Results 71 to 80 of about 13,859 (190)

Financial Time Series Uncertainty: A Review of Probabilistic AI Applications

Journal of Economic Surveys, Volume 40, Issue 2, Page 915-953, April 2026.
ABSTRACT Probabilistic machine learning models offer a distinct advantage over traditional deterministic approaches by quantifying both epistemic uncertainty (stemming from limited data or model knowledge) and aleatoric uncertainty (due to inherent randomness in the data), along with full distributional forecasts.
Sivert Eggen, Tord Johan Espe, Kristoffer Grude, Morten Risstad, Rickard Sandberg   +4 more
wiley   +1 more source

An Overview of Deep Learning Techniques for Big Data IoT Applications

International Journal of Communication Systems, Volume 39, Issue 4, 10 March 2026.
Reviews deep learning integration with cloud, fog, and edge computing in IoT architectures. Examines model suitability across IoT applications, key challenges, and emerging trends Provides a comparative analysis to guide future deep learning research in IoT environments.
Gagandeep Kaur, Vipin Balyan, Sindhu Hak Gupta   +2 more
wiley   +1 more source

WOT-AE: Weighted Optimal Transport Autoencoder for Patterned Fabric Defect Detection

Symmetry
Patterned fabrics are characterized by strong periodic and symmetric structures, and defect detection in such materials is essentially the task of identifying local disruptions of global texture symmetry. Conventional low-rank decomposition methods separate defect-free regions as low-rank and defects as sparse components, yet singular value ...
Hui Yang, Linyan Kang, Tianjin Yang
openaire   +1 more source

Comparative analysis of autoencoder architectures for breast cancer detection using dynamic infrared thermography

Engineering Science and Technology, an International Journal
Breast cancer is the most diagnosed cancer among women worldwide. Early detection substantially improves treatment outcomes, especially when lesions are small and localized.
Burcu Acar Demirci, Mehmet Engin, Erkan Zeki Engin   +2 more
doaj   +1 more source

Intelligent Fault Diagnosis of Gas Pressure Regulator Based on AE-GWO-SVM Algorithm

Automation
A pressure regulator is essential for pressure control in a gas transmission system. The traditional maintenance approaches for pressure regulators involve equipment disassembly that disrupts normal production.
Shunyuan Hu, Zhixiang Dai, Keqing Zhang, Jingjian Liu, Qing Wen, Yanhua Qiu, Weidong Li   +6 more
doaj   +1 more source

Investigation of an Optimized Linear Regression Model with Nonlinear Error Compensation for Tool Wear Prediction

Machines
To solve the problem of insufficient accuracy in tool wear process modeling and Remaining Useful Life (RUL) estimation, this study proposes a two-stage prediction method.
Lihua Shen, Baorui Du, He Fan, Hailong Yang   +3 more
doaj   +1 more source

Evaluating Reconstruction-Based and Proximity-Based Methods: A Four-Way Comparison (AE, LSTM-AE, OCSVM, IF) in SCADA Anomaly Detection Under Inverted Imbalance

Future Internet
This article investigates and compares four unsupervised anomaly detection algorithms: the Autoencoder (AE), LSTM-Autoencoder (LSTM-AE), One-Class SVM (OCSVM), and the Isolation Forest (IF). The analysis focuses on SCADA telemetry data from an urban wind
Lukasz Pawlik
doaj   +1 more source

SMALL-DATA REDUCED-ORDER MODELING OF CHAOTIC DYNAMICS THROUGH SYCO-AE: SYNTHETICALLY CONSTRAINED AUTOENCODERS

Journal of Machine Learning for Modeling and Computing
Data-driven reduced-order modeling of chaotic dynamics can result in systems that either dissipate or diverge catastrophically. Leveraging nonlinear dimensionality reduction of autoencoders and the freedom of nonlinear operator inference with neural networks, we aim to solve this problem by imposing a synthetic constraint in the reduced-order space ...
Popov, Andrey A., Zanetti, Renato
openaire   +2 more sources

AE-MCDM: an autoencoder-based multi-criteria decision-making approach for unsupervised feature selection

The Journal of Supercomputing
Feature selection is a fundamental technique for reducing the dimensionality of high-dimensional data by identifying the most relevant features while discarding redundant or irrelevant ones. In unsupervised settings, where labeled data are unavailable and labeling is costly, effective feature selection becomes even more challenging. This paper proposes
Hashemi, Amin, Dowlatshahi, Mohammad Bagher, Farshidi, Siamak, Moradi, Parham   +3 more
openaire   +1 more source

Improving Recognition of Defective Epoxy Images in Integrated Circuit Manufacturing by Data Augmentation

Sensors
This paper discusses the problem of recognizing defective epoxy drop images for the purpose of performing vision-based die attachment inspection in integrated circuit (IC) manufacturing based on deep neural networks.
Lamia Alam, Nasser Kehtarnavaz
doaj   +1 more source