Results 171 to 180 of about 219,479 (266)

Optimal structural design method for reinforced concrete column in buildings with high floor heights using a genetic algorithm

open access: yesStructural Concrete, EarlyView.
Abstract Globally, there is a growing trend toward taller, larger, and more structurally diverse buildings that require expansive interior spaces. Rapid technological advancements have surged the demand for data centers, while the expansion of e‐commerce has increased logistics volumes, driving the need for large‐scale warehouses.
Han Yong Lee   +2 more
wiley   +1 more source

Real‐Time Detection of Crossing‐Gate Rod Breakage: Sequential Classification and Alerting Based on One‐Class SVM in a Railway Telemeter System

open access: yesArtificial Intelligence for Engineering, EarlyView.
This study presents a real‐time anomaly detection method for railway crossing‐gate rod breakage using one‐class SVM. The proposed sequential framework monitors classification score transitions and issues alerts based on a dynamic threshold, enabling unsupervised, field‐deployable failure detection without relying on labelled fault data.
Tomoaki Kashiwao   +5 more
wiley   +1 more source

Enhancing generalized spectral clustering with embedding Laplacian graph regularization

open access: yesCAAI Transactions on Intelligence Technology, EarlyView.
Abstract An enhanced generalised spectral clustering framework that addresses the limitations of existing methods by incorporating the Laplacian graph and group effect into a regularisation term is presented. By doing so, the framework significantly enhances discrimination power and proves highly effective in handling noisy data.
Hengmin Zhang   +5 more
wiley   +1 more source

An extension of Lagrange’s equations [PDF]

open access: yesBulletin of the American Mathematical Society, 1932
openaire   +2 more sources

Boosted unsupervised feature selection for tumor gene expression profiles

open access: yesCAAI Transactions on Intelligence Technology, EarlyView.
Abstract In an unsupervised scenario, it is challenging but essential to eliminate noise and redundant features for tumour gene expression profiles. However, the current unsupervised feature selection methods treat all samples equally, which tend to learn discriminative features from simple samples.
Yifan Shi   +5 more
wiley   +1 more source

Home - About - Disclaimer - Privacy