)
Article
Engineering, Environmental
Olumide Bolarinwa Ayodele, Toyin Daniel Shittu, Olayinka S. Togunwa, Dan Yu, Zhen-Yu Tian
Summary: This study focused on the semihydrogenation of acetylene in an ethylene-rich stream using two alloyed Pt catalysts PtCu and PtCo. The PtCu catalyst showed higher activity and ethylene yield compared to PtCo due to its higher unoccupied Pt d-orbital density. This indicates that alloying Pt with Cu is more promising for industrial relevant SHA catalyst.
CHEMICAL ENGINEERING JOURNAL
(2024)
Article
Engineering, Environmental
Guowei Chen, Wen-Cheng Chen, Yaozu Su, Ruicheng Wang, Jia-Ming Jin, Hui Liang, Bingxue Tan, Dehua Hu, Shaomin Ji, Hao-Li Zhang, Yanping Huo, Yuguang Ma
Summary: This study proposes an intramolecular dual-locking design for organic luminescent materials, achieving high luminescence efficiency and performance for deep-blue organic light-emitting diodes. The material also exhibits unique mechanochromic luminescence behavior and strong fatigue resistance.
CHEMICAL ENGINEERING JOURNAL
(2024)
Article
Engineering, Environmental
Joren van Stee, Gregory Hermans, Jinu Joseph John, Koen Binnemans, Tom Van Gerven
Summary: This work presents a continuous solvent extraction method for the separation of cobalt and nickel in a millifluidic system using Cyphos IL 101 (C101) as the extractant. The optimal conditions for extraction performance and solvent properties were determined by investigating the effects of channel length, flow rate, and temperature. The performance of a developed manifold structure was compared to a single-channel system, and excellent separation results were achieved. The continuous separation process using the manifold structure resulted in high purity cobalt and nickel products.
CHEMICAL ENGINEERING JOURNAL
(2024)
Article
Engineering, Environmental
Yan Xu, Jingai Jiang, Xinyi Lv, Hui Li, Dongliang Yang, Wenjun Wang, Yanling Hu, Longcai Liu, Xiaochen Dong, Yu Cai
Summary: A programmed gas release nanoparticle was developed to address the challenges in treating diabetic infected wounds. It effectively removes drug-resistant pathogens and remodels the wound microenvironment using NO and H2S. The nanoparticle can eliminate bacteria and promote wound healing through antibacterial and anti-inflammatory effects.
CHEMICAL ENGINEERING JOURNAL
(2024)
Article
Engineering, Environmental
Tong Xia, Zhilin Xi, Lianquan Suo, Chen Wang
Summary: This study investigated a highly efficient coal dust suppressant with low initial viscosity and high adhesion-solidification properties. The results demonstrated that the dust suppressant formed a network of multiple hydrogen bonding cross-linking and achieved effective adhesion and solidification of coal dust through various chemical reactions.
CHEMICAL ENGINEERING JOURNAL
(2024)
Article
Engineering, Environmental
Jinzhi Cai, Zhenshan Li
Summary: A density functional theory-based rate equation was developed to predict the gas-solid reaction kinetics of CaO carbonation with CO2 in calcium looping. The negative activation energy of CaO carbonation close to equilibrium was accurately predicted through experimental validation.
CHEMICAL ENGINEERING JOURNAL
(2024)
Article
Engineering, Environmental
Jianxiong Chen, Fuhao Ren, Ningning Yin, Jie Mao
Summary: This study presents an economically efficient and easily implementable surface modification approach to enhance the high-temperature electrical insulation and energy storage performance of polymer dielectrics. The self-assembly of high-insulation-performance boron nitride nanosheets (BNNS) on the film surface through electrostatic interactions effectively impedes charge injection from electrodes while promoting charge dissipation and heat transfer.
