Digital‐Twin‐Enabled, Time‐Aware Anomaly Detection for Industrial Cyber‐Physical Systems
Digital Twins and Applications, Volume 3, Issue 1, January/December 2026.The graphical abstract (Graphical Abstract figure) summarises the proposed pipeline: multivariate ICS data streams are windowed and normalised, fed into a temporal LSTM–DNN encoder and per‐sensor operating‐envelope learner, combined via calibrated fusion and finally surfaced through an operator‐facing digital twin that provides event timelines, top ...
Wulfran Fendzi Mbasso +5 more
wiley +1 more source
Addressing Technical Challenges in Large Language Model-Driven Educational Software System
IEEE AccessThe integration of large language models (LLMs) into educational systems poses significant challenges across several key attributes, including integration, explainability, testability, and scalability.
Nacha Chondamrongkul +2 more
doaj +1 more source
Pretreatment Methods for Enhancing Machine Learning Performance on Metabolomics Data
IEEE AccessPretreatment methods are critical for metabolomics data analysis, yet their impact on machine learning performance remains insufficiently explored.
Rustam
doaj +1 more source
Predictive Autoscaling for Multilayered Cloud Deployments [PDF]
, 2022 This thesis introduces a holistic model of predictive autoscaling for multilayered cloud deployments. The multilayered aspect is reflected in treating autoscaling as a hierarchical process where scaling on the application level acts as a driver for scaling on the level of VM clusters.
openaire
A high dynamic range digital LinLog CMOS image sensor architecture based on Event Readout of pixels and suitable for low voltage operation [PDF]
, 2007 Several approaches have been developed to extend the dynamic range of image sensor in order to keep all the information content of natural scenes covering a very broad range of illumination.
Guilvard, Alexandre +3 more
core
Treatments of non-metric variables in partial least squares and principal component analysis [PDF]
, 2015 This paper reviews various treatments of non-metric variables in Partial Least Squares (PLS) and Principal Component Analysis (PCA) algorithms. The performance of different treatments is compared in the extensive simulation study under several typical ...
Krivobokova, Tatyana, Yoon, Jisu
core
Application of Proximal Policy Optimization for Resource Orchestration in Serverless Edge Computing
ComputersServerless computing is a new cloud computing model suitable for providing services in both large cloud and edge clusters. In edge clusters, the autoscaling functions play a key role on serverless platforms as the dynamic scaling of function instances ...
Mauro Femminella, Gianluca Reali
doaj +1 more source
Composite indices based on partial least squares [PDF]
, 2015 In this paper, we compare Principal Component Analysis (PCA) and Partial Least Squares (PLS) methods to generate weights for composite indices. In this context we also consider various treatments of non-metric variables when constructing such composite ...
Dreher, Axel +3 more
core
Significance Regression: A Statistical Approach to Biased Linear Regression and Partial Least Squares [PDF]
, 1993 This paper first examines the properties of biased regressors that proceed by restricting the search for the optimal regressor to a subspace. These properties suggest features such biased regression methods should incorporate.
Hjalmarsson, Hakan +2 more
core +1 more source
Citation: 'autoscaling' in the IUPAC Compendium of Chemical Terminology, 5th ed.; International Union of Pure and Applied Chemistry; 2025. Online version 5.0.0, 2025. 10.1351/goldbook.10044 • License: The IUPAC Gold Book is licensed under Creative Commons Attribution-ShareAlike CC BY-SA 4.0 International for individual terms.
openaire +1 more source