Results 51 to 60 of about 8,961 (241)

Substation Equipment 3D Identification Based on KNN Classification of Subspace Feature Vector

Journal of Intelligent Systems, 2017
Aiming to realize rapid and efficient three-dimensional (3D) identification of substation equipment, this article proposes a new method in which the 3D identification of substation equipment is based on K-nearest neighbor (KNN) classification of subspace
Guo Weiying, Ji Yong, Luo Yong, Zhou Yan
doaj   +1 more source

Customizing Tactile Sensors via Machine Learning‐Driven Inverse Design

Advanced Science, EarlyView.
ABSTRACT Replicating the sophisticated sense of touch in artificial systems requires tactile sensors with precisely tailored properties. However, manually navigating the complex microstructure‐property relationship results in inefficient and suboptimal designs.
Baocheng Wang, Depeng Kong, Zhiao He, Jikai Liang, Yuyao Lu, Zikang Deng, Honghe Li, Mengke Wang, M. Jamal Deen, Zhiqiu Ye, Shuyao Zhou, Huayong Yang, Honghao Lyu, Jun Chen, Kaichen Xu, Geng Yang   +15 more
wiley   +1 more source

Staged Diversity‐Constrained Machine Learning for High‐Dimensional Reaction Condition Optimization

Angewandte Chemie, EarlyView.
Staged diversity‐constrained modeling enables efficient navigation of high‐dimensional reaction spaces, validated on cross‐coupling HTE data and applied to ruthenium‐catalyzed meta‐C─H functionalization. ABSTRACT Optimizing reaction conditions in high‐dimensional chemical spaces remains a central challenge in modern synthesis.
Shu‐Wen Li, Shan Chen, João C. A. Oliveira, Shuo‐Qing Zhang, Lutz Ackermann, Xin Hong   +5 more
wiley   +2 more sources

Robust multichannel subspace identification

Electronics Letters, 1999
The non-robustness to channel order overestimation and lack of disparity of the Moulines subspace (SS) and the Tong least-squares (LS) approaches are considered to be major limitations to their use in practical situations. A remedial technique is proposed that can be applied to both approaches, offering them the robustness they lack.
openaire   +1 more source

Real‐time fault detection in multicomponent nuclear‐waste slurries through data fusion of spectroscopic sensors

AIChE Journal, EarlyView.
Abstract Three instruments–Raman spectroscopy, attenuated total reflectance–Fourier transform infrared spectroscopy, and focused beam reflectance measurement–were used to detect sensor faults, mixing faults, and unanticipated chemistry in a system of multicomponent slurries.
Steven H. Crouse, Ronald W. Rousseau, Martha A. Grover   +2 more
wiley   +1 more source

Unsupervised Locality-Preserving Robust Latent Low-Rank Recovery-Based Subspace Clustering for Fault Diagnosis

IEEE Access, 2018
With the increasing demand for unsupervised learning for fault diagnosis, the subspace clustering has been considered as a promising technique enabling unsupervised fault diagnosis. Although various subspace clustering methods have been developed to deal
Jie Gao, Myeongsu Kang, Jing Tian, Lifeng Wu, Michael Pecht   +4 more
doaj   +1 more source

Trust‐region filter algorithms utilizing Hessian information for gray‐box optimization

AIChE Journal, EarlyView.
Abstract Optimizing industrial processes often involves gray‐box models that couple algebraic glass‐box equations with black‐box components lacking analytic derivatives. Such systems challenge derivative‐based solvers. The classical trust‐region filter (TRF) algorithm provides a robust framework but requires extensive parameter tuning and numerous ...
Gul Hameed, Tao Chen, Antonio del Rio Chanona, Lorenz T. Biegler, Michael Short   +4 more
wiley   +1 more source

Identification of Exhaled Volatile Organic Compounds Biomarkers for Lung Cancer Under Data‐Limited Conditions Using Data Augmentation and Multi‐View Feature Selection

Advanced Intelligent Discovery, EarlyView.
This work introduces a novel framework for identifying non‐small cell lung cancer biomarkers from hundreds of volatile organic compounds in breath, analyzed via gas chromatography‐mass spectrometry. This method integrates generative data augmentation and multi‐view feature selection, providing a stable and accurate solution for biomarker discovery in ...
Guancheng Ren, Bohao Liu, Zhiyuan Qu, Xue Jiang, Heng Zhao, Danyao Qu, Ruizhi Ning, Chen Su, Taoping Liu, Guangjian Zhang, Weiwei Wu   +10 more
wiley   +1 more source

Machine Learning‐Enhanced Random Matrix Theory Design for Human Immunodeficiency Virus Vaccine Development

Advanced Intelligent Discovery, EarlyView.
This study integrates random matrix theory (RMT) and principal component analysis (PCA) to improve the identification of correlated regions in HIV protein sequences for vaccine design. PCA validation enhances the reliability of RMT‐derived correlations, particularly in small‐sample, high‐dimensional datasets, enabling more accurate detection of ...
Mariyam Siddiqah, Muhammad Zulqarnain Zeb, Muhammad Husnain Zeb, Babar Shabbir   +3 more
wiley   +1 more source

Research on Model Identification of Permanent Magnet DC Brushless Motor Based on Auxiliary Variable Subspace Identification Algorithm

World Electric Vehicle Journal
This paper proposes a model identification method based on the auxiliary variable closed-loop subspace identification algorithm to address the problem of modeling difficulties caused by various complex factors affecting permanent magnet brushless DC ...
Jing Zhang, Yuhui Liu, Te Chen, Guowei Dou   +3 more
doaj   +1 more source