CHEMICAL ENGINEERING JOURNAL
(2024)
Article
Engineering, Environmental
Zijian Li, Zhaohui Yang, Shao Wang, Hongxia Luo, Zhimin Xue, Zhenghui Liu, Tiancheng Mu
Summary: This study reports a strategy for upgrading polyester plastics into value-added chemicals using electrocatalytic methods. By inducing the targeted transfer of *OH species, polyethylene terephthalate was successfully upgraded into potassium diformate with high purity. This work not only develops an excellent electrocatalyst, but also provides guidance for the design of medium entropy metal oxides.
CHEMICAL ENGINEERING JOURNAL
(2024)
Article
Engineering, Environmental
Navneet Singh Shekhawat, Surendra Kumar Patra, Ashok Kumar Patra, Bamaprasad Bag
Summary: This study primarily focuses on developing a sulphur dyeing process at room temperature using bacterial Lysate, which is environmentally friendly, energy and cost effective, and sustainable. The process shows promising improvements in dye uptake and fastness properties.
CHEMICAL ENGINEERING JOURNAL
(2024)
Article
Engineering, Environmental
Dengjia Shen, Hongyang Ma, Madani Khan, Benjamin S. Hsiao
Summary: This study developed cationic PVC nanofibrous membranes with high filtration and adsorption capability for the removal of bacteria and hexavalent chromium ions from wastewater. The membranes demonstrated remarkable performance in terms of filtration efficiency and maximum adsorption capacity. Additionally, modified nanofibrous membranes were produced using recycled materials and showed excellent retention rates in dynamic adsorption processes.
CHEMICAL ENGINEERING JOURNAL
(2024)
Article
Engineering, Environmental
Xiaoyan Wang, Zhikun Wang, Ben Jia, Chunling Li, Shuangqing Sun, Songqing Hu
Summary: Inspired by photosystem II, self-supported Fe-doped NiCoP nanowire arrays modified with carboxylate were constructed to boost industrial-level overall water splitting by employing the concerted proton-coupled electron transfer mechanism. The introduction of Fe and carboxyl ligand led to improved catalytic activity for HER and OER, and NCFCP@NF exhibited long-term durability for overall water splitting.
CHEMICAL ENGINEERING JOURNAL
(2024)
Article
Engineering, Environmental
Pengyao Yu, Ge Yang, Yongming Chai, Lubomira Tosheva, Chunzheng Wang, Heqing Jiang, Chenguang Liu, Hailing Guo
Summary: Thin LTA zeolite membranes were prepared through secondary growth of nano LTA seeds in a highly reactive gel, resulting in membranes with superior permeability and selectivity in gas separation applications.
CHEMICAL ENGINEERING JOURNAL
(2024)
Article
Engineering, Environmental
Baiqin Zhou, Huiping Li, Ziyu Wang, Hui Huang, Yujun Wang, Ruichun Yang, Ranran Huo, Xiaoyan Xu, Ting Zhou, Xiaochen Dong
Summary: The use of machine learning to predict the performance of specific adsorbents in phosphate adsorption shows great promise in saving time and revealing underlying mechanisms. However, the small size of the dataset and insufficient detailed information limits the model training process and the accuracy of results. To address this, the study employs a fuzzing strategy that replaces detailed numeric information with descriptive text messages on the physiochemical properties of adsorbents. This strategy allows the recovery of discarded samples with limited information, leading to accurate prediction of adsorption amount, capacity, and kinetics. The study also finds that phosphate uptake by adsorbents is generally through physisorption, with some involvement of chemisorption. The framework established in this study provides a practical approach for quickly predicting phosphate adsorption performance in urgent scenarios, using easily accessible information.
CHEMICAL ENGINEERING JOURNAL
(2024)
Article
Engineering, Environmental
Paula Alejandra Lamprea Pineda, Joren Bruneel, Kristof Demeestere, Lisa Deraedt, Tex Goetschalckx, Herman Van Langenhove, Christophe Walgraeve
Summary: This study evaluates the use of four esterified fatty acids and three vegetable oils as absorption liquids for hydrophobic VOCs. The experimental results show that isopropyl myristate is the most efficient liquid for absorbing the target VOCs.
CHEMICAL ENGINEERING JOURNAL
(2024